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}()
  ...

4 files changed, 93 insertions, 14 deletions

diff --git a/arch/sh/include/asm/atomic-grb.h b/arch/sh/include/asm/atomic-grb.h
index b94df40..d755e96 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 23fcdad..8e2da5f 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 33d34b1..caea2c4 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 bdc0f3b..416834b 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