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}()
  ...

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
 
 /**

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 */

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 */

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;

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 */

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 */