Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking changes from Ingo Molnar:
 "The main changes in this cycle were:

   - More gradual enhancements to atomic ops: new atomic*_read_ctrl()
     ops, synchronize atomic_{read,set}() ordering requirements between
     architectures, add atomic_long_t bitops.  (Peter Zijlstra)

   - Add _{relaxed|acquire|release}() variants for inc/dec atomics and
     use them in various locking primitives: mutex, rtmutex, mcs, rwsem.
     This enables weakly ordered architectures (such as arm64) to make
     use of more locking related optimizations.  (Davidlohr Bueso)

   - Implement atomic[64]_{inc,dec}_relaxed() on ARM.  (Will Deacon)

   - Futex kernel data cache footprint micro-optimization.  (Rasmus
     Villemoes)

   - pvqspinlock runtime overhead micro-optimization.  (Waiman Long)

   - misc smaller fixlets"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  ARM, locking/atomics: Implement _relaxed variants of atomic[64]_{inc,dec}
  locking/rwsem: Use acquire/release semantics
  locking/mcs: Use acquire/release semantics
  locking/rtmutex: Use acquire/release semantics
  locking/mutex: Use acquire/release semantics
  locking/asm-generic: Add _{relaxed|acquire|release}() variants for inc/dec atomics
  atomic: Implement atomic_read_ctrl()
  atomic, arch: Audit atomic_{read,set}()
  atomic: Add atomic_long_t bitops
  futex: Force hot variables into a single cache line
  locking/pvqspinlock: Kick the PV CPU unconditionally when _Q_SLOW_VAL
  locking/osq: Relax atomic semantics
  locking/qrwlock: Rename ->lock to ->wait_lock
  locking/Documentation/lockstat: Fix typo - lokcing -> locking
  locking/atomics, cmpxchg: Privatize the inclusion of asm/cmpxchg.h

Documentation/atomic_ops.txt

@@ -542,6 +542,10 @@ The routines xchg() and cmpxchg() must provide the same exact
 memory-barrier semantics as the atomic and bit operations returning
 values.
 
+Note: If someone wants to use xchg(), cmpxchg() and their variants,
+linux/atomic.h should be included rather than asm/cmpxchg.h, unless
+the code is in arch/* and can take care of itself.
+
 Spinlocks and rwlocks have memory barrier expectations as well.
 The rule to follow is simple:
 

Documentation/locking/lockstat.txt

@@ -12,7 +12,7 @@ Because things like lock contention can severely impact performance.
 - HOW
 
 Lockdep already has hooks in the lock functions and maps lock instances to
-lock classes. We build on that (see Documentation/lokcing/lockdep-design.txt).
+lock classes. We build on that (see Documentation/locking/lockdep-design.txt).
 The graph below shows the relation between the lock functions and the various
 hooks therein.
 

Documentation/memory-barriers.txt

@@ -637,7 +637,8 @@ as follows:
 	b = p;  /* BUG: Compiler and CPU can both reorder!!! */
 
 Finally, the READ_ONCE_CTRL() includes an smp_read_barrier_depends()
-that DEC Alpha needs in order to respect control depedencies.
+that DEC Alpha needs in order to respect control depedencies. Alternatively
+use one of atomic{,64}_read_ctrl().
 
 So don't leave out the READ_ONCE_CTRL().
 
@@ -796,9 +797,9 @@ site: https://www.cl.cam.ac.uk/~pes20/ppcmem/index.html.
 
 In summary:
 
-  (*) Control dependencies must be headed by READ_ONCE_CTRL().
-      Or, as a much less preferable alternative, interpose
-      smp_read_barrier_depends() between a READ_ONCE() and the
+  (*) Control dependencies must be headed by READ_ONCE_CTRL(),
+      atomic{,64}_read_ctrl(). Or, as a much less preferable alternative,
+      interpose smp_read_barrier_depends() between a READ_ONCE() and the
       control-dependent write.
 
   (*) Control dependencies can order prior loads against later stores.
@@ -820,10 +821,10 @@ In summary:
       and WRITE_ONCE() can help to preserve the needed conditional.
 
   (*) Control dependencies require that the compiler avoid reordering the
-      dependency into nonexistence.  Careful use of READ_ONCE_CTRL()
-      or smp_read_barrier_depends() can help to preserve your control
-      dependency.  Please see the Compiler Barrier section for more
-      information.
+      dependency into nonexistence.  Careful use of READ_ONCE_CTRL(),
+      atomic{,64}_read_ctrl() or smp_read_barrier_depends() can help to
+      preserve your control dependency.  Please see the Compiler Barrier
+      section for more information.
 
   (*) Control dependencies pair normally with other types of barriers.
 

arch/alpha/include/asm/atomic.h

@@ -17,11 +17,11 @@
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
-#define atomic_read(v)		ACCESS_ONCE((v)->counter)
-#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
+#define atomic_read(v)		READ_ONCE((v)->counter)
+#define atomic64_read(v)	READ_ONCE((v)->counter)
 
-#define atomic_set(v,i)		((v)->counter = (i))
-#define atomic64_set(v,i)	((v)->counter = (i))
+#define atomic_set(v,i)		WRITE_ONCE((v)->counter, (i))
+#define atomic64_set(v,i)	WRITE_ONCE((v)->counter, (i))
 
 /*
  * To get proper branch prediction for the main line, we must branch

arch/arc/include/asm/atomic.h

@@ -17,11 +17,11 @@
 #include <asm/barrier.h>
 #include <asm/smp.h>
 
-#define atomic_read(v)  ((v)->counter)
+#define atomic_read(v)  READ_ONCE((v)->counter)
 
 #ifdef CONFIG_ARC_HAS_LLSC
 
-#define atomic_set(v, i) (((v)->counter) = (i))
+#define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i))
 
 #ifdef CONFIG_ARC_STAR_9000923308
 
@@ -107,7 +107,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 #ifndef CONFIG_SMP
 
  /* violating atomic_xxx API locking protocol in UP for optimization sake */
-#define atomic_set(v, i) (((v)->counter) = (i))
+#define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i))
 
 #else
 
@@ -125,7 +125,7 @@ static inline void atomic_set(atomic_t *v, int i)
 	unsigned long flags;
 
 	atomic_ops_lock(flags);
-	v->counter = i;
+	WRITE_ONCE(v->counter, i);
 	atomic_ops_unlock(flags);
 }
 

arch/arm/include/asm/atomic.h

@@ -27,8 +27,8 @@
  * strex/ldrex monitor on some implementations. The reason we can use it for
  * atomic_set() is the clrex or dummy strex done on every exception return.
  */
-#define atomic_read(v)	ACCESS_ONCE((v)->counter)
-#define atomic_set(v,i)	(((v)->counter) = (i))
+#define atomic_read(v)	READ_ONCE((v)->counter)
+#define atomic_set(v,i)	WRITE_ONCE(((v)->counter), (i))
 
 #if __LINUX_ARM_ARCH__ >= 6
 
@@ -210,8 +210,8 @@ ATOMIC_OP(xor, ^=, eor)
 
 #define atomic_inc_and_test(v)	(atomic_add_return(1, v) == 0)
 #define atomic_dec_and_test(v)	(atomic_sub_return(1, v) == 0)
-#define atomic_inc_return(v)    (atomic_add_return(1, v))
-#define atomic_dec_return(v)    (atomic_sub_return(1, v))
+#define atomic_inc_return_relaxed(v)    (atomic_add_return_relaxed(1, v))
+#define atomic_dec_return_relaxed(v)    (atomic_sub_return_relaxed(1, v))
 #define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
 
 #define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
@@ -442,11 +442,11 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 
 #define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
 #define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
+#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1LL, (v))
 #define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
 #define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
 #define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
+#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1LL, (v))
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 #define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
 

arch/arm64/include/asm/atomic.h

@@ -54,7 +54,7 @@
 #define ATOMIC_INIT(i)	{ (i) }
 
 #define atomic_read(v)			READ_ONCE((v)->counter)
-#define atomic_set(v, i)		(((v)->counter) = (i))
+#define atomic_set(v, i)		WRITE_ONCE(((v)->counter), (i))
 #define atomic_xchg(v, new)		xchg(&((v)->counter), (new))
 #define atomic_cmpxchg(v, old, new)	cmpxchg(&((v)->counter), (old), (new))
 

arch/avr32/include/asm/atomic.h

@@ -19,8 +19,8 @@
 
 #define ATOMIC_INIT(i)  { (i) }
 
-#define atomic_read(v)		ACCESS_ONCE((v)->counter)
-#define atomic_set(v, i)	(((v)->counter) = i)
+#define atomic_read(v)		READ_ONCE((v)->counter)
+#define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
 
 #define ATOMIC_OP_RETURN(op, asm_op, asm_con)				\
 static inline int __atomic_##op##_return(int i, atomic_t *v)		\

arch/frv/include/asm/atomic.h

@@ -32,8 +32,8 @@
  */
 
 #define ATOMIC_INIT(i)		{ (i) }
-#define atomic_read(v)		ACCESS_ONCE((v)->counter)
-#define atomic_set(v, i)	(((v)->counter) = (i))
+#define atomic_read(v)		READ_ONCE((v)->counter)
+#define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
 
 static inline int atomic_inc_return(atomic_t *v)
 {

arch/h8300/include/asm/atomic.h

@@ -11,8 +11,8 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define atomic_read(v)		ACCESS_ONCE((v)->counter)
-#define atomic_set(v, i)	(((v)->counter) = i)
+#define atomic_read(v)		READ_ONCE((v)->counter)
+#define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
 
 #include <linux/kernel.h>
 

arch/hexagon/include/asm/atomic.h

@@ -48,7 +48,7 @@ static inline void atomic_set(atomic_t *v, int new)
  *
  * Assumes all word reads on our architecture are atomic.
  */
-#define atomic_read(v)		((v)->counter)
+#define atomic_read(v)		READ_ONCE((v)->counter)
 
 /**
  * atomic_xchg - atomic

arch/ia64/include/asm/atomic.h

@@ -21,11 +21,11 @@
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
-#define atomic_read(v)		ACCESS_ONCE((v)->counter)
-#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
+#define atomic_read(v)		READ_ONCE((v)->counter)
+#define atomic64_read(v)	READ_ONCE((v)->counter)
 
-#define atomic_set(v,i)		(((v)->counter) = (i))
-#define atomic64_set(v,i)	(((v)->counter) = (i))
+#define atomic_set(v,i)		WRITE_ONCE(((v)->counter), (i))
+#define atomic64_set(v,i)	WRITE_ONCE(((v)->counter), (i))
 
 #define ATOMIC_OP(op, c_op)						\
 static __inline__ int							\

arch/m32r/include/asm/atomic.h

@@ -28,7 +28,7 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)	ACCESS_ONCE((v)->counter)
+#define atomic_read(v)	READ_ONCE((v)->counter)
 
 /**
  * atomic_set - set atomic variable
@@ -37,7 +37,7 @@
  *
  * Atomically sets the value of @v to @i.
  */
-#define atomic_set(v,i)	(((v)->counter) = (i))
+#define atomic_set(v,i)	WRITE_ONCE(((v)->counter), (i))
 
 #ifdef CONFIG_CHIP_M32700_TS1
 #define __ATOMIC_CLOBBER	, "r4"

arch/m68k/include/asm/atomic.h

@@ -17,8 +17,8 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define atomic_read(v)		ACCESS_ONCE((v)->counter)
-#define atomic_set(v, i)	(((v)->counter) = i)
+#define atomic_read(v)		READ_ONCE((v)->counter)
+#define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
 
 /*
  * The ColdFire parts cannot do some immediate to memory operations,

arch/metag/include/asm/atomic_lnkget.h

@@ -3,7 +3,7 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define atomic_set(v, i)		((v)->counter = (i))
+#define atomic_set(v, i)		WRITE_ONCE((v)->counter, (i))
 
 #include <linux/compiler.h>
 

arch/metag/include/asm/atomic_lock1.h

@@ -10,7 +10,7 @@
 
 static inline int atomic_read(const atomic_t *v)
 {
-	return (v)->counter;
+	return READ_ONCE((v)->counter);
 }
 
 /*

arch/mips/include/asm/atomic.h

@@ -30,7 +30,7 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)		ACCESS_ONCE((v)->counter)
+#define atomic_read(v)		READ_ONCE((v)->counter)
 
 /*
  * atomic_set - set atomic variable
@@ -39,7 +39,7 @@
  *
  * Atomically sets the value of @v to @i.
  */
-#define atomic_set(v, i)		((v)->counter = (i))
+#define atomic_set(v, i)	WRITE_ONCE((v)->counter, (i))
 
 #define ATOMIC_OP(op, c_op, asm_op)					      \
 static __inline__ void atomic_##op(int i, atomic_t * v)			      \
@@ -315,14 +315,14 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
  * @v: pointer of type atomic64_t
  *
  */
-#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
+#define atomic64_read(v)	READ_ONCE((v)->counter)
 
 /*
  * atomic64_set - set atomic variable
  * @v: pointer of type atomic64_t
  * @i: required value
  */
-#define atomic64_set(v, i)	((v)->counter = (i))
+#define atomic64_set(v, i)	WRITE_ONCE((v)->counter, (i))
 
 #define ATOMIC64_OP(op, c_op, asm_op)					      \
 static __inline__ void atomic64_##op(long i, atomic64_t * v)		      \

arch/mn10300/include/asm/atomic.h

@@ -34,7 +34,7 @@
  *
  * Atomically reads the value of @v.  Note that the guaranteed
  */
-#define atomic_read(v)	(ACCESS_ONCE((v)->counter))
+#define atomic_read(v)	READ_ONCE((v)->counter)
 
 /**
  * atomic_set - set atomic variable
@@ -43,7 +43,7 @@
  *
  * Atomically sets the value of @v to @i.  Note that the guaranteed
  */
-#define atomic_set(v, i) (((v)->counter) = (i))
+#define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i))
 
 #define ATOMIC_OP(op)							\
 static inline void atomic_##op(int i, atomic_t *v)			\

arch/parisc/include/asm/atomic.h

@@ -67,7 +67,7 @@ static __inline__ void atomic_set(atomic_t *v, int i)
 
 static __inline__ int atomic_read(const atomic_t *v)
 {
-	return ACCESS_ONCE((v)->counter);
+	return READ_ONCE((v)->counter);
 }
 
 /* exported interface */

arch/sh/include/asm/atomic.h

@@ -14,8 +14,8 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define atomic_read(v)		ACCESS_ONCE((v)->counter)
-#define atomic_set(v,i)		((v)->counter = (i))
+#define atomic_read(v)		READ_ONCE((v)->counter)
+#define atomic_set(v,i)		WRITE_ONCE((v)->counter, (i))
 
 #if defined(CONFIG_GUSA_RB)
 #include <asm/atomic-grb.h>