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}()
  ...

108 files changed, 3268 insertions, 958 deletions

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 147ae8ec836f..a4d0a99de04d 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -806,6 +806,41 @@ out-guess your code.  More generally, although READ_ONCE() does force
 the compiler to actually emit code for a given load, it does not force
 the compiler to use the results.
 
+In addition, control dependencies apply only to the then-clause and
+else-clause of the if-statement in question.  In particular, it does
+not necessarily apply to code following the if-statement:
+
+	q = READ_ONCE(a);
+	if (q) {
+		WRITE_ONCE(b, p);
+	} else {
+		WRITE_ONCE(b, r);
+	}
+	WRITE_ONCE(c, 1);  /* BUG: No ordering against the read from "a". */
+
+It is tempting to argue that there in fact is ordering because the
+compiler cannot reorder volatile accesses and also cannot reorder
+the writes to "b" with the condition.  Unfortunately for this line
+of reasoning, the compiler might compile the two writes to "b" as
+conditional-move instructions, as in this fanciful pseudo-assembly
+language:
+
+	ld r1,a
+	ld r2,p
+	ld r3,r
+	cmp r1,$0
+	cmov,ne r4,r2
+	cmov,eq r4,r3
+	st r4,b
+	st $1,c
+
+A weakly ordered CPU would have no dependency of any sort between the load
+from "a" and the store to "c".  The control dependencies would extend
+only to the pair of cmov instructions and the store depending on them.
+In short, control dependencies apply only to the stores in the then-clause
+and else-clause of the if-statement in question (including functions
+invoked by those two clauses), not to code following that if-statement.
+
 Finally, control dependencies do -not- provide transitivity.  This is
 demonstrated by two related examples, with the initial values of
 x and y both being zero:
@@ -869,6 +904,12 @@ In summary:
       atomic{,64}_read() can help to preserve your control dependency.
       Please see the COMPILER BARRIER section for more information.
 
+  (*) Control dependencies apply only to the then-clause and else-clause
+      of the if-statement containing the control dependency, including
+      any functions that these two clauses call.  Control dependencies
+      do -not- apply to code following the if-statement containing the
+      control dependency.
+
   (*) Control dependencies pair normally with other types of barriers.
 
   (*) Control dependencies do -not- provide transitivity.  If you
diff --git a/MAINTAINERS b/MAINTAINERS
index 452beeeb7fbd..09bb92fb80c8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7024,15 +7024,23 @@ Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 S:	Maintained
 F:	drivers/media/usb/dvb-usb-v2/lmedm04*
 
-LOCKDEP AND LOCKSTAT
+LOCKING PRIMITIVES
 M:	Peter Zijlstra <peterz@infradead.org>
 M:	Ingo Molnar <mingo@redhat.com>
 L:	linux-kernel@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core/locking
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core
 S:	Maintained
-F:	Documentation/locking/lockdep*.txt
-F:	Documentation/locking/lockstat.txt
+F:	Documentation/locking/
 F:	include/linux/lockdep.h
+F:	include/linux/spinlock*.h
+F:	arch/*/include/asm/spinlock*.h
+F:	include/linux/rwlock*.h
+F:	include/linux/mutex*.h
+F:	arch/*/include/asm/mutex*.h
+F:	include/linux/rwsem*.h
+F:	arch/*/include/asm/rwsem.h
+F:	include/linux/seqlock.h
+F:	lib/locking*.[ch]
 F:	kernel/locking/
 
 LOGICAL DISK MANAGER SUPPORT (LDM, Windows 2000/XP/Vista Dynamic Disks)
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 572b228c44c7..498933a7df97 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -46,10 +46,9 @@ static __inline__ void atomic_##op(int i, atomic_t * v)			\
 }									\
 
 #define ATOMIC_OP_RETURN(op, asm_op)					\
-static inline int atomic_##op##_return(int i, atomic_t *v)		\
+static inline int atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 {									\
 	long temp, result;						\
-	smp_mb();							\
 	__asm__ __volatile__(						\
 	"1:	ldl_l %0,%1\n"						\
 	"	" #asm_op " %0,%3,%2\n"					\
@@ -61,7 +60,23 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_mb();							\
+	return result;							\
+}
+
+#define ATOMIC_FETCH_OP(op, asm_op)					\
+static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
+{									\
+	long temp, result;						\
+	__asm__ __volatile__(						\
+	"1:	ldl_l %2,%1\n"						\
+	"	" #asm_op " %2,%3,%0\n"					\
+	"	stl_c %0,%1\n"						\
+	"	beq %0,2f\n"						\
+	".subsection 2\n"						\
+	"2:	br 1b\n"						\
+	".previous"							\
+	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
+	:"Ir" (i), "m" (v->counter) : "memory");			\
 	return result;							\
 }
 
@@ -82,10 +97,9 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v)		\
 }									\
 
 #define ATOMIC64_OP_RETURN(op, asm_op)					\
-static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	\
+static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v)	\
 {									\
 	long temp, result;						\
-	smp_mb();							\
 	__asm__ __volatile__(						\
 	"1:	ldq_l %0,%1\n"						\
 	"	" #asm_op " %0,%3,%2\n"					\
@@ -97,34 +111,77 @@ static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_mb();							\
+	return result;							\
+}
+
+#define ATOMIC64_FETCH_OP(op, asm_op)					\
+static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v)	\
+{									\
+	long temp, result;						\
+	__asm__ __volatile__(						\
+	"1:	ldq_l %2,%1\n"						\
+	"	" #asm_op " %2,%3,%0\n"					\
+	"	stq_c %0,%1\n"						\
+	"	beq %0,2f\n"						\
+	".subsection 2\n"						\
+	"2:	br 1b\n"						\
+	".previous"							\
+	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
+	:"Ir" (i), "m" (v->counter) : "memory");			\
 	return result;							\
 }
 
 #define ATOMIC_OPS(op)							\
 	ATOMIC_OP(op, op##l)						\
 	ATOMIC_OP_RETURN(op, op##l)					\
+	ATOMIC_FETCH_OP(op, op##l)					\