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}()
  ...

3 files changed, 33 insertions, 47 deletions

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();
 }
 
 /*