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
  ...

5 files changed, 4 insertions, 50 deletions

diff --git a/arch/tile/gxio/dma_queue.c b/arch/tile/gxio/dma_queue.c
index baa60357f8ba..b7ba577d82ca 100644
--- a/arch/tile/gxio/dma_queue.c
+++ b/arch/tile/gxio/dma_queue.c
@@ -163,14 +163,14 @@ int __gxio_dma_queue_is_complete(__gxio_dma_queue_t *dma_queue,
 				 int64_t completion_slot, int update)
 {
 	if (update) {
-		if (ACCESS_ONCE(dma_queue->hw_complete_count) >
+		if (READ_ONCE(dma_queue->hw_complete_count) >
 		    completion_slot)
 			return 1;
 
 		__gxio_dma_queue_update_credits(dma_queue);
 	}
 
-	return ACCESS_ONCE(dma_queue->hw_complete_count) > completion_slot;
+	return READ_ONCE(dma_queue->hw_complete_count) > completion_slot;
 }
 
 EXPORT_SYMBOL_GPL(__gxio_dma_queue_is_complete);
diff --git a/arch/tile/include/asm/spinlock_32.h b/arch/tile/include/asm/spinlock_32.h
index cba8ba9b8da6..fb5313d77315 100644
--- a/arch/tile/include/asm/spinlock_32.h
+++ b/arch/tile/include/asm/spinlock_32.h
@@ -51,9 +51,6 @@ static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 
 void arch_spin_lock(arch_spinlock_t *lock);
 
-/* We cannot take an interrupt after getting a ticket, so don't enable them. */
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-
 int arch_spin_trylock(arch_spinlock_t *lock);
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
@@ -80,22 +77,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 #define _RD_COUNT_WIDTH 8
 
 /**
- * arch_read_can_lock() - would read_trylock() succeed?
- */
-static inline int arch_read_can_lock(arch_rwlock_t *rwlock)
-{
-	return (rwlock->lock << _RD_COUNT_WIDTH) == 0;
-}
-
-/**
- * arch_write_can_lock() - would write_trylock() succeed?
- */
-static inline int arch_write_can_lock(arch_rwlock_t *rwlock)
-{
-	return rwlock->lock == 0;
-}
-
-/**
  * arch_read_lock() - acquire a read lock.
  */
 void arch_read_lock(arch_rwlock_t *rwlock);
@@ -125,7 +106,4 @@ void arch_read_unlock(arch_rwlock_t *rwlock);
  */
 void arch_write_unlock(arch_rwlock_t *rwlock);
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
 #endif /* _ASM_TILE_SPINLOCK_32_H */
diff --git a/arch/tile/include/asm/spinlock_64.h b/arch/tile/include/asm/spinlock_64.h
index 9a2c2d605752..5b616ef642a8 100644
--- a/arch/tile/include/asm/spinlock_64.h
+++ b/arch/tile/include/asm/spinlock_64.h
@@ -75,9 +75,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 /* Try to get the lock, and return whether we succeeded. */
 int arch_spin_trylock(arch_spinlock_t *lock);
 
-/* We cannot take an interrupt after getting a ticket, so don't enable them. */
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-
 /*
  * Read-write spinlocks, allowing multiple readers
  * but only one writer.
@@ -93,24 +90,6 @@ static inline int arch_write_val_locked(int val)
 	return val < 0;  /* Optimize "val & __WRITE_LOCK_BIT". */
 }
 
-/**
- * read_can_lock - would read_trylock() succeed?
- * @lock: the rwlock in question.
- */
-static inline int arch_read_can_lock(arch_rwlock_t *rw)
-{
-	return !arch_write_val_locked(rw->lock);
-}
-
-/**
- * write_can_lock - would write_trylock() succeed?
- * @lock: the rwlock in question.
- */
-static inline int arch_write_can_lock(arch_rwlock_t *rw)
-{
-	return rw->lock == 0;
-}
-
 extern void __read_lock_failed(arch_rwlock_t *rw);
 
 static inline void arch_read_lock(arch_rwlock_t *rw)
@@ -156,7 +135,4 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 	return 0;
 }
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
 #endif /* _ASM_TILE_SPINLOCK_64_H */
diff --git a/arch/tile/include/gxio/dma_queue.h b/arch/tile/include/gxio/dma_queue.h
index b9e45e37649e..c8fd47edba30 100644
--- a/arch/tile/include/gxio/dma_queue.h
+++ b/arch/tile/include/gxio/dma_queue.h
@@ -121,7 +121,7 @@ static inline int64_t __gxio_dma_queue_reserve(__gxio_dma_queue_t *dma_queue,
 		 * if the result is LESS than "hw_complete_count".
 		 */
 		uint64_t complete;
-		complete = ACCESS_ONCE(dma_queue->hw_complete_count);
+		complete = READ_ONCE(dma_queue->hw_complete_count);
 		slot |= (complete & 0xffffffffff000000);
 		if (slot < complete)
 			slot += 0x1000000;
diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c
index e1a078e6828e..d516d61751c2 100644
--- a/arch/tile/kernel/ptrace.c
+++ b/arch/tile/kernel/ptrace.c
@@ -255,7 +255,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 
 int do_syscall_trace_enter(struct pt_regs *regs)
 {
-	u32 work = ACCESS_ONCE(current_thread_info()->flags);
+	u32 work = READ_ONCE(current_thread_info()->flags);
 
 	if ((work & _TIF_SYSCALL_TRACE) &&
 	    tracehook_report_syscall_entry(regs)) {