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}()
  ...

lib/atomic64.c

@@ -96,17 +96,41 @@ long long atomic64_##op##_return(long long a, atomic64_t *v)		\
 }									\
 EXPORT_SYMBOL(atomic64_##op##_return);
 
+#define ATOMIC64_FETCH_OP(op, c_op)					\
+long long atomic64_fetch_##op(long long a, atomic64_t *v)		\
+{									\
+	unsigned long flags;						\
+	raw_spinlock_t *lock = lock_addr(v);				\
+	long long val;							\
+									\
+	raw_spin_lock_irqsave(lock, flags);				\
+	val = v->counter;						\
+	v->counter c_op a;						\
+	raw_spin_unlock_irqrestore(lock, flags);			\
+	return val;							\
+}									\
+EXPORT_SYMBOL(atomic64_fetch_##op);
+
 #define ATOMIC64_OPS(op, c_op)						\
 	ATOMIC64_OP(op, c_op)						\
-	ATOMIC64_OP_RETURN(op, c_op)
+	ATOMIC64_OP_RETURN(op, c_op)					\
+	ATOMIC64_FETCH_OP(op, c_op)
 
 ATOMIC64_OPS(add, +=)
 ATOMIC64_OPS(sub, -=)
-ATOMIC64_OP(and, &=)
-ATOMIC64_OP(or, |=)
-ATOMIC64_OP(xor, ^=)
 
 #undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op, c_op)						\
+	ATOMIC64_OP_RETURN(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_RETURN
 #undef ATOMIC64_OP
 

lib/atomic64_test.c

@@ -53,11 +53,25 @@ do {								\
 	BUG_ON(atomic##bit##_read(&v) != r);			\
 } while (0)
 
+#define TEST_FETCH(bit, op, c_op, val)				\
+do {								\
+	atomic##bit##_set(&v, v0);				\
+	r = v0;							\
+	r c_op val;						\
+	BUG_ON(atomic##bit##_##op(val, &v) != v0);		\
+	BUG_ON(atomic##bit##_read(&v) != r);			\
+} while (0)
+
 #define RETURN_FAMILY_TEST(bit, op, c_op, val)			\
 do {								\
 	FAMILY_TEST(TEST_RETURN, bit, op, c_op, val);		\
 } while (0)
 
+#define FETCH_FAMILY_TEST(bit, op, c_op, val)			\
+do {								\
+	FAMILY_TEST(TEST_FETCH, bit, op, c_op, val);		\
+} while (0)
+
 #define TEST_ARGS(bit, op, init, ret, expect, args...)		\
 do {								\
 	atomic##bit##_set(&v, init);				\
@@ -114,6 +128,16 @@ static __init void test_atomic(void)
 	RETURN_FAMILY_TEST(, sub_return, -=, onestwos);
 	RETURN_FAMILY_TEST(, sub_return, -=, -one);
 
+	FETCH_FAMILY_TEST(, fetch_add, +=, onestwos);
+	FETCH_FAMILY_TEST(, fetch_add, +=, -one);
+	FETCH_FAMILY_TEST(, fetch_sub, -=, onestwos);
+	FETCH_FAMILY_TEST(, fetch_sub, -=, -one);
+
+	FETCH_FAMILY_TEST(, fetch_or,  |=, v1);
+	FETCH_FAMILY_TEST(, fetch_and, &=, v1);
+	FETCH_FAMILY_TEST(, fetch_andnot, &= ~, v1);
+	FETCH_FAMILY_TEST(, fetch_xor, ^=, v1);
+
 	INC_RETURN_FAMILY_TEST(, v0);
 	DEC_RETURN_FAMILY_TEST(, v0);
 
@@ -154,6 +178,16 @@ static __init void test_atomic64(void)
 	RETURN_FAMILY_TEST(64, sub_return, -=, onestwos);
 	RETURN_FAMILY_TEST(64, sub_return, -=, -one);
 
+	FETCH_FAMILY_TEST(64, fetch_add, +=, onestwos);
+	FETCH_FAMILY_TEST(64, fetch_add, +=, -one);
+	FETCH_FAMILY_TEST(64, fetch_sub, -=, onestwos);
+	FETCH_FAMILY_TEST(64, fetch_sub, -=, -one);
+
+	FETCH_FAMILY_TEST(64, fetch_or,  |=, v1);
+	FETCH_FAMILY_TEST(64, fetch_and, &=, v1);
+	FETCH_FAMILY_TEST(64, fetch_andnot, &= ~, v1);
+	FETCH_FAMILY_TEST(64, fetch_xor, ^=, v1);
+
 	INIT(v0);
 	atomic64_inc(&v);
 	r += one;