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

Pull core locking updates from Ingo Molnar:
 "The main changes in this cycle are:

   - Another attempt at enabling cross-release lockdep dependency
     tracking (automatically part of CONFIG_PROVE_LOCKING=y), this time
     with better performance and fewer false positives. (Byungchul Park)

   - Introduce lockdep_assert_irqs_enabled()/disabled() and convert
     open-coded equivalents to lockdep variants. (Frederic Weisbecker)

   - Add down_read_killable() and use it in the VFS's iterate_dir()
     method. (Kirill Tkhai)

   - Convert remaining uses of ACCESS_ONCE() to
     READ_ONCE()/WRITE_ONCE(). Most of the conversion was Coccinelle
     driven. (Mark Rutland, Paul E. McKenney)

   - Get rid of lockless_dereference(), by strengthening Alpha atomics,
     strengthening READ_ONCE() with smp_read_barrier_depends() and thus
     being able to convert users of lockless_dereference() to
     READ_ONCE(). (Will Deacon)

   - Various micro-optimizations:

        - better PV qspinlocks (Waiman Long),
        - better x86 barriers (Michael S. Tsirkin)
        - better x86 refcounts (Kees Cook)

   - ... plus other fixes and enhancements. (Borislav Petkov, Juergen
     Gross, Miguel Bernal Marin)"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits)
  locking/x86: Use LOCK ADD for smp_mb() instead of MFENCE
  rcu: Use lockdep to assert IRQs are disabled/enabled
  netpoll: Use lockdep to assert IRQs are disabled/enabled
  timers/posix-cpu-timers: Use lockdep to assert IRQs are disabled/enabled
  sched/clock, sched/cputime: Use lockdep to assert IRQs are disabled/enabled
  irq_work: Use lockdep to assert IRQs are disabled/enabled
  irq/timings: Use lockdep to assert IRQs are disabled/enabled
  perf/core: Use lockdep to assert IRQs are disabled/enabled
  x86: Use lockdep to assert IRQs are disabled/enabled
  smp/core: Use lockdep to assert IRQs are disabled/enabled
  timers/hrtimer: Use lockdep to assert IRQs are disabled/enabled
  timers/nohz: Use lockdep to assert IRQs are disabled/enabled
  workqueue: Use lockdep to assert IRQs are disabled/enabled
  irq/softirqs: Use lockdep to assert IRQs are disabled/enabled
  locking/lockdep: Add IRQs disabled/enabled assertion APIs: lockdep_assert_irqs_enabled()/disabled()
  locking/pvqspinlock: Implement hybrid PV queued/unfair locks
  locking/rwlocks: Fix comments
  x86/paravirt: Set up the virt_spin_lock_key after static keys get initialized
  block, locking/lockdep: Assign a lock_class per gendisk used for wait_for_completion()
  workqueue: Remove now redundant lock acquisitions wrt. workqueue flushes
  ...

2 files changed, 28 insertions, 17 deletions

diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
index 7d6fceb3d567..917910607e0e 100644
--- a/arch/ia64/include/asm/rwsem.h
+++ b/arch/ia64/include/asm/rwsem.h
@@ -38,15 +38,31 @@
 /*
  * lock for reading
  */
-static inline void
-__down_read (struct rw_semaphore *sem)
+static inline int
+___down_read (struct rw_semaphore *sem)
 {
 	long result = ia64_fetchadd8_acq((unsigned long *)&sem->count.counter, 1);
 
-	if (result < 0)
+	return (result < 0);
+}
+
+static inline void
+__down_read (struct rw_semaphore *sem)
+{
+	if (___down_read(sem))
 		rwsem_down_read_failed(sem);
 }
 
+static inline int
+__down_read_killable (struct rw_semaphore *sem)
+{
+	if (___down_read(sem))
+		if (IS_ERR(rwsem_down_read_failed_killable(sem)))
+			return -EINTR;
+
+	return 0;
+}
+
 /*
  * lock for writing
  */
@@ -73,9 +89,10 @@ __down_write (struct rw_semaphore *sem)
 static inline int
 __down_write_killable (struct rw_semaphore *sem)
 {
-	if (___down_write(sem))
+	if (___down_write(sem)) {
 		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
 			return -EINTR;
+	}
 
 	return 0;
 }
diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h
index aa057abd948e..afd0b3121b4c 100644
--- a/arch/ia64/include/asm/spinlock.h
+++ b/arch/ia64/include/asm/spinlock.h
@@ -62,7 +62,7 @@ static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
 
 static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
 {
-	int tmp = ACCESS_ONCE(lock->lock);
+	int tmp = READ_ONCE(lock->lock);
 
 	if (!(((tmp >> TICKET_SHIFT) ^ tmp) & TICKET_MASK))
 		return ia64_cmpxchg(acq, &lock->lock, tmp, tmp + 1, sizeof (tmp)) == tmp;
@@ -74,19 +74,19 @@ static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
 	unsigned short	*p = (unsigned short *)&lock->lock + 1, tmp;
 
 	asm volatile ("ld2.bias %0=[%1]" : "=r"(tmp) : "r"(p));
-	ACCESS_ONCE(*p) = (tmp + 2) & ~1;
+	WRITE_ONCE(*p, (tmp + 2) & ~1);
 }
 
 static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
 {
-	long tmp = ACCESS_ONCE(lock->lock);
+	long tmp = READ_ONCE(lock->lock);
 
 	return !!(((tmp >> TICKET_SHIFT) ^ tmp) & TICKET_MASK);
 }
 
 static inline int __ticket_spin_is_contended(arch_spinlock_t *lock)
 {
-	long tmp = ACCESS_ONCE(lock->lock);
+	long tmp = READ_ONCE(lock->lock);
 
 	return ((tmp - (tmp >> TICKET_SHIFT)) & TICKET_MASK) > 1;
 }
@@ -127,9 +127,7 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 {
 	arch_spin_lock(lock);
 }
-
-#define arch_read_can_lock(rw)		(*(volatile int *)(rw) >= 0)
-#define arch_write_can_lock(rw)	(*(volatile int *)(rw) == 0)
+#define arch_spin_lock_flags	arch_spin_lock_flags
 
 #ifdef ASM_SUPPORTED
 
@@ -157,6 +155,7 @@ arch_read_lock_flags(arch_rwlock_t *lock, unsigned long flags)
 		: "p6", "p7", "r2", "memory");
 }
 
+#define arch_read_lock_flags arch_read_lock_flags
 #define arch_read_lock(lock) arch_read_lock_flags(lock, 0)
 
 #else /* !ASM_SUPPORTED */
@@ -209,6 +208,7 @@ arch_write_lock_flags(arch_rwlock_t *lock, unsigned long flags)
 		: "ar.ccv", "p6", "p7", "r2", "r29", "memory");
 }
 
+#define arch_write_lock_flags arch_write_lock_flags
 #define arch_write_lock(rw) arch_write_lock_flags(rw, 0)
 
 #define arch_write_trylock(rw)							\
@@ -232,8 +232,6 @@ static inline void arch_write_unlock(arch_rwlock_t *x)
 
 #else /* !ASM_SUPPORTED */
 
-#define arch_write_lock_flags(l, flags) arch_write_lock(l)
-
 #define arch_write_lock(l)								\
 ({											\
 	__u64 ia64_val, ia64_set_val = ia64_dep_mi(-1, 0, 31, 1);			\
@@ -273,8 +271,4 @@ static inline int arch_read_trylock(arch_rwlock_t *x)
 	return (u32)ia64_cmpxchg4_acq((__u32 *)(x), new.word, old.word) == old.word;
 }
 
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif /*  _ASM_IA64_SPINLOCK_H */