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}()
  ...

108 files changed, 3268 insertions, 958 deletions

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 147ae8ec836f..a4d0a99de04d 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -806,6 +806,41 @@ out-guess your code.  More generally, although READ_ONCE() does force
 the compiler to actually emit code for a given load, it does not force
 the compiler to use the results.
 
+In addition, control dependencies apply only to the then-clause and
+else-clause of the if-statement in question.  In particular, it does
+not necessarily apply to code following the if-statement:
+
+	q = READ_ONCE(a);
+	if (q) {
+		WRITE_ONCE(b, p);
+	} else {
+		WRITE_ONCE(b, r);
+	}
+	WRITE_ONCE(c, 1);  /* BUG: No ordering against the read from "a". */
+
+It is tempting to argue that there in fact is ordering because the
+compiler cannot reorder volatile accesses and also cannot reorder
+the writes to "b" with the condition.  Unfortunately for this line
+of reasoning, the compiler might compile the two writes to "b" as
+conditional-move instructions, as in this fanciful pseudo-assembly
+language:
+
+	ld r1,a
+	ld r2,p
+	ld r3,r
+	cmp r1,$0
+	cmov,ne r4,r2
+	cmov,eq r4,r3
+	st r4,b
+	st $1,c
+
+A weakly ordered CPU would have no dependency of any sort between the load
+from "a" and the store to "c".  The control dependencies would extend
+only to the pair of cmov instructions and the store depending on them.
+In short, control dependencies apply only to the stores in the then-clause
+and else-clause of the if-statement in question (including functions
+invoked by those two clauses), not to code following that if-statement.
+
 Finally, control dependencies do -not- provide transitivity.  This is
 demonstrated by two related examples, with the initial values of
 x and y both being zero:
@@ -869,6 +904,12 @@ In summary:
       atomic{,64}_read() can help to preserve your control dependency.
       Please see the COMPILER BARRIER section for more information.
 
+  (*) Control dependencies apply only to the then-clause and else-clause
+      of the if-statement containing the control dependency, including
+      any functions that these two clauses call.  Control dependencies
+      do -not- apply to code following the if-statement containing the
+      control dependency.
+
   (*) Control dependencies pair normally with other types of barriers.
 
   (*) Control dependencies do -not- provide transitivity.  If you
diff --git a/MAINTAINERS b/MAINTAINERS
index 452beeeb7fbd..09bb92fb80c8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7024,15 +7024,23 @@ Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 S:	Maintained
 F:	drivers/media/usb/dvb-usb-v2/lmedm04*
 
-LOCKDEP AND LOCKSTAT
+LOCKING PRIMITIVES
 M:	Peter Zijlstra <peterz@infradead.org>
 M:	Ingo Molnar <mingo@redhat.com>
 L:	linux-kernel@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core/locking
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core
 S:	Maintained
-F:	Documentation/locking/lockdep*.txt
-F:	Documentation/locking/lockstat.txt
+F:	Documentation/locking/
 F:	include/linux/lockdep.h
+F:	include/linux/spinlock*.h
+F:	arch/*/include/asm/spinlock*.h
+F:	include/linux/rwlock*.h
+F:	include/linux/mutex*.h
+F:	arch/*/include/asm/mutex*.h
+F:	include/linux/rwsem*.h
+F:	arch/*/include/asm/rwsem.h
+F:	include/linux/seqlock.h
+F:	lib/locking*.[ch]
 F:	kernel/locking/
 
 LOGICAL DISK MANAGER SUPPORT (LDM, Windows 2000/XP/Vista Dynamic Disks)
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)
 
diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h
index 5e1f345b58dd..288cc9e96395 100644
--- a/include/asm-generic/atomic-long.h
+++ b/include/asm-generic/atomic-long.h
@@ -112,6 +112,62 @@ static __always_inline void atomic_long_dec(atomic_long_t *l)
 	ATOMIC_LONG_PFX(_dec)(v);
 }
 
+#define ATOMIC_LONG_FETCH_OP(op, mo)					\
+static inline long							\
+atomic_long_fetch_##op##mo(long i, atomic_long_t *l)			\
+{									\
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;		\
+									\
+	return (long)ATOMIC_LONG_PFX(_fetch_##op##mo)(i, v);		\
+}
+
+ATOMIC_LONG_FETCH_OP(add, )
+ATOMIC_LONG_FETCH_OP(add, _relaxed)
+ATOMIC_LONG_FETCH_OP(add, _acquire)
+ATOMIC_LONG_FETCH_OP(add, _release)
+ATOMIC_LONG_FETCH_OP(sub, )
+ATOMIC_LONG_FETCH_OP(sub, _relaxed)
+ATOMIC_LONG_FETCH_OP(sub, _acquire)
+ATOMIC_LONG_FETCH_OP(sub, _release)
+ATOMIC_LONG_FETCH_OP(and, )
+ATOMIC_LONG_FETCH_OP(and, _relaxed)
+ATOMIC_LONG_FETCH_OP(and, _acquire)
+ATOMIC_LONG_FETCH_OP(and, _release)
+ATOMIC_LONG_FETCH_OP(andnot, )
+ATOMIC_LONG_FETCH_OP(andnot, _relaxed)
+ATOMIC_LONG_FETCH_OP(andnot, _acquire)
+ATOMIC_LONG_FETCH_OP(andnot, _release)
+ATOMIC_LONG_FETCH_OP(or, )
+ATOMIC_LONG_FETCH_OP(or, _relaxed)
+ATOMIC_LONG_FETCH_OP(or, _acquire)
+ATOMIC_LONG_FETCH_OP(or, _release)
+ATOMIC_LONG_FETCH_OP(xor, )
+ATOMIC_LONG_FETCH_OP(xor, _relaxed)
+ATOMIC_LONG_FETCH_OP(xor, _acquire)
+ATOMIC_LONG_FETCH_OP(xor, _release)
+
+#undef ATOMIC_LONG_FETCH_OP
+
+#define ATOMIC_LONG_FETCH_INC_DEC_OP(op, mo)					\
+static inline long							\
+atomic_long_fetch_##op##mo(atomic_long_t *l)				\
+{									\
+	ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l;		\
+									\
+	return (long)ATOMIC_LONG_PFX(_fetch_##op##mo)(v);		\
+}
+
+ATOMIC_LONG_FETCH_INC_DEC_OP(inc,)
+ATOMIC_LONG_FETCH_INC_DEC_OP(inc, _relaxed)
+ATOMIC_LONG_FETCH_INC_DEC_OP(inc, _acquire)
+ATOMIC_LONG_FETCH_INC_DEC_OP(inc, _release)
+ATOMIC_LONG_FETCH_INC_DEC_OP(dec,)
+ATOMIC_LONG_FETCH_INC_DEC_OP(dec, _relaxed)
+ATOMIC_LONG_FETCH_INC_DEC_OP(dec, _acquire)
+ATOMIC_LONG_FETCH_INC_DEC_OP(dec, _release)
+
+#undef ATOMIC_LONG_FETCH_INC_DEC_OP
+
 #define ATOMIC_LONG_OP(op)						\
 static __always_inline void						\
 atomic_long_##op(long i, atomic_long_t *l)				\
@@ -124,9 +180,9 @@ atomic_long_##op(long i, atomic_long_t *l)				\
 ATOMIC_LONG_OP(add)
 ATOMIC_LONG_OP(sub)
 ATOMIC_LONG_OP(and)
+ATOMIC_LONG_OP(andnot)
 ATOMIC_LONG_OP(or)
 ATOMIC_LONG_OP(xor)
-ATOMIC_LONG_OP(andnot)
 
 #undef ATOMIC_LONG_OP
 
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 74f1a3704d7a..9ed8b987185b 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -61,6 +61,18 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	return c c_op i;						\
 }
 
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int c, old;							\
+									\
+	c = v->counter;							\
+	while ((old = cmpxchg(&v->counter, c, c c_op i)) != c)		\
+		c = old;						\
+									\
+	return c;							\
+}
+
 #else
 
 #include <linux/irqflags.h>
@@ -88,6 +100,20 @@ 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)			\
+{									\
+	unsigned long flags;						\
+	int ret;							\
+									\
+	raw_local_irq_save(flags);					\
+	ret = v->counter;						\
+	v->counter = v->counter c_op i;					\
+	raw_local_irq_restore(flags);					\
+									\
+	return ret;							\
+}
+
 #endif /* CONFIG_SMP */
 
 #ifndef atomic_add_return
@@ -98,6 +124,26 @@ ATOMIC_OP_RETURN(add, +)
 ATOMIC_OP_RETURN(sub, -)
 #endif
 
+#ifndef atomic_fetch_add
+ATOMIC_FETCH_OP(add, +)
+#endif
+
+#ifndef atomic_fetch_sub
+ATOMIC_FETCH_OP(sub, -)
+#endif
+
+#ifndef atomic_fetch_and
+ATOMIC_FETCH_OP(and, &)
+#endif
+
+#ifndef atomic_fetch_or
+ATOMIC_FETCH_OP(or, |)
+#endif
+
+#ifndef atomic_fetch_xor
+ATOMIC_FETCH_OP(xor, ^)
+#endif
+
 #ifndef atomic_and
 ATOMIC_OP(and, &)
 #endif
@@ -110,6 +156,7 @@ ATOMIC_OP(or, |)
 ATOMIC_OP(xor, ^)
 #endif
 
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index d48e78ccad3d..dad68bf46c77 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -27,16 +27,23 @@ extern void	 atomic64_##op(long long a, atomic64_t *v);
 #define ATOMIC64_OP_RETURN(op)						\
 extern long long atomic64_##op##_return(long long a, atomic64_t *v);
 
-#define ATOMIC64_OPS(op)	ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op)
+#define ATOMIC64_FETCH_OP(op)						\
+extern long long atomic64_fetch_##op(long long a, atomic64_t *v);
+
+#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/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 1cceca146905..fe297b599b0a 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -194,7 +194,7 @@ do {									\
 })
 #endif
 
-#endif
+#endif	/* CONFIG_SMP */
 
 /* Barriers for virtual machine guests when talking to an SMP host */
 #define virt_mb() __smp_mb()
@@ -207,5 +207,44 @@ do {									\
 #define virt_store_release(p, v) __smp_store_release(p, v)
 #define virt_load_acquire(p) __smp_load_acquire(p)
 
+/**
+ * smp_acquire__after_ctrl_dep() - Provide ACQUIRE ordering after a control dependency
+ *
+ * A control dependency provides a LOAD->STORE order, the additional RMB
+ * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order,
+ * aka. (load)-ACQUIRE.
+ *
+ * Architectures that do not do load speculation can have this be barrier().
+ */
+#ifndef smp_acquire__after_ctrl_dep
+#define smp_acquire__after_ctrl_dep()		smp_rmb()
+#endif
+
+/**
+ * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering
+ * @ptr: pointer to the variable to wait on
+ * @cond: boolean expression to wait for
+ *
+ * Equivalent to using smp_load_acquire() on the condition variable but employs
+ * the control dependency of the wait to reduce the barrier on many platforms.
+ *
+ * Due to C lacking lambda expressions we load the value of *ptr into a
+ * pre-named variable @VAL to be used in @cond.
+ */
+#ifndef smp_cond_load_acquire
+#define smp_cond_load_acquire(ptr, cond_expr) ({		\
+	typeof(ptr) __PTR = (ptr);				\
+	typeof(*ptr) VAL;					\
+	for (;;) {						\
+		VAL = READ_ONCE(*__PTR);			\
+		if (cond_expr)					\
+			break;					\
+		cpu_relax();					\
+	}							\
+	smp_acquire__after_ctrl_dep();				\
+	VAL;							\
+})
+#endif
+
 #endif /* !__ASSEMBLY__ */
 #endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/asm-generic/mutex-dec.h b/include/asm-generic/mutex-dec.h
index fd694cfd678a..c54829d3de37 100644
--- a/include/asm-generic/mutex-dec.h
+++ b/include/asm-generic/mutex-dec.h
@@ -80,7 +80,7 @@ __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(atomic_cmpxchg_acquire(count, 1, 0) == 1))
+	if (likely(atomic_read(count) == 1 && atomic_cmpxchg_acquire(count, 1, 0) == 1))
 		return 1;
 	return 0;
 }
diff --git a/include/asm-generic/mutex-xchg.h b/include/asm-generic/mutex-xchg.h
index a6b4a7bd6ac9..3269ec4e195f 100644
--- a/include/asm-generic/mutex-xchg.h
+++ b/include/asm-generic/mutex-xchg.h
@@ -91,8 +91,12 @@ __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 *))
 {
-	int prev = atomic_xchg_acquire(count, 0);
+	int prev;
 
+	if (atomic_read(count) != 1)
+		return 0;
+
+	prev = atomic_xchg_acquire(count, 0);
 	if (unlikely(prev < 0)) {
 		/*
 		 * The lock was marked contended so we must restore that
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 05f05f17a7c2..9f0681bf1e87 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -111,10 +111,9 @@ static __always_inline void queued_spin_lock(struct qspinlock *lock)
 static __always_inline void queued_spin_unlock(struct qspinlock *lock)
 {
 	/*
-	 * smp_mb__before_atomic() in order to guarantee release semantics
+	 * unlock() needs release semantics:
 	 */
-	smp_mb__before_atomic();
-	atomic_sub(_Q_LOCKED_VAL, &lock->val);
+	(void)atomic_sub_return_release(_Q_LOCKED_VAL, &lock->val);
 }
 #endif
 
diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h
index 3fc94a046bf5..5be122e3d326 100644
--- a/include/asm-generic/rwsem.h
+++ b/include/asm-generic/rwsem.h
@@ -41,8 +41,8 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
 	long tmp;
 
-	while ((tmp = sem->count) >= 0) {
-		if (tmp == cmpxchg_acquire(&sem->count, tmp,
+	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
+		if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp,
 				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
 			return 1;
 		}
@@ -79,7 +79,7 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
 	long tmp;
 
-	tmp = cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
+	tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
 		      RWSEM_ACTIVE_WRITE_BIAS);
 	return tmp == RWSEM_UNLOCKED_VALUE;
 }
@@ -107,14 +107,6 @@ static inline void __up_write(struct rw_semaphore *sem)
 }
 
 /*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
-{
-	atomic_long_add(delta, (atomic_long_t *)&sem->count);
-}
-
-/*
  * downgrade write lock to read lock
  */
 static inline void __downgrade_write(struct rw_semaphore *sem)
@@ -134,13 +126,5 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 		rwsem_downgrade_wake(sem);
 }
 
-/*
- * implement exchange and add functionality
- */
-static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
-{
-	return atomic_long_add_return(delta, (atomic_long_t *)&sem->count);
-}
-
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_GENERIC_RWSEM_H */
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index e451534fe54d..e71835bf60a9 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -163,206 +163,265 @@
 #endif
 #endif /* atomic_dec_return_relaxed */
 
-/* atomic_xchg_relaxed */
-#ifndef atomic_xchg_relaxed
-#define  atomic_xchg_relaxed		atomic_xchg
-#define  atomic_xchg_acquire		atomic_xchg
-#define  atomic_xchg_release		atomic_xchg
 
-#else /* atomic_xchg_relaxed */
+/* atomic_fetch_add_relaxed */
+#ifndef atomic_fetch_add_relaxed
+#define atomic_fetch_add_relaxed	atomic_fetch_add
+#define atomic_fetch_add_acquire	atomic_fetch_add
+#define atomic_fetch_add_release	atomic_fetch_add
 
-#ifndef atomic_xchg_acquire
-#define  atomic_xchg_acquire(...)					\
-	__atomic_op_acquire(atomic_xchg, __VA_ARGS__)
+#else /* atomic_fetch_add_relaxed */
+
+#ifndef atomic_fetch_add_acquire
+#define atomic_fetch_add_acquire(...)					\
+	__atomic_op_acquire(atomic_fetch_add, __VA_ARGS__)
 #endif
 
-#ifndef atomic_xchg_release
-#define  atomic_xchg_release(...)					\
-	__atomic_op_release(atomic_xchg, __VA_ARGS__)
+#ifndef atomic_fetch_add_release
+#define atomic_fetch_add_release(...)					\
+	__atomic_op_release(atomic_fetch_add, __VA_ARGS__)
 #endif
 
-#ifndef atomic_xchg
-#define  atomic_xchg(...)						\
-	__atomic_op_fence(atomic_xchg, __VA_ARGS__)
+#ifndef atomic_fetch_add
+#define atomic_fetch_add(...)						\
+	__atomic_op_fence(atomic_fetch_add, __VA_ARGS__)
+#endif
+#endif /* atomic_fetch_add_relaxed */
+
+/* atomic_fetch_inc_relaxed */
+#ifndef atomic_fetch_inc_relaxed
+
+#ifndef atomic_fetch_inc
+#define atomic_fetch_inc(v)	        atomic_fetch_add(1, (v))
+#define atomic_fetch_inc_relaxed(v)	atomic_fetch_add_relaxed(1, (v))
+#define atomic_fetch_inc_acquire(v)	atomic_fetch_add_acquire(1, (v))
+#define atomic_fetch_inc_release(v)	atomic_fetch_add_release(1, (v))
+#else /* atomic_fetch_inc */
+#define atomic_fetch_inc_relaxed	atomic_fetch_inc
+#define atomic_fetch_inc_acquire	atomic_fetch_inc
+#define atomic_fetch_inc_release	atomic_fetch_inc
+#endif /* atomic_fetch_inc */
+
+#else /* atomic_fetch_inc_relaxed */
+
+#ifndef atomic_fetch_inc_acquire
+#define atomic_fetch_inc_acquire(...)					\
+	__atomic_op_acquire(atomic_fetch_inc, __VA_ARGS__)
 #endif
-#endif /* atomic_xchg_relaxed */
 
-/* atomic_cmpxchg_relaxed */
-#ifndef atomic_cmpxchg_relaxed
-#define  atomic_cmpxchg_relaxed		atomic_cmpxchg
-#define  atomic_cmpxchg_acquire		atomic_cmpxchg
-#define  atomic_cmpxchg_release		atomic_cmpxchg
+#ifndef atomic_fetch_inc_release
+#define atomic_fetch_inc_release(...)					\
+	__atomic_op_release(atomic_fetch_inc, __VA_ARGS__)
+#endif
 
-#else /* atomic_cmpxchg_relaxed */
+#ifndef atomic_fetch_inc
+#define atomic_fetch_inc(...)						\
+	__atomic_op_fence(atomic_fetch_inc, __VA_ARGS__)
+#endif
+#endif /* atomic_fetch_inc_relaxed */
 
-#ifndef atomic_cmpxchg_acquire
-#define  atomic_cmpxchg_acquire(...)					\
-	__atomic_op_acquire(atomic_cmpxchg, __VA_ARGS__)
+/* atomic_fetch_sub_relaxed */
+#ifndef atomic_fetch_sub_relaxed
+#define atomic_fetch_sub_relaxed	atomic_fetch_sub
+#define atomic_fetch_sub_acquire	atomic_fetch_sub
+#define atomic_fetch_sub_release	atomic_fetch_sub
+
+#else /* atomic_fetch_sub_relaxed */
+
+#ifndef atomic_fetch_sub_acquire
+#define atomic_fetch_sub_acquire(...)					\
+	__atomic_op_acquire(atomic_fetch_sub, __VA_ARGS__)
 #endif
 
-#ifndef atomic_cmpxchg_release
-#define  atomic_cmpxchg_release(...)					\
-	__atomic_op_release(atomic_cmpxchg, __VA_ARGS__)
+#ifndef atomic_fetch_sub_release
+#define atomic_fetch_sub_release(...)					\
+	__atomic_op_release(atomic_fetch_sub, __VA_ARGS__)
 #endif
 
-#ifndef atomic_cmpxchg
-#define  atomic_cmpxchg(...)						\
-	__atomic_op_fence(atomic_cmpxchg, __VA_ARGS__)
+#ifndef atomic_fetch_sub
+#define atomic_fetch_sub(...)						\
+	__atomic_op_fence(atomic_fetch_sub, __VA_ARGS__)
+#endif
+#endif /* atomic_fetch_sub_relaxed */
+
+/* atomic_fetch_dec_relaxed */
+#ifndef atomic_fetch_dec_relaxed
+
+#ifndef atomic_fetch_dec
+#define atomic_fetch_dec(v)	        atomic_fetch_sub(1, (v))
+#define atomic_fetch_dec_relaxed(v)	atomic_fetch_sub_relaxed(1, (v))
+#define atomic_fetch_dec_acquire(v)	atomic_fetch_sub_acquire(1, (v))
+#define atomic_fetch_dec_release(v)	atomic_fetch_sub_release(1, (v))
+#else /* atomic_fetch_dec */
+#define atomic_fetch_dec_relaxed	atomic_fetch_dec
+#define atomic_fetch_dec_acquire	atomic_fetch_dec
+#define atomic_fetch_dec_release	atomic_fetch_dec
+#endif /* atomic_fetch_dec */
+
+#else /* atomic_fetch_dec_relaxed */
+
+#ifndef atomic_fetch_dec_acquire
+#define atomic_fetch_dec_acquire(...)					\
+	__atomic_op_acquire(atomic_fetch_dec, __VA_ARGS__)
 #endif
-#endif /* atomic_cmpxchg_relaxed */
 
-#ifndef atomic64_read_acquire
-#define  atomic64_read_acquire(v)	smp_load_acquire(&(v)->counter)
+#ifndef atomic_fetch_dec_release
+#define atomic_fetch_dec_release(...)					\
+	__atomic_op_release(atomic_fetch_dec, __VA_ARGS__)
 #endif
 
-#ifndef atomic64_set_release
-#define  atomic64_set_release(v, i)	smp_store_release(&(v)->counter, (i))
+#ifndef atomic_fetch_dec
+#define atomic_fetch_dec(...)						\
+	__atomic_op_fence(atomic_fetch_dec, __VA_ARGS__)
 #endif
+#endif /* atomic_fetch_dec_relaxed */
 
-/* atomic64_add_return_relaxed */
-#ifndef atomic64_add_return_relaxed
-#define  atomic64_add_return_relaxed	atomic64_add_return
-#define  atomic64_add_return_acquire	atomic64_add_return
-#define  atomic64_add_return_release	atomic64_add_return
+/* atomic_fetch_or_relaxed */
+#ifndef atomic_fetch_or_relaxed
+#define atomic_fetch_or_relaxed	atomic_fetch_or
+#define atomic_fetch_or_acquire	atomic_fetch_or
+#define atomic_fetch_or_release	atomic_fetch_or
 
-#else /* atomic64_add_return_relaxed */
+#else /* atomic_fetch_or_relaxed */
 
-#ifndef atomic64_add_return_acquire
-#define  atomic64_add_return_acquire(...)				\
-	__atomic_op_acquire(atomic64_add_return, __VA_ARGS__)
+#ifndef atomic_fetch_or_acquire
+#define atomic_fetch_or_acquire(...)					\
+	__atomic_op_acquire(atomic_fetch_or, __VA_ARGS__)
 #endif
 
-#ifndef atomic64_add_return_release
-#define  atomic64_add_return_release(...)				\
-	__atomic_op_release(atomic64_add_return, __VA_ARGS__)
+#ifndef atomic_fetch_or_release
+#define atomic_fetch_or_release(...)					\
+	__atomic_op_release(atomic_fetch_or, __VA_ARGS__)
 #endif
 
-#ifndef atomic64_add_return
-#define  atomic64_add_return(...)					\
-	__atomic_op_fence(atomic64_add_return, __VA_ARGS__)
+#ifndef atomic_fetch_or
+#define atomic_fetch_or(...)						\
+	__atomic_op_fence(atomic_fetch_or, __VA_ARGS__)
 #endif
-#endif /* atomic64_add_return_relaxed */
+#endif /* atomic_fetch_or_relaxed */
 
-/* atomic64_inc_return_relaxed */
-#ifndef atomic64_inc_return_relaxed
-#define  atomic64_inc_return_relaxed	atomic64_inc_return
-#define  atomic64_inc_return_acquire	atomic64_inc_return
-#define  atomic64_inc_return_release	atomic64_inc_return
+/* atomic_fetch_and_relaxed */
+#ifndef atomic_fetch_and_relaxed
+#define atomic_fetch_and_relaxed	atomic_fetch_and
+#define atomic_fetch_and_acquire	atomic_fetch_and
+#define atomic_fetch_and_release	atomic_fetch_and
 
-#else /* atomic64_inc_return_relaxed */
+#else /* atomic_fetch_and_relaxed */
 
-#ifndef atomic64_inc_return_acquire
-#define  atomic64_inc_return_acquire(...)				\
-	__atomic_op_acquire(atomic64_inc_return, __VA_ARGS__)
+#ifndef atomic_fetch_and_acquire
+#define atomic_fetch_and_acquire(...)					\
+	__atomic_op_acquire(atomic_fetch_and, __VA_ARGS__)
 #endif
 
-#ifndef atomic64_inc_return_release
-#define  atomic64_inc_return_release(...)				\
-	__atomic_op_release(atomic64_inc_return, __VA_ARGS__)
+#ifndef atomic_fetch_and_release
+#define atomic_fetch_and_release(...)					\
+	__atomic_op_release(atomic_fetch_and, __VA_ARGS__)
 #endif
 
-#ifndef atomic64_inc_return
-#define  atomic64_inc_return(...)					\
-	__atomic_op_fence(atomic64_inc_return, __VA_ARGS__)
+#ifndef atomic_fetch_and
+#define atomic_fetch_and(...)						\
+	__atomic_op_fence(atomic_fetch_and, __VA_ARGS__)
 #endif
-#endif /* atomic64_inc_return_relaxed */
-
+#endif /* atomic_fetch_and_relaxed */
 
-/* atomic64_sub_return_relaxed */
-#ifndef atomic64_sub_return_relaxed
-#define  atomic64_sub_return_relaxed	atomic64_sub_return
-#define  atomic64_sub_return_acquire	atomic64_sub_return
-#define  atomic64_sub_return_release	atomic64_sub_return
+#ifdef atomic_andnot
+/* atomic_fetch_andnot_relaxed */
+#ifndef atomic_fetch_andnot_relaxed
+#define atomic_fetch_andnot_relaxed	atomic_fetch_andnot
+#define atomic_fetch_andnot_acquire	atomic_fetch_andnot
+#define atomic_fetch_andnot_release	atomic_fetch_andnot
 
-#else /* atomic64_sub_return_relaxed */
+#else /* atomic_fetch_andnot_relaxed */
 
-#ifndef atomic64_sub_return_acquire
-#define  atomic64_sub_return_acquire(...)				\
-	__atomic_op_acquire(atomic64_sub_return, __VA_ARGS__)
+#ifndef atomic_fetch_andnot_acquire
+#define atomic_fetch_andnot_acquire(...)					\
+	__atomic_op_acquire(atomic_fetch_andnot, __VA_ARGS__)
 #endif
 
-#ifndef atomic64_sub_return_release
-#define  atomic64_sub_return_release(...)				\
-	__atomic_op_release(atomic64_sub_return, __VA_ARGS__)
+#ifndef atomic_fetch_andnot_release
+#define atomic_fetch_andnot_release(...)					\
+	__atomic_op_release(atomic_fetch_andnot, __VA_ARGS__)
 #endif
 
-#ifndef atomic64_sub_return
-#define  atomic64_sub_return(...)					\
-	__atomic_op_fence(atomic64_sub_return, __VA_ARGS__)
+#ifndef atomic_fetch_andnot
+#define atomic_fetch_andnot(...)						\
+	__atomic_op_fence(atomic_fetch_andnot, __VA_ARGS__)
 #endif
-#endif /* atomic64_sub_return_relaxed */
+#endif /* atomic_fetch_andnot_relaxed */
+#endif /* atomic_andnot */
 
-/* atomic64_dec_return_relaxed */
-#ifndef atomic64_dec_return_relaxed
-#define  atomic64_dec_return_relaxed	atomic64_dec_return
-#define  atomic64_dec_return_acquire	atomic64_dec_return
-#define  atomic64_dec_return_release	atomic64_dec_return
+/* atomic_fetch_xor_relaxed */
+#ifndef atomic_fetch_xor_relaxed
+#define atomic_fetch_xor_relaxed	atomic_fetch_xor
+#define atomic_fetch_xor_acquire	atomic_fetch_xor
+#define atomic_fetch_xor_release	atomic_fetch_xor
 
-#else /* atomic64_dec_return_relaxed */
+#else /* atomic_fetch_xor_relaxed */
 
-#ifndef atomic64_dec_return_acquire
-#define  atomic64_dec_return_acquire(...)				\
-	__atomic_op_acquire(atomic64_dec_return, __VA_ARGS__)
+#ifndef atomic_fetch_xor_acquire
+#define atomic_fetch_xor_acquire(...)					\
+	__atomic_op_acquire(atomic_fetch_xor, __VA_ARGS__)
 #endif
 
-#ifndef atomic64_dec_return_release
-#define  atomic64_dec_return_release(...)				\
-	__atomic_op_release(atomic64_dec_return, __VA_ARGS__)
+#ifndef atomic_fetch_xor_release
+#define atomic_fetch_xor_release(...)					\
+	__atomic_op_release(atomic_fetch_xor, __VA_ARGS__)
 #endif
 
-#ifndef atomic64_dec_return
-#define  atomic64_dec_return(...)					\
-	__atomic_op_fence(atomic64_dec_return, __VA_ARGS__)
+#ifndef atomic_fetch_xor
+#define atomic_fetch_xor(...)						\
+	__atomic_op_fence(atomic_fetch_xor, __VA_ARGS__)
 #endif
-#endif /* atomic64_dec_return_relaxed */
+#endif /* atomic_fetch_xor_relaxed */
 
-/* atomic64_xchg_relaxed */
-#ifndef atomic64_xchg_relaxed
-#define  atomic64_xchg_relaxed		atomic64_xchg
-#define  atomic64_xchg_acquire		atomic64_xchg
-#define  atomic64_xchg_release		atomic64_xchg
 
-#else /* atomic64_xchg_relaxed */
+/* atomic_xchg_relaxed */
+#ifndef atomic_xchg_relaxed
+#define  atomic_xchg_relaxed		atomic_xchg
+#define  atomic_xchg_acquire		atomic_xchg
+#define  atomic_xchg_release		atomic_xchg
 
-#ifndef atomic64_xchg_acquire
-#define  atomic64_xchg_acquire(...)					\
-	__atomic_op_acquire(atomic64_xchg, __VA_ARGS__)
+#else /* atomic_xchg_relaxed */
+
+#ifndef atomic_xchg_acquire
+#define  atomic_xchg_acquire(...)					\
+	__atomic_op_acquire(atomic_xchg, __VA_ARGS__)
 #endif
 
-#ifndef atomic64_xchg_release
-#define  atomic64_xchg_release(...)					\
-	__atomic_op_release(atomic64_xchg, __VA_ARGS__)
+#ifndef atomic_xchg_release
+#define  atomic_xchg_release(...)					\
+	__atomic_op_release(atomic_xchg, __VA_ARGS__)
 #endif
 
-#ifndef atomic64_xchg
-#define  atomic64_xchg(...)						\
-	__atomic_op_fence(atomic64_xchg, __VA_ARGS__)
+#ifndef atomic_xchg
+#define  atomic_xchg(...)						\
+	__atomic_op_fence(atomic_xchg, __VA_ARGS__)
 #endif
-#endif /* atomic64_xchg_relaxed */
+#endif /* atomic_xchg_relaxed */
 
-/* atomic64_cmpxchg_relaxed */
-#ifndef atomic64_cmpxchg_relaxed
-#define  atomic64_cmpxchg_relaxed	atomic64_cmpxchg
-#define  atomic64_cmpxchg_acquire	atomic64_cmpxchg
-#define  atomic64_cmpxchg_release	atomic64_cmpxchg
+/* atomic_cmpxchg_relaxed */
+#ifndef atomic_cmpxchg_relaxed
+#define  atomic_cmpxchg_relaxed		atomic_cmpxchg
+#define  atomic_cmpxchg_acquire		atomic_cmpxchg
+#define  atomic_cmpxchg_release		atomic_cmpxchg
 
-#else /* atomic64_cmpxchg_relaxed */
+#else /* atomic_cmpxchg_relaxed */
 
-#ifndef atomic64_cmpxchg_acquire
-#define  atomic64_cmpxchg_acquire(...)					\
-	__atomic_op_acquire(atomic64_cmpxchg, __VA_ARGS__)
+#ifndef atomic_cmpxchg_acquire
+#define  atomic_cmpxchg_acquire(...)					\
+	__atomic_op_acquire(atomic_cmpxchg, __VA_ARGS__)
 #endif
 
-#ifndef atomic64_cmpxchg_release
-#define  atomic64_cmpxchg_release(...)					\
-	__atomic_op_release(atomic64_cmpxchg, __VA_ARGS__)
+#ifndef atomic_cmpxchg_release
+#define  atomic_cmpxchg_release(...)					\
+	__atomic_op_release(atomic_cmpxchg, __VA_ARGS__)
 #endif
 
-#ifndef atomic64_cmpxchg
-#define  atomic64_cmpxchg(...)						\
-	__atomic_op_fence(atomic64_cmpxchg, __VA_ARGS__)
+#ifndef atomic_cmpxchg
+#define  atomic_cmpxchg(...)						\
+	__atomic_op_fence(atomic_cmpxchg, __VA_ARGS__)
 #endif
-#endif /* atomic64_cmpxchg_relaxed */
+#endif /* atomic_cmpxchg_relaxed */
 
 /* cmpxchg_relaxed */
 #ifndef cmpxchg_relaxed
@@ -463,18 +522,28 @@ static inline void atomic_andnot(int i, atomic_t *v)
 {
 	atomic_and(~i, v);
 }
-#endif
 
-static inline __deprecated void atomic_clear_mask(unsigned int mask, atomic_t *v)
+static inline int atomic_fetch_andnot(int i, atomic_t *v)
 {
-	atomic_andnot(mask, v);
+	return atomic_fetch_and(~i, v);
 }
 
-static inline __deprecated void atomic_set_mask(unsigned int mask, atomic_t *v)
+static inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v)
 {
-	atomic_or(mask, v);
+	return atomic_fetch_and_relaxed(~i, v);
 }
 
+static inline int atomic_fetch_andnot_acquire(int i, atomic_t *v)
+{
+	return atomic_fetch_and_acquire(~i, v);
+}
+
+static inline int atomic_fetch_andnot_release(int i, atomic_t *v)
+{
+	return atomic_fetch_and_release(~i, v);
+}
+#endif
+
 /**
  * atomic_inc_not_zero_hint - increment if not null
  * @v: pointer of type atomic_t
@@ -558,36 +627,400 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 }
 #endif
 
-/**
- * atomic_fetch_or - perform *p |= mask and return old value of *p
- * @mask: mask to OR on the atomic_t
- * @p: pointer to atomic_t
- */
-#ifndef atomic_fetch_or
-static inline int atomic_fetch_or(int mask, atomic_t *p)
-{
-	int old, val = atomic_read(p);
+#ifdef CONFIG_GENERIC_ATOMIC64
+#include <asm-generic/atomic64.h>
+#endif
 
-	for (;;) {
-		old = atomic_cmpxchg(p, val, val | mask);
-		if (old == val)
-			break;
-		val = old;
-	}
+#ifndef atomic64_read_acquire
+#define  atomic64_read_acquire(v)	smp_load_acquire(&(v)->counter)
+#endif
 
-	return old;
-}
+#ifndef atomic64_set_release
+#define  atomic64_set_release(v, i)	smp_store_release(&(v)->counter, (i))
 #endif
 
-#ifdef CONFIG_GENERIC_ATOMIC64
-#include <asm-generic/atomic64.h>
+/* atomic64_add_return_relaxed */
+#ifndef atomic64_add_return_relaxed
+#define  atomic64_add_return_relaxed	atomic64_add_return
+#define  atomic64_add_return_acquire	atomic64_add_return
+#define  atomic64_add_return_release	atomic64_add_return
+
+#else /* atomic64_add_return_relaxed */
+
+#ifndef atomic64_add_return_acquire
+#define  atomic64_add_return_acquire(...)				\
+	__atomic_op_acquire(atomic64_add_return, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_add_return_release
+#define  atomic64_add_return_release(...)				\
+	__atomic_op_release(atomic64_add_return, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_add_return
+#define  atomic64_add_return(...)					\
+	__atomic_op_fence(atomic64_add_return, __VA_ARGS__)
+#endif
+#endif /* atomic64_add_return_relaxed */
+
+/* atomic64_inc_return_relaxed */
+#ifndef atomic64_inc_return_relaxed
+#define  atomic64_inc_return_relaxed	atomic64_inc_return
+#define  atomic64_inc_return_acquire	atomic64_inc_return
+#define  atomic64_inc_return_release	atomic64_inc_return
+
+#else /* atomic64_inc_return_relaxed */
+
+#ifndef atomic64_inc_return_acquire
+#define  atomic64_inc_return_acquire(...)				\
+	__atomic_op_acquire(atomic64_inc_return, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_inc_return_release
+#define  atomic64_inc_return_release(...)				\
+	__atomic_op_release(atomic64_inc_return, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_inc_return
+#define  atomic64_inc_return(...)					\
+	__atomic_op_fence(atomic64_inc_return, __VA_ARGS__)
+#endif
+#endif /* atomic64_inc_return_relaxed */
+
+
+/* atomic64_sub_return_relaxed */
+#ifndef atomic64_sub_return_relaxed
+#define  atomic64_sub_return_relaxed	atomic64_sub_return
+#define  atomic64_sub_return_acquire	atomic64_sub_return
+#define  atomic64_sub_return_release	atomic64_sub_return
+
+#else /* atomic64_sub_return_relaxed */
+
+#ifndef atomic64_sub_return_acquire
+#define  atomic64_sub_return_acquire(...)				\
+	__atomic_op_acquire(atomic64_sub_return, __VA_ARGS__)
 #endif
 
+#ifndef atomic64_sub_return_release
+#define  atomic64_sub_return_release(...)				\
+	__atomic_op_release(atomic64_sub_return, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_sub_return
+#define  atomic64_sub_return(...)					\
+	__atomic_op_fence(atomic64_sub_return, __VA_ARGS__)
+#endif
+#endif /* atomic64_sub_return_relaxed */
+
+/* atomic64_dec_return_relaxed */
+#ifndef atomic64_dec_return_relaxed
+#define  atomic64_dec_return_relaxed	atomic64_dec_return
+#define  atomic64_dec_return_acquire	atomic64_dec_return
+#define  atomic64_dec_return_release	atomic64_dec_return
+
+#else /* atomic64_dec_return_relaxed */
+
+#ifndef atomic64_dec_return_acquire
+#define  atomic64_dec_return_acquire(...)				\
+	__atomic_op_acquire(atomic64_dec_return, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_dec_return_release
+#define  atomic64_dec_return_release(...)				\
+	__atomic_op_release(atomic64_dec_return, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_dec_return
+#define  atomic64_dec_return(...)					\
+	__atomic_op_fence(atomic64_dec_return, __VA_ARGS__)
+#endif
+#endif /* atomic64_dec_return_relaxed */
+
+
+/* atomic64_fetch_add_relaxed */
+#ifndef atomic64_fetch_add_relaxed
+#define atomic64_fetch_add_relaxed	atomic64_fetch_add
+#define atomic64_fetch_add_acquire	atomic64_fetch_add
+#define atomic64_fetch_add_release	atomic64_fetch_add
+
+#else /* atomic64_fetch_add_relaxed */
+
+#ifndef atomic64_fetch_add_acquire
+#define atomic64_fetch_add_acquire(...)					\
+	__atomic_op_acquire(atomic64_fetch_add, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_add_release
+#define atomic64_fetch_add_release(...)					\
+	__atomic_op_release(atomic64_fetch_add, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_add
+#define atomic64_fetch_add(...)						\
+	__atomic_op_fence(atomic64_fetch_add, __VA_ARGS__)
+#endif
+#endif /* atomic64_fetch_add_relaxed */
+
+/* atomic64_fetch_inc_relaxed */
+#ifndef atomic64_fetch_inc_relaxed
+
+#ifndef atomic64_fetch_inc
+#define atomic64_fetch_inc(v)		atomic64_fetch_add(1, (v))
+#define atomic64_fetch_inc_relaxed(v)	atomic64_fetch_add_relaxed(1, (v))
+#define atomic64_fetch_inc_acquire(v)	atomic64_fetch_add_acquire(1, (v))
+#define atomic64_fetch_inc_release(v)	atomic64_fetch_add_release(1, (v))
+#else /* atomic64_fetch_inc */
+#define atomic64_fetch_inc_relaxed	atomic64_fetch_inc
+#define atomic64_fetch_inc_acquire	atomic64_fetch_inc
+#define atomic64_fetch_inc_release	atomic64_fetch_inc
+#endif /* atomic64_fetch_inc */
+
+#else /* atomic64_fetch_inc_relaxed */
+
+#ifndef atomic64_fetch_inc_acquire
+#define atomic64_fetch_inc_acquire(...)					\
+	__atomic_op_acquire(atomic64_fetch_inc, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_inc_release
+#define atomic64_fetch_inc_release(...)					\
+	__atomic_op_release(atomic64_fetch_inc, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_inc
+#define atomic64_fetch_inc(...)						\
+	__atomic_op_fence(atomic64_fetch_inc, __VA_ARGS__)
+#endif
+#endif /* atomic64_fetch_inc_relaxed */
+
+/* atomic64_fetch_sub_relaxed */
+#ifndef atomic64_fetch_sub_relaxed
+#define atomic64_fetch_sub_relaxed	atomic64_fetch_sub
+#define atomic64_fetch_sub_acquire	atomic64_fetch_sub
+#define atomic64_fetch_sub_release	atomic64_fetch_sub
+
+#else /* atomic64_fetch_sub_relaxed */
+
+#ifndef atomic64_fetch_sub_acquire
+#define atomic64_fetch_sub_acquire(...)					\
+	__atomic_op_acquire(atomic64_fetch_sub, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_sub_release
+#define atomic64_fetch_sub_release(...)					\
+	__atomic_op_release(atomic64_fetch_sub, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_sub
+#define atomic64_fetch_sub(...)						\
+	__atomic_op_fence(atomic64_fetch_sub, __VA_ARGS__)
+#endif
+#endif /* atomic64_fetch_sub_relaxed */
+
+/* atomic64_fetch_dec_relaxed */
+#ifndef atomic64_fetch_dec_relaxed
+
+#ifndef atomic64_fetch_dec
+#define atomic64_fetch_dec(v)		atomic64_fetch_sub(1, (v))
+#define atomic64_fetch_dec_relaxed(v)	atomic64_fetch_sub_relaxed(1, (v))
+#define atomic64_fetch_dec_acquire(v)	atomic64_fetch_sub_acquire(1, (v))
+#define atomic64_fetch_dec_release(v)	atomic64_fetch_sub_release(1, (v))
+#else /* atomic64_fetch_dec */
+#define atomic64_fetch_dec_relaxed	atomic64_fetch_dec
+#define atomic64_fetch_dec_acquire	atomic64_fetch_dec
+#define atomic64_fetch_dec_release	atomic64_fetch_dec
+#endif /* atomic64_fetch_dec */
+
+#else /* atomic64_fetch_dec_relaxed */
+
+#ifndef atomic64_fetch_dec_acquire
+#define atomic64_fetch_dec_acquire(...)					\
+	__atomic_op_acquire(atomic64_fetch_dec, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_dec_release
+#define atomic64_fetch_dec_release(...)					\
+	__atomic_op_release(atomic64_fetch_dec, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_dec
+#define atomic64_fetch_dec(...)						\
+	__atomic_op_fence(atomic64_fetch_dec, __VA_ARGS__)
+#endif
+#endif /* atomic64_fetch_dec_relaxed */
+
+/* atomic64_fetch_or_relaxed */
+#ifndef atomic64_fetch_or_relaxed
+#define atomic64_fetch_or_relaxed	atomic64_fetch_or
+#define atomic64_fetch_or_acquire	atomic64_fetch_or
+#define atomic64_fetch_or_release	atomic64_fetch_or
+
+#else /* atomic64_fetch_or_relaxed */
+
+#ifndef atomic64_fetch_or_acquire
+#define atomic64_fetch_or_acquire(...)					\
+	__atomic_op_acquire(atomic64_fetch_or, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_or_release
+#define atomic64_fetch_or_release(...)					\
+	__atomic_op_release(atomic64_fetch_or, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_or
+#define atomic64_fetch_or(...)						\
+	__atomic_op_fence(atomic64_fetch_or, __VA_ARGS__)
+#endif
+#endif /* atomic64_fetch_or_relaxed */
+
+/* atomic64_fetch_and_relaxed */
+#ifndef atomic64_fetch_and_relaxed
+#define atomic64_fetch_and_relaxed	atomic64_fetch_and
+#define atomic64_fetch_and_acquire	atomic64_fetch_and
+#define atomic64_fetch_and_release	atomic64_fetch_and
+
+#else /* atomic64_fetch_and_relaxed */
+
+#ifndef atomic64_fetch_and_acquire
+#define atomic64_fetch_and_acquire(...)					\
+	__atomic_op_acquire(atomic64_fetch_and, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_and_release
+#define atomic64_fetch_and_release(...)					\
+	__atomic_op_release(atomic64_fetch_and, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_and
+#define atomic64_fetch_and(...)						\
+	__atomic_op_fence(atomic64_fetch_and, __VA_ARGS__)
+#endif
+#endif /* atomic64_fetch_and_relaxed */
+
+#ifdef atomic64_andnot
+/* atomic64_fetch_andnot_relaxed */
+#ifndef atomic64_fetch_andnot_relaxed
+#define atomic64_fetch_andnot_relaxed	atomic64_fetch_andnot
+#define atomic64_fetch_andnot_acquire	atomic64_fetch_andnot
+#define atomic64_fetch_andnot_release	atomic64_fetch_andnot
+
+#else /* atomic64_fetch_andnot_relaxed */
+
+#ifndef atomic64_fetch_andnot_acquire
+#define atomic64_fetch_andnot_acquire(...)					\
+	__atomic_op_acquire(atomic64_fetch_andnot, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_andnot_release
+#define atomic64_fetch_andnot_release(...)					\
+	__atomic_op_release(atomic64_fetch_andnot, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_andnot
+#define atomic64_fetch_andnot(...)						\
+	__atomic_op_fence(atomic64_fetch_andnot, __VA_ARGS__)
+#endif
+#endif /* atomic64_fetch_andnot_relaxed */
+#endif /* atomic64_andnot */
+
+/* atomic64_fetch_xor_relaxed */
+#ifndef atomic64_fetch_xor_relaxed
+#define atomic64_fetch_xor_relaxed	atomic64_fetch_xor
+#define atomic64_fetch_xor_acquire	atomic64_fetch_xor
+#define atomic64_fetch_xor_release	atomic64_fetch_xor
+
+#else /* atomic64_fetch_xor_relaxed */
+
+#ifndef atomic64_fetch_xor_acquire
+#define atomic64_fetch_xor_acquire(...)					\
+	__atomic_op_acquire(atomic64_fetch_xor, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_xor_release
+#define atomic64_fetch_xor_release(...)					\
+	__atomic_op_release(atomic64_fetch_xor, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_fetch_xor
+#define atomic64_fetch_xor(...)						\
+	__atomic_op_fence(atomic64_fetch_xor, __VA_ARGS__)
+#endif
+#endif /* atomic64_fetch_xor_relaxed */
+
+
+/* atomic64_xchg_relaxed */
+#ifndef atomic64_xchg_relaxed
+#define  atomic64_xchg_relaxed		atomic64_xchg
+#define  atomic64_xchg_acquire		atomic64_xchg
+#define  atomic64_xchg_release		atomic64_xchg
+
+#else /* atomic64_xchg_relaxed */
+
+#ifndef atomic64_xchg_acquire
+#define  atomic64_xchg_acquire(...)					\
+	__atomic_op_acquire(atomic64_xchg, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_xchg_release
+#define  atomic64_xchg_release(...)					\
+	__atomic_op_release(atomic64_xchg, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_xchg
+#define  atomic64_xchg(...)						\
+	__atomic_op_fence(atomic64_xchg, __VA_ARGS__)
+#endif
+#endif /* atomic64_xchg_relaxed */
+
+/* atomic64_cmpxchg_relaxed */
+#ifndef atomic64_cmpxchg_relaxed
+#define  atomic64_cmpxchg_relaxed	atomic64_cmpxchg
+#define  atomic64_cmpxchg_acquire	atomic64_cmpxchg
+#define  atomic64_cmpxchg_release	atomic64_cmpxchg
+
+#else /* atomic64_cmpxchg_relaxed */
+
+#ifndef atomic64_cmpxchg_acquire
+#define  atomic64_cmpxchg_acquire(...)					\
+	__atomic_op_acquire(atomic64_cmpxchg, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_cmpxchg_release
+#define  atomic64_cmpxchg_release(...)					\
+	__atomic_op_release(atomic64_cmpxchg, __VA_ARGS__)
+#endif
+
+#ifndef atomic64_cmpxchg
+#define  atomic64_cmpxchg(...)						\
+	__atomic_op_fence(atomic64_cmpxchg, __VA_ARGS__)
+#endif
+#endif /* atomic64_cmpxchg_relaxed */
+
 #ifndef atomic64_andnot
 static inline void atomic64_andnot(long long i, atomic64_t *v)
 {
 	atomic64_and(~i, v);
 }
+
+static inline long long atomic64_fetch_andnot(long long i, atomic64_t *v)
+{
+	return atomic64_fetch_and(~i, v);
+}
+
+static inline long long atomic64_fetch_andnot_relaxed(long long i, atomic64_t *v)
+{
+	return atomic64_fetch_and_relaxed(~i, v);
+}
+
+static inline long long atomic64_fetch_andnot_acquire(long long i, atomic64_t *v)
+{
+	return atomic64_fetch_and_acquire(~i, v);
+}
+
+static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v)
+{
+	return atomic64_fetch_and_release(~i, v);
+}
 #endif
 
 #include <asm-generic/atomic-long.h>
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 793c0829e3a3..2e853b679a5d 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -304,23 +304,6 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 	__u.__val;					\
 })
 
-/**
- * smp_cond_acquire() - Spin wait for cond with ACQUIRE ordering
- * @cond: boolean expression to wait for
- *
- * Equivalent to using smp_load_acquire() on the condition variable but employs
- * the control dependency of the wait to reduce the barrier on many platforms.
- *
- * The control dependency provides a LOAD->STORE order, the additional RMB
- * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order,
- * aka. ACQUIRE.
- */
-#define smp_cond_acquire(cond)	do {		\
-	while (!(cond))				\
-		cpu_relax();			\
-	smp_rmb(); /* ctrl + rmb := acquire */	\
-} while (0)
-
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
@@ -545,10 +528,14 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
  * Similar to rcu_dereference(), but for situations where the pointed-to
  * object's lifetime is managed by something other than RCU.  That
  * "something other" might be reference counting or simple immortality.
+ *
+ * The seemingly unused void * variable is to validate @p is indeed a pointer
+ * type. All pointer types silently cast to void *.
  */
 #define lockless_dereference(p) \
 ({ \
 	typeof(p) _________p1 = READ_ONCE(p); \
+	__maybe_unused const void * const _________p2 = _________p1; \
 	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
 	(_________p1); \
 })
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 84f542df7ff5..1c7eec09e5eb 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -136,14 +136,12 @@ static inline bool __ref_is_percpu(struct percpu_ref *ref,
 	 * used as a pointer.  If the compiler generates a separate fetch
 	 * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in
 	 * between contaminating the pointer value, meaning that
-	 * ACCESS_ONCE() is required when fetching it.
-	 *
-	 * Also, we need a data dependency barrier to be paired with
-	 * smp_store_release() in __percpu_ref_switch_to_percpu().
-	 *
-	 * Use lockless deref which contains both.
+	 * READ_ONCE() is required when fetching it.
 	 */
-	percpu_ptr = lockless_dereference(ref->percpu_count_ptr);
+	percpu_ptr = READ_ONCE(ref->percpu_count_ptr);
+
+	/* paired with smp_store_release() in __percpu_ref_switch_to_percpu() */
+	smp_read_barrier_depends();
 
 	/*
 	 * Theoretically, the following could test just ATOMIC; however,
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index d37fbb34d06f..dd1d14250340 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -23,10 +23,11 @@ struct rw_semaphore;
 
 #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
 #include <linux/rwsem-spinlock.h> /* use a generic implementation */
+#define __RWSEM_INIT_COUNT(name)	.count = RWSEM_UNLOCKED_VALUE
 #else
 /* All arch specific implementations share the same struct */
 struct rw_semaphore {
-	long count;
+	atomic_long_t count;
 	struct list_head wait_list;
 	raw_spinlock_t wait_lock;
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
@@ -54,9 +55,10 @@ extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
 /* In all implementations count != 0 means locked */
 static inline int rwsem_is_locked(struct rw_semaphore *sem)
 {
-	return sem->count != 0;
+	return atomic_long_read(&sem->count) != 0;
 }
 
+#define __RWSEM_INIT_COUNT(name)	.count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE)
 #endif
 
 /* Common initializer macros and functions */
@@ -74,7 +76,7 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 #endif
 
 #define __RWSEM_INITIALIZER(name)				\
-	{ .count = RWSEM_UNLOCKED_VALUE,			\
+	{ __RWSEM_INIT_COUNT(name),				\
 	  .wait_list = LIST_HEAD_INIT((name).wait_list),	\
 	  .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock)	\
 	  __RWSEM_OPT_INIT(name)				\
diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h
index 8b3ac0d718eb..0d9848de677d 100644
--- a/include/linux/spinlock_up.h
+++ b/include/linux/spinlock_up.h
@@ -6,6 +6,7 @@
 #endif
 
 #include <asm/processor.h>	/* for cpu_relax() */
+#include <asm/barrier.h>
 
 /*
  * include/linux/spinlock_up.h - UP-debug version of spinlocks.
@@ -25,6 +26,11 @@
 #ifdef CONFIG_DEBUG_SPINLOCK
 #define arch_spin_is_locked(x)		((x)->slock == 0)
 
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->slock, VAL);
+}
+
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	lock->slock = 0;
@@ -67,6 +73,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 #else /* DEBUG_SPINLOCK */
 #define arch_spin_is_locked(lock)	((void)(lock), 0)
+#define arch_spin_unlock_wait(lock)	do { barrier(); (void)(lock); } while (0)
 /* for sched/core.c and kernel_lock.c: */
 # define arch_spin_lock(lock)		do { barrier(); (void)(lock); } while (0)
 # define arch_spin_lock_flags(lock, flags)	do { barrier(); (void)(lock); } while (0)
@@ -79,7 +86,4 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 #define arch_read_can_lock(lock)	(((void)(lock), 1))
 #define arch_write_can_lock(lock)	(((void)(lock), 1))
 
-#define arch_spin_unlock_wait(lock) \
-		do { cpu_relax(); } while (arch_spin_is_locked(lock))
-
 #endif /* __LINUX_SPINLOCK_UP_H */
diff --git a/ipc/sem.c b/ipc/sem.c
index b3757ea0694b..ae72b3cddc8d 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -260,16 +260,6 @@ static void sem_rcu_free(struct rcu_head *head)
 }
 
 /*
- * spin_unlock_wait() and !spin_is_locked() are not memory barriers, they
- * are only control barriers.
- * The code must pair with spin_unlock(&sem->lock) or
- * spin_unlock(&sem_perm.lock), thus just the control barrier is insufficient.
- *
- * smp_rmb() is sufficient, as writes cannot pass the control barrier.
- */
-#define ipc_smp_acquire__after_spin_is_unlocked()	smp_rmb()
-
-/*
  * Wait until all currently ongoing simple ops have completed.
  * Caller must own sem_perm.lock.
  * New simple ops cannot start, because simple ops first check
@@ -292,7 +282,6 @@ static void sem_wait_array(struct sem_array *sma)
 		sem = sma->sem_base + i;
 		spin_unlock_wait(&sem->lock);
 	}
-	ipc_smp_acquire__after_spin_is_unlocked();
 }
 
 /*
@@ -350,7 +339,7 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 			 *	complex_count++;
 			 *	spin_unlock(sem_perm.lock);
 			 */
-			ipc_smp_acquire__after_spin_is_unlocked();
+			smp_acquire__after_ctrl_dep();
 
 			/*
 			 * Now repeat the test of complex_count:
diff --git a/kernel/exit.c b/kernel/exit.c
index 9e6e1356e6bb..0b40791b9e70 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -700,10 +700,14 @@ void do_exit(long code)
 
 	exit_signals(tsk);  /* sets PF_EXITING */
 	/*
-	 * tsk->flags are checked in the futex code to protect against
-	 * an exiting task cleaning up the robust pi futexes.
+	 * Ensure that all new tsk->pi_lock acquisitions must observe
+	 * PF_EXITING. Serializes against futex.c:attach_to_pi_owner().
 	 */
 	smp_mb();
+	/*
+	 * Ensure that we must observe the pi_state in exit_mm() ->
+	 * mm_release() -> exit_pi_state_list().
+	 */
 	raw_spin_unlock_wait(&tsk->pi_lock);
 
 	if (unlikely(in_atomic())) {
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 4b353e0be121..0dbea887d625 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -452,7 +452,7 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val,
 	return notifier_from_errno(ret);
 }
 
-struct notifier_block jump_label_module_nb = {
+static struct notifier_block jump_label_module_nb = {
 	.notifier_call = jump_label_module_notify,
 	.priority = 1, /* higher than tracepoints */
 };
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 81f1a7107c0e..589d763a49b3 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -46,6 +46,7 @@
 #include <linux/gfp.h>
 #include <linux/kmemcheck.h>
 #include <linux/random.h>
+#include <linux/jhash.h>
 
 #include <asm/sections.h>
 
@@ -309,10 +310,14 @@ static struct hlist_head chainhash_table[CHAINHASH_SIZE];
  * It's a 64-bit hash, because it's important for the keys to be
  * unique.
  */
-#define iterate_chain_key(key1, key2) \
-	(((key1) << MAX_LOCKDEP_KEYS_BITS) ^ \
-	((key1) >> (64-MAX_LOCKDEP_KEYS_BITS)) ^ \
-	(key2))
+static inline u64 iterate_chain_key(u64 key, u32 idx)
+{
+	u32 k0 = key, k1 = key >> 32;
+
+	__jhash_mix(idx, k0, k1); /* Macro that modifies arguments! */
+
+	return k0 | (u64)k1 << 32;
+}
 
 void lockdep_off(void)
 {
diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h
index d06ae3bb46c5..57a871ae3c81 100644
--- a/kernel/locking/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
@@ -29,12 +29,12 @@ extern void debug_mutex_init(struct mutex *lock, const char *name,
 
 static inline void mutex_set_owner(struct mutex *lock)
 {
-	lock->owner = current;
+	WRITE_ONCE(lock->owner, current);
 }
 
 static inline void mutex_clear_owner(struct mutex *lock)
 {
-	lock->owner = NULL;
+	WRITE_ONCE(lock->owner, NULL);
 }
 
 #define spin_lock_mutex(lock, flags)			\
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index a68bae5e852a..6cd6b8e9efd7 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -17,14 +17,20 @@
 		__list_del((waiter)->list.prev, (waiter)->list.next)
 
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+/*
+ * The mutex owner can get read and written to locklessly.
+ * We should use WRITE_ONCE when writing the owner value to
+ * avoid store tearing, otherwise, a thread could potentially
+ * read a partially written and incomplete owner value.
+ */
 static inline void mutex_set_owner(struct mutex *lock)
 {
-	lock->owner = current;
+	WRITE_ONCE(lock->owner, current);
 }
 
 static inline void mutex_clear_owner(struct mutex *lock)
 {
-	lock->owner = NULL;
+	WRITE_ONCE(lock->owner, NULL);
 }
 #else
 static inline void mutex_set_owner(struct mutex *lock)
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index fec082338668..19248ddf37ce 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -93,7 +93,7 @@ void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts)
 	 * that accesses can't leak upwards out of our subsequent critical
 	 * section in the case that the lock is currently held for write.
 	 */
-	cnts = atomic_add_return_acquire(_QR_BIAS, &lock->cnts) - _QR_BIAS;
+	cnts = atomic_fetch_add_acquire(_QR_BIAS, &lock->cnts);
 	rspin_until_writer_unlock(lock, cnts);
 
 	/*
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 5fc8c311b8fe..b2caec7315af 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -90,7 +90,7 @@ static DEFINE_PER_CPU_ALIGNED(struct mcs_spinlock, mcs_nodes[MAX_NODES]);
  * therefore increment the cpu number by one.
  */
 
-static inline u32 encode_tail(int cpu, int idx)
+static inline __pure u32 encode_tail(int cpu, int idx)
 {
 	u32 tail;
 
@@ -103,7 +103,7 @@ static inline u32 encode_tail(int cpu, int idx)
 	return tail;
 }
 
-static inline struct mcs_spinlock *decode_tail(u32 tail)
+static inline __pure struct mcs_spinlock *decode_tail(u32 tail)
 {
 	int cpu = (tail >> _Q_TAIL_CPU_OFFSET) - 1;
 	int idx = (tail &  _Q_TAIL_IDX_MASK) >> _Q_TAIL_IDX_OFFSET;
@@ -268,6 +268,63 @@ static __always_inline u32  __pv_wait_head_or_lock(struct qspinlock *lock,
 #endif
 
 /*
+ * Various notes on spin_is_locked() and spin_unlock_wait(), which are
+ * 'interesting' functions:
+ *
+ * PROBLEM: some architectures have an interesting issue with atomic ACQUIRE
+ * operations in that the ACQUIRE applies to the LOAD _not_ the STORE (ARM64,
+ * PPC). Also qspinlock has a similar issue per construction, the setting of
+ * the locked byte can be unordered acquiring the lock proper.
+ *
+ * This gets to be 'interesting' in the following cases, where the /should/s
+ * end up false because of this issue.
+ *
+ *
+ * CASE 1:
+ *
+ * So the spin_is_locked() correctness issue comes from something like:
+ *
+ *   CPU0				CPU1
+ *
+ *   global_lock();			local_lock(i)
+ *     spin_lock(&G)			  spin_lock(&L[i])
+ *     for (i)				  if (!spin_is_locked(&G)) {
+ *       spin_unlock_wait(&L[i]);	    smp_acquire__after_ctrl_dep();
+ *					    return;
+ *					  }
+ *					  // deal with fail
+ *
+ * Where it is important CPU1 sees G locked or CPU0 sees L[i] locked such
+ * that there is exclusion between the two critical sections.
+ *
+ * The load from spin_is_locked(&G) /should/ be constrained by the ACQUIRE from
+ * spin_lock(&L[i]), and similarly the load(s) from spin_unlock_wait(&L[i])
+ * /should/ be constrained by the ACQUIRE from spin_lock(&G).
+ *
+ * Similarly, later stuff is constrained by the ACQUIRE from CTRL+RMB.
+ *
+ *
+ * CASE 2:
+ *
+ * For spin_unlock_wait() there is a second correctness issue, namely:
+ *
+ *   CPU0				CPU1
+ *
+ *   flag = set;
+ *   smp_mb();				spin_lock(&l)
+ *   spin_unlock_wait(&l);		if (!flag)
+ *					  // add to lockless list
+ *					spin_unlock(&l);
+ *   // iterate lockless list
+ *
+ * Which wants to ensure that CPU1 will stop adding bits to the list and CPU0
+ * will observe the last entry on the list (if spin_unlock_wait() had ACQUIRE
+ * semantics etc..)
+ *
+ * Where flag /should/ be ordered against the locked store of l.
+ */
+
+/*
  * queued_spin_lock_slowpath() can (load-)ACQUIRE the lock before
  * issuing an _unordered_ store to set _Q_LOCKED_VAL.
  *
@@ -322,7 +379,7 @@ void queued_spin_unlock_wait(struct qspinlock *lock)
 		cpu_relax();
 
 done:
-	smp_rmb(); /* CTRL + RMB -> ACQUIRE */
+	smp_acquire__after_ctrl_dep();
 }
 EXPORT_SYMBOL(queued_spin_unlock_wait);
 #endif
@@ -418,7 +475,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 * sequentiality; this is because not all clear_pending_set_locked()
 	 * implementations imply full barriers.
 	 */
-	smp_cond_acquire(!(atomic_read(&lock->val) & _Q_LOCKED_MASK));
+	smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_MASK));
 
 	/*
 	 * take ownership and clear the pending bit.
@@ -455,6 +512,8 @@ queue:
 	 * pending stuff.
 	 *
 	 * p,*,* -> n,*,*
+	 *
+	 * RELEASE, such that the stores to @node must be complete.
 	 */
 	old = xchg_tail(lock, tail);
 	next = NULL;
@@ -465,6 +524,15 @@ queue:
 	 */
 	if (old & _Q_TAIL_MASK) {
 		prev = decode_tail(old);
+		/*
+		 * The above xchg_tail() is also a load of @lock which generates,
+		 * through decode_tail(), a pointer.
+		 *
+		 * The address dependency matches the RELEASE of xchg_tail()
+		 * such that the access to @prev must happen after.
+		 */
+		smp_read_barrier_depends();
+
 		WRITE_ONCE(prev->next, node);
 
 		pv_wait_node(node, prev);
@@ -494,7 +562,7 @@ queue:
 	 *
 	 * The PV pv_wait_head_or_lock function, if active, will acquire
 	 * the lock and return a non-zero value. So we have to skip the
-	 * smp_cond_acquire() call. As the next PV queue head hasn't been
+	 * smp_cond_load_acquire() call. As the next PV queue head hasn't been
 	 * designated yet, there is no way for the locked value to become
 	 * _Q_SLOW_VAL. So both the set_locked() and the
 	 * atomic_cmpxchg_relaxed() calls will be safe.
@@ -505,7 +573,7 @@ queue:
 	if ((val = pv_wait_head_or_lock(lock, node)))
 		goto locked;
 
-	smp_cond_acquire(!((val = atomic_read(&lock->val)) & _Q_LOCKED_PENDING_MASK));
+	val = smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_PENDING_MASK));
 
 locked:
 	/*
@@ -525,9 +593,9 @@ locked:
 			break;
 		}
 		/*
-		 * The smp_cond_acquire() call above has provided the necessary
-		 * acquire semantics required for locking. At most two
-		 * iterations of this loop may be ran.
+		 * The smp_cond_load_acquire() call above has provided the
+		 * necessary acquire semantics required for locking. At most
+		 * two iterations of this loop may be ran.
 		 */
 		old = atomic_cmpxchg_relaxed(&lock->val, val, _Q_LOCKED_VAL);
 		if (old == val)
@@ -551,7 +619,7 @@ release:
 	/*
 	 * release the node
 	 */
-	this_cpu_dec(mcs_nodes[0].count);
+	__this_cpu_dec(mcs_nodes[0].count);
 }
 EXPORT_SYMBOL(queued_spin_lock_slowpath);
 
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 21ede57f68b3..37649e69056c 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -112,12 +112,12 @@ static __always_inline int trylock_clear_pending(struct qspinlock *lock)
 #else /* _Q_PENDING_BITS == 8 */
 static __always_inline void set_pending(struct qspinlock *lock)
 {
-	atomic_set_mask(_Q_PENDING_VAL, &lock->val);
+	atomic_or(_Q_PENDING_VAL, &lock->val);
 }
 
 static __always_inline void clear_pending(struct qspinlock *lock)
 {
-	atomic_clear_mask(_Q_PENDING_VAL, &lock->val);
+	atomic_andnot(_Q_PENDING_VAL, &lock->val);
 }
 
 static __always_inline int trylock_clear_pending(struct qspinlock *lock)
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 3e746607abe5..1ec0f48962b3 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1478,7 +1478,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
  */
 int __sched rt_mutex_trylock(struct rt_mutex *lock)
 {
-	if (WARN_ON(in_irq() || in_nmi() || in_serving_softirq()))
+	if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq()))
 		return 0;
 
 	return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock);
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 09e30c6225e5..447e08de1fab 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -80,7 +80,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
 	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
 	lockdep_init_map(&sem->dep_map, name, key, 0);
 #endif
-	sem->count = RWSEM_UNLOCKED_VALUE;
+	atomic_long_set(&sem->count, RWSEM_UNLOCKED_VALUE);
 	raw_spin_lock_init(&sem->wait_lock);
 	INIT_LIST_HEAD(&sem->wait_list);
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
@@ -114,12 +114,16 @@ enum rwsem_wake_type {
  *   - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed)
  *   - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so)
  * - there must be someone on the queue
- * - the spinlock must be held by the caller
+ * - the wait_lock must be held by the caller
+ * - tasks are marked for wakeup, the caller must later invoke wake_up_q()
+ *   to actually wakeup the blocked task(s) and drop the reference count,
+ *   preferably when the wait_lock is released
  * - woken process blocks are discarded from the list after having task zeroed
- * - writers are only woken if downgrading is false
+ * - writers are only marked woken if downgrading is false
  */
 static struct rw_semaphore *
-__rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
+__rwsem_mark_wake(struct rw_semaphore *sem,
+		  enum rwsem_wake_type wake_type, struct wake_q_head *wake_q)
 {
 	struct rwsem_waiter *waiter;
 	struct task_struct *tsk;
@@ -128,13 +132,16 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
 
 	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
 	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
-		if (wake_type == RWSEM_WAKE_ANY)
-			/* Wake writer at the front of the queue, but do not
-			 * grant it the lock yet as we want other writers
-			 * to be able to steal it.  Readers, on the other hand,
-			 * will block as they will notice the queued writer.
+		if (wake_type == RWSEM_WAKE_ANY) {
+			/*
+			 * Mark writer at the front of the queue for wakeup.
+			 * Until the task is actually later awoken later by
+			 * the caller, other writers are able to steal it.
+			 * Readers, on the other hand, will block as they
+			 * will notice the queued writer.
 			 */
-			wake_up_process(waiter->task);
+			wake_q_add(wake_q, waiter->task);
+		}
 		goto out;
 	}
 
@@ -146,15 +153,27 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
 	if (wake_type != RWSEM_WAKE_READ_OWNED) {
 		adjustment = RWSEM_ACTIVE_READ_BIAS;
  try_reader_grant:
-		oldcount = rwsem_atomic_update(adjustment, sem) - adjustment;
+		oldcount = atomic_long_fetch_add(adjustment, &sem->count);
+
 		if (unlikely(oldcount < RWSEM_WAITING_BIAS)) {
-			/* A writer stole the lock. Undo our reader grant. */
-			if (rwsem_atomic_update(-adjustment, sem) &
-						RWSEM_ACTIVE_MASK)
+			/*
+			 * If the count is still less than RWSEM_WAITING_BIAS
+			 * after removing the adjustment, it is assumed that
+			 * a writer has stolen the lock. We have to undo our
+			 * reader grant.
+			 */
+			if (atomic_long_add_return(-adjustment, &sem->count) <
+			    RWSEM_WAITING_BIAS)
 				goto out;
 			/* Last active locker left. Retry waking readers. */
 			goto try_reader_grant;
 		}
+		/*
+		 * It is not really necessary to set it to reader-owned here,
+		 * but it gives the spinners an early indication that the
+		 * readers now have the lock.
+		 */
+		rwsem_set_reader_owned(sem);
 	}
 
 	/* Grant an infinite number of read locks to the readers at the front
@@ -179,7 +198,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
 		adjustment -= RWSEM_WAITING_BIAS;
 
 	if (adjustment)
-		rwsem_atomic_add(adjustment, sem);
+		atomic_long_add(adjustment, &sem->count);
 
 	next = sem->wait_list.next;
 	loop = woken;
@@ -187,17 +206,15 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
 		waiter = list_entry(next, struct rwsem_waiter, list);
 		next = waiter->list.next;
 		tsk = waiter->task;
+
+		wake_q_add(wake_q, tsk);
 		/*
-		 * Make sure we do not wakeup the next reader before
-		 * setting the nil condition to grant the next reader;
-		 * otherwise we could miss the wakeup on the other
-		 * side and end up sleeping again. See the pairing
-		 * in rwsem_down_read_failed().
+		 * Ensure that the last operation is setting the reader
+		 * waiter to nil such that rwsem_down_read_failed() cannot
+		 * race with do_exit() by always holding a reference count
+		 * to the task to wakeup.
 		 */
-		smp_mb();
-		waiter->task = NULL;
-		wake_up_process(tsk);
-		put_task_struct(tsk);
+		smp_store_release(&waiter->task, NULL);
 	} while (--loop);
 
 	sem->wait_list.next = next;
@@ -216,11 +233,11 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
 	struct rwsem_waiter waiter;
 	struct task_struct *tsk = current;
+	WAKE_Q(wake_q);
 
 	/* set up my own style of waitqueue */
 	waiter.task = tsk;
 	waiter.type = RWSEM_WAITING_FOR_READ;
-	get_task_struct(tsk);
 
 	raw_spin_lock_irq(&sem->wait_lock);
 	if (list_empty(&sem->wait_list))
@@ -228,7 +245,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 	list_add_tail(&waiter.list, &sem->wait_list);
 
 	/* we're now waiting on the lock, but no longer actively locking */
-	count = rwsem_atomic_update(adjustment, sem);
+	count = atomic_long_add_return(adjustment, &sem->count);
 
 	/* If there are no active locks, wake the front queued process(es).
 	 *
@@ -238,9 +255,10 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 	if (count == RWSEM_WAITING_BIAS ||
 	    (count > RWSEM_WAITING_BIAS &&
 	     adjustment != -RWSEM_ACTIVE_READ_BIAS))
-		sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+		sem = __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
 
 	raw_spin_unlock_irq(&sem->wait_lock);
+	wake_up_q(&wake_q);
 
 	/* wait to be given the lock */
 	while (true) {
@@ -255,17 +273,29 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 }
 EXPORT_SYMBOL(rwsem_down_read_failed);
 
+/*
+ * This function must be called with the sem->wait_lock held to prevent
+ * race conditions between checking the rwsem wait list and setting the
+ * sem->count accordingly.
+ */
 static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
 {
 	/*
-	 * Try acquiring the write lock. Check count first in order
-	 * to reduce unnecessary expensive cmpxchg() operations.
+	 * Avoid trying to acquire write lock if count isn't RWSEM_WAITING_BIAS.
 	 */
-	if (count == RWSEM_WAITING_BIAS &&
-	    cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS,
-		    RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) {
-		if (!list_is_singular(&sem->wait_list))
-			rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
+	if (count != RWSEM_WAITING_BIAS)
+		return false;
+
+	/*
+	 * Acquire the lock by trying to set it to ACTIVE_WRITE_BIAS. If there
+	 * are other tasks on the wait list, we need to add on WAITING_BIAS.
+	 */
+	count = list_is_singular(&sem->wait_list) ?
+			RWSEM_ACTIVE_WRITE_BIAS :
+			RWSEM_ACTIVE_WRITE_BIAS + RWSEM_WAITING_BIAS;
+
+	if (atomic_long_cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS, count)
+							== RWSEM_WAITING_BIAS) {
 		rwsem_set_owner(sem);
 		return true;
 	}
@@ -279,13 +309,13 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
  */
 static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
 {
-	long old, count = READ_ONCE(sem->count);
+	long old, count = atomic_long_read(&sem->count);
 
 	while (true) {
 		if (!(count == 0 || count == RWSEM_WAITING_BIAS))
 			return false;
 
-		old = cmpxchg_acquire(&sem->count, count,
+		old = atomic_long_cmpxchg_acquire(&sem->count, count,
 				      count + RWSEM_ACTIVE_WRITE_BIAS);
 		if (old == count) {
 			rwsem_set_owner(sem);
@@ -306,16 +336,11 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 
 	rcu_read_lock();
 	owner = READ_ONCE(sem->owner);
-	if (!owner) {
-		long count = READ_ONCE(sem->count);
+	if (!rwsem_owner_is_writer(owner)) {
 		/*
-		 * If sem->owner is not set, yet we have just recently entered the
-		 * slowpath with the lock being active, then there is a possibility
-		 * reader(s) may have the lock. To be safe, bail spinning in these
-		 * situations.
+		 * Don't spin if the rwsem is readers owned.
 		 */
-		if (count & RWSEM_ACTIVE_MASK)
-			ret = false;
+		ret = !rwsem_owner_is_reader(owner);
 		goto done;
 	}
 
@@ -325,10 +350,15 @@ done:
 	return ret;
 }
 
-static noinline
-bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner)
+/*
+ * Return true only if we can still spin on the owner field of the rwsem.
+ */
+static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
 {
-	long count;
+	struct task_struct *owner = READ_ONCE(sem->owner);
+
+	if (!rwsem_owner_is_writer(owner))
+		goto out;
 
 	rcu_read_lock();
 	while (sem->owner == owner) {
@@ -349,22 +379,16 @@ bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner)
 		cpu_relax_lowlatency();
 	}
 	rcu_read_unlock();
-
-	if (READ_ONCE(sem->owner))
-		return true; /* new owner, continue spinning */
-
+out:
 	/*
-	 * When the owner is not set, the lock could be free or
-	 * held by readers. Check the counter to verify the
-	 * state.
+	 * If there is a new owner or the owner is not set, we continue
+	 * spinning.
 	 */
-	count = READ_ONCE(sem->count);
-	return (count == 0 || count == RWSEM_WAITING_BIAS);
+	return !rwsem_owner_is_reader(READ_ONCE(sem->owner));
 }
 
 static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 {
-	struct task_struct *owner;
 	bool taken = false;
 
 	preempt_disable();
@@ -376,12 +400,17 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 	if (!osq_lock(&sem->osq))
 		goto done;
 
-	while (true) {
-		owner = READ_ONCE(sem->owner);
-		if (owner && !rwsem_spin_on_owner(sem, owner))
-			break;
-
-		/* wait_lock will be acquired if write_lock is obtained */
+	/*
+	 * Optimistically spin on the owner field and attempt to acquire the
+	 * lock whenever the owner changes. Spinning will be stopped when:
+	 *  1) the owning writer isn't running; or
+	 *  2) readers own the lock as we can't determine if they are
+	 *     actively running or not.
+	 */
+	while (rwsem_spin_on_owner(sem)) {
+		/*
+		 * Try to acquire the lock
+		 */
 		if (rwsem_try_write_lock_unqueued(sem)) {
 			taken = true;
 			break;
@@ -393,7 +422,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 		 * we're an RT task that will live-lock because we won't let
 		 * the owner complete.
 		 */
-		if (!owner && (need_resched() || rt_task(current)))
+		if (!sem->owner && (need_resched() || rt_task(current)))
 			break;
 
 		/*
@@ -440,9 +469,10 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 	bool waiting = true; /* any queued threads before us */
 	struct rwsem_waiter waiter;
 	struct rw_semaphore *ret = sem;
+	WAKE_Q(wake_q);
 
 	/* undo write bias from down_write operation, stop active locking */
-	count = rwsem_atomic_update(-RWSEM_ACTIVE_WRITE_BIAS, sem);
+	count = atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS, &sem->count);
 
 	/* do optimistic spinning and steal lock if possible */
 	if (rwsem_optimistic_spin(sem))
@@ -465,18 +495,29 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 
 	/* we're now waiting on the lock, but no longer actively locking */
 	if (waiting) {
-		count = READ_ONCE(sem->count);
+		count = atomic_long_read(&sem->count);
 
 		/*
 		 * If there were already threads queued before us and there are
 		 * no active writers, the lock must be read owned; so we try to
 		 * wake any read locks that were queued ahead of us.
 		 */
-		if (count > RWSEM_WAITING_BIAS)
-			sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS);
+		if (count > RWSEM_WAITING_BIAS) {
+			WAKE_Q(wake_q);
+
+			sem = __rwsem_mark_wake(sem, RWSEM_WAKE_READERS, &wake_q);
+			/*
+			 * The wakeup is normally called _after_ the wait_lock
+			 * is released, but given that we are proactively waking
+			 * readers we can deal with the wake_q overhead as it is
+			 * similar to releasing and taking the wait_lock again
+			 * for attempting rwsem_try_write_lock().
+			 */
+			wake_up_q(&wake_q);
+		}
 
 	} else
-		count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
+		count = atomic_long_add_return(RWSEM_WAITING_BIAS, &sem->count);
 
 	/* wait until we successfully acquire the lock */
 	set_current_state(state);
@@ -492,7 +533,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 
 			schedule();
 			set_current_state(state);
-		} while ((count = sem->count) & RWSEM_ACTIVE_MASK);
+		} while ((count = atomic_long_read(&sem->count)) & RWSEM_ACTIVE_MASK);
 
 		raw_spin_lock_irq(&sem->wait_lock);
 	}
@@ -507,10 +548,11 @@ out_nolock:
 	raw_spin_lock_irq(&sem->wait_lock);
 	list_del(&waiter.list);
 	if (list_empty(&sem->wait_list))
-		rwsem_atomic_update(-RWSEM_WAITING_BIAS, sem);
+		atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
 	else
-		__rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
 	raw_spin_unlock_irq(&sem->wait_lock);
+	wake_up_q(&wake_q);
 
 	return ERR_PTR(-EINTR);
 }
@@ -537,6 +579,7 @@ __visible
 struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
+	WAKE_Q(wake_q);
 
 	/*
 	 * If a spinner is present, it is not necessary to do the wakeup.
@@ -573,9 +616,10 @@ locked:
 
 	/* do nothing if list empty */
 	if (!list_empty(&sem->wait_list))
-		sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+		sem = __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
 
 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+	wake_up_q(&wake_q);
 
 	return sem;
 }
@@ -590,14 +634,16 @@ __visible
 struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
+	WAKE_Q(wake_q);
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
 	/* do nothing if list empty */
 	if (!list_empty(&sem->wait_list))
-		sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED);
+		sem = __rwsem_mark_wake(sem, RWSEM_WAKE_READ_OWNED, &wake_q);
 
 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+	wake_up_q(&wake_q);
 
 	return sem;
 }
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 2e853ad93a3a..45ba475d4be3 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -22,6 +22,7 @@ void __sched down_read(struct rw_semaphore *sem)
 	rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
+	rwsem_set_reader_owned(sem);
 }
 
 EXPORT_SYMBOL(down_read);
@@ -33,8 +34,10 @@ int down_read_trylock(struct rw_semaphore *sem)
 {
 	int ret = __down_read_trylock(sem);
 
-	if (ret == 1)
+	if (ret == 1) {
 		rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_);
+		rwsem_set_reader_owned(sem);
+	}
 	return ret;
 }
 
@@ -124,7 +127,7 @@ void downgrade_write(struct rw_semaphore *sem)
 	 * lockdep: a downgraded write will live on as a write
 	 * dependency.
 	 */
-	rwsem_clear_owner(sem);
+	rwsem_set_reader_owned(sem);
 	__downgrade_write(sem);
 }
 
@@ -138,6 +141,7 @@ void down_read_nested(struct rw_semaphore *sem, int subclass)
 	rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
+	rwsem_set_reader_owned(sem);
 }
 
 EXPORT_SYMBOL(down_read_nested);
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index 870ed9a5b426..a699f4048ba1 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -1,14 +1,58 @@
+/*
+ * The owner field of the rw_semaphore structure will be set to
+ * RWSEM_READ_OWNED when a reader grabs the lock. A writer will clear
+ * the owner field when it unlocks. A reader, on the other hand, will
+ * not touch the owner field when it unlocks.
+ *
+ * In essence, the owner field now has the following 3 states:
+ *  1) 0
+ *     - lock is free or the owner hasn't set the field yet
+ *  2) RWSEM_READER_OWNED
+ *     - lock is currently or previously owned by readers (lock is free
+ *       or not set by owner yet)
+ *  3) Other non-zero value
+ *     - a writer owns the lock
+ */
+#define RWSEM_READER_OWNED	((struct task_struct *)1UL)
+
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+/*
+ * All writes to owner are protected by WRITE_ONCE() to make sure that
+ * store tearing can't happen as optimistic spinners may read and use
+ * the owner value concurrently without lock. Read from owner, however,
+ * may not need READ_ONCE() as long as the pointer value is only used
+ * for comparison and isn't being dereferenced.
+ */
 static inline void rwsem_set_owner(struct rw_semaphore *sem)
 {
-	sem->owner = current;
+	WRITE_ONCE(sem->owner, current);
 }
 
 static inline void rwsem_clear_owner(struct rw_semaphore *sem)
 {
-	sem->owner = NULL;
+	WRITE_ONCE(sem->owner, NULL);
+}
+
+static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
+{
+	/*
+	 * We check the owner value first to make sure that we will only
+	 * do a write to the rwsem cacheline when it is really necessary
+	 * to minimize cacheline contention.
+	 */
+	if (sem->owner != RWSEM_READER_OWNED)
+		WRITE_ONCE(sem->owner, RWSEM_READER_OWNED);
+}
+
+static inline bool rwsem_owner_is_writer(struct task_struct *owner)
+{
+	return owner && owner != RWSEM_READER_OWNED;
 }
 
+static inline bool rwsem_owner_is_reader(struct task_struct *owner)
+{
+	return owner == RWSEM_READER_OWNED;
+}
 #else
 static inline void rwsem_set_owner(struct rw_semaphore *sem)
 {
@@ -17,4 +61,8 @@ static inline void rwsem_set_owner(struct rw_semaphore *sem)
 static inline void rwsem_clear_owner(struct rw_semaphore *sem)
 {
 }
+
+static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
+{
+}
 #endif
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index d400434af6b2..6d86ab6ec2c9 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -253,7 +253,6 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
 	if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s) &&
 	    (rnp == rnp_root ||
 	     ULONG_CMP_LT(READ_ONCE(rnp_root->exp_seq_rq), s)) &&
-	    !mutex_is_locked(&rsp->exp_mutex) &&
 	    mutex_trylock(&rsp->exp_mutex))
 		goto fastpath;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 97ee9ac7e97c..af0ef74df23c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1937,7 +1937,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * chain to provide order. Instead we do:
  *
  *   1) smp_store_release(X->on_cpu, 0)
- *   2) smp_cond_acquire(!X->on_cpu)
+ *   2) smp_cond_load_acquire(!X->on_cpu)
  *
  * Example:
  *
@@ -1948,7 +1948,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *   sched-out X
  *   smp_store_release(X->on_cpu, 0);
  *
- *                    smp_cond_acquire(!X->on_cpu);
+ *                    smp_cond_load_acquire(&X->on_cpu, !VAL);
  *                    X->state = WAKING
  *                    set_task_cpu(X,2)
  *
@@ -1974,7 +1974,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * This means that any means of doing remote wakeups must order the CPU doing
  * the wakeup against the CPU the task is going to end up running on. This,
  * however, is already required for the regular Program-Order guarantee above,
- * since the waking CPU is the one issueing the ACQUIRE (smp_cond_acquire).
+ * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
  *
  */
 
@@ -2047,7 +2047,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * This ensures that tasks getting woken will be fully ordered against
 	 * their previous state and preserve Program Order.
 	 */
-	smp_cond_acquire(!p->on_cpu);
+	smp_cond_load_acquire(&p->on_cpu, !VAL);
 
 	p->sched_contributes_to_load = !!task_contributes_to_load(p);
 	p->state = TASK_WAKING;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 898c0d2f18fe..81283592942b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1113,7 +1113,7 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 	 * In particular, the load of prev->state in finish_task_switch() must
 	 * happen before this.
 	 *
-	 * Pairs with the smp_cond_acquire() in try_to_wake_up().
+	 * Pairs with the smp_cond_load_acquire() in try_to_wake_up().
 	 */
 	smp_store_release(&prev->on_cpu, 0);
 #endif
diff --git a/kernel/smp.c b/kernel/smp.c
index 74165443c240..36552beed397 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -107,7 +107,7 @@ void __init call_function_init(void)
  */
 static __always_inline void csd_lock_wait(struct call_single_data *csd)
 {
-	smp_cond_acquire(!(csd->flags & CSD_FLAG_LOCK));
+	smp_cond_load_acquire(&csd->flags, !(VAL & CSD_FLAG_LOCK));
 }
 
 static __always_inline void csd_lock(struct call_single_data *csd)
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 53fa971d000d..6ab4842b00e8 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -108,7 +108,6 @@ void task_work_run(void)
 		 * fail, but it can play with *work and other entries.
 		 */
 		raw_spin_unlock_wait(&task->pi_lock);
-		smp_mb();
 
 		do {
 			next = work->next;
diff --git a/lib/atomic64.c b/lib/atomic64.c
index 2886ebac6567..53c2d5edc826 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -96,17 +96,41 @@ long long atomic64_##op##_return(long long a, atomic64_t *v)		\
 }									\
 EXPORT_SYMBOL(atomic64_##op##_return);
 
+#define ATOMIC64_FETCH_OP(op, c_op)					\
+long long atomic64_fetch_##op(long long a, atomic64_t *v)		\
+{									\
+	unsigned long flags;						\
+	raw_spinlock_t *lock = lock_addr(v);				\
+	long long val;							\
+									\
+	raw_spin_lock_irqsave(lock, flags);				\
+	val = v->counter;						\
+	v->counter c_op a;						\
+	raw_spin_unlock_irqrestore(lock, flags);			\
+	return val;							\
+}									\
+EXPORT_SYMBOL(atomic64_fetch_##op);
+
 #define ATOMIC64_OPS(op, c_op)						\
 	ATOMIC64_OP(op, c_op)						\
-	ATOMIC64_OP_RETURN(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_OP_RETURN(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/lib/atomic64_test.c b/lib/atomic64_test.c
index 123481814320..dbb369145dda 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -53,11 +53,25 @@ do {								\
 	BUG_ON(atomic##bit##_read(&v) != r);			\
 } while (0)
 
+#define TEST_FETCH(bit, op, c_op, val)				\
+do {								\
+	atomic##bit##_set(&v, v0);				\
+	r = v0;							\
+	r c_op val;						\
+	BUG_ON(atomic##bit##_##op(val, &v) != v0);		\
+	BUG_ON(atomic##bit##_read(&v) != r);			\
+} while (0)
+
 #define RETURN_FAMILY_TEST(bit, op, c_op, val)			\
 do {								\
 	FAMILY_TEST(TEST_RETURN, bit, op, c_op, val);		\
 } while (0)
 
+#define FETCH_FAMILY_TEST(bit, op, c_op, val)			\
+do {								\
+	FAMILY_TEST(TEST_FETCH, bit, op, c_op, val);		\
+} while (0)
+
 #define TEST_ARGS(bit, op, init, ret, expect, args...)		\
 do {								\
 	atomic##bit##_set(&v, init);				\
@@ -114,6 +128,16 @@ static __init void test_atomic(void)
 	RETURN_FAMILY_TEST(, sub_return, -=, onestwos);
 	RETURN_FAMILY_TEST(, sub_return, -=, -one);
 
+	FETCH_FAMILY_TEST(, fetch_add, +=, onestwos);
+	FETCH_FAMILY_TEST(, fetch_add, +=, -one);
+	FETCH_FAMILY_TEST(, fetch_sub, -=, onestwos);
+	FETCH_FAMILY_TEST(, fetch_sub, -=, -one);
+
+	FETCH_FAMILY_TEST(, fetch_or,  |=, v1);
+	FETCH_FAMILY_TEST(, fetch_and, &=, v1);
+	FETCH_FAMILY_TEST(, fetch_andnot, &= ~, v1);
+	FETCH_FAMILY_TEST(, fetch_xor, ^=, v1);
+
 	INC_RETURN_FAMILY_TEST(, v0);
 	DEC_RETURN_FAMILY_TEST(, v0);
 
@@ -154,6 +178,16 @@ static __init void test_atomic64(void)
 	RETURN_FAMILY_TEST(64, sub_return, -=, onestwos);
 	RETURN_FAMILY_TEST(64, sub_return, -=, -one);
 
+	FETCH_FAMILY_TEST(64, fetch_add, +=, onestwos);
+	FETCH_FAMILY_TEST(64, fetch_add, +=, -one);
+	FETCH_FAMILY_TEST(64, fetch_sub, -=, onestwos);
+	FETCH_FAMILY_TEST(64, fetch_sub, -=, -one);
+
+	FETCH_FAMILY_TEST(64, fetch_or,  |=, v1);
+	FETCH_FAMILY_TEST(64, fetch_and, &=, v1);
+	FETCH_FAMILY_TEST(64, fetch_andnot, &= ~, v1);
+	FETCH_FAMILY_TEST(64, fetch_xor, ^=, v1);
+
 	INIT(v0);
 	atomic64_inc(&v);
 	r += one;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 9f530adad10d..4cbda4bd8926 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -83,6 +83,13 @@ void nf_conntrack_lock(spinlock_t *lock) __acquires(lock)
 	spin_lock(lock);
 	while (unlikely(nf_conntrack_locks_all)) {
 		spin_unlock(lock);
+
+		/*
+		 * Order the 'nf_conntrack_locks_all' load vs. the
+		 * spin_unlock_wait() loads below, to ensure
+		 * that 'nf_conntrack_locks_all_lock' is indeed held:
+		 */
+		smp_rmb(); /* spin_lock(&nf_conntrack_locks_all_lock) */
 		spin_unlock_wait(&nf_conntrack_locks_all_lock);
 		spin_lock(lock);
 	}
@@ -128,6 +135,14 @@ static void nf_conntrack_all_lock(void)
 	spin_lock(&nf_conntrack_locks_all_lock);
 	nf_conntrack_locks_all = true;
 
+	/*
+	 * Order the above store of 'nf_conntrack_locks_all' against
+	 * the spin_unlock_wait() loads below, such that if
+	 * nf_conntrack_lock() observes 'nf_conntrack_locks_all'
+	 * we must observe nf_conntrack_locks[] held:
+	 */
+	smp_mb(); /* spin_lock(&nf_conntrack_locks_all_lock) */
+
 	for (i = 0; i < CONNTRACK_LOCKS; i++) {
 		spin_unlock_wait(&nf_conntrack_locks[i]);
 	}
@@ -135,7 +150,13 @@ static void nf_conntrack_all_lock(void)
 
 static void nf_conntrack_all_unlock(void)
 {
-	nf_conntrack_locks_all = false;
+	/*
+	 * All prior stores must be complete before we clear
+	 * 'nf_conntrack_locks_all'. Otherwise nf_conntrack_lock()
+	 * might observe the false value but not the entire
+	 * critical section:
+	 */
+	smp_store_release(&nf_conntrack_locks_all, false);
 	spin_unlock(&nf_conntrack_locks_all_lock);
 }