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, 73 insertions, 10 deletions

diff --git a/arch/metag/include/asm/atomic_lnkget.h b/arch/metag/include/asm/atomic_lnkget.h
index 88fa25fae8bd..def2c642f053 100644
--- a/arch/metag/include/asm/atomic_lnkget.h
+++ b/arch/metag/include/asm/atomic_lnkget.h
@@ -69,16 +69,44 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
         return result;                                                  \
 }
 
-#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 result, temp;                                               \
+                                                                        \
+        smp_mb();                                                       \
+                                                                        \
+        asm volatile (                                                  \
+                "1:     LNKGETD %1, [%2]\n"                             \
+                "       " #op " %0, %1, %3\n"                           \
+                "       LNKSETD [%2], %0\n"                             \
+                "       DEFR    %0, TXSTAT\n"                           \
+                "       ANDT    %0, %0, #HI(0x3f000000)\n"              \
+                "       CMPT    %0, #HI(0x02000000)\n"                  \
+                "       BNZ 1b\n"                                       \
+                : "=&d" (temp), "=&d" (result)                          \
+                : "da" (&v->counter), "bd" (i)                          \
+                : "cc");                                                \
+                                                                        \
+        smp_mb();                                                       \
+                                                                        \
+        return result;                                                  \
+}
+
+#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/metag/include/asm/atomic_lock1.h b/arch/metag/include/asm/atomic_lock1.h
index 0295d9b8d5bf..6c1380a8a0d4 100644
--- a/arch/metag/include/asm/atomic_lock1.h
+++ b/arch/metag/include/asm/atomic_lock1.h
@@ -64,15 +64,40 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
         return result;                                                  \
 }
 
-#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 result;                                           \
+        unsigned long flags;                                            \
+                                                                        \
+        __global_lock1(flags);                                          \
+        result = v->counter;                                            \
+        fence();                                                        \
+        v->counter c_op i;                                              \
+        __global_unlock1(flags);                                        \
+                                                                        \
+        return result;                                                  \
+}
+
+#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/metag/include/asm/spinlock.h b/arch/metag/include/asm/spinlock.h
index 86a7cf3d1386..c0c7a22be1ae 100644
--- a/arch/metag/include/asm/spinlock.h
+++ b/arch/metag/include/asm/spinlock.h
@@ -1,14 +1,24 @@
 #ifndef __ASM_SPINLOCK_H
 #define __ASM_SPINLOCK_H
 
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
 #ifdef CONFIG_METAG_ATOMICITY_LOCK1
 #include <asm/spinlock_lock1.h>
 #else
 #include <asm/spinlock_lnkget.h>
 #endif
 
-#define arch_spin_unlock_wait(lock) \
-        do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+/*
+ * both lock1 and lnkget are test-and-set spinlocks with 0 unlocked and 1
+ * locked.
+ */
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+        smp_cond_load_acquire(&lock->lock, !VAL);
+}
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)