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

Pull locking updates from Ingo Molnar:
 "The locking tree was busier in this cycle than the usual pattern - a
  couple of major projects happened to coincide.

  The main changes are:

   - implement the atomic_fetch_{add,sub,and,or,xor}() API natively
     across all SMP architectures (Peter Zijlstra)

   - add atomic_fetch_{inc/dec}() as well, using the generic primitives
     (Davidlohr Bueso)

   - optimize various aspects of rwsems (Jason Low, Davidlohr Bueso,
     Waiman Long)

   - optimize smp_cond_load_acquire() on arm64 and implement LSE based
     atomic{,64}_fetch_{add,sub,and,andnot,or,xor}{,_relaxed,_acquire,_release}()
     on arm64 (Will Deacon)

   - introduce smp_acquire__after_ctrl_dep() and fix various barrier
     mis-uses and bugs (Peter Zijlstra)

   - after discovering ancient spin_unlock_wait() barrier bugs in its
     implementation and usage, strengthen its semantics and update/fix
     usage sites (Peter Zijlstra)

   - optimize mutex_trylock() fastpath (Peter Zijlstra)

   - ... misc fixes and cleanups"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (67 commits)
  locking/atomic: Introduce inc/dec variants for the atomic_fetch_$op() API
  locking/barriers, arch/arm64: Implement LDXR+WFE based smp_cond_load_acquire()
  locking/static_keys: Fix non static symbol Sparse warning
  locking/qspinlock: Use __this_cpu_dec() instead of full-blown this_cpu_dec()
  locking/atomic, arch/tile: Fix tilepro build
  locking/atomic, arch/m68k: Remove comment
  locking/atomic, arch/arc: Fix build
  locking/Documentation: Clarify limited control-dependency scope
  locking/atomic, arch/rwsem: Employ atomic_long_fetch_add()
  locking/atomic, arch/qrwlock: Employ atomic_fetch_add_acquire()
  locking/atomic, arch/mips: Convert to _relaxed atomics
  locking/atomic, arch/alpha: Convert to _relaxed atomics
  locking/atomic: Remove the deprecated atomic_{set,clear}_mask() functions
  locking/atomic: Remove linux/atomic.h:atomic_fetch_or()
  locking/atomic: Implement atomic{,64,_long}_fetch_{add,sub,and,andnot,or,xor}{,_relaxed,_acquire,_release}()
  locking/atomic: Fix atomic64_relaxed() bits
  locking/atomic, arch/xtensa: Implement atomic_fetch_{add,sub,and,or,xor}()
  locking/atomic, arch/x86: Implement atomic{,64}_fetch_{add,sub,and,or,xor}()
  locking/atomic, arch/tile: Implement atomic{,64}_fetch_{add,sub,and,or,xor}()
  locking/atomic, arch/sparc: Implement atomic{,64}_fetch_{add,sub,and,or,xor}()
  ...

72 files changed, 2063 insertions, 609 deletions

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 572b228c44c7..498933a7df97 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -46,10 +46,9 @@ static __inline__ void atomic_##op(int i, atomic_t * v)			\
 }									\
 
 #define ATOMIC_OP_RETURN(op, asm_op)					\
-static inline int atomic_##op##_return(int i, atomic_t *v)		\
+static inline int atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 {									\
 	long temp, result;						\
-	smp_mb();							\
 	__asm__ __volatile__(						\
 	"1:	ldl_l %0,%1\n"						\
 	"	" #asm_op " %0,%3,%2\n"					\
@@ -61,7 +60,23 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_mb();							\
+	return result;							\
+}
+
+#define ATOMIC_FETCH_OP(op, asm_op)					\
+static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
+{									\
+	long temp, result;						\
+	__asm__ __volatile__(						\
+	"1:	ldl_l %2,%1\n"						\
+	"	" #asm_op " %2,%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");			\
 	return result;							\
 }
 
@@ -82,10 +97,9 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v)		\
 }									\
 
 #define ATOMIC64_OP_RETURN(op, asm_op)					\
-static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	\
+static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v)	\
 {									\
 	long temp, result;						\
-	smp_mb();							\
 	__asm__ __volatile__(						\
 	"1:	ldq_l %0,%1\n"						\
 	"	" #asm_op " %0,%3,%2\n"					\
@@ -97,34 +111,77 @@ static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_mb();							\
+	return result;							\
+}
+
+#define ATOMIC64_FETCH_OP(op, asm_op)					\
+static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v)	\
+{									\
+	long temp, result;						\
+	__asm__ __volatile__(						\
+	"1:	ldq_l %2,%1\n"						\
+	"	" #asm_op " %2,%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");			\
 	return result;							\
 }
 
 #define ATOMIC_OPS(op)							\
 	ATOMIC_OP(op, op##l)						\
 	ATOMIC_OP_RETURN(op, op##l)					\
+	ATOMIC_FETCH_OP(op, op##l)					\
 	ATOMIC64_OP(op, op##q)						\
-	ATOMIC64_OP_RETURN(op, op##q)
+	ATOMIC64_OP_RETURN(op, op##q)					\
+	ATOMIC64_FETCH_OP(op, op##q)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
+#define atomic_add_return_relaxed	atomic_add_return_relaxed
+#define atomic_sub_return_relaxed	atomic_sub_return_relaxed
+#define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
+#define atomic_fetch_sub_relaxed	atomic_fetch_sub_relaxed
+
+#define atomic64_add_return_relaxed	atomic64_add_return_relaxed
+#define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
+#define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
+#define atomic64_fetch_sub_relaxed	atomic64_fetch_sub_relaxed
+
 #define atomic_andnot atomic_andnot
 #define atomic64_andnot atomic64_andnot
 
-ATOMIC_OP(and, and)
-ATOMIC_OP(andnot, bic)
-ATOMIC_OP(or, bis)
-ATOMIC_OP(xor, xor)
-ATOMIC64_OP(and, and)
-ATOMIC64_OP(andnot, bic)
-ATOMIC64_OP(or, bis)
-ATOMIC64_OP(xor, xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, asm)						\
+	ATOMIC_OP(op, asm)						\
+	ATOMIC_FETCH_OP(op, asm)					\
+	ATOMIC64_OP(op, asm)						\
+	ATOMIC64_FETCH_OP(op, asm)
+
+ATOMIC_OPS(and, and)
+ATOMIC_OPS(andnot, bic)
+ATOMIC_OPS(or, bis)
+ATOMIC_OPS(xor, xor)
+
+#define atomic_fetch_and_relaxed	atomic_fetch_and_relaxed
+#define atomic_fetch_andnot_relaxed	atomic_fetch_andnot_relaxed
+#define atomic_fetch_or_relaxed		atomic_fetch_or_relaxed
+#define atomic_fetch_xor_relaxed	atomic_fetch_xor_relaxed
+
+#define atomic64_fetch_and_relaxed	atomic64_fetch_and_relaxed
+#define atomic64_fetch_andnot_relaxed	atomic64_fetch_andnot_relaxed
+#define atomic64_fetch_or_relaxed	atomic64_fetch_or_relaxed
+#define atomic64_fetch_xor_relaxed	atomic64_fetch_xor_relaxed
 
 #undef ATOMIC_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h
index 0131a7058778..77873d0ad293 100644
--- a/arch/alpha/include/asm/rwsem.h
+++ b/arch/alpha/include/asm/rwsem.h
@@ -25,8 +25,8 @@ static inline void __down_read(struct rw_semaphore *sem)
 {
 	long oldcount;
 #ifndef	CONFIG_SMP
-	oldcount = sem->count;
-	sem->count += RWSEM_ACTIVE_READ_BIAS;
+	oldcount = sem->count.counter;
+	sem->count.counter += RWSEM_ACTIVE_READ_BIAS;
 #else
 	long temp;
 	__asm__ __volatile__(
@@ -52,13 +52,13 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
 	long old, new, res;
 
-	res = sem->count;
+	res = atomic_long_read(&sem->count);
 	do {
 		new = res + RWSEM_ACTIVE_READ_BIAS;
 		if (new <= 0)
 			break;
 		old = res;
-		res = cmpxchg(&sem->count, old, new);
+		res = atomic_long_cmpxchg(&sem->count, old, new);
 	} while (res != old);
 	return res >= 0 ? 1 : 0;
 }
@@ -67,8 +67,8 @@ static inline long ___down_write(struct rw_semaphore *sem)
 {
 	long oldcount;
 #ifndef	CONFIG_SMP
-	oldcount = sem->count;
-	sem->count += RWSEM_ACTIVE_WRITE_BIAS;
+	oldcount = sem->count.counter;
+	sem->count.counter += RWSEM_ACTIVE_WRITE_BIAS;
 #else
 	long temp;
 	__asm__ __volatile__(
@@ -106,7 +106,7 @@ static inline int __down_write_killable(struct rw_semaphore *sem)
  */
 static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
-	long ret = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
+	long ret = atomic_long_cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
 			   RWSEM_ACTIVE_WRITE_BIAS);
 	if (ret == RWSEM_UNLOCKED_VALUE)
 		return 1;
@@ -117,8 +117,8 @@ static inline void __up_read(struct rw_semaphore *sem)
 {
 	long oldcount;
 #ifndef	CONFIG_SMP
-	oldcount = sem->count;
-	sem->count -= RWSEM_ACTIVE_READ_BIAS;
+	oldcount = sem->count.counter;
+	sem->count.counter -= RWSEM_ACTIVE_READ_BIAS;
 #else
 	long temp;
 	__asm__ __volatile__(
@@ -142,8 +142,8 @@ static inline void __up_write(struct rw_semaphore *sem)
 {
 	long count;
 #ifndef	CONFIG_SMP
-	sem->count -= RWSEM_ACTIVE_WRITE_BIAS;
-	count = sem->count;
+	sem->count.counter -= RWSEM_ACTIVE_WRITE_BIAS;
+	count = sem->count.counter;
 #else
 	long temp;
 	__asm__ __volatile__(
@@ -171,8 +171,8 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 {
 	long oldcount;
 #ifndef	CONFIG_SMP
-	oldcount = sem->count;
-	sem->count -= RWSEM_WAITING_BIAS;
+	oldcount = sem->count.counter;
+	sem->count.counter -= RWSEM_WAITING_BIAS;
 #else
 	long temp;
 	__asm__ __volatile__(
@@ -191,47 +191,5 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 		rwsem_downgrade_wake(sem);
 }
 
-static inline void rwsem_atomic_add(long val, struct rw_semaphore *sem)
-{
-#ifndef	CONFIG_SMP
-	sem->count += val;
-#else
-	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" (sem->count)
-	:"Ir" (val), "m" (sem->count));
-#endif
-}
-
-static inline long rwsem_atomic_update(long val, struct rw_semaphore *sem)
-{
-#ifndef	CONFIG_SMP
-	sem->count += val;
-	return sem->count;
-#else
-	long ret, temp;
-	__asm__ __volatile__(
-	"1:	ldq_l	%0,%1\n"
-	"	addq 	%0,%3,%2\n"
-	"	addq	%0,%3,%0\n"
-	"	stq_c	%2,%1\n"
-	"	beq	%2,2f\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	:"=&r" (ret), "=m" (sem->count), "=&r" (temp)
-	:"Ir" (val), "m" (sem->count));
-
-	return ret;
-#endif
-}
-
 #endif /* __KERNEL__ */
 #endif /* _ALPHA_RWSEM_H */
diff --git a/arch/alpha/include/asm/spinlock.h b/arch/alpha/include/asm/spinlock.h
index fed9c6f44c19..a40b9fc0c6c3 100644
--- a/arch/alpha/include/asm/spinlock.h
+++ b/arch/alpha/include/asm/spinlock.h
@@ -3,6 +3,8 @@
 
 #include <linux/kernel.h>
 #include <asm/current.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
 
 /*
  * Simple spin lock operations.  There are two variants, one clears IRQ's
@@ -13,8 +15,11 @@
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 #define arch_spin_is_locked(x)	((x)->lock != 0)
-#define arch_spin_unlock_wait(x) \
-		do { cpu_relax(); } while ((x)->lock)
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->lock, !VAL);
+}
 
 static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 {
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index dd683995bc9d..4e3c1b6b0806 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -67,6 +67,33 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return val;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned int val, orig;						\
+									\
+	/*								\
+	 * Explicit full memory barrier needed before/after as		\
+	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
+	 */								\
+	smp_mb();							\
+									\
+	__asm__ __volatile__(						\
+	"1:	llock   %[orig], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[orig], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"						\n"		\
+	: [val]	"=&r"	(val),						\
+	  [orig] "=&r" (orig)						\
+	: [ctr]	"r"	(&v->counter),					\
+	  [i]	"ir"	(i)						\
+	: "cc");							\
+									\
+	smp_mb();							\
+									\
+	return orig;							\
+}
+
 #else	/* !CONFIG_ARC_HAS_LLSC */
 
 #ifndef CONFIG_SMP
@@ -129,25 +156,44 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return temp;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+	unsigned long orig;						\
+									\
+	/*								\
+	 * spin lock/unlock provides the needed smp_mb() before/after	\
+	 */								\
+	atomic_ops_lock(flags);						\
+	orig = v->counter;						\
+	v->counter c_op i;						\
+	atomic_ops_unlock(flags);					\
+									\
+	return orig;							\
+}
+
 #endif /* !CONFIG_ARC_HAS_LLSC */
 
 #define ATOMIC_OPS(op, c_op, asm_op)					\
 	ATOMIC_OP(op, c_op, asm_op)					\
-	ATOMIC_OP_RETURN(op, c_op, asm_op)
+	ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
 #define atomic_andnot atomic_andnot
 
-ATOMIC_OP(and, &=, and)
-ATOMIC_OP(andnot, &= ~, bic)
-ATOMIC_OP(or, |=, or)
-ATOMIC_OP(xor, ^=, xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
-#undef SCOND_FAIL_RETRY_VAR_DEF
-#undef SCOND_FAIL_RETRY_ASM
-#undef SCOND_FAIL_RETRY_VARS
+ATOMIC_OPS(and, &=, and)
+ATOMIC_OPS(andnot, &= ~, bic)
+ATOMIC_OPS(or, |=, or)
+ATOMIC_OPS(xor, ^=, xor)
 
 #else /* CONFIG_ARC_PLAT_EZNPS */
 
@@ -208,22 +254,51 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return temp;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned int temp = i;						\
+									\
+	/* Explicit full memory barrier needed before/after */		\
+	smp_mb();							\
+									\
+	__asm__ __volatile__(						\
+	"	mov r2, %0\n"						\
+	"	mov r3, %1\n"						\
+	"       .word %2\n"						\
+	"	mov %0, r2"						\
+	: "+r"(temp)							\
+	: "r"(&v->counter), "i"(asm_op)					\
+	: "r2", "r3", "memory");					\
+									\
+	smp_mb();							\
+									\
+	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)
+	ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3)
 #define atomic_sub(i, v) atomic_add(-(i), (v))
 #define atomic_sub_return(i, v) atomic_add_return(-(i), (v))
 
-ATOMIC_OP(and, &=, CTOP_INST_AAND_DI_R2_R2_R3)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC_OPS(and, &=, CTOP_INST_AAND_DI_R2_R2_R3)
 #define atomic_andnot(mask, v) atomic_and(~(mask), (v))
-ATOMIC_OP(or, |=, CTOP_INST_AOR_DI_R2_R2_R3)
-ATOMIC_OP(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
+ATOMIC_OPS(or, |=, CTOP_INST_AOR_DI_R2_R2_R3)
+ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 
 #endif /* CONFIG_ARC_PLAT_EZNPS */
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index cded4a9b5438..233d5ffe6ec7 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -15,8 +15,11 @@
 
 #define arch_spin_is_locked(x)	((x)->slock != __ARCH_SPIN_LOCK_UNLOCKED__)
 #define arch_spin_lock_flags(lock, flags)	arch_spin_lock(lock)
-#define arch_spin_unlock_wait(x) \
-	do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0)
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->slock, !VAL);
+}
 
 #ifdef CONFIG_ARC_HAS_LLSC
 
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 9e10c4567eb4..66d0e215a773 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -77,8 +77,36 @@ static inline int atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 	return result;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
+{									\
+	unsigned long tmp;						\
+	int result, val;						\
+									\
+	prefetchw(&v->counter);						\
+									\
+	__asm__ __volatile__("@ atomic_fetch_" #op "\n"			\
+"1:	ldrex	%0, [%4]\n"						\
+"	" #asm_op "	%1, %0, %5\n"					\
+"	strex	%2, %1, [%4]\n"						\
+"	teq	%2, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Qo" (v->counter)	\
+	: "r" (&v->counter), "Ir" (i)					\
+	: "cc");							\
+									\
+	return result;							\
+}
+
 #define atomic_add_return_relaxed	atomic_add_return_relaxed
 #define atomic_sub_return_relaxed	atomic_sub_return_relaxed
+#define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
+#define atomic_fetch_sub_relaxed	atomic_fetch_sub_relaxed
+
+#define atomic_fetch_and_relaxed	atomic_fetch_and_relaxed
+#define atomic_fetch_andnot_relaxed	atomic_fetch_andnot_relaxed
+#define atomic_fetch_or_relaxed		atomic_fetch_or_relaxed
+#define atomic_fetch_xor_relaxed	atomic_fetch_xor_relaxed
 
 static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new)
 {
@@ -159,6 +187,20 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return val;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+	int val;							\
+									\
+	raw_local_irq_save(flags);					\
+	val = v->counter;						\
+	v->counter c_op i;						\
+	raw_local_irq_restore(flags);					\
+									\
+	return val;							\
+}
+
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int ret;
@@ -187,19 +229,26 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 
 #define ATOMIC_OPS(op, c_op, asm_op)					\
 	ATOMIC_OP(op, c_op, asm_op)					\
-	ATOMIC_OP_RETURN(op, c_op, asm_op)
+	ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
 #define atomic_andnot atomic_andnot
 
-ATOMIC_OP(and, &=, and)
-ATOMIC_OP(andnot, &= ~, bic)
-ATOMIC_OP(or,  |=, orr)
-ATOMIC_OP(xor, ^=, eor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC_OPS(and, &=, and)
+ATOMIC_OPS(andnot, &= ~, bic)
+ATOMIC_OPS(or,  |=, orr)
+ATOMIC_OPS(xor, ^=, eor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
@@ -317,24 +366,61 @@ atomic64_##op##_return_relaxed(long long i, atomic64_t *v)		\
 	return result;							\
 }
 
+#define ATOMIC64_FETCH_OP(op, op1, op2)					\
+static inline long long							\
+atomic64_fetch_##op##_relaxed(long long i, atomic64_t *v)		\
+{									\
+	long long result, val;						\
+	unsigned long tmp;						\
+									\
+	prefetchw(&v->counter);						\
+									\
+	__asm__ __volatile__("@ atomic64_fetch_" #op "\n"		\
+"1:	ldrexd	%0, %H0, [%4]\n"					\
+"	" #op1 " %Q1, %Q0, %Q5\n"					\
+"	" #op2 " %R1, %R0, %R5\n"					\
+"	strexd	%2, %1, %H1, [%4]\n"					\
+"	teq	%2, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Qo" (v->counter)	\
+	: "r" (&v->counter), "r" (i)					\
+	: "cc");							\
+									\
+	return result;							\
+}
+
 #define ATOMIC64_OPS(op, op1, op2)					\
 	ATOMIC64_OP(op, op1, op2)					\
-	ATOMIC64_OP_RETURN(op, op1, op2)
+	ATOMIC64_OP_RETURN(op, op1, op2)				\
+	ATOMIC64_FETCH_OP(op, op1, op2)
 
 ATOMIC64_OPS(add, adds, adc)
 ATOMIC64_OPS(sub, subs, sbc)
 
 #define atomic64_add_return_relaxed	atomic64_add_return_relaxed
 #define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
+#define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
+#define atomic64_fetch_sub_relaxed	atomic64_fetch_sub_relaxed
+
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op, op1, op2)					\
+	ATOMIC64_OP(op, op1, op2)					\
+	ATOMIC64_FETCH_OP(op, op1, op2)
 
 #define atomic64_andnot atomic64_andnot
 
-ATOMIC64_OP(and, and, and)
-ATOMIC64_OP(andnot, bic, bic)
-ATOMIC64_OP(or,  orr, orr)
-ATOMIC64_OP(xor, eor, eor)
+ATOMIC64_OPS(and, and, and)
+ATOMIC64_OPS(andnot, bic, bic)
+ATOMIC64_OPS(or,  orr, orr)
+ATOMIC64_OPS(xor, eor, eor)
+
+#define atomic64_fetch_and_relaxed	atomic64_fetch_and_relaxed
+#define atomic64_fetch_andnot_relaxed	atomic64_fetch_andnot_relaxed
+#define atomic64_fetch_or_relaxed	atomic64_fetch_or_relaxed
+#define atomic64_fetch_xor_relaxed	atomic64_fetch_xor_relaxed
 
 #undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index 0fa418463f49..4bec45442072 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -6,6 +6,8 @@
 #endif
 
 #include <linux/prefetch.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
 
 /*
  * sev and wfe are ARMv6K extensions.  Uniprocessor ARMv6 may not have the K
@@ -50,8 +52,21 @@ static inline void dsb_sev(void)
  * memory.
  */
 
-#define arch_spin_unlock_wait(lock) \
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	u16 owner = READ_ONCE(lock->tickets.owner);
+
+	for (;;) {
+		arch_spinlock_t tmp = READ_ONCE(*lock);
+
+		if (tmp.tickets.owner == tmp.tickets.next ||
+		    tmp.tickets.owner != owner)
+			break;
+
+		wfe();
+	}
+	smp_acquire__after_ctrl_dep();
+}
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index f3a3586a421c..c0235e0ff849 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -76,6 +76,36 @@
 #define atomic_dec_return_release(v)	atomic_sub_return_release(1, (v))
 #define atomic_dec_return(v)		atomic_sub_return(1, (v))
 
+#define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
+#define atomic_fetch_add_acquire	atomic_fetch_add_acquire
+#define atomic_fetch_add_release	atomic_fetch_add_release
+#define atomic_fetch_add		atomic_fetch_add
+
+#define atomic_fetch_sub_relaxed	atomic_fetch_sub_relaxed
+#define atomic_fetch_sub_acquire	atomic_fetch_sub_acquire
+#define atomic_fetch_sub_release	atomic_fetch_sub_release
+#define atomic_fetch_sub		atomic_fetch_sub
+
+#define atomic_fetch_and_relaxed	atomic_fetch_and_relaxed
+#define atomic_fetch_and_acquire	atomic_fetch_and_acquire
+#define atomic_fetch_and_release	atomic_fetch_and_release
+#define atomic_fetch_and		atomic_fetch_and
+
+#define atomic_fetch_andnot_relaxed	atomic_fetch_andnot_relaxed
+#define atomic_fetch_andnot_acquire	atomic_fetch_andnot_acquire
+#define atomic_fetch_andnot_release	atomic_fetch_andnot_release
+#define atomic_fetch_andnot		atomic_fetch_andnot
+
+#define atomic_fetch_or_relaxed		atomic_fetch_or_relaxed
+#define atomic_fetch_or_acquire		atomic_fetch_or_acquire
+#define atomic_fetch_or_release		atomic_fetch_or_release
+#define atomic_fetch_or			atomic_fetch_or
+
+#define atomic_fetch_xor_relaxed	atomic_fetch_xor_relaxed
+#define atomic_fetch_xor_acquire	atomic_fetch_xor_acquire
+#define atomic_fetch_xor_release	atomic_fetch_xor_release
+#define atomic_fetch_xor		atomic_fetch_xor
+
 #define atomic_xchg_relaxed(v, new)	xchg_relaxed(&((v)->counter), (new))
 #define atomic_xchg_acquire(v, new)	xchg_acquire(&((v)->counter), (new))
 #define atomic_xchg_release(v, new)	xchg_release(&((v)->counter), (new))
@@ -125,6 +155,36 @@
 #define atomic64_dec_return_release(v)	atomic64_sub_return_release(1, (v))
 #define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
 
+#define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
+#define atomic64_fetch_add_acquire	atomic64_fetch_add_acquire
+#define atomic64_fetch_add_release	atomic64_fetch_add_release
+#define atomic64_fetch_add		atomic64_fetch_add
+
+#define atomic64_fetch_sub_relaxed	atomic64_fetch_sub_relaxed
+#define atomic64_fetch_sub_acquire	atomic64_fetch_sub_acquire
+#define atomic64_fetch_sub_release	atomic64_fetch_sub_release
+#define atomic64_fetch_sub		atomic64_fetch_sub
+
+#define atomic64_fetch_and_relaxed	atomic64_fetch_and_relaxed
+#define atomic64_fetch_and_acquire	atomic64_fetch_and_acquire
+#define atomic64_fetch_and_release	atomic64_fetch_and_release
+#define atomic64_fetch_and		atomic64_fetch_and
+
+#define atomic64_fetch_andnot_relaxed	atomic64_fetch_andnot_relaxed
+#define atomic64_fetch_andnot_acquire	atomic64_fetch_andnot_acquire
+#define atomic64_fetch_andnot_release	atomic64_fetch_andnot_release
+#define atomic64_fetch_andnot		atomic64_fetch_andnot
+
+#define atomic64_fetch_or_relaxed	atomic64_fetch_or_relaxed
+#define atomic64_fetch_or_acquire	atomic64_fetch_or_acquire
+#define atomic64_fetch_or_release	atomic64_fetch_or_release
+#define atomic64_fetch_or		atomic64_fetch_or
+
+#define atomic64_fetch_xor_relaxed	atomic64_fetch_xor_relaxed
+#define atomic64_fetch_xor_acquire	atomic64_fetch_xor_acquire
+#define atomic64_fetch_xor_release	atomic64_fetch_xor_release
+#define atomic64_fetch_xor		atomic64_fetch_xor
+
 #define atomic64_xchg_relaxed		atomic_xchg_relaxed
 #define atomic64_xchg_acquire		atomic_xchg_acquire
 #define atomic64_xchg_release		atomic_xchg_release
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index f61c84f6ba02..f819fdcff1ac 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -77,26 +77,57 @@ __LL_SC_PREFIX(atomic_##op##_return##name(int i, atomic_t *v))		\
 }									\
 __LL_SC_EXPORT(atomic_##op##_return##name);
 
+#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op)		\
+__LL_SC_INLINE int							\
+__LL_SC_PREFIX(atomic_fetch_##op##name(int i, atomic_t *v))		\
+{									\
+	unsigned long tmp;						\
+	int val, result;						\
+									\
+	asm volatile("// atomic_fetch_" #op #name "\n"			\
+"	prfm	pstl1strm, %3\n"					\
+"1:	ld" #acq "xr	%w0, %3\n"					\
+"	" #asm_op "	%w1, %w0, %w4\n"				\
+"	st" #rel "xr	%w2, %w1, %3\n"					\
+"	cbnz	%w2, 1b\n"						\
+"	" #mb								\
+	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter)	\
+	: "Ir" (i)							\
+	: cl);								\
+									\
+	return result;							\
+}									\
+__LL_SC_EXPORT(atomic_fetch_##op##name);
+
 #define ATOMIC_OPS(...)							\
 	ATOMIC_OP(__VA_ARGS__)						\
-	ATOMIC_OP_RETURN(        , dmb ish,  , l, "memory", __VA_ARGS__)
-
-#define ATOMIC_OPS_RLX(...)						\
-	ATOMIC_OPS(__VA_ARGS__)						\
+	ATOMIC_OP_RETURN(        , dmb ish,  , l, "memory", __VA_ARGS__)\
 	ATOMIC_OP_RETURN(_relaxed,        ,  ,  ,         , __VA_ARGS__)\
 	ATOMIC_OP_RETURN(_acquire,        , a,  , "memory", __VA_ARGS__)\
-	ATOMIC_OP_RETURN(_release,        ,  , l, "memory", __VA_ARGS__)
+	ATOMIC_OP_RETURN(_release,        ,  , l, "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (        , dmb ish,  , l, "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_relaxed,        ,  ,  ,         , __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_acquire,        , a,  , "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_release,        ,  , l, "memory", __VA_ARGS__)
 
-ATOMIC_OPS_RLX(add, add)
-ATOMIC_OPS_RLX(sub, sub)
+ATOMIC_OPS(add, add)
+ATOMIC_OPS(sub, sub)
+
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(...)							\
+	ATOMIC_OP(__VA_ARGS__)						\
+	ATOMIC_FETCH_OP (        , dmb ish,  , l, "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_relaxed,        ,  ,  ,         , __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_acquire,        , a,  , "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_release,        ,  , l, "memory", __VA_ARGS__)
 
-ATOMIC_OP(and, and)
-ATOMIC_OP(andnot, bic)
-ATOMIC_OP(or, orr)
-ATOMIC_OP(xor, eor)
+ATOMIC_OPS(and, and)
+ATOMIC_OPS(andnot, bic)
+ATOMIC_OPS(or, orr)
+ATOMIC_OPS(xor, eor)
 
-#undef ATOMIC_OPS_RLX
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
@@ -140,26 +171,57 @@ __LL_SC_PREFIX(atomic64_##op##_return##name(long i, atomic64_t *v))	\
 }									\
 __LL_SC_EXPORT(atomic64_##op##_return##name);
 
+#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op)		\
+__LL_SC_INLINE long							\
+__LL_SC_PREFIX(atomic64_fetch_##op##name(long i, atomic64_t *v))	\
+{									\
+	long result, val;						\
+	unsigned long tmp;						\
+									\
+	asm volatile("// atomic64_fetch_" #op #name "\n"		\
+"	prfm	pstl1strm, %3\n"					\
+"1:	ld" #acq "xr	%0, %3\n"					\
+"	" #asm_op "	%1, %0, %4\n"					\
+"	st" #rel "xr	%w2, %1, %3\n"					\
+"	cbnz	%w2, 1b\n"						\
+"	" #mb								\
+	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter)	\
+	: "Ir" (i)							\
+	: cl);								\
+									\
+	return result;							\
+}									\
+__LL_SC_EXPORT(atomic64_fetch_##op##name);
+
 #define ATOMIC64_OPS(...)						\
 	ATOMIC64_OP(__VA_ARGS__)					\
-	ATOMIC64_OP_RETURN(, dmb ish,  , l, "memory", __VA_ARGS__)
-
-#define ATOMIC64_OPS_RLX(...)						\
-	ATOMIC64_OPS(__VA_ARGS__)					\
+	ATOMIC64_OP_RETURN(, dmb ish,  , l, "memory", __VA_ARGS__)	\
 	ATOMIC64_OP_RETURN(_relaxed,,  ,  ,         , __VA_ARGS__)	\
 	ATOMIC64_OP_RETURN(_acquire,, a,  , "memory", __VA_ARGS__)	\
-	ATOMIC64_OP_RETURN(_release,,  , l, "memory", __VA_ARGS__)
+	ATOMIC64_OP_RETURN(_release,,  , l, "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (, dmb ish,  , l, "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_relaxed,,  ,  ,         , __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_acquire,, a,  , "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_release,,  , l, "memory", __VA_ARGS__)
 
-ATOMIC64_OPS_RLX(add, add)
-ATOMIC64_OPS_RLX(sub, sub)
+ATOMIC64_OPS(add, add)
+ATOMIC64_OPS(sub, sub)
+
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(...)						\
+	ATOMIC64_OP(__VA_ARGS__)					\
+	ATOMIC64_FETCH_OP (, dmb ish,  , l, "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_relaxed,,  ,  ,         , __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_acquire,, a,  , "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_release,,  , l, "memory", __VA_ARGS__)
 
-ATOMIC64_OP(and, and)
-ATOMIC64_OP(andnot, bic)
-ATOMIC64_OP(or, orr)
-ATOMIC64_OP(xor, eor)
+ATOMIC64_OPS(and, and)
+ATOMIC64_OPS(andnot, bic)
+ATOMIC64_OPS(or, orr)
+ATOMIC64_OPS(xor, eor)
 
-#undef ATOMIC64_OPS_RLX
 #undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 39c1d340fec5..b5890be8f257 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -26,54 +26,57 @@
 #endif
 
 #define __LL_SC_ATOMIC(op)	__LL_SC_CALL(atomic_##op)
-
-static inline void atomic_andnot(int i, atomic_t *v)
-{
-	register int w0 asm ("w0") = i;
-	register atomic_t *x1 asm ("x1") = v;
-
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(andnot),
-	"	stclr	%w[i], %[v]\n")
-	: [i] "+r" (w0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
+#define ATOMIC_OP(op, asm_op)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	register int w0 asm ("w0") = i;					\
+	register atomic_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(op),		\
+"	" #asm_op "	%w[i], %[v]\n")					\
+	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS);						\
 }
 
-static inline void atomic_or(int i, atomic_t *v)
-{
-	register int w0 asm ("w0") = i;
-	register atomic_t *x1 asm ("x1") = v;
+ATOMIC_OP(andnot, stclr)
+ATOMIC_OP(or, stset)
+ATOMIC_OP(xor, steor)
+ATOMIC_OP(add, stadd)
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(or),
-	"	stset	%w[i], %[v]\n")
-	: [i] "+r" (w0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
-}
+#undef ATOMIC_OP
 
-static inline void atomic_xor(int i, atomic_t *v)
-{
-	register int w0 asm ("w0") = i;
-	register atomic_t *x1 asm ("x1") = v;
-
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(xor),
-	"	steor	%w[i], %[v]\n")
-	: [i] "+r" (w0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
+#define ATOMIC_FETCH_OP(name, mb, op, asm_op, cl...)			\
+static inline int atomic_fetch_##op##name(int i, atomic_t *v)		\
+{									\
+	register int w0 asm ("w0") = i;					\
+	register atomic_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	__LL_SC_ATOMIC(fetch_##op##name),				\
+	/* LSE atomics */						\
+"	" #asm_op #mb "	%w[i], %w[i], %[v]")				\
+	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS, ##cl);					\
+									\
+	return w0;							\
 }
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	register int w0 asm ("w0") = i;
-	register atomic_t *x1 asm ("x1") = v;
+#define ATOMIC_FETCH_OPS(op, asm_op)					\
+	ATOMIC_FETCH_OP(_relaxed,   , op, asm_op)			\
+	ATOMIC_FETCH_OP(_acquire,  a, op, asm_op, "memory")		\
+	ATOMIC_FETCH_OP(_release,  l, op, asm_op, "memory")		\
+	ATOMIC_FETCH_OP(        , al, op, asm_op, "memory")
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(add),
-	"	stadd	%w[i], %[v]\n")
-	: [i] "+r" (w0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
-}
+ATOMIC_FETCH_OPS(andnot, ldclr)
+ATOMIC_FETCH_OPS(or, ldset)
+ATOMIC_FETCH_OPS(xor, ldeor)
+ATOMIC_FETCH_OPS(add, ldadd)
+
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_FETCH_OPS
 
 #define ATOMIC_OP_ADD_RETURN(name, mb, cl...)				\
 static inline int atomic_add_return##name(int i, atomic_t *v)		\
@@ -119,6 +122,33 @@ static inline void atomic_and(int i, atomic_t *v)
 	: __LL_SC_CLOBBERS);
 }
 
+#define ATOMIC_FETCH_OP_AND(name, mb, cl...)				\
+static inline int atomic_fetch_and##name(int i, atomic_t *v)		\
+{									\
+	register int w0 asm ("w0") = i;					\
+	register atomic_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+	__LL_SC_ATOMIC(fetch_and##name),				\
+	/* LSE atomics */						\
+	"	mvn	%w[i], %w[i]\n"					\
+	"	ldclr" #mb "	%w[i], %w[i], %[v]")			\
+	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS, ##cl);					\
+									\
+	return w0;							\
+}
+
+ATOMIC_FETCH_OP_AND(_relaxed,   )
+ATOMIC_FETCH_OP_AND(_acquire,  a, "memory")
+ATOMIC_FETCH_OP_AND(_release,  l, "memory")
+ATOMIC_FETCH_OP_AND(        , al, "memory")
+
+#undef ATOMIC_FETCH_OP_AND
+
 static inline void atomic_sub(int i, atomic_t *v)
 {
 	register int w0 asm ("w0") = i;
@@ -164,57 +194,87 @@ ATOMIC_OP_SUB_RETURN(_release,  l, "memory")
 ATOMIC_OP_SUB_RETURN(        , al, "memory")
 
 #undef ATOMIC_OP_SUB_RETURN
-#undef __LL_SC_ATOMIC
-
-#define __LL_SC_ATOMIC64(op)	__LL_SC_CALL(atomic64_##op)
-
-static inline void atomic64_andnot(long i, atomic64_t *v)
-{
-	register long x0 asm ("x0") = i;
-	register atomic64_t *x1 asm ("x1") = v;
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(andnot),
-	"	stclr	%[i], %[v]\n")
-	: [i] "+r" (x0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
+#define ATOMIC_FETCH_OP_SUB(name, mb, cl...)				\
+static inline int atomic_fetch_sub##name(int i, atomic_t *v)		\
+{									\
+	register int w0 asm ("w0") = i;					\
+	register atomic_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+	__LL_SC_ATOMIC(fetch_sub##name),				\
+	/* LSE atomics */						\
+	"	neg	%w[i], %w[i]\n"					\
+	"	ldadd" #mb "	%w[i], %w[i], %[v]")			\
+	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS, ##cl);					\
+									\
+	return w0;							\
 }
 
-static inline void atomic64_or(long i, atomic64_t *v)
-{
-	register long x0 asm ("x0") = i;
-	register atomic64_t *x1 asm ("x1") = v;
+ATOMIC_FETCH_OP_SUB(_relaxed,   )
+ATOMIC_FETCH_OP_SUB(_acquire,  a, "memory")
+ATOMIC_FETCH_OP_SUB(_release,  l, "memory")
+ATOMIC_FETCH_OP_SUB(        , al, "memory")
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(or),
-	"	stset	%[i], %[v]\n")
-	: [i] "+r" (x0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
+#undef ATOMIC_FETCH_OP_SUB
+#undef __LL_SC_ATOMIC
+
+#define __LL_SC_ATOMIC64(op)	__LL_SC_CALL(atomic64_##op)
+#define ATOMIC64_OP(op, asm_op)						\
+static inline void atomic64_##op(long i, atomic64_t *v)			\
+{									\
+	register long x0 asm ("x0") = i;				\
+	register atomic64_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(op),	\
+"	" #asm_op "	%[i], %[v]\n")					\
+	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS);						\
 }
 
-static inline void atomic64_xor(long i, atomic64_t *v)
-{
-	register long x0 asm ("x0") = i;
-	register atomic64_t *x1 asm ("x1") = v;
+ATOMIC64_OP(andnot, stclr)
+ATOMIC64_OP(or, stset)
+ATOMIC64_OP(xor, steor)
+ATOMIC64_OP(add, stadd)
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(xor),
-	"	steor	%[i], %[v]\n")
-	: [i] "+r" (x0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
+#undef ATOMIC64_OP
+
+#define ATOMIC64_FETCH_OP(name, mb, op, asm_op, cl...)			\
+static inline long atomic64_fetch_##op##name(long i, atomic64_t *v)	\
+{									\
+	register long x0 asm ("x0") = i;				\
+	register atomic64_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	__LL_SC_ATOMIC64(fetch_##op##name),				\
+	/* LSE atomics */						\
+"	" #asm_op #mb "	%[i], %[i], %[v]")				\
+	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS, ##cl);					\
+									\
+	return x0;							\
 }
 
-static inline void atomic64_add(long i, atomic64_t *v)
-{
-	register long x0 asm ("x0") = i;
-	register atomic64_t *x1 asm ("x1") = v;
+#define ATOMIC64_FETCH_OPS(op, asm_op)					\
+	ATOMIC64_FETCH_OP(_relaxed,   , op, asm_op)			\
+	ATOMIC64_FETCH_OP(_acquire,  a, op, asm_op, "memory")		\
+	ATOMIC64_FETCH_OP(_release,  l, op, asm_op, "memory")		\
+	ATOMIC64_FETCH_OP(        , al, op, asm_op, "memory")
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(add),
-	"	stadd	%[i], %[v]\n")
-	: [i] "+r" (x0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: __LL_SC_CLOBBERS);
-}
+ATOMIC64_FETCH_OPS(andnot, ldclr)
+ATOMIC64_FETCH_OPS(or, ldset)
+ATOMIC64_FETCH_OPS(xor, ldeor)
+ATOMIC64_FETCH_OPS(add, ldadd)
+
+#undef ATOMIC64_FETCH_OP
+#undef ATOMIC64_FETCH_OPS
 
 #define ATOMIC64_OP_ADD_RETURN(name, mb, cl...)				\
 static inline long atomic64_add_return##name(long i, atomic64_t *v)	\
@@ -260,6 +320,33 @@ static inline void atomic64_and(long i, atomic64_t *v)
 	: __LL_SC_CLOBBERS);
 }
 
+#define ATOMIC64_FETCH_OP_AND(name, mb, cl...)				\
+static inline long atomic64_fetch_and##name(long i, atomic64_t *v)	\
+{									\
+	register long x0 asm ("w0") = i;				\
+	register atomic64_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+	__LL_SC_ATOMIC64(fetch_and##name),				\
+	/* LSE atomics */						\
+	"	mvn	%[i], %[i]\n"					\
+	"	ldclr" #mb "	%[i], %[i], %[v]")			\
+	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS, ##cl);					\
+									\
+	return x0;							\
+}
+
+ATOMIC64_FETCH_OP_AND(_relaxed,   )
+ATOMIC64_FETCH_OP_AND(_acquire,  a, "memory")
+ATOMIC64_FETCH_OP_AND(_release,  l, "memory")
+ATOMIC64_FETCH_OP_AND(        , al, "memory")
+
+#undef ATOMIC64_FETCH_OP_AND
+
 static inline void atomic64_sub(long i, atomic64_t *v)
 {
 	register long x0 asm ("x0") = i;
@@ -306,6 +393,33 @@ ATOMIC64_OP_SUB_RETURN(        , al, "memory")
 
 #undef ATOMIC64_OP_SUB_RETURN
 
+#define ATOMIC64_FETCH_OP_SUB(name, mb, cl...)				\
+static inline long atomic64_fetch_sub##name(long i, atomic64_t *v)	\
+{									\
+	register long x0 asm ("w0") = i;				\
+	register atomic64_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+	__LL_SC_ATOMIC64(fetch_sub##name),				\
+	/* LSE atomics */						\
+	"	neg	%[i], %[i]\n"					\
+	"	ldadd" #mb "	%[i], %[i], %[v]")			\
+	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: __LL_SC_CLOBBERS, ##cl);					\
+									\
+	return x0;							\
+}
+
+ATOMIC64_FETCH_OP_SUB(_relaxed,   )
+ATOMIC64_FETCH_OP_SUB(_acquire,  a, "memory")
+ATOMIC64_FETCH_OP_SUB(_release,  l, "memory")
+ATOMIC64_FETCH_OP_SUB(        , al, "memory")
+
+#undef ATOMIC64_FETCH_OP_SUB
+
 static inline long atomic64_dec_if_positive(atomic64_t *v)
 {
 	register long x0 asm ("x0") = (long)v;
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index dae5c49618db..4eea7f618dce 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -91,6 +91,19 @@ do {									\
 	__u.__val;							\
 })
 
+#define smp_cond_load_acquire(ptr, cond_expr)				\
+({									\
+	typeof(ptr) __PTR = (ptr);					\
+	typeof(*ptr) VAL;						\
+	for (;;) {							\
+		VAL = smp_load_acquire(__PTR);				\
+		if (cond_expr)						\
+			break;						\
+		__cmpwait_relaxed(__PTR, VAL);				\
+	}								\
+	VAL;								\
+})
+
 #include <asm-generic/barrier.h>
 
 #endif	/* __ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 510c7b404454..bd86a79491bc 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -224,4 +224,55 @@ __CMPXCHG_GEN(_mb)
 	__ret;								\
 })
 
+#define __CMPWAIT_CASE(w, sz, name)					\
+static inline void __cmpwait_case_##name(volatile void *ptr,		\
+					 unsigned long val)		\
+{									\
+	unsigned long tmp;						\
+									\
+	asm volatile(							\
+	"	ldxr" #sz "\t%" #w "[tmp], %[v]\n"		\
+	"	eor	%" #w "[tmp], %" #w "[tmp], %" #w "[val]\n"	\
+	"	cbnz	%" #w "[tmp], 1f\n"				\
+	"	wfe\n"							\
+	"1:"								\
+	: [tmp] "=&r" (tmp), [v] "+Q" (*(unsigned long *)ptr)		\
+	: [val] "r" (val));						\
+}
+
+__CMPWAIT_CASE(w, b, 1);
+__CMPWAIT_CASE(w, h, 2);
+__CMPWAIT_CASE(w,  , 4);
+__CMPWAIT_CASE( ,  , 8);
+
+#undef __CMPWAIT_CASE
+
+#define __CMPWAIT_GEN(sfx)						\
+static inline void __cmpwait##sfx(volatile void *ptr,			\
+				  unsigned long val,			\
+				  int size)				\
+{									\
+	switch (size) {							\
+	case 1:								\
+		return __cmpwait_case##sfx##_1(ptr, (u8)val);		\
+	case 2:								\
+		return __cmpwait_case##sfx##_2(ptr, (u16)val);		\
+	case 4:								\
+		return __cmpwait_case##sfx##_4(ptr, val);		\
+	case 8:								\
+		return __cmpwait_case##sfx##_8(ptr, val);		\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+									\
+	unreachable();							\
+}
+
+__CMPWAIT_GEN()
+
+#undef __CMPWAIT_GEN
+
+#define __cmpwait_relaxed(ptr, val) \
+	__cmpwait((ptr), (unsigned long)(val), sizeof(*(ptr)))
+
 #endif	/* __ASM_CMPXCHG_H */
diff --git a/arch/avr32/include/asm/atomic.h b/arch/avr32/include/asm/atomic.h
index d74fd8ce980a..3d5ce38a6f0b 100644
--- a/arch/avr32/include/asm/atomic.h
+++ b/arch/avr32/include/asm/atomic.h
@@ -41,21 +41,49 @@ static inline int __atomic_##op##_return(int i, atomic_t *v)		\
 	return result;							\
 }
 
+#define ATOMIC_FETCH_OP(op, asm_op, asm_con)				\
+static inline int __atomic_fetch_##op(int i, atomic_t *v)		\
+{									\
+	int result, val;						\
+									\
+	asm volatile(							\
+		"/* atomic_fetch_" #op " */\n"				\
+		"1:	ssrf	5\n"					\
+		"	ld.w	%0, %3\n"				\
+		"	mov	%1, %0\n"				\
+		"	" #asm_op "	%1, %4\n"			\
+		"	stcond	%2, %1\n"				\
+		"	brne	1b"					\
+		: "=&r" (result), "=&r" (val), "=o" (v->counter)	\
+		: "m" (v->counter), #asm_con (i)			\
+		: "cc");						\
+									\
+	return result;							\
+}
+
 ATOMIC_OP_RETURN(sub, sub, rKs21)
 ATOMIC_OP_RETURN(add, add, r)
+ATOMIC_FETCH_OP (sub, sub, rKs21)
+ATOMIC_FETCH_OP (add, add, r)
 
-#define ATOMIC_OP(op, asm_op)						\
+#define ATOMIC_OPS(op, asm_op)						\
 ATOMIC_OP_RETURN(op, asm_op, r)						\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
 	(void)__atomic_##op##_return(i, v);				\
+}									\
+ATOMIC_FETCH_OP(op, asm_op, r)						\
+static inline int atomic_fetch_##op(int i, atomic_t *v)		\
+{									\
+	return __atomic_fetch_##op(i, v);				\
 }
 
-ATOMIC_OP(and, and)
-ATOMIC_OP(or, or)
-ATOMIC_OP(xor, eor)
+ATOMIC_OPS(and, and)
+ATOMIC_OPS(or, or)
+ATOMIC_OPS(xor, eor)
 
-#undef ATOMIC_OP
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 
 /*
@@ -87,6 +115,14 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	return __atomic_add_return(i, v);
 }
 
+static inline int atomic_fetch_add(int i, atomic_t *v)
+{
+	if (IS_21BIT_CONST(i))
+		return __atomic_fetch_sub(-i, v);
+
+	return __atomic_fetch_add(i, v);
+}
+
 /*
  * atomic_sub_return - subtract the atomic variable
  * @i: integer value to subtract
@@ -102,6 +138,14 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 	return __atomic_add_return(-i, v);
 }
 
+static inline int atomic_fetch_sub(int i, atomic_t *v)
+{
+	if (IS_21BIT_CONST(i))
+		return __atomic_fetch_sub(i, v);
+
+	return __atomic_fetch_add(-i, v);
+}
+
 /*
  * __atomic_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
diff --git a/arch/blackfin/include/asm/atomic.h b/arch/blackfin/include/asm/atomic.h
index 1c1c42330c99..63c7deceeeb6 100644
--- a/arch/blackfin/include/asm/atomic.h
+++ b/arch/blackfin/include/asm/atomic.h
@@ -17,6 +17,7 @@
 
 asmlinkage int __raw_uncached_fetch_asm(const volatile int *ptr);
 asmlinkage int __raw_atomic_add_asm(volatile int *ptr, int value);
+asmlinkage int __raw_atomic_xadd_asm(volatile int *ptr, int value);
 
 asmlinkage int __raw_atomic_and_asm(volatile int *ptr, int value);
 asmlinkage int __raw_atomic_or_asm(volatile int *ptr, int value);
@@ -28,10 +29,17 @@ asmlinkage int __raw_atomic_test_asm(const volatile int *ptr, int value);
 #define atomic_add_return(i, v) __raw_atomic_add_asm(&(v)->counter, i)
 #define atomic_sub_return(i, v) __raw_atomic_add_asm(&(v)->counter, -(i))
 
+#define atomic_fetch_add(i, v) __raw_atomic_xadd_asm(&(v)->counter, i)
+#define atomic_fetch_sub(i, v) __raw_atomic_xadd_asm(&(v)->counter, -(i))
+
 #define atomic_or(i, v)  (void)__raw_atomic_or_asm(&(v)->counter, i)
 #define atomic_and(i, v) (void)__raw_atomic_and_asm(&(v)->counter, i)
 #define atomic_xor(i, v) (void)__raw_atomic_xor_asm(&(v)->counter, i)
 
+#define atomic_fetch_or(i, v)  __raw_atomic_or_asm(&(v)->counter, i)
+#define atomic_fetch_and(i, v) __raw_atomic_and_asm(&(v)->counter, i)
+#define atomic_fetch_xor(i, v) __raw_atomic_xor_asm(&(v)->counter, i)
+
 #endif
 
 #include <asm-generic/atomic.h>
diff --git a/arch/blackfin/include/asm/spinlock.h b/arch/blackfin/include/asm/spinlock.h
index 490c7caa02d9..c58f4a83ed6f 100644
--- a/arch/blackfin/include/asm/spinlock.h
+++ b/arch/blackfin/include/asm/spinlock.h
@@ -12,6 +12,8 @@
 #else
 
 #include <linux/atomic.h>
+#include <asm/processor.h>
+#include <asm/barrier.h>
 
 asmlinkage int __raw_spin_is_locked_asm(volatile int *ptr);
 asmlinkage void __raw_spin_lock_asm(volatile int *ptr);
@@ -48,8 +50,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
-	while (arch_spin_is_locked(lock))
-		cpu_relax();
+	smp_cond_load_acquire(&lock->lock, !VAL);
 }
 
 static inline int arch_read_can_lock(arch_rwlock_t *rw)
diff --git a/arch/blackfin/kernel/bfin_ksyms.c b/arch/blackfin/kernel/bfin_ksyms.c
index a401c27b69b4..68096e8f787f 100644
--- a/arch/blackfin/kernel/bfin_ksyms.c
+++ b/arch/blackfin/kernel/bfin_ksyms.c
@@ -84,6 +84,7 @@ EXPORT_SYMBOL(insl_16);
 
 #ifdef CONFIG_SMP
 EXPORT_SYMBOL(__raw_atomic_add_asm);
+EXPORT_SYMBOL(__raw_atomic_xadd_asm);
 EXPORT_SYMBOL(__raw_atomic_and_asm);
 EXPORT_SYMBOL(__raw_atomic_or_asm);
 EXPORT_SYMBOL(__raw_atomic_xor_asm);
diff --git a/arch/blackfin/mach-bf561/atomic.S b/arch/blackfin/mach-bf561/atomic.S
index 26fccb5568b9..1e2989c5d6b2 100644
--- a/arch/blackfin/mach-bf561/atomic.S
+++ b/arch/blackfin/mach-bf561/atomic.S
@@ -607,6 +607,28 @@ ENDPROC(___raw_atomic_add_asm)
 
 /*
  * r0 = ptr
+ * r1 = value
+ *
+ * ADD a signed value to a 32bit word and return the old value atomically.
+ * Clobbers: r3:0, p1:0
+ */
+ENTRY(___raw_atomic_xadd_asm)
+	p1 = r0;
+	r3 = r1;
+	[--sp] = rets;
+	call _get_core_lock;
+	r3 = [p1];
+	r2 = r3 + r2;
+	[p1] = r2;
+	r1 = p1;
+	call _put_core_lock;
+	r0 = r3;
+	rets = [sp++];
+	rts;
+ENDPROC(___raw_atomic_add_asm)
+
+/*
+ * r0 = ptr
  * r1 = mask
  *
  * AND the mask bits from a 32bit word and return the old 32bit value
@@ -618,10 +640,9 @@ ENTRY(___raw_atomic_and_asm)
 	r3 = r1;
 	[--sp] = rets;
 	call _get_core_lock;
-	r2 = [p1];
-	r3 = r2 & r3;
-	[p1] = r3;
-	r3 = r2;
+	r3 = [p1];
+	r2 = r2 & r3;
+	[p1] = r2;
 	r1 = p1;
 	call _put_core_lock;
 	r0 = r3;
@@ -642,10 +663,9 @@ ENTRY(___raw_atomic_or_asm)
 	r3 = r1;
 	[--sp] = rets;
 	call _get_core_lock;
-	r2 = [p1];
-	r3 = r2 | r3;
-	[p1] = r3;
-	r3 = r2;
+	r3 = [p1];
+	r2 = r2 | r3;
+	[p1] = r2;
 	r1 = p1;
 	call _put_core_lock;
 	r0 = r3;
@@ -666,10 +686,9 @@ ENTRY(___raw_atomic_xor_asm)
 	r3 = r1;
 	[--sp] = rets;
 	call _get_core_lock;
-	r2 = [p1];
-	r3 = r2 ^ r3;
-	[p1] = r3;
-	r3 = r2;
+	r3 = [p1];
+	r2 = r2 ^ r3;
+	[p1] = r2;
 	r1 = p1;
 	call _put_core_lock;
 	r0 = r3;
diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h
index 64f02d451aa8..1c2a5e264fc7 100644
--- a/arch/frv/include/asm/atomic.h
+++ b/arch/frv/include/asm/atomic.h
@@ -60,16 +60,6 @@ static inline int atomic_add_negative(int i, atomic_t *v)
 	return atomic_add_return(i, v) < 0;
 }
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	atomic_add_return(i, v);
-}
-
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	atomic_sub_return(i, v);
-}
-
 static inline void atomic_inc(atomic_t *v)
 {
 	atomic_inc_return(v);
@@ -136,16 +126,6 @@ static inline long long atomic64_add_negative(long long i, atomic64_t *v)
 	return atomic64_add_return(i, v) < 0;
 }
 
-static inline void atomic64_add(long long i, atomic64_t *v)
-{
-	atomic64_add_return(i, v);
-}
-
-static inline void atomic64_sub(long long i, atomic64_t *v)
-{
-	atomic64_sub_return(i, v);
-}
-
 static inline void atomic64_inc(atomic64_t *v)
 {
 	atomic64_inc_return(v);
@@ -182,11 +162,19 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 }
 
 #define ATOMIC_OP(op)							\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	return __atomic32_fetch_##op(i, &v->counter);			\
+}									\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
 	(void)__atomic32_fetch_##op(i, &v->counter);			\
 }									\
 									\
+static inline long long atomic64_fetch_##op(long long i, atomic64_t *v)	\
+{									\
+	return __atomic64_fetch_##op(i, &v->counter);			\
+}									\
 static inline void atomic64_##op(long long i, atomic64_t *v)		\
 {									\
 	(void)__atomic64_fetch_##op(i, &v->counter);			\
@@ -195,6 +183,8 @@ static inline void atomic64_##op(long long i, atomic64_t *v)		\
 ATOMIC_OP(or)
 ATOMIC_OP(and)
 ATOMIC_OP(xor)
+ATOMIC_OP(add)
+ATOMIC_OP(sub)
 
 #undef ATOMIC_OP
 
diff --git a/arch/frv/include/asm/atomic_defs.h b/arch/frv/include/asm/atomic_defs.h
index 36e126d2f801..d4912c88b829 100644
--- a/arch/frv/include/asm/atomic_defs.h
+++ b/arch/frv/include/asm/atomic_defs.h
@@ -162,6 +162,8 @@ ATOMIC_EXPORT(__atomic64_fetch_##op);
 ATOMIC_FETCH_OP(or)
 ATOMIC_FETCH_OP(and)
 ATOMIC_FETCH_OP(xor)
+ATOMIC_FETCH_OP(add)
+ATOMIC_FETCH_OP(sub)
 
 ATOMIC_OP_RETURN(add)
 ATOMIC_OP_RETURN(sub)
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index 4435a445ae7e..349a47a918db 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -28,6 +28,19 @@ static inline int atomic_##op##_return(int i, atomic_t *v)	\
 	return ret;						\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op)				\
+static inline int atomic_fetch_##op(int i, atomic_t *v)		\
+{								\
+	h8300flags flags;					\
+	int ret;						\
+								\
+	flags = arch_local_irq_save();				\
+	ret = v->counter;					\
+	v->counter c_op i;					\
+	arch_local_irq_restore(flags);				\
+	return ret;						\
+}
+
 #define ATOMIC_OP(op, c_op)					\
 static inline void atomic_##op(int i, atomic_t *v)		\
 {								\
@@ -41,17 +54,21 @@ static inline void atomic_##op(int i, atomic_t *v)		\
 ATOMIC_OP_RETURN(add, +=)
 ATOMIC_OP_RETURN(sub, -=)
 
-ATOMIC_OP(and, &=)
-ATOMIC_OP(or,  |=)
-ATOMIC_OP(xor, ^=)
+#define ATOMIC_OPS(op, c_op)					\
+	ATOMIC_OP(op, c_op)					\
+	ATOMIC_FETCH_OP(op, c_op)
+
+ATOMIC_OPS(and, &=)
+ATOMIC_OPS(or,  |=)
+ATOMIC_OPS(xor, ^=)
+ATOMIC_OPS(add, +=)
+ATOMIC_OPS(sub, -=)
 
+#undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_add(i, v)		(void)atomic_add_return(i, v)
 #define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
-#define atomic_sub(i, v)		(void)atomic_sub_return(i, v)
 #define atomic_sub_and_test(i, v)	(atomic_sub_return(i, v) == 0)
 
 #define atomic_inc_return(v)		atomic_add_return(1, v)
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index 55696c4100d4..a62ba368b27d 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -110,7 +110,7 @@ static inline void atomic_##op(int i, atomic_t *v)			\
 	);								\
 }									\
 
-#define ATOMIC_OP_RETURN(op)							\
+#define ATOMIC_OP_RETURN(op)						\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
 	int output;							\
@@ -127,16 +127,37 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return output;							\
 }
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int output, val;						\
+									\
+	__asm__ __volatile__ (						\
+		"1:	%0 = memw_locked(%2);\n"			\
+		"	%1 = "#op "(%0,%3);\n"				\
+		"	memw_locked(%2,P3)=%1;\n"			\
+		"	if !P3 jump 1b;\n"				\
+		: "=&r" (output), "=&r" (val)				\
+		: "r" (&v->counter), "r" (i)				\
+		: "memory", "p3"					\
+	);								\
+	return output;							\
+}
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/hexagon/include/asm/spinlock.h b/arch/hexagon/include/asm/spinlock.h
index 12ca4ebc0338..a1c55788c5d6 100644
--- a/arch/hexagon/include/asm/spinlock.h
+++ b/arch/hexagon/include/asm/spinlock.h
@@ -23,6 +23,8 @@
 #define _ASM_SPINLOCK_H
 
 #include <asm/irqflags.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
 
 /*
  * This file is pulled in for SMP builds.
@@ -176,8 +178,12 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
  * SMP spinlocks are intended to allow only a single CPU at the lock
  */
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-#define arch_spin_unlock_wait(lock) \
-	do {while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->lock, !VAL);
+}
+
 #define arch_spin_is_locked(x) ((x)->lock != 0)
 
 #define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 8dfb5f6f6c35..f565ad376142 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -42,8 +42,27 @@ ia64_atomic_##op (int i, atomic_t *v)					\
 	return new;							\
 }
 
-ATOMIC_OP(add, +)
-ATOMIC_OP(sub, -)
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static __inline__ int							\
+ia64_atomic_fetch_##op (int i, atomic_t *v)				\
+{									\
+	__s32 old, new;							\
+	CMPXCHG_BUGCHECK_DECL						\
+									\
+	do {								\
+		CMPXCHG_BUGCHECK(v);					\
+		old = atomic_read(v);					\
+		new = old c_op i;					\
+	} while (ia64_cmpxchg(acq, v, old, new, sizeof(atomic_t)) != old); \
+	return old;							\
+}
+
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op, c_op)						\
+	ATOMIC_FETCH_OP(op, c_op)
+
+ATOMIC_OPS(add, +)
+ATOMIC_OPS(sub, -)
 
 #define atomic_add_return(i,v)						\
 ({									\
@@ -69,14 +88,44 @@ ATOMIC_OP(sub, -)
 		: ia64_atomic_sub(__ia64_asr_i, v);			\
 })
 
-ATOMIC_OP(and, &)
-ATOMIC_OP(or, |)
-ATOMIC_OP(xor, ^)
+#define atomic_fetch_add(i,v)						\
+({									\
+	int __ia64_aar_i = (i);						\
+	(__builtin_constant_p(i)					\
+	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
+	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
+	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
+	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+		? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq)	\
+		: ia64_atomic_fetch_add(__ia64_aar_i, v);		\
+})
+
+#define atomic_fetch_sub(i,v)						\
+({									\
+	int __ia64_asr_i = (i);						\
+	(__builtin_constant_p(i)					\
+	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
+	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
+	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
+	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+		? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq)	\
+		: ia64_atomic_fetch_sub(__ia64_asr_i, v);		\
+})
+
+ATOMIC_FETCH_OP(and, &)
+ATOMIC_FETCH_OP(or, |)
+ATOMIC_FETCH_OP(xor, ^)
+
+#define atomic_and(i,v)	(void)ia64_atomic_fetch_and(i,v)
+#define atomic_or(i,v)	(void)ia64_atomic_fetch_or(i,v)
+#define atomic_xor(i,v)	(void)ia64_atomic_fetch_xor(i,v)
 
-#define atomic_and(i,v)	(void)ia64_atomic_and(i,v)
-#define atomic_or(i,v)	(void)ia64_atomic_or(i,v)
-#define atomic_xor(i,v)	(void)ia64_atomic_xor(i,v)
+#define atomic_fetch_and(i,v)	ia64_atomic_fetch_and(i,v)
+#define atomic_fetch_or(i,v)	ia64_atomic_fetch_or(i,v)
+#define atomic_fetch_xor(i,v)	ia64_atomic_fetch_xor(i,v)
 
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP
 
 #define ATOMIC64_OP(op, c_op)						\
@@ -94,8 +143,27 @@ ia64_atomic64_##op (__s64 i, atomic64_t *v)				\
 	return new;							\
 }
 
-ATOMIC64_OP(add, +)
-ATOMIC64_OP(sub, -)
+#define ATOMIC64_FETCH_OP(op, c_op)					\
+static __inline__ long							\
+ia64_atomic64_fetch_##op (__s64 i, atomic64_t *v)			\
+{									\
+	__s64 old, new;							\
+	CMPXCHG_BUGCHECK_DECL						\
+									\
+	do {								\
+		CMPXCHG_BUGCHECK(v);					\
+		old = atomic64_read(v);					\
+		new = old c_op i;					\
+	} while (ia64_cmpxchg(acq, v, old, new, sizeof(atomic64_t)) != old); \
+	return old;							\
+}
+
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op, c_op)						\
+	ATOMIC64_FETCH_OP(op, c_op)
+
+ATOMIC64_OPS(add, +)
+ATOMIC64_OPS(sub, -)
 
 #define atomic64_add_return(i,v)					\
 ({									\
@@ -121,14 +189,44 @@ ATOMIC64_OP(sub, -)
 		: ia64_atomic64_sub(__ia64_asr_i, v);			\
 })
 
-ATOMIC64_OP(and, &)
-ATOMIC64_OP(or, |)
-ATOMIC64_OP(xor, ^)
+#define atomic64_fetch_add(i,v)						\
+({									\
+	long __ia64_aar_i = (i);					\
+	(__builtin_constant_p(i)					\
+	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
+	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
+	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
+	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+		? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq)	\
+		: ia64_atomic64_fetch_add(__ia64_aar_i, v);		\
+})
+
+#define atomic64_fetch_sub(i,v)						\
+({									\
+	long __ia64_asr_i = (i);					\
+	(__builtin_constant_p(i)					\
+	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
+	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
+	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
+	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+		? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq)	\
+		: ia64_atomic64_fetch_sub(__ia64_asr_i, v);		\
+})
+
+ATOMIC64_FETCH_OP(and, &)
+ATOMIC64_FETCH_OP(or, |)
+ATOMIC64_FETCH_OP(xor, ^)
+
+#define atomic64_and(i,v)	(void)ia64_atomic64_fetch_and(i,v)
+#define atomic64_or(i,v)	(void)ia64_atomic64_fetch_or(i,v)
+#define atomic64_xor(i,v)	(void)ia64_atomic64_fetch_xor(i,v)
 
-#define atomic64_and(i,v)	(void)ia64_atomic64_and(i,v)
-#define atomic64_or(i,v)	(void)ia64_atomic64_or(i,v)
-#define atomic64_xor(i,v)	(void)ia64_atomic64_xor(i,v)
+#define atomic64_fetch_and(i,v)	ia64_atomic64_fetch_and(i,v)
+#define atomic64_fetch_or(i,v)	ia64_atomic64_fetch_or(i,v)
+#define atomic64_fetch_xor(i,v)	ia64_atomic64_fetch_xor(i,v)
 
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP
 
 #define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), old, new))
diff --git a/arch/ia64/include/asm/mutex.h b/arch/ia64/include/asm/mutex.h
index f41e66d65e31..28cb819e0ff9 100644
--- a/arch/ia64/include/asm/mutex.h
+++ b/arch/ia64/include/asm/mutex.h
@@ -82,7 +82,7 @@ __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
 static inline int
 __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
 {
-	if (cmpxchg_acq(count, 1, 0) == 1)
+	if (atomic_read(count) == 1 && cmpxchg_acq(count, 1, 0) == 1)
 		return 1;
 	return 0;
 }
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
index 8b23e070b844..8fa98dd303b4 100644
--- a/arch/ia64/include/asm/rwsem.h
+++ b/arch/ia64/include/asm/rwsem.h
@@ -40,7 +40,7 @@
 static inline void
 __down_read (struct rw_semaphore *sem)
 {
-	long result = ia64_fetchadd8_acq((unsigned long *)&sem->count, 1);
+	long result = ia64_fetchadd8_acq((unsigned long *)&sem->count.counter, 1);
 
 	if (result < 0)
 		rwsem_down_read_failed(sem);
@@ -55,9 +55,9 @@ ___down_write (struct rw_semaphore *sem)
 	long old, new;
 
 	do {
-		old = sem->count;
+		old = atomic_long_read(&sem->count);
 		new = old + RWSEM_ACTIVE_WRITE_BIAS;
-	} while (cmpxchg_acq(&sem->count, old, new) != old);
+	} while (atomic_long_cmpxchg_acquire(&sem->count, old, new) != old);
 
 	return old;
 }
@@ -85,7 +85,7 @@ __down_write_killable (struct rw_semaphore *sem)
 static inline void
 __up_read (struct rw_semaphore *sem)
 {
-	long result = ia64_fetchadd8_rel((unsigned long *)&sem->count, -1);
+	long result = ia64_fetchadd8_rel((unsigned long *)&sem->count.counter, -1);
 
 	if (result < 0 && (--result & RWSEM_ACTIVE_MASK) == 0)
 		rwsem_wake(sem);
@@ -100,9 +100,9 @@ __up_write (struct rw_semaphore *sem)
 	long old, new;
 
 	do {
-		old = sem->count;
+		old = atomic_long_read(&sem->count);
 		new = old - RWSEM_ACTIVE_WRITE_BIAS;
-	} while (cmpxchg_rel(&sem->count, old, new) != old);
+	} while (atomic_long_cmpxchg_release(&sem->count, old, new) != old);
 
 	if (new < 0 && (new & RWSEM_ACTIVE_MASK) == 0)
 		rwsem_wake(sem);
@@ -115,8 +115,8 @@ static inline int
 __down_read_trylock (struct rw_semaphore *sem)
 {
 	long tmp;
-	while ((tmp = sem->count) >= 0) {
-		if (tmp == cmpxchg_acq(&sem->count, tmp, tmp+1)) {
+	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
+		if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp, tmp+1)) {
 			return 1;
 		}
 	}
@@ -129,8 +129,8 @@ __down_read_trylock (struct rw_semaphore *sem)
 static inline int
 __down_write_trylock (struct rw_semaphore *sem)
 {
-	long tmp = cmpxchg_acq(&sem->count, RWSEM_UNLOCKED_VALUE,
-			      RWSEM_ACTIVE_WRITE_BIAS);
+	long tmp = atomic_long_cmpxchg_acquire(&sem->count,
+			RWSEM_UNLOCKED_VALUE, RWSEM_ACTIVE_WRITE_BIAS);
 	return tmp == RWSEM_UNLOCKED_VALUE;
 }
 
@@ -143,19 +143,12 @@ __downgrade_write (struct rw_semaphore *sem)
 	long old, new;
 
 	do {
-		old = sem->count;
+		old = atomic_long_read(&sem->count);
 		new = old - RWSEM_WAITING_BIAS;
-	} while (cmpxchg_rel(&sem->count, old, new) != old);
+	} while (atomic_long_cmpxchg_release(&sem->count, old, new) != old);
 
 	if (old < 0)
 		rwsem_downgrade_wake(sem);
 }
 
-/*
- * Implement atomic add functionality.  These used to be "inline" functions, but GCC v3.1
- * doesn't quite optimize this stuff right and ends up with bad calls to fetchandadd.
- */
-#define rwsem_atomic_add(delta, sem)	atomic64_add(delta, (atomic64_t *)(&(sem)->count))
-#define rwsem_atomic_update(delta, sem)	atomic64_add_return(delta, (atomic64_t *)(&(sem)->count))
-
 #endif /* _ASM_IA64_RWSEM_H */
diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h
index 45698cd15b7b..ca9e76149a4a 100644
--- a/arch/ia64/include/asm/spinlock.h
+++ b/arch/ia64/include/asm/spinlock.h
@@ -15,6 +15,8 @@
 
 #include <linux/atomic.h>
 #include <asm/intrinsics.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
 
 #define arch_spin_lock_init(x)			((x)->lock = 0)
 
@@ -86,6 +88,8 @@ static __always_inline void __ticket_spin_unlock_wait(arch_spinlock_t *lock)
 			return;
 		cpu_relax();
 	}
+
+	smp_acquire__after_ctrl_dep();
 }
 
 static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
diff --git a/arch/m32r/include/asm/atomic.h b/arch/m32r/include/asm/atomic.h
index ea35160d632b..640cc1c7099f 100644
--- a/arch/m32r/include/asm/atomic.h
+++ b/arch/m32r/include/asm/atomic.h
@@ -89,16 +89,44 @@ static __inline__ int atomic_##op##_return(int i, atomic_t *v)		\
 	return result;							\
 }
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+static __inline__ int atomic_fetch_##op(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	int result, val;						\
+									\
+	local_irq_save(flags);						\
+	__asm__ __volatile__ (						\
+		"# atomic_fetch_" #op "		\n\t"			\
+		DCACHE_CLEAR("%0", "r4", "%2")				\
+		M32R_LOCK" %1, @%2;		\n\t"			\
+		"mv %0, %1			\n\t" 			\
+		#op " %1, %3;			\n\t"			\
+		M32R_UNLOCK" %1, @%2;		\n\t"			\
+		: "=&r" (result), "=&r" (val)				\
+		: "r" (&v->counter), "r" (i)				\
+		: "memory"						\
+		__ATOMIC_CLOBBER					\
+	);								\
+	local_irq_restore(flags);					\
+									\
+	return result;							\
+}
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/m32r/include/asm/spinlock.h b/arch/m32r/include/asm/spinlock.h
index fa13694eaae3..323c7fc953cd 100644
--- a/arch/m32r/include/asm/spinlock.h
+++ b/arch/m32r/include/asm/spinlock.h
@@ -13,6 +13,8 @@
 #include <linux/atomic.h>
 #include <asm/dcache_clear.h>
 #include <asm/page.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
 
 /*
  * Your basic SMP spinlocks, allowing only a single CPU anywhere
@@ -27,8 +29,11 @@
 
 #define arch_spin_is_locked(x)		(*(volatile int *)(&(x)->slock) <= 0)
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-#define arch_spin_unlock_wait(x) \
-		do { cpu_relax(); } while (arch_spin_is_locked(x))
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->slock, VAL > 0);
+}
 
 /**
  * arch_spin_trylock - Try spin lock and return a result
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index 4858178260f9..cf4c3a7b1a45 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -53,6 +53,21 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return t;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int t, tmp;							\
+									\
+	__asm__ __volatile__(						\
+			"1:	movel %2,%1\n"				\
+			"	" #asm_op "l %3,%1\n"			\
+			"	casl %2,%1,%0\n"			\
+			"	jne 1b"					\
+			: "+m" (*v), "=&d" (t), "=&d" (tmp)		\
+			: "g" (i), "2" (atomic_read(v)));		\
+	return tmp;							\
+}
+
 #else
 
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
@@ -68,20 +83,41 @@ static inline int atomic_##op##_return(int i, atomic_t * v)		\
 	return t;							\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				\
+static inline int atomic_fetch_##op(int i, atomic_t * v)		\
+{									\
+	unsigned long flags;						\
+	int t;								\
+									\
+	local_irq_save(flags);						\
+	t = v->counter;							\
+	v->counter c_op i;						\
+	local_irq_restore(flags);					\
+									\
+	return t;							\
+}
+
 #endif /* CONFIG_RMW_INSNS */
 
 #define ATOMIC_OPS(op, c_op, asm_op)					\
 	ATOMIC_OP(op, c_op, asm_op)					\
-	ATOMIC_OP_RETURN(op, c_op, asm_op)
+	ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
-ATOMIC_OP(and, &=, and)
-ATOMIC_OP(or, |=, or)
-ATOMIC_OP(xor, ^=, eor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC_OPS(and, &=, and)
+ATOMIC_OPS(or, |=, or)
+ATOMIC_OPS(xor, ^=, eor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/metag/include/asm/atomic_lnkget.h b/arch/metag/include/asm/atomic_lnkget.h
index 88fa25fae8bd..def2c642f053 100644
--- a/arch/metag/include/asm/atomic_lnkget.h
+++ b/arch/metag/include/asm/atomic_lnkget.h
@@ -69,16 +69,44 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return result;							\
 }
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int result, temp;						\
+									\
+	smp_mb();							\
+									\
+	asm volatile (							\
+		"1:	LNKGETD %1, [%2]\n"				\
+		"	" #op "	%0, %1, %3\n"				\
+		"	LNKSETD [%2], %0\n"				\
+		"	DEFR	%0, TXSTAT\n"				\
+		"	ANDT	%0, %0, #HI(0x3f000000)\n"		\
+		"	CMPT	%0, #HI(0x02000000)\n"			\
+		"	BNZ 1b\n"					\
+		: "=&d" (temp), "=&d" (result)				\
+		: "da" (&v->counter), "bd" (i)				\
+		: "cc");						\
+									\
+	smp_mb();							\
+									\
+	return result;							\
+}
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/metag/include/asm/atomic_lock1.h b/arch/metag/include/asm/atomic_lock1.h
index 0295d9b8d5bf..6c1380a8a0d4 100644
--- a/arch/metag/include/asm/atomic_lock1.h
+++ b/arch/metag/include/asm/atomic_lock1.h
@@ -64,15 +64,40 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return result;							\
 }
 
-#define ATOMIC_OPS(op, c_op) ATOMIC_OP(op, c_op) ATOMIC_OP_RETURN(op, c_op)
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long result;						\
+	unsigned long flags;						\
+									\
+	__global_lock1(flags);						\
+	result = v->counter;						\
+	fence();							\
+	v->counter c_op i;						\
+	__global_unlock1(flags);					\
+									\
+	return result;							\
+}
+
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op, c_op)						\
+	ATOMIC_OP_RETURN(op, c_op)					\
+	ATOMIC_FETCH_OP(op, c_op)
 
 ATOMIC_OPS(add, +=)
 ATOMIC_OPS(sub, -=)
-ATOMIC_OP(and, &=)
-ATOMIC_OP(or, |=)
-ATOMIC_OP(xor, ^=)
 
 #undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op, c_op)						\
+	ATOMIC_FETCH_OP(op, c_op)
+
+ATOMIC_OPS(and, &=)
+ATOMIC_OPS(or, |=)
+ATOMIC_OPS(xor, ^=)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/metag/include/asm/spinlock.h b/arch/metag/include/asm/spinlock.h
index 86a7cf3d1386..c0c7a22be1ae 100644
--- a/arch/metag/include/asm/spinlock.h
+++ b/arch/metag/include/asm/spinlock.h
@@ -1,14 +1,24 @@
 #ifndef __ASM_SPINLOCK_H
 #define __ASM_SPINLOCK_H
 
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
 #ifdef CONFIG_METAG_ATOMICITY_LOCK1
 #include <asm/spinlock_lock1.h>
 #else
 #include <asm/spinlock_lnkget.h>
 #endif
 
-#define arch_spin_unlock_wait(lock) \
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+/*
+ * both lock1 and lnkget are test-and-set spinlocks with 0 unlocked and 1
+ * locked.
+ */
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->lock, !VAL);
+}
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 835b402e4574..0ab176bdb8e8 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -66,7 +66,7 @@ static __inline__ void atomic_##op(int i, atomic_t * v)			      \
 			"	" #asm_op " %0, %2			\n"   \
 			"	sc	%0, %1				\n"   \
 			"	.set	mips0				\n"   \
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)      \
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)  \
 			: "Ir" (i));					      \
 		} while (unlikely(!temp));				      \
 	} else {							      \
@@ -79,12 +79,10 @@ static __inline__ void atomic_##op(int i, atomic_t * v)			      \
 }
 
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				      \
-static __inline__ int atomic_##op##_return(int i, atomic_t * v)		      \
+static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v)	      \
 {									      \
 	int result;							      \
 									      \
-	smp_mb__before_llsc();						      \
-									      \
 	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
 		int temp;						      \
 									      \
@@ -125,23 +123,84 @@ static __inline__ int atomic_##op##_return(int i, atomic_t * v)		      \
 		raw_local_irq_restore(flags);				      \
 	}								      \
 									      \
-	smp_llsc_mb();							      \
+	return result;							      \
+}
+
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				      \
+static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v)	      \
+{									      \
+	int result;							      \
+									      \
+	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+		int temp;						      \
+									      \
+		__asm__ __volatile__(					      \
+		"	.set	arch=r4000				\n"   \
+		"1:	ll	%1, %2		# atomic_fetch_" #op "	\n"   \
+		"	" #asm_op " %0, %1, %3				\n"   \
+		"	sc	%0, %2					\n"   \
+		"	beqzl	%0, 1b					\n"   \
+		"	move	%0, %1					\n"   \
+		"	.set	mips0					\n"   \
+		: "=&r" (result), "=&r" (temp),				      \
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
+		: "Ir" (i));						      \
+	} else if (kernel_uses_llsc) {					      \
+		int temp;						      \
+									      \
+		do {							      \
+			__asm__ __volatile__(				      \
+			"	.set	"MIPS_ISA_LEVEL"		\n"   \
+			"	ll	%1, %2	# atomic_fetch_" #op "	\n"   \
+			"	" #asm_op " %0, %1, %3			\n"   \
+			"	sc	%0, %2				\n"   \
+			"	.set	mips0				\n"   \
+			: "=&r" (result), "=&r" (temp),			      \
+			  "+" GCC_OFF_SMALL_ASM() (v->counter)		      \
+			: "Ir" (i));					      \
+		} while (unlikely(!result));				      \
+									      \
+		result = temp;						      \
+	} else {							      \
+		unsigned long flags;					      \
+									      \
+		raw_local_irq_save(flags);				      \
+		result = v->counter;					      \
+		v->counter c_op i;					      \
+		raw_local_irq_restore(flags);				      \
+	}								      \
 									      \
 	return result;							      \
 }
 
 #define ATOMIC_OPS(op, c_op, asm_op)					      \
 	ATOMIC_OP(op, c_op, asm_op)					      \
-	ATOMIC_OP_RETURN(op, c_op, asm_op)
+	ATOMIC_OP_RETURN(op, c_op, asm_op)				      \
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(add, +=, addu)
 ATOMIC_OPS(sub, -=, subu)
 
-ATOMIC_OP(and, &=, and)
-ATOMIC_OP(or, |=, or)
-ATOMIC_OP(xor, ^=, xor)
+#define atomic_add_return_relaxed	atomic_add_return_relaxed
+#define atomic_sub_return_relaxed	atomic_sub_return_relaxed
+#define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
+#define atomic_fetch_sub_relaxed	atomic_fetch_sub_relaxed
+
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op, asm_op)					      \
+	ATOMIC_OP(op, c_op, asm_op)					      \
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC_OPS(and, &=, and)
+ATOMIC_OPS(or, |=, or)
+ATOMIC_OPS(xor, ^=, xor)
+
+#define atomic_fetch_and_relaxed	atomic_fetch_and_relaxed
+#define atomic_fetch_or_relaxed		atomic_fetch_or_relaxed
+#define atomic_fetch_xor_relaxed	atomic_fetch_xor_relaxed
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
@@ -362,12 +421,10 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v)		      \
 }
 
 #define ATOMIC64_OP_RETURN(op, c_op, asm_op)				      \
-static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	      \
+static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \
 {									      \
 	long result;							      \
 									      \
-	smp_mb__before_llsc();						      \
-									      \
 	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
 		long temp;						      \
 									      \
@@ -409,22 +466,85 @@ static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	      \
 		raw_local_irq_restore(flags);				      \
 	}								      \
 									      \
-	smp_llsc_mb();							      \
+	return result;							      \
+}
+
+#define ATOMIC64_FETCH_OP(op, c_op, asm_op)				      \
+static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v)  \
+{									      \
+	long result;							      \
+									      \
+	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+		long temp;						      \
+									      \
+		__asm__ __volatile__(					      \
+		"	.set	arch=r4000				\n"   \
+		"1:	lld	%1, %2		# atomic64_fetch_" #op "\n"   \
+		"	" #asm_op " %0, %1, %3				\n"   \
+		"	scd	%0, %2					\n"   \
+		"	beqzl	%0, 1b					\n"   \
+		"	move	%0, %1					\n"   \
+		"	.set	mips0					\n"   \
+		: "=&r" (result), "=&r" (temp),				      \
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
+		: "Ir" (i));						      \
+	} else if (kernel_uses_llsc) {					      \
+		long temp;						      \
+									      \
+		do {							      \
+			__asm__ __volatile__(				      \
+			"	.set	"MIPS_ISA_LEVEL"		\n"   \
+			"	lld	%1, %2	# atomic64_fetch_" #op "\n"   \
+			"	" #asm_op " %0, %1, %3			\n"   \
+			"	scd	%0, %2				\n"   \
+			"	.set	mips0				\n"   \
+			: "=&r" (result), "=&r" (temp),			      \
+			  "=" GCC_OFF_SMALL_ASM() (v->counter)		      \
+			: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)	      \
+			: "memory");					      \
+		} while (unlikely(!result));				      \
+									      \
+		result = temp;						      \
+	} else {							      \
+		unsigned long flags;					      \
+									      \
+		raw_local_irq_save(flags);				      \
+		result = v->counter;					      \
+		v->counter c_op i;					      \
+		raw_local_irq_restore(flags);				      \
+	}								      \
 									      \
 	return result;							      \
 }
 
 #define ATOMIC64_OPS(op, c_op, asm_op)					      \
 	ATOMIC64_OP(op, c_op, asm_op)					      \
-	ATOMIC64_OP_RETURN(op, c_op, asm_op)
+	ATOMIC64_OP_RETURN(op, c_op, asm_op)				      \
+	ATOMIC64_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC64_OPS(add, +=, daddu)
 ATOMIC64_OPS(sub, -=, dsubu)
-ATOMIC64_OP(and, &=, and)
-ATOMIC64_OP(or, |=, or)
-ATOMIC64_OP(xor, ^=, xor)
+
+#define atomic64_add_return_relaxed	atomic64_add_return_relaxed
+#define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
+#define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
+#define atomic64_fetch_sub_relaxed	atomic64_fetch_sub_relaxed
+
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op, c_op, asm_op)					      \
+	ATOMIC64_OP(op, c_op, asm_op)					      \
+	ATOMIC64_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC64_OPS(and, &=, and)
+ATOMIC64_OPS(or, |=, or)
+ATOMIC64_OPS(xor, ^=, xor)
+
+#define atomic64_fetch_and_relaxed	atomic64_fetch_and_relaxed
+#define atomic64_fetch_or_relaxed	atomic64_fetch_or_relaxed
+#define atomic64_fetch_xor_relaxed	atomic64_fetch_xor_relaxed
 
 #undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h
index 40196bebe849..f485afe51514 100644
--- a/arch/mips/include/asm/spinlock.h
+++ b/arch/mips/include/asm/spinlock.h
@@ -12,6 +12,7 @@
 #include <linux/compiler.h>
 
 #include <asm/barrier.h>
+#include <asm/processor.h>
 #include <asm/compiler.h>
 #include <asm/war.h>
 
@@ -48,8 +49,22 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 }
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-#define arch_spin_unlock_wait(x) \
-	while (arch_spin_is_locked(x)) { cpu_relax(); }
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	u16 owner = READ_ONCE(lock->h.serving_now);
+	smp_rmb();
+	for (;;) {
+		arch_spinlock_t tmp = READ_ONCE(*lock);
+
+		if (tmp.h.serving_now == tmp.h.ticket ||
+		    tmp.h.serving_now != owner)
+			break;
+
+		cpu_relax();
+	}
+	smp_acquire__after_ctrl_dep();
+}
 
 static inline int arch_spin_is_contended(arch_spinlock_t *lock)
 {
diff --git a/arch/mn10300/include/asm/atomic.h b/arch/mn10300/include/asm/atomic.h
index ce318d5ab23b..36389efd45e8 100644
--- a/arch/mn10300/include/asm/atomic.h
+++ b/arch/mn10300/include/asm/atomic.h
@@ -84,16 +84,41 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return retval;							\
 }
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int retval, status;						\
+									\
+	asm volatile(							\
+		"1:	mov	%4,(_AAR,%3)	\n"			\
+		"	mov	(_ADR,%3),%1	\n"			\
+		"	mov	%1,%0		\n"			\
+		"	" #op "	%5,%0		\n"			\
+		"	mov	%0,(_ADR,%3)	\n"			\
+		"	mov	(_ADR,%3),%0	\n"	/* flush */	\
+		"	mov	(_ASR,%3),%0	\n"			\
+		"	or	%0,%0		\n"			\
+		"	bne	1b		\n"			\
+		: "=&r"(status), "=&r"(retval), "=m"(v->counter)	\
+		: "a"(ATOMIC_OPS_BASE_ADDR), "r"(&v->counter), "r"(i)	\
+		: "memory", "cc");					\
+	return retval;							\
+}
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/mn10300/include/asm/spinlock.h b/arch/mn10300/include/asm/spinlock.h
index 1ae580f38933..9c7b8f7942d8 100644
--- a/arch/mn10300/include/asm/spinlock.h
+++ b/arch/mn10300/include/asm/spinlock.h
@@ -12,6 +12,8 @@
 #define _ASM_SPINLOCK_H
 
 #include <linux/atomic.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
 #include <asm/rwlock.h>
 #include <asm/page.h>
 
@@ -23,7 +25,11 @@
  */
 
 #define arch_spin_is_locked(x)	(*(volatile signed char *)(&(x)->slock) != 0)
-#define arch_spin_unlock_wait(x) do { barrier(); } while (arch_spin_is_locked(x))
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->slock, !VAL);
+}
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 1d109990a022..5394b9c5f914 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -121,16 +121,39 @@ static __inline__ int atomic_##op##_return(int i, atomic_t *v)		\
 	return ret;							\
 }
 
-#define ATOMIC_OPS(op, c_op) ATOMIC_OP(op, c_op) ATOMIC_OP_RETURN(op, c_op)
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static __inline__ int atomic_fetch_##op(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	int ret;							\
+									\
+	_atomic_spin_lock_irqsave(v, flags);				\
+	ret = v->counter;						\
+	v->counter c_op i;						\
+	_atomic_spin_unlock_irqrestore(v, flags);			\
+									\
+	return ret;							\
+}
+
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op, c_op)						\
+	ATOMIC_OP_RETURN(op, c_op)					\
+	ATOMIC_FETCH_OP(op, c_op)
 
 ATOMIC_OPS(add, +=)
 ATOMIC_OPS(sub, -=)
 
-ATOMIC_OP(and, &=)
-ATOMIC_OP(or, |=)
-ATOMIC_OP(xor, ^=)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op, c_op)						\
+	ATOMIC_FETCH_OP(op, c_op)
+
+ATOMIC_OPS(and, &=)
+ATOMIC_OPS(or, |=)
+ATOMIC_OPS(xor, ^=)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
@@ -185,15 +208,39 @@ static __inline__ s64 atomic64_##op##_return(s64 i, atomic64_t *v)	\
 	return ret;							\
 }
 
-#define ATOMIC64_OPS(op, c_op) ATOMIC64_OP(op, c_op) ATOMIC64_OP_RETURN(op, c_op)
+#define ATOMIC64_FETCH_OP(op, c_op)					\
+static __inline__ s64 atomic64_fetch_##op(s64 i, atomic64_t *v)		\
+{									\
+	unsigned long flags;						\
+	s64 ret;							\
+									\
+	_atomic_spin_lock_irqsave(v, flags);				\
+	ret = v->counter;						\
+	v->counter c_op i;						\
+	_atomic_spin_unlock_irqrestore(v, flags);			\
+									\
+	return ret;							\
+}
+
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op, c_op)						\
+	ATOMIC64_OP_RETURN(op, c_op)					\
+	ATOMIC64_FETCH_OP(op, c_op)
 
 ATOMIC64_OPS(add, +=)
 ATOMIC64_OPS(sub, -=)
-ATOMIC64_OP(and, &=)
-ATOMIC64_OP(or, |=)
-ATOMIC64_OP(xor, ^=)
 
 #undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op, c_op)						\
+	ATOMIC64_FETCH_OP(op, c_op)
+
+ATOMIC64_OPS(and, &=)
+ATOMIC64_OPS(or, |=)
+ATOMIC64_OPS(xor, ^=)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h
index 64f2992e439f..e32936cd7f10 100644
--- a/arch/parisc/include/asm/spinlock.h
+++ b/arch/parisc/include/asm/spinlock.h
@@ -13,8 +13,13 @@ static inline int arch_spin_is_locked(arch_spinlock_t *x)
 }
 
 #define arch_spin_lock(lock) arch_spin_lock_flags(lock, 0)
-#define arch_spin_unlock_wait(x) \
-		do { cpu_relax(); } while (arch_spin_is_locked(x))
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *x)
+{
+	volatile unsigned int *a = __ldcw_align(x);
+
+	smp_cond_load_acquire(a, VAL);
+}
 
 static inline void arch_spin_lock_flags(arch_spinlock_t *x,
 					 unsigned long flags)
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index ae0751ef8788..f08d567e0ca4 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -78,21 +78,53 @@ static inline int atomic_##op##_return_relaxed(int a, atomic_t *v)	\
 	return t;							\
 }
 
+#define ATOMIC_FETCH_OP_RELAXED(op, asm_op)				\
+static inline int atomic_fetch_##op##_relaxed(int a, atomic_t *v)	\
+{									\
+	int res, t;							\
+									\
+	__asm__ __volatile__(						\
+"1:	lwarx	%0,0,%4		# atomic_fetch_" #op "_relaxed\n"	\
+	#asm_op " %1,%3,%0\n"						\
+	PPC405_ERR77(0, %4)						\
+"	stwcx.	%1,0,%4\n"						\
+"	bne-	1b\n"							\
+	: "=&r" (res), "=&r" (t), "+m" (v->counter)			\
+	: "r" (a), "r" (&v->counter)					\
+	: "cc");							\
+									\
+	return res;							\
+}
+
 #define ATOMIC_OPS(op, asm_op)						\
 	ATOMIC_OP(op, asm_op)						\
-	ATOMIC_OP_RETURN_RELAXED(op, asm_op)
+	ATOMIC_OP_RETURN_RELAXED(op, asm_op)				\
+	ATOMIC_FETCH_OP_RELAXED(op, asm_op)
 
 ATOMIC_OPS(add, add)
 ATOMIC_OPS(sub, subf)
 
-ATOMIC_OP(and, and)
-ATOMIC_OP(or, or)
-ATOMIC_OP(xor, xor)
-
 #define atomic_add_return_relaxed atomic_add_return_relaxed
 #define atomic_sub_return_relaxed atomic_sub_return_relaxed
 
+#define atomic_fetch_add_relaxed atomic_fetch_add_relaxed
+#define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed
+
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, asm_op)						\
+	ATOMIC_OP(op, asm_op)						\
+	ATOMIC_FETCH_OP_RELAXED(op, asm_op)
+
+ATOMIC_OPS(and, and)
+ATOMIC_OPS(or, or)
+ATOMIC_OPS(xor, xor)
+
+#define atomic_fetch_and_relaxed atomic_fetch_and_relaxed
+#define atomic_fetch_or_relaxed  atomic_fetch_or_relaxed
+#define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed
+
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP_RELAXED
 #undef ATOMIC_OP_RETURN_RELAXED
 #undef ATOMIC_OP
 
@@ -329,20 +361,53 @@ atomic64_##op##_return_relaxed(long a, atomic64_t *v)			\
 	return t;							\
 }
 
+#define ATOMIC64_FETCH_OP_RELAXED(op, asm_op)				\
+static inline long							\
+atomic64_fetch_##op##_relaxed(long a, atomic64_t *v)			\
+{									\
+	long res, t;							\
+									\
+	__asm__ __volatile__(						\
+"1:	ldarx	%0,0,%4		# atomic64_fetch_" #op "_relaxed\n"	\
+	#asm_op " %1,%3,%0\n"						\
+"	stdcx.	%1,0,%4\n"						\
+"	bne-	1b\n"							\
+	: "=&r" (res), "=&r" (t), "+m" (v->counter)			\
+	: "r" (a), "r" (&v->counter)					\
+	: "cc");							\
+									\
+	return res;							\
+}
+
 #define ATOMIC64_OPS(op, asm_op)					\
 	ATOMIC64_OP(op, asm_op)						\
-	ATOMIC64_OP_RETURN_RELAXED(op, asm_op)
+	ATOMIC64_OP_RETURN_RELAXED(op, asm_op)				\
+	ATOMIC64_FETCH_OP_RELAXED(op, asm_op)
 
 ATOMIC64_OPS(add, add)
 ATOMIC64_OPS(sub, subf)
-ATOMIC64_OP(and, and)
-ATOMIC64_OP(or, or)
-ATOMIC64_OP(xor, xor)
 
 #define atomic64_add_return_relaxed atomic64_add_return_relaxed
 #define atomic64_sub_return_relaxed atomic64_sub_return_relaxed
 
+#define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed
+#define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed
+
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op, asm_op)					\
+	ATOMIC64_OP(op, asm_op)						\
+	ATOMIC64_FETCH_OP_RELAXED(op, asm_op)
+
+ATOMIC64_OPS(and, and)
+ATOMIC64_OPS(or, or)
+ATOMIC64_OPS(xor, xor)
+
+#define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed
+#define atomic64_fetch_or_relaxed  atomic64_fetch_or_relaxed
+#define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed
+
 #undef ATOPIC64_OPS
+#undef ATOMIC64_FETCH_OP_RELAXED
 #undef ATOMIC64_OP_RETURN_RELAXED
 #undef ATOMIC64_OP
 
diff --git a/arch/powerpc/include/asm/mutex.h b/arch/powerpc/include/asm/mutex.h
index 127ab23e1f6c..078155fa1189 100644
--- a/arch/powerpc/include/asm/mutex.h
+++ b/arch/powerpc/include/asm/mutex.h
@@ -124,7 +124,7 @@ __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
 static inline int
 __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
 {
-	if (likely(__mutex_cmpxchg_lock(count, 1, 0) == 1))
+	if (likely(atomic_read(count) == 1 && __mutex_cmpxchg_lock(count, 1, 0) == 1))
 		return 1;
 	return 0;
 }
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 911064aa59b2..d28cc2f5b7b2 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -93,6 +93,11 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	return __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_BARRIER) + i;
 }
 
+static inline int atomic_fetch_add(int i, atomic_t *v)
+{
+	return __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_BARRIER);
+}
+
 static inline void atomic_add(int i, atomic_t *v)
 {
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
@@ -114,22 +119,27 @@ static inline void atomic_add(int i, atomic_t *v)
 #define atomic_inc_and_test(_v)		(atomic_add_return(1, _v) == 0)
 #define atomic_sub(_i, _v)		atomic_add(-(int)(_i), _v)
 #define atomic_sub_return(_i, _v)	atomic_add_return(-(int)(_i), _v)
+#define atomic_fetch_sub(_i, _v)	atomic_fetch_add(-(int)(_i), _v)
 #define atomic_sub_and_test(_i, _v)	(atomic_sub_return(_i, _v) == 0)
 #define atomic_dec(_v)			atomic_sub(1, _v)
 #define atomic_dec_return(_v)		atomic_sub_return(1, _v)
 #define atomic_dec_and_test(_v)		(atomic_sub_return(1, _v) == 0)
 
-#define ATOMIC_OP(op, OP)						\
+#define ATOMIC_OPS(op, OP)						\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
 	__ATOMIC_LOOP(v, i, __ATOMIC_##OP, __ATOMIC_NO_BARRIER);	\
+}									\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	return __ATOMIC_LOOP(v, i, __ATOMIC_##OP, __ATOMIC_BARRIER);	\
 }
 
-ATOMIC_OP(and, AND)
-ATOMIC_OP(or, OR)
-ATOMIC_OP(xor, XOR)
+ATOMIC_OPS(and, AND)
+ATOMIC_OPS(or, OR)
+ATOMIC_OPS(xor, XOR)
 
-#undef ATOMIC_OP
+#undef ATOMIC_OPS
 
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
@@ -236,6 +246,11 @@ static inline long long atomic64_add_return(long long i, atomic64_t *v)
 	return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_BARRIER) + i;
 }
 
+static inline long long atomic64_fetch_add(long long i, atomic64_t *v)
+{
+	return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_BARRIER);
+}
+
 static inline void atomic64_add(long long i, atomic64_t *v)
 {
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
@@ -264,17 +279,21 @@ static inline long long atomic64_cmpxchg(atomic64_t *v,
 	return old;
 }
 
-#define ATOMIC64_OP(op, OP)						\
+#define ATOMIC64_OPS(op, OP)						\
 static inline void atomic64_##op(long i, atomic64_t *v)			\
 {									\
 	__ATOMIC64_LOOP(v, i, __ATOMIC64_##OP, __ATOMIC64_NO_BARRIER);	\
+}									\
+static inline long atomic64_fetch_##op(long i, atomic64_t *v)		\
+{									\
+	return __ATOMIC64_LOOP(v, i, __ATOMIC64_##OP, __ATOMIC64_BARRIER); \
 }
 
-ATOMIC64_OP(and, AND)
-ATOMIC64_OP(or, OR)
-ATOMIC64_OP(xor, XOR)
+ATOMIC64_OPS(and, AND)
+ATOMIC64_OPS(or, OR)
+ATOMIC64_OPS(xor, XOR)
 
-#undef ATOMIC64_OP
+#undef ATOMIC64_OPS
 #undef __ATOMIC64_LOOP
 
 static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
@@ -315,6 +334,7 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 #define atomic64_inc_return(_v)		atomic64_add_return(1, _v)
 #define atomic64_inc_and_test(_v)	(atomic64_add_return(1, _v) == 0)
 #define atomic64_sub_return(_i, _v)	atomic64_add_return(-(long long)(_i), _v)
+#define atomic64_fetch_sub(_i, _v)	atomic64_fetch_add(-(long long)(_i), _v)
 #define atomic64_sub(_i, _v)		atomic64_add(-(long long)(_i), _v)
 #define atomic64_sub_and_test(_i, _v)	(atomic64_sub_return(_i, _v) == 0)
 #define atomic64_dec(_v)		atomic64_sub(1, _v)
diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h
index c75e4471e618..597e7e96b59e 100644
--- a/arch/s390/include/asm/rwsem.h
+++ b/arch/s390/include/asm/rwsem.h
@@ -207,41 +207,4 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 		rwsem_downgrade_wake(sem);
 }
 
-/*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
-{
-	signed long old, new;
-
-	asm volatile(
-		"	lg	%0,%2\n"
-		"0:	lgr	%1,%0\n"
-		"	agr	%1,%4\n"
-		"	csg	%0,%1,%2\n"
-		"	jl	0b"
-		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
-		: "Q" (sem->count), "d" (delta)
-		: "cc", "memory");
-}
-
-/*
- * implement exchange and add functionality
- */
-static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
-{
-	signed long old, new;
-
-	asm volatile(
-		"	lg	%0,%2\n"
-		"0:	lgr	%1,%0\n"
-		"	agr	%1,%4\n"
-		"	csg	%0,%1,%2\n"
-		"	jl	0b"
-		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
-		: "Q" (sem->count), "d" (delta)
-		: "cc", "memory");
-	return new;
-}
-
 #endif /* _S390_RWSEM_H */
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index 63ebf37d3143..7e9e09f600fa 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -10,6 +10,8 @@
 #define __ASM_SPINLOCK_H
 
 #include <linux/smp.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
 
 #define SPINLOCK_LOCKVAL (S390_lowcore.spinlock_lockval)
 
@@ -97,6 +99,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
 	while (arch_spin_is_locked(lock))
 		arch_spin_relax(lock);
+	smp_acquire__after_ctrl_dep();
 }
 
 /*
diff --git a/arch/sh/include/asm/atomic-grb.h b/arch/sh/include/asm/atomic-grb.h
index b94df40e5f2d..d755e96c3064 100644
--- a/arch/sh/include/asm/atomic-grb.h
+++ b/arch/sh/include/asm/atomic-grb.h
@@ -43,16 +43,42 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return tmp;							\
 }
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int res, tmp;							\
+									\
+	__asm__ __volatile__ (						\
+		"   .align 2              \n\t"				\
+		"   mova    1f,   r0      \n\t" /* r0 = end point */	\
+		"   mov    r15,   r1      \n\t" /* r1 = saved sp */	\
+		"   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */	\
+		"   mov.l  @%2,   %0      \n\t" /* load old value */	\
+		"   mov     %0,   %1      \n\t" /* save old value */	\
+		" " #op "   %3,   %0      \n\t" /* $op */		\
+		"   mov.l   %0,   @%2     \n\t" /* store new value */	\
+		"1: mov     r1,   r15     \n\t" /* LOGOUT */		\
+		: "=&r" (tmp), "=&r" (res), "+r"  (v)			\
+		: "r"   (i)						\
+		: "memory" , "r0", "r1");				\
+									\
+	return res;							\
+}
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/sh/include/asm/atomic-irq.h b/arch/sh/include/asm/atomic-irq.h
index 23fcdad5773e..8e2da5fa0178 100644
--- a/arch/sh/include/asm/atomic-irq.h
+++ b/arch/sh/include/asm/atomic-irq.h
@@ -33,15 +33,38 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return temp;							\
 }
 
-#define ATOMIC_OPS(op, c_op) ATOMIC_OP(op, c_op) ATOMIC_OP_RETURN(op, c_op)
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long temp, flags;					\
+									\
+	raw_local_irq_save(flags);					\
+	temp = v->counter;						\
+	v->counter c_op i;						\
+	raw_local_irq_restore(flags);					\
+									\
+	return temp;							\
+}
+
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op, c_op)						\
+	ATOMIC_OP_RETURN(op, c_op)					\
+	ATOMIC_FETCH_OP(op, c_op)
 
 ATOMIC_OPS(add, +=)
 ATOMIC_OPS(sub, -=)
-ATOMIC_OP(and, &=)
-ATOMIC_OP(or, |=)
-ATOMIC_OP(xor, ^=)
 
 #undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op, c_op)						\
+	ATOMIC_FETCH_OP(op, c_op)
+
+ATOMIC_OPS(and, &=)
+ATOMIC_OPS(or, |=)
+ATOMIC_OPS(xor, ^=)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/sh/include/asm/atomic-llsc.h b/arch/sh/include/asm/atomic-llsc.h
index 33d34b16d4d6..caea2c45f6c2 100644
--- a/arch/sh/include/asm/atomic-llsc.h
+++ b/arch/sh/include/asm/atomic-llsc.h
@@ -48,15 +48,39 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return temp;							\
 }
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long res, temp;					\
+									\
+	__asm__ __volatile__ (						\
+"1:	movli.l @%3, %0		! atomic_fetch_" #op "	\n"		\
+"	mov %0, %1					\n"		\
+"	" #op "	%2, %0					\n"		\
+"	movco.l	%0, @%3					\n"		\
+"	bf	1b					\n"		\
+"	synco						\n"		\
+	: "=&z" (temp), "=&z" (res)					\
+	: "r" (i), "r" (&v->counter)					\
+	: "t");								\
+									\
+	return res;							\
+}
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
 
 #undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/sh/include/asm/spinlock.h b/arch/sh/include/asm/spinlock.h
index bdc0f3b6c56a..416834b60ad0 100644
--- a/arch/sh/include/asm/spinlock.h
+++ b/arch/sh/include/asm/spinlock.h
@@ -19,14 +19,20 @@
 #error "Need movli.l/movco.l for spinlocks"
 #endif
 
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
 /*
  * Your basic SMP spinlocks, allowing only a single CPU anywhere
  */
 
 #define arch_spin_is_locked(x)		((x)->lock <= 0)
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-#define arch_spin_unlock_wait(x) \
-	do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0)
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->lock, VAL > 0);
+}
 
 /*
  * Simple spin lock operations.  There are two variants, one clears IRQ's
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 7dcbebbcaec6..ee3f11c43cda 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -20,9 +20,10 @@
 #define ATOMIC_INIT(i)  { (i) }
 
 int atomic_add_return(int, atomic_t *);
-void atomic_and(int, atomic_t *);
-void atomic_or(int, atomic_t *);
-void atomic_xor(int, atomic_t *);
+int atomic_fetch_add(int, atomic_t *);
+int atomic_fetch_and(int, atomic_t *);
+int atomic_fetch_or(int, atomic_t *);
+int atomic_fetch_xor(int, atomic_t *);
 int atomic_cmpxchg(atomic_t *, int, int);
 int atomic_xchg(atomic_t *, int);
 int __atomic_add_unless(atomic_t *, int, int);
@@ -35,7 +36,13 @@ void atomic_set(atomic_t *, int);
 #define atomic_inc(v)		((void)atomic_add_return(        1, (v)))
 #define atomic_dec(v)		((void)atomic_add_return(       -1, (v)))
 
+#define atomic_and(i, v)	((void)atomic_fetch_and((i), (v)))
+#define atomic_or(i, v)		((void)atomic_fetch_or((i), (v)))
+#define atomic_xor(i, v)	((void)atomic_fetch_xor((i), (v)))
+
 #define atomic_sub_return(i, v)	(atomic_add_return(-(int)(i), (v)))
+#define atomic_fetch_sub(i, v)  (atomic_fetch_add (-(int)(i), (v)))
+
 #define atomic_inc_return(v)	(atomic_add_return(        1, (v)))
 #define atomic_dec_return(v)	(atomic_add_return(       -1, (v)))
 
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index f2fbf9e16faf..24827a3f733a 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -28,16 +28,24 @@ void atomic64_##op(long, atomic64_t *);
 int atomic_##op##_return(int, atomic_t *);				\
 long atomic64_##op##_return(long, atomic64_t *);
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+int atomic_fetch_##op(int, atomic_t *);					\
+long atomic64_fetch_##op(long, atomic64_t *);
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h
index bcc98fc35281..d9c5876c6121 100644
--- a/arch/sparc/include/asm/spinlock_32.h
+++ b/arch/sparc/include/asm/spinlock_32.h
@@ -9,12 +9,15 @@
 #ifndef __ASSEMBLY__
 
 #include <asm/psr.h>
+#include <asm/barrier.h>
 #include <asm/processor.h> /* for cpu_relax */
 
 #define arch_spin_is_locked(lock) (*((volatile unsigned char *)(lock)) != 0)
 
-#define arch_spin_unlock_wait(lock) \
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->lock, !VAL);
+}
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h
index 968917694978..87990b7c6b0d 100644
--- a/arch/sparc/include/asm/spinlock_64.h
+++ b/arch/sparc/include/asm/spinlock_64.h
@@ -8,6 +8,9 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/processor.h>
+#include <asm/barrier.h>
+
 /* To get debugging spinlocks which detect and catch
  * deadlock situations, set CONFIG_DEBUG_SPINLOCK
  * and rebuild your kernel.
@@ -23,9 +26,10 @@
 
 #define arch_spin_is_locked(lp)	((lp)->lock != 0)
 
-#define arch_spin_unlock_wait(lp)	\
-	do {	rmb();			\
-	} while((lp)->lock)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->lock, !VAL);
+}
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index b9d63c0a7aab..2c373329d5cb 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -27,39 +27,44 @@ static DEFINE_SPINLOCK(dummy);
 
 #endif /* SMP */
 
-#define ATOMIC_OP_RETURN(op, c_op)					\
-int atomic_##op##_return(int i, atomic_t *v)				\
+#define ATOMIC_FETCH_OP(op, c_op)					\
+int atomic_fetch_##op(int i, atomic_t *v)				\
 {									\
 	int ret;							\
 	unsigned long flags;						\
 	spin_lock_irqsave(ATOMIC_HASH(v), flags);			\
 									\
-	ret = (v->counter c_op i);					\
+	ret = v->counter;						\
+	v->counter c_op i;						\
 									\
 	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);			\
 	return ret;							\
 }									\
-EXPORT_SYMBOL(atomic_##op##_return);
+EXPORT_SYMBOL(atomic_fetch_##op);
 
-#define ATOMIC_OP(op, c_op)						\
-void atomic_##op(int i, atomic_t *v)					\
+#define ATOMIC_OP_RETURN(op, c_op)					\
+int atomic_##op##_return(int i, atomic_t *v)				\
 {									\
+	int ret;							\
 	unsigned long flags;						\
 	spin_lock_irqsave(ATOMIC_HASH(v), flags);			\
 									\
-	v->counter c_op i;						\
+	ret = (v->counter c_op i);					\
 									\
 	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);			\
+	return ret;							\
 }									\
-EXPORT_SYMBOL(atomic_##op);
+EXPORT_SYMBOL(atomic_##op##_return);
 
 ATOMIC_OP_RETURN(add, +=)
-ATOMIC_OP(and, &=)
-ATOMIC_OP(or, |=)
-ATOMIC_OP(xor, ^=)
 
+ATOMIC_FETCH_OP(add, +=)
+ATOMIC_FETCH_OP(and, &=)
+ATOMIC_FETCH_OP(or, |=)
+ATOMIC_FETCH_OP(xor, ^=)
+
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
-#undef ATOMIC_OP
 
 int atomic_xchg(atomic_t *v, int new)
 {
diff --git a/arch/sparc/lib/atomic_64.S b/arch/sparc/lib/atomic_64.S
index d6b0363f345b..a5c5a0279ccc 100644
--- a/arch/sparc/lib/atomic_64.S
+++ b/arch/sparc/lib/atomic_64.S
@@ -9,10 +9,11 @@
 
 	.text
 
-	/* Two versions of the atomic routines, one that
+	/* Three versions of the atomic routines, one that
 	 * does not return a value and does not perform
-	 * memory barriers, and a second which returns
-	 * a value and does the barriers.
+	 * memory barriers, and a two which return
+	 * a value, the new and old value resp. and does the
+	 * barriers.
 	 */
 
 #define ATOMIC_OP(op)							\
@@ -43,15 +44,34 @@ ENTRY(atomic_##op##_return) /* %o0 = increment, %o1 = atomic_ptr */	\
 2:	BACKOFF_SPIN(%o2, %o3, 1b);					\
 ENDPROC(atomic_##op##_return);
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+ENTRY(atomic_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */	\
+	BACKOFF_SETUP(%o2);						\
+1:	lduw	[%o1], %g1;						\
+	op	%g1, %o0, %g7;						\
+	cas	[%o1], %g1, %g7;					\
+	cmp	%g1, %g7;						\
+	bne,pn	%icc, BACKOFF_LABEL(2f, 1b);				\
+	 nop;								\
+	retl;								\
+	 sra	%g1, 0, %o0;						\
+2:	BACKOFF_SPIN(%o2, %o3, 1b);					\
+ENDPROC(atomic_fetch_##op);
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
 
 #undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
@@ -83,15 +103,34 @@ ENTRY(atomic64_##op##_return) /* %o0 = increment, %o1 = atomic_ptr */	\
 2:	BACKOFF_SPIN(%o2, %o3, 1b);					\
 ENDPROC(atomic64_##op##_return);
 
-#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op)
+#define ATOMIC64_FETCH_OP(op)						\
+ENTRY(atomic64_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */	\
+	BACKOFF_SETUP(%o2);						\
+1:	ldx	[%o1], %g1;						\
+	op	%g1, %o0, %g7;						\
+	casx	[%o1], %g1, %g7;					\
+	cmp	%g1, %g7;						\
+	bne,pn	%xcc, BACKOFF_LABEL(2f, 1b);				\
+	 nop;								\
+	retl;								\
+	 mov	%g1, %o0;						\
+2:	BACKOFF_SPIN(%o2, %o3, 1b);					\
+ENDPROC(atomic64_fetch_##op);
+
+#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op)
 
 ATOMIC64_OPS(add)
 ATOMIC64_OPS(sub)
-ATOMIC64_OP(and)
-ATOMIC64_OP(or)
-ATOMIC64_OP(xor)
 
 #undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_FETCH_OP(op)
+
+ATOMIC64_OPS(and)
+ATOMIC64_OPS(or)
+ATOMIC64_OPS(xor)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 8eb454cfe05c..de5e97817bdb 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -107,15 +107,24 @@ EXPORT_SYMBOL(atomic64_##op);
 EXPORT_SYMBOL(atomic_##op##_return);					\
 EXPORT_SYMBOL(atomic64_##op##_return);
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_FETCH_OP(op)						\
+EXPORT_SYMBOL(atomic_fetch_##op);					\
+EXPORT_SYMBOL(atomic64_fetch_##op);
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
 
 #undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/tile/include/asm/atomic.h b/arch/tile/include/asm/atomic.h
index 9fc0107a9c5e..8dda3c8ff5ab 100644
--- a/arch/tile/include/asm/atomic.h
+++ b/arch/tile/include/asm/atomic.h
@@ -46,6 +46,8 @@ static inline int atomic_read(const atomic_t *v)
  */
 #define atomic_sub_return(i, v)		atomic_add_return((int)(-(i)), (v))
 
+#define atomic_fetch_sub(i, v)		atomic_fetch_add(-(int)(i), (v))
+
 /**
  * atomic_sub - subtract integer from atomic variable
  * @i: integer value to subtract
diff --git a/arch/tile/include/asm/atomic_32.h b/arch/tile/include/asm/atomic_32.h
index d320ce253d86..a93774255136 100644
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -34,18 +34,29 @@ static inline void atomic_add(int i, atomic_t *v)
 	_atomic_xchg_add(&v->counter, i);
 }
 
-#define ATOMIC_OP(op)							\
-unsigned long _atomic_##op(volatile unsigned long *p, unsigned long mask); \
+#define ATOMIC_OPS(op)							\
+unsigned long _atomic_fetch_##op(volatile unsigned long *p, unsigned long mask); \
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
-	_atomic_##op((unsigned long *)&v->counter, i);			\
+	_atomic_fetch_##op((unsigned long *)&v->counter, i);		\
+}									\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	smp_mb();							\
+	return _atomic_fetch_##op((unsigned long *)&v->counter, i);	\
 }
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
-#undef ATOMIC_OP
+#undef ATOMIC_OPS
+
+static inline int atomic_fetch_add(int i, atomic_t *v)
+{
+	smp_mb();
+	return _atomic_xchg_add(&v->counter, i);
+}
 
 /**
  * atomic_add_return - add integer and return
@@ -126,16 +137,29 @@ static inline void atomic64_add(long long i, atomic64_t *v)
 	_atomic64_xchg_add(&v->counter, i);
 }
 
-#define ATOMIC64_OP(op)						\
-long long _atomic64_##op(long long *v, long long n);		\
+#define ATOMIC64_OPS(op)					\
+long long _atomic64_fetch_##op(long long *v, long long n);	\
 static inline void atomic64_##op(long long i, atomic64_t *v)	\
 {								\
-	_atomic64_##op(&v->counter, i);				\
+	_atomic64_fetch_##op(&v->counter, i);			\
+}								\
+static inline long long atomic64_fetch_##op(long long i, atomic64_t *v)	\
+{								\
+	smp_mb();						\
+	return _atomic64_fetch_##op(&v->counter, i);		\
 }
 
-ATOMIC64_OP(and)
-ATOMIC64_OP(or)
-ATOMIC64_OP(xor)
+ATOMIC64_OPS(and)
+ATOMIC64_OPS(or)
+ATOMIC64_OPS(xor)
+
+#undef ATOMIC64_OPS
+
+static inline long long atomic64_fetch_add(long long i, atomic64_t *v)
+{
+	smp_mb();
+	return _atomic64_xchg_add(&v->counter, i);
+}
 
 /**
  * atomic64_add_return - add integer and return
@@ -186,6 +210,7 @@ static inline void atomic64_set(atomic64_t *v, long long n)
 #define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
 #define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
 #define atomic64_sub_return(i, v)	atomic64_add_return(-(i), (v))
+#define atomic64_fetch_sub(i, v)	atomic64_fetch_add(-(i), (v))
 #define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
 #define atomic64_sub(i, v)		atomic64_add(-(i), (v))
 #define atomic64_dec(v)			atomic64_sub(1LL, (v))
@@ -193,7 +218,6 @@ static inline void atomic64_set(atomic64_t *v, long long n)
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 #define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
 
-
 #endif /* !__ASSEMBLY__ */
 
 /*
@@ -242,16 +266,16 @@ struct __get_user {
 	unsigned long val;
 	int err;
 };
-extern struct __get_user __atomic_cmpxchg(volatile int *p,
+extern struct __get_user __atomic32_cmpxchg(volatile int *p,
 					  int *lock, int o, int n);
-extern struct __get_user __atomic_xchg(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_xchg_add(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_xchg_add_unless(volatile int *p,
+extern struct __get_user __atomic32_xchg(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_xchg_add(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_xchg_add_unless(volatile int *p,
 						  int *lock, int o, int n);
-extern struct __get_user __atomic_or(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_and(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_andn(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_xor(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_fetch_or(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_fetch_and(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_fetch_andn(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_fetch_xor(volatile int *p, int *lock, int n);
 extern long long __atomic64_cmpxchg(volatile long long *p, int *lock,
 					long long o, long long n);
 extern long long __atomic64_xchg(volatile long long *p, int *lock, long long n);
@@ -259,9 +283,9 @@ extern long long __atomic64_xchg_add(volatile long long *p, int *lock,
 					long long n);
 extern long long __atomic64_xchg_add_unless(volatile long long *p,
 					int *lock, long long o, long long n);
-extern long long __atomic64_and(volatile long long *p, int *lock, long long n);
-extern long long __atomic64_or(volatile long long *p, int *lock, long long n);
-extern long long __atomic64_xor(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_fetch_and(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_fetch_or(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_fetch_xor(volatile long long *p, int *lock, long long n);
 
 /* Return failure from the atomic wrappers. */
 struct __get_user __atomic_bad_address(int __user *addr);
diff --git a/arch/tile/include/asm/atomic_64.h b/arch/tile/include/asm/atomic_64.h
index b0531a623653..4cefa0c9fd81 100644
--- a/arch/tile/include/asm/atomic_64.h
+++ b/arch/tile/include/asm/atomic_64.h
@@ -32,11 +32,6 @@
  * on any routine which updates memory and returns a value.
  */
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	__insn_fetchadd4((void *)&v->counter, i);
-}
-
 /*
  * Note a subtlety of the locking here.  We are required to provide a
  * full memory barrier before and after the operation.  However, we
@@ -59,28 +54,39 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	return val;
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+#define ATOMIC_OPS(op)							\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int val;							\
+	smp_mb();							\
+	val = __insn_fetch##op##4((void *)&v->counter, i);		\
+	smp_mb();							\
+	return val;							\
+}									\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	__insn_fetch##op##4((void *)&v->counter, i);			\
+}
+
+ATOMIC_OPS(add)
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+
+#undef ATOMIC_OPS
+
+static inline int atomic_fetch_xor(int i, atomic_t *v)
 {
 	int guess, oldval = v->counter;
+	smp_mb();
 	do {
-		if (oldval == u)
-			break;
 		guess = oldval;
-		oldval = cmpxchg(&v->counter, guess, guess + a);
+		__insn_mtspr(SPR_CMPEXCH_VALUE, guess);
+		oldval = __insn_cmpexch4(&v->counter, guess ^ i);
 	} while (guess != oldval);
+	smp_mb();
 	return oldval;
 }
 
-static inline void atomic_and(int i, atomic_t *v)
-{
-	__insn_fetchand4((void *)&v->counter, i);
-}
-
-static inline void atomic_or(int i, atomic_t *v)
-{
-	__insn_fetchor4((void *)&v->counter, i);
-}
-
 static inline void atomic_xor(int i, atomic_t *v)
 {
 	int guess, oldval = v->counter;
@@ -91,6 +97,18 @@ static inline void atomic_xor(int i, atomic_t *v)
 	} while (guess != oldval);
 }
 
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int guess, oldval = v->counter;
+	do {
+		if (oldval == u)
+			break;
+		guess = oldval;
+		oldval = cmpxchg(&v->counter, guess, guess + a);
+	} while (guess != oldval);
+	return oldval;
+}
+
 /* Now the true 64-bit operations. */
 
 #define ATOMIC64_INIT(i)	{ (i) }
@@ -98,11 +116,6 @@ static inline void atomic_xor(int i, atomic_t *v)
 #define atomic64_read(v)	READ_ONCE((v)->counter)
 #define atomic64_set(v, i)	WRITE_ONCE((v)->counter, (i))
 
-static inline void atomic64_add(long i, atomic64_t *v)
-{
-	__insn_fetchadd((void *)&v->counter, i);
-}
-
 static inline long atomic64_add_return(long i, atomic64_t *v)
 {
 	int val;
@@ -112,26 +125,37 @@ static inline long atomic64_add_return(long i, atomic64_t *v)
 	return val;
 }
 
-static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
+#define ATOMIC64_OPS(op)						\
+static inline long atomic64_fetch_##op(long i, atomic64_t *v)		\
+{									\
+	long val;							\
+	smp_mb();							\
+	val = __insn_fetch##op((void *)&v->counter, i);			\
+	smp_mb();							\
+	return val;							\
+}									\
+static inline void atomic64_##op(long i, atomic64_t *v)			\
+{									\
+	__insn_fetch##op((void *)&v->counter, i);			\
+}
+
+ATOMIC64_OPS(add)
+ATOMIC64_OPS(and)
+ATOMIC64_OPS(or)
+
+#undef ATOMIC64_OPS
+
+static inline long atomic64_fetch_xor(long i, atomic64_t *v)
 {
 	long guess, oldval = v->counter;
+	smp_mb();
 	do {
-		if (oldval == u)
-			break;
 		guess = oldval;
-		oldval = cmpxchg(&v->counter, guess, guess + a);
+		__insn_mtspr(SPR_CMPEXCH_VALUE, guess);
+		oldval = __insn_cmpexch(&v->counter, guess ^ i);
 	} while (guess != oldval);
-	return oldval != u;
-}
-
-static inline void atomic64_and(long i, atomic64_t *v)
-{
-	__insn_fetchand((void *)&v->counter, i);
-}
-
-static inline void atomic64_or(long i, atomic64_t *v)
-{
-	__insn_fetchor((void *)&v->counter, i);
+	smp_mb();
+	return oldval;
 }
 
 static inline void atomic64_xor(long i, atomic64_t *v)
@@ -144,7 +168,20 @@ static inline void atomic64_xor(long i, atomic64_t *v)
 	} while (guess != oldval);
 }
 
+static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
+{
+	long guess, oldval = v->counter;
+	do {
+		if (oldval == u)
+			break;
+		guess = oldval;
+		oldval = cmpxchg(&v->counter, guess, guess + a);
+	} while (guess != oldval);
+	return oldval != u;
+}
+
 #define atomic64_sub_return(i, v)	atomic64_add_return(-(i), (v))
+#define atomic64_fetch_sub(i, v)	atomic64_fetch_add(-(i), (v))
 #define atomic64_sub(i, v)		atomic64_add(-(i), (v))
 #define atomic64_inc_return(v)		atomic64_add_return(1, (v))
 #define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
diff --git a/arch/tile/include/asm/barrier.h b/arch/tile/include/asm/barrier.h
index d55222806c2f..4c419ab95ab7 100644
--- a/arch/tile/include/asm/barrier.h
+++ b/arch/tile/include/asm/barrier.h
@@ -87,6 +87,13 @@ mb_incoherent(void)
 #define __smp_mb__after_atomic()	__smp_mb()
 #endif
 
+/*
+ * The TILE architecture does not do speculative reads; this ensures
+ * that a control dependency also orders against loads and already provides
+ * a LOAD->{LOAD,STORE} order and can forgo the additional RMB.
+ */
+#define smp_acquire__after_ctrl_dep()	barrier()
+
 #include <asm-generic/barrier.h>
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/tile/include/asm/bitops_32.h b/arch/tile/include/asm/bitops_32.h
index bbf7b666f21d..d1406a95f6b7 100644
--- a/arch/tile/include/asm/bitops_32.h
+++ b/arch/tile/include/asm/bitops_32.h
@@ -19,9 +19,9 @@
 #include <asm/barrier.h>
 
 /* Tile-specific routines to support <asm/bitops.h>. */
-unsigned long _atomic_or(volatile unsigned long *p, unsigned long mask);
-unsigned long _atomic_andn(volatile unsigned long *p, unsigned long mask);
-unsigned long _atomic_xor(volatile unsigned long *p, unsigned long mask);
+unsigned long _atomic_fetch_or(volatile unsigned long *p, unsigned long mask);
+unsigned long _atomic_fetch_andn(volatile unsigned long *p, unsigned long mask);
+unsigned long _atomic_fetch_xor(volatile unsigned long *p, unsigned long mask);
 
 /**
  * set_bit - Atomically set a bit in memory
@@ -35,7 +35,7 @@ unsigned long _atomic_xor(volatile unsigned long *p, unsigned long mask);
  */
 static inline void set_bit(unsigned nr, volatile unsigned long *addr)
 {
-	_atomic_or(addr + BIT_WORD(nr), BIT_MASK(nr));
+	_atomic_fetch_or(addr + BIT_WORD(nr), BIT_MASK(nr));
 }
 
 /**
@@ -54,7 +54,7 @@ static inline void set_bit(unsigned nr, volatile unsigned long *addr)
  */
 static inline void clear_bit(unsigned nr, volatile unsigned long *addr)
 {
-	_atomic_andn(addr + BIT_WORD(nr), BIT_MASK(nr));
+	_atomic_fetch_andn(addr + BIT_WORD(nr), BIT_MASK(nr));
 }
 
 /**
@@ -69,7 +69,7 @@ static inline void clear_bit(unsigned nr, volatile unsigned long *addr)
  */
 static inline void change_bit(unsigned nr, volatile unsigned long *addr)
 {
-	_atomic_xor(addr + BIT_WORD(nr), BIT_MASK(nr));
+	_atomic_fetch_xor(addr + BIT_WORD(nr), BIT_MASK(nr));
 }
 
 /**
@@ -85,7 +85,7 @@ static inline int test_and_set_bit(unsigned nr, volatile unsigned long *addr)
 	unsigned long mask = BIT_MASK(nr);
 	addr += BIT_WORD(nr);
 	smp_mb();  /* barrier for proper semantics */
-	return (_atomic_or(addr, mask) & mask) != 0;
+	return (_atomic_fetch_or(addr, mask) & mask) != 0;
 }
 
 /**
@@ -101,7 +101,7 @@ static inline int test_and_clear_bit(unsigned nr, volatile unsigned long *addr)
 	unsigned long mask = BIT_MASK(nr);
 	addr += BIT_WORD(nr);
 	smp_mb();  /* barrier for proper semantics */
-	return (_atomic_andn(addr, mask) & mask) != 0;
+	return (_atomic_fetch_andn(addr, mask) & mask) != 0;
 }
 
 /**
@@ -118,7 +118,7 @@ static inline int test_and_change_bit(unsigned nr,
 	unsigned long mask = BIT_MASK(nr);
 	addr += BIT_WORD(nr);
 	smp_mb();  /* barrier for proper semantics */
-	return (_atomic_xor(addr, mask) & mask) != 0;
+	return (_atomic_fetch_xor(addr, mask) & mask) != 0;
 }
 
 #include <asm-generic/bitops/ext2-atomic.h>
diff --git a/arch/tile/include/asm/futex.h b/arch/tile/include/asm/futex.h
index 1a6ef1b69cb1..e64a1b75fc38 100644
--- a/arch/tile/include/asm/futex.h
+++ b/arch/tile/include/asm/futex.h
@@ -80,16 +80,16 @@
 		ret = gu.err;						\
 	}
 
-#define __futex_set() __futex_call(__atomic_xchg)
-#define __futex_add() __futex_call(__atomic_xchg_add)
-#define __futex_or() __futex_call(__atomic_or)
-#define __futex_andn() __futex_call(__atomic_andn)
-#define __futex_xor() __futex_call(__atomic_xor)
+#define __futex_set() __futex_call(__atomic32_xchg)
+#define __futex_add() __futex_call(__atomic32_xchg_add)
+#define __futex_or() __futex_call(__atomic32_fetch_or)
+#define __futex_andn() __futex_call(__atomic32_fetch_andn)
+#define __futex_xor() __futex_call(__atomic32_fetch_xor)
 
 #define __futex_cmpxchg()						\
 	{								\
-		struct __get_user gu = __atomic_cmpxchg((u32 __force *)uaddr, \
-							lock, oldval, oparg); \
+		struct __get_user gu = __atomic32_cmpxchg((u32 __force *)uaddr, \
+							  lock, oldval, oparg); \
 		val = gu.val;						\
 		ret = gu.err;						\
 	}
diff --git a/arch/tile/lib/atomic_32.c b/arch/tile/lib/atomic_32.c
index 298df1e9912a..f8128800dbf5 100644
--- a/arch/tile/lib/atomic_32.c
+++ b/arch/tile/lib/atomic_32.c
@@ -61,13 +61,13 @@ static inline int *__atomic_setup(volatile void *v)
 
 int _atomic_xchg(int *v, int n)
 {
-	return __atomic_xchg(v, __atomic_setup(v), n).val;
+	return __atomic32_xchg(v, __atomic_setup(v), n).val;
 }
 EXPORT_SYMBOL(_atomic_xchg);
 
 int _atomic_xchg_add(int *v, int i)
 {
-	return __atomic_xchg_add(v, __atomic_setup(v), i).val;
+	return __atomic32_xchg_add(v, __atomic_setup(v), i).val;
 }
 EXPORT_SYMBOL(_atomic_xchg_add);
 
@@ -78,39 +78,39 @@ int _atomic_xchg_add_unless(int *v, int a, int u)
 	 * to use the first argument consistently as the "old value"
 	 * in the assembly, as is done for _atomic_cmpxchg().
 	 */
-	return __atomic_xchg_add_unless(v, __atomic_setup(v), u, a).val;
+	return __atomic32_xchg_add_unless(v, __atomic_setup(v), u, a).val;
 }
 EXPORT_SYMBOL(_atomic_xchg_add_unless);
 
 int _atomic_cmpxchg(int *v, int o, int n)
 {
-	return __atomic_cmpxchg(v, __atomic_setup(v), o, n).val;
+	return __atomic32_cmpxchg(v, __atomic_setup(v), o, n).val;
 }
 EXPORT_SYMBOL(_atomic_cmpxchg);
 
-unsigned long _atomic_or(volatile unsigned long *p, unsigned long mask)
+unsigned long _atomic_fetch_or(volatile unsigned long *p, unsigned long mask)
 {
-	return __atomic_or((int *)p, __atomic_setup(p), mask).val;
+	return __atomic32_fetch_or((int *)p, __atomic_setup(p), mask).val;
 }
-EXPORT_SYMBOL(_atomic_or);
+EXPORT_SYMBOL(_atomic_fetch_or);
 
-unsigned long _atomic_and(volatile unsigned long *p, unsigned long mask)
+unsigned long _atomic_fetch_and(volatile unsigned long *p, unsigned long mask)
 {
-	return __atomic_and((int *)p, __atomic_setup(p), mask).val;
+	return __atomic32_fetch_and((int *)p, __atomic_setup(p), mask).val;
 }
-EXPORT_SYMBOL(_atomic_and);
+EXPORT_SYMBOL(_atomic_fetch_and);
 
-unsigned long _atomic_andn(volatile unsigned long *p, unsigned long mask)
+unsigned long _atomic_fetch_andn(volatile unsigned long *p, unsigned long mask)
 {
-	return __atomic_andn((int *)p, __atomic_setup(p), mask).val;
+	return __atomic32_fetch_andn((int *)p, __atomic_setup(p), mask).val;
 }
-EXPORT_SYMBOL(_atomic_andn);
+EXPORT_SYMBOL(_atomic_fetch_andn);
 
-unsigned long _atomic_xor(volatile unsigned long *p, unsigned long mask)
+unsigned long _atomic_fetch_xor(volatile unsigned long *p, unsigned long mask)
 {
-	return __atomic_xor((int *)p, __atomic_setup(p), mask).val;
+	return __atomic32_fetch_xor((int *)p, __atomic_setup(p), mask).val;
 }
-EXPORT_SYMBOL(_atomic_xor);
+EXPORT_SYMBOL(_atomic_fetch_xor);
 
 
 long long _atomic64_xchg(long long *v, long long n)
@@ -142,23 +142,23 @@ long long _atomic64_cmpxchg(long long *v, long long o, long long n)
 }
 EXPORT_SYMBOL(_atomic64_cmpxchg);
 
-long long _atomic64_and(long long *v, long long n)
+long long _atomic64_fetch_and(long long *v, long long n)
 {
-	return __atomic64_and(v, __atomic_setup(v), n);
+	return __atomic64_fetch_and(v, __atomic_setup(v), n);
 }
-EXPORT_SYMBOL(_atomic64_and);
+EXPORT_SYMBOL(_atomic64_fetch_and);
 
-long long _atomic64_or(long long *v, long long n)
+long long _atomic64_fetch_or(long long *v, long long n)
 {
-	return __atomic64_or(v, __atomic_setup(v), n);
+	return __atomic64_fetch_or(v, __atomic_setup(v), n);
 }
-EXPORT_SYMBOL(_atomic64_or);
+EXPORT_SYMBOL(_atomic64_fetch_or);
 
-long long _atomic64_xor(long long *v, long long n)
+long long _atomic64_fetch_xor(long long *v, long long n)
 {
-	return __atomic64_xor(v, __atomic_setup(v), n);
+	return __atomic64_fetch_xor(v, __atomic_setup(v), n);
 }
-EXPORT_SYMBOL(_atomic64_xor);
+EXPORT_SYMBOL(_atomic64_fetch_xor);
 
 /*
  * If any of the atomic or futex routines hit a bad address (not in
diff --git a/arch/tile/lib/atomic_asm_32.S b/arch/tile/lib/atomic_asm_32.S
index f611265633d6..1a70e6c0f259 100644
--- a/arch/tile/lib/atomic_asm_32.S
+++ b/arch/tile/lib/atomic_asm_32.S
@@ -172,15 +172,20 @@ STD_ENTRY_SECTION(__atomic\name, .text.atomic)
 	.endif
 	.endm
 
-atomic_op _cmpxchg, 32, "seq r26, r22, r2; { bbns r26, 3f; move r24, r3 }"
-atomic_op _xchg, 32, "move r24, r2"
-atomic_op _xchg_add, 32, "add r24, r22, r2"
-atomic_op _xchg_add_unless, 32, \
+
+/*
+ * Use __atomic32 prefix to avoid collisions with GCC builtin __atomic functions.
+ */
+
+atomic_op 32_cmpxchg, 32, "seq r26, r22, r2; { bbns r26, 3f; move r24, r3 }"
+atomic_op 32_xchg, 32, "move r24, r2"
+atomic_op 32_xchg_add, 32, "add r24, r22, r2"
+atomic_op 32_xchg_add_unless, 32, \
 	"sne r26, r22, r2; { bbns r26, 3f; add r24, r22, r3 }"
-atomic_op _or, 32, "or r24, r22, r2"
-atomic_op _and, 32, "and r24, r22, r2"
-atomic_op _andn, 32, "nor r2, r2, zero; and r24, r22, r2"
-atomic_op _xor, 32, "xor r24, r22, r2"
+atomic_op 32_fetch_or, 32, "or r24, r22, r2"
+atomic_op 32_fetch_and, 32, "and r24, r22, r2"
+atomic_op 32_fetch_andn, 32, "nor r2, r2, zero; and r24, r22, r2"
+atomic_op 32_fetch_xor, 32, "xor r24, r22, r2"
 
 atomic_op 64_cmpxchg, 64, "{ seq r26, r22, r2; seq r27, r23, r3 }; \
 	{ bbns r26, 3f; move r24, r4 }; { bbns r27, 3f; move r25, r5 }"
@@ -192,9 +197,9 @@ atomic_op 64_xchg_add_unless, 64, \
 	{ bbns r26, 3f; add r24, r22, r4 }; \
 	{ bbns r27, 3f; add r25, r23, r5 }; \
 	slt_u r26, r24, r22; add r25, r25, r26"
-atomic_op 64_or, 64, "{ or r24, r22, r2; or r25, r23, r3 }"
-atomic_op 64_and, 64, "{ and r24, r22, r2; and r25, r23, r3 }"
-atomic_op 64_xor, 64, "{ xor r24, r22, r2; xor r25, r23, r3 }"
+atomic_op 64_fetch_or, 64, "{ or r24, r22, r2; or r25, r23, r3 }"
+atomic_op 64_fetch_and, 64, "{ and r24, r22, r2; and r25, r23, r3 }"
+atomic_op 64_fetch_xor, 64, "{ xor r24, r22, r2; xor r25, r23, r3 }"
 
 	jrp     lr              /* happy backtracer */
 
diff --git a/arch/tile/lib/spinlock_32.c b/arch/tile/lib/spinlock_32.c
index 88c2a53362e7..076c6cc43113 100644
--- a/arch/tile/lib/spinlock_32.c
+++ b/arch/tile/lib/spinlock_32.c
@@ -76,6 +76,12 @@ void arch_spin_unlock_wait(arch_spinlock_t *lock)
 	do {
 		delay_backoff(iterations++);
 	} while (READ_ONCE(lock->current_ticket) == curr);
+
+	/*
+	 * The TILE architecture doesn't do read speculation; therefore
+	 * a control dependency guarantees a LOAD->{LOAD,STORE} order.
+	 */
+	barrier();
 }
 EXPORT_SYMBOL(arch_spin_unlock_wait);
 
diff --git a/arch/tile/lib/spinlock_64.c b/arch/tile/lib/spinlock_64.c
index c8d1f94ff1fe..a4b5b2cbce93 100644
--- a/arch/tile/lib/spinlock_64.c
+++ b/arch/tile/lib/spinlock_64.c
@@ -76,6 +76,12 @@ void arch_spin_unlock_wait(arch_spinlock_t *lock)
 	do {
 		delay_backoff(iterations++);
 	} while (arch_spin_current(READ_ONCE(lock->lock)) == curr);
+
+	/*
+	 * The TILE architecture doesn't do read speculation; therefore
+	 * a control dependency guarantees a LOAD->{LOAD,STORE} order.
+	 */
+	barrier();
 }
 EXPORT_SYMBOL(arch_spin_unlock_wait);
 
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 3e8674288198..a58b99811105 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -171,6 +171,16 @@ static __always_inline int atomic_sub_return(int i, atomic_t *v)
 #define atomic_inc_return(v)  (atomic_add_return(1, v))
 #define atomic_dec_return(v)  (atomic_sub_return(1, v))
 
+static __always_inline int atomic_fetch_add(int i, atomic_t *v)
+{
+	return xadd(&v->counter, i);
+}
+
+static __always_inline int atomic_fetch_sub(int i, atomic_t *v)
+{
+	return xadd(&v->counter, -i);
+}
+
 static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	return cmpxchg(&v->counter, old, new);
@@ -190,10 +200,29 @@ static inline void atomic_##op(int i, atomic_t *v)			\
 			: "memory");					\
 }
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static inline int atomic_fetch_##op(int i, atomic_t *v)		\
+{									\
+	int old, val = atomic_read(v);					\
+	for (;;) {							\
+		old = atomic_cmpxchg(v, val, val c_op i);		\
+		if (old == val)						\
+			break;						\
+		val = old;						\
+	}								\
+	return old;							\
+}
+
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op)							\
+	ATOMIC_FETCH_OP(op, c_op)
+
+ATOMIC_OPS(and, &)
+ATOMIC_OPS(or , |)
+ATOMIC_OPS(xor, ^)
 
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP
 
 /**
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index a984111135b1..71d7705fb303 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -320,10 +320,29 @@ static inline void atomic64_##op(long long i, atomic64_t *v)		\
 		c = old;						\
 }
 
-ATOMIC64_OP(and, &)
-ATOMIC64_OP(or, |)
-ATOMIC64_OP(xor, ^)
+#define ATOMIC64_FETCH_OP(op, c_op)					\
+static inline long long atomic64_fetch_##op(long long i, atomic64_t *v)	\
+{									\
+	long long old, c = 0;						\
+	while ((old = atomic64_cmpxchg(v, c, c c_op i)) != c)		\
+		c = old;						\
+	return old;							\
+}
+
+ATOMIC64_FETCH_OP(add, +)
+
+#define atomic64_fetch_sub(i, v)	atomic64_fetch_add(-(i), (v))
+
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op, c_op)						\
+	ATOMIC64_FETCH_OP(op, c_op)
+
+ATOMIC64_OPS(and, &)
+ATOMIC64_OPS(or, |)
+ATOMIC64_OPS(xor, ^)
 
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP
 
 #endif /* _ASM_X86_ATOMIC64_32_H */
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 037351022f54..70eed0e14553 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -158,6 +158,16 @@ static inline long atomic64_sub_return(long i, atomic64_t *v)
 	return atomic64_add_return(-i, v);
 }
 
+static inline long atomic64_fetch_add(long i, atomic64_t *v)
+{
+	return xadd(&v->counter, i);
+}
+
+static inline long atomic64_fetch_sub(long i, atomic64_t *v)
+{
+	return xadd(&v->counter, -i);
+}
+
 #define atomic64_inc_return(v)  (atomic64_add_return(1, (v)))
 #define atomic64_dec_return(v)  (atomic64_sub_return(1, (v)))
 
@@ -229,10 +239,29 @@ static inline void atomic64_##op(long i, atomic64_t *v)			\
 			: "memory");					\
 }
 
-ATOMIC64_OP(and)
-ATOMIC64_OP(or)
-ATOMIC64_OP(xor)
+#define ATOMIC64_FETCH_OP(op, c_op)					\
+static inline long atomic64_fetch_##op(long i, atomic64_t *v)		\
+{									\
+	long old, val = atomic64_read(v);				\
+	for (;;) {							\
+		old = atomic64_cmpxchg(v, val, val c_op i);		\
+		if (old == val)						\
+			break;						\
+		val = old;						\
+	}								\
+	return old;							\
+}
+
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op)							\
+	ATOMIC64_FETCH_OP(op, c_op)
+
+ATOMIC64_OPS(and, &)
+ATOMIC64_OPS(or, |)
+ATOMIC64_OPS(xor, ^)
 
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP
 
 #endif /* _ASM_X86_ATOMIC64_64_H */
diff --git a/arch/x86/include/asm/mutex_32.h b/arch/x86/include/asm/mutex_32.h
index 85e6cda45a02..e9355a84fc67 100644
--- a/arch/x86/include/asm/mutex_32.h
+++ b/arch/x86/include/asm/mutex_32.h
@@ -101,7 +101,7 @@ static inline int __mutex_fastpath_trylock(atomic_t *count,
 					   int (*fail_fn)(atomic_t *))
 {
 	/* cmpxchg because it never induces a false contention state. */
-	if (likely(atomic_cmpxchg(count, 1, 0) == 1))
+	if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1))
 		return 1;
 
 	return 0;
diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h
index 07537a44216e..d9850758464e 100644
--- a/arch/x86/include/asm/mutex_64.h
+++ b/arch/x86/include/asm/mutex_64.h
@@ -118,10 +118,10 @@ do {								\
 static inline int __mutex_fastpath_trylock(atomic_t *count,
 					   int (*fail_fn)(atomic_t *))
 {
-	if (likely(atomic_cmpxchg(count, 1, 0) == 1))
+	if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1))
 		return 1;
-	else
-		return 0;
+
+	return 0;
 }
 
 #endif /* _ASM_X86_MUTEX_64_H */
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index 453744c1d347..089ced4edbbc 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -213,23 +213,5 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 		     : "memory", "cc");
 }
 
-/*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
-{
-	asm volatile(LOCK_PREFIX _ASM_ADD "%1,%0"
-		     : "+m" (sem->count)
-		     : "er" (delta));
-}
-
-/*
- * implement exchange and add functionality
- */
-static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
-{
-	return delta + xadd(&sem->count, delta);
-}
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_RWSEM_H */
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index fd8017ce298a..e7a23f2a519a 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -98,6 +98,26 @@ static inline int atomic_##op##_return(int i, atomic_t * v)		\
 	return result;							\
 }
 
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t * v)		\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	__asm__ __volatile__(						\
+			"1:     l32i    %1, %3, 0\n"			\
+			"       wsr     %1, scompare1\n"		\
+			"       " #op " %0, %1, %2\n"			\
+			"       s32c1i  %0, %3, 0\n"			\
+			"       bne     %0, %1, 1b\n"			\
+			: "=&a" (result), "=&a" (tmp)			\
+			: "a" (i), "a" (v)				\
+			: "memory"					\
+			);						\
+									\
+	return result;							\
+}
+
 #else /* XCHAL_HAVE_S32C1I */
 
 #define ATOMIC_OP(op)							\
@@ -138,18 +158,42 @@ static inline int atomic_##op##_return(int i, atomic_t * v)		\
 	return vval;							\
 }
 
+#define ATOMIC_FETCH_OP(op)						\
+static inline int atomic_fetch_##op(int i, atomic_t * v)		\
+{									\
+	unsigned int tmp, vval;						\
+									\
+	__asm__ __volatile__(						\
+			"       rsil    a15,"__stringify(TOPLEVEL)"\n"	\
+			"       l32i    %0, %3, 0\n"			\
+			"       " #op " %1, %0, %2\n"			\
+			"       s32i    %1, %3, 0\n"			\
+			"       wsr     a15, ps\n"			\
+			"       rsync\n"				\
+			: "=&a" (vval), "=&a" (tmp)			\
+			: "a" (i), "a" (v)				\
+			: "a15", "memory"				\
+			);						\
+									\
+	return vval;							\
+}
+
 #endif /* XCHAL_HAVE_S32C1I */
 
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op) ATOMIC_OP_RETURN(op)
 
 ATOMIC_OPS(add)
 ATOMIC_OPS(sub)
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
+
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/arch/xtensa/include/asm/spinlock.h b/arch/xtensa/include/asm/spinlock.h
index 1d95fa5dcd10..a36221cf6363 100644
--- a/arch/xtensa/include/asm/spinlock.h
+++ b/arch/xtensa/include/asm/spinlock.h
@@ -11,6 +11,9 @@
 #ifndef _XTENSA_SPINLOCK_H
 #define _XTENSA_SPINLOCK_H
 
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
 /*
  * spinlock
  *
@@ -29,8 +32,11 @@
  */
 
 #define arch_spin_is_locked(x) ((x)->slock != 0)
-#define arch_spin_unlock_wait(lock) \
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->slock, !VAL);
+}
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)