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}()
  ...

8 files changed, 166 insertions, 30 deletions

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 */