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
  ...

6 files changed, 34 insertions, 53 deletions

diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h
index 49be4bba1e96..34a028a7bcc5 100644
--- a/include/asm-generic/atomic-long.h
+++ b/include/asm-generic/atomic-long.h
@@ -244,4 +244,7 @@ static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u)
 #define atomic_long_inc_not_zero(l) \
 	ATOMIC_LONG_PFX(_inc_not_zero)((ATOMIC_LONG_PFX(_t) *)(l))
 
+#define atomic_long_cond_read_acquire(v, c) \
+	ATOMIC_LONG_PFX(_cond_read_acquire)((ATOMIC_LONG_PFX(_t) *)(v), (c))
+
 #endif  /*  _ASM_GENERIC_ATOMIC_LONG_H  */
diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h
index 7d026bf27713..0f7062bd55e5 100644
--- a/include/asm-generic/qrwlock.h
+++ b/include/asm-generic/qrwlock.h
@@ -26,51 +26,20 @@
 
 /*
  * Writer states & reader shift and bias.
- *
- *       | +0 | +1 | +2 | +3 |
- *   ----+----+----+----+----+
- *    LE | 78 | 56 | 34 | 12 | 0x12345678
- *   ----+----+----+----+----+
- *       | wr |      rd      |
- *       +----+----+----+----+
- *
- *   ----+----+----+----+----+
- *    BE | 12 | 34 | 56 | 78 | 0x12345678
- *   ----+----+----+----+----+
- *       |      rd      | wr |
- *       +----+----+----+----+
  */
-#define	_QW_WAITING	1		/* A writer is waiting	   */
-#define	_QW_LOCKED	0xff		/* A writer holds the lock */
-#define	_QW_WMASK	0xff		/* Writer mask		   */
-#define	_QR_SHIFT	8		/* Reader count shift	   */
+#define	_QW_WAITING	0x100		/* A writer is waiting	   */
+#define	_QW_LOCKED	0x0ff		/* A writer holds the lock */
+#define	_QW_WMASK	0x1ff		/* Writer mask		   */
+#define	_QR_SHIFT	9		/* Reader count shift	   */
 #define _QR_BIAS	(1U << _QR_SHIFT)
 
 /*
  * External function declarations
  */
-extern void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts);
+extern void queued_read_lock_slowpath(struct qrwlock *lock);
 extern void queued_write_lock_slowpath(struct qrwlock *lock);
 
 /**
- * queued_read_can_lock- would read_trylock() succeed?
- * @lock: Pointer to queue rwlock structure
- */
-static inline int queued_read_can_lock(struct qrwlock *lock)
-{
-	return !(atomic_read(&lock->cnts) & _QW_WMASK);
-}
-
-/**
- * queued_write_can_lock- would write_trylock() succeed?
- * @lock: Pointer to queue rwlock structure
- */
-static inline int queued_write_can_lock(struct qrwlock *lock)
-{
-	return !atomic_read(&lock->cnts);
-}
-
-/**
  * queued_read_trylock - try to acquire read lock of a queue rwlock
  * @lock : Pointer to queue rwlock structure
  * Return: 1 if lock acquired, 0 if failed
@@ -118,7 +87,7 @@ static inline void queued_read_lock(struct qrwlock *lock)
 		return;
 
 	/* The slowpath will decrement the reader count, if necessary. */
-	queued_read_lock_slowpath(lock, cnts);
+	queued_read_lock_slowpath(lock);
 }
 
 /**
@@ -147,30 +116,18 @@ static inline void queued_read_unlock(struct qrwlock *lock)
 }
 
 /**
- * __qrwlock_write_byte - retrieve the write byte address of a queue rwlock
- * @lock : Pointer to queue rwlock structure
- * Return: the write byte address of a queue rwlock
- */
-static inline u8 *__qrwlock_write_byte(struct qrwlock *lock)
-{
-	return (u8 *)lock + 3 * IS_BUILTIN(CONFIG_CPU_BIG_ENDIAN);
-}
-
-/**
  * queued_write_unlock - release write lock of a queue rwlock
  * @lock : Pointer to queue rwlock structure
  */
 static inline void queued_write_unlock(struct qrwlock *lock)
 {
-	smp_store_release(__qrwlock_write_byte(lock), 0);
+	smp_store_release(&lock->wlocked, 0);
 }
 
 /*
  * Remapping rwlock architecture specific functions to the corresponding
  * queue rwlock functions.
  */
-#define arch_read_can_lock(l)	queued_read_can_lock(l)
-#define arch_write_can_lock(l)	queued_write_can_lock(l)
 #define arch_read_lock(l)	queued_read_lock(l)
 #define arch_write_lock(l)	queued_write_lock(l)
 #define arch_read_trylock(l)	queued_read_trylock(l)
diff --git a/include/asm-generic/qrwlock_types.h b/include/asm-generic/qrwlock_types.h
index d93573eff162..137ecdd16daa 100644
--- a/include/asm-generic/qrwlock_types.h
+++ b/include/asm-generic/qrwlock_types.h
@@ -10,12 +10,23 @@
  */
 
 typedef struct qrwlock {
-	atomic_t		cnts;
+	union {
+		atomic_t cnts;
+		struct {
+#ifdef __LITTLE_ENDIAN
+			u8 wlocked;	/* Locked for write? */
+			u8 __lstate[3];
+#else
+			u8 __lstate[3];
+			u8 wlocked;	/* Locked for write? */
+#endif
+		};
+	};
 	arch_spinlock_t		wait_lock;
 } arch_rwlock_t;
 
 #define	__ARCH_RW_LOCK_UNLOCKED {		\
-	.cnts = ATOMIC_INIT(0),			\
+	{ .cnts = ATOMIC_INIT(0), },		\
 	.wait_lock = __ARCH_SPIN_LOCK_UNLOCKED,	\
 }
 
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 66260777d644..b37b4ad7eb94 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -121,6 +121,5 @@ static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 #define arch_spin_lock(l)		queued_spin_lock(l)
 #define arch_spin_trylock(l)		queued_spin_trylock(l)
 #define arch_spin_unlock(l)		queued_spin_unlock(l)
-#define arch_spin_lock_flags(l, f)	queued_spin_lock(l)
 
 #endif /* __ASM_GENERIC_QSPINLOCK_H */
diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h
index bdbe43bac230..93e67a055a4d 100644
--- a/include/asm-generic/rwsem.h
+++ b/include/asm-generic/rwsem.h
@@ -38,6 +38,16 @@ static inline void __down_read(struct rw_semaphore *sem)
 		rwsem_down_read_failed(sem);
 }
 
+static inline int __down_read_killable(struct rw_semaphore *sem)
+{
+	if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) {
+		if (IS_ERR(rwsem_down_read_failed_killable(sem)))
+			return -EINTR;
+	}
+
+	return 0;
+}
+
 static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
 	long tmp;
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 8acfc1e099e1..e549bff87c5b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -459,6 +459,7 @@
 #define TEXT_TEXT							\
 		ALIGN_FUNCTION();					\
 		*(.text.hot TEXT_MAIN .text.fixup .text.unlikely)	\
+		*(.text..refcount)					\
 		*(.ref.text)						\
 	MEM_KEEP(init.text)						\
 	MEM_KEEP(exit.text)						\