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/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)))
 

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
 

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)
 {

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)
 {