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

Pull locking updates from Ingo Molnar:

 - Add 'cross-release' support to lockdep, which allows APIs like
   completions, where it's not the 'owner' who releases the lock, to be
   tracked. It's all activated automatically under
   CONFIG_PROVE_LOCKING=y.

 - Clean up (restructure) the x86 atomics op implementation to be more
   readable, in preparation of KASAN annotations. (Dmitry Vyukov)

 - Fix static keys (Paolo Bonzini)

 - Add killable versions of down_read() et al (Kirill Tkhai)

 - Rework and fix jump_label locking (Marc Zyngier, Paolo Bonzini)

 - Rework (and fix) tlb_flush_pending() barriers (Peter Zijlstra)

 - Remove smp_mb__before_spinlock() and convert its usages, introduce
   smp_mb__after_spinlock() (Peter Zijlstra)

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (56 commits)
  locking/lockdep/selftests: Fix mixed read-write ABBA tests
  sched/completion: Avoid unnecessary stack allocation for COMPLETION_INITIALIZER_ONSTACK()
  acpi/nfit: Fix COMPLETION_INITIALIZER_ONSTACK() abuse
  locking/pvqspinlock: Relax cmpxchg's to improve performance on some architectures
  smp: Avoid using two cache lines for struct call_single_data
  locking/lockdep: Untangle xhlock history save/restore from task independence
  locking/refcounts, x86/asm: Disable CONFIG_ARCH_HAS_REFCOUNT for the time being
  futex: Remove duplicated code and fix undefined behaviour
  Documentation/locking/atomic: Finish the document...
  locking/lockdep: Fix workqueue crossrelease annotation
  workqueue/lockdep: 'Fix' flush_work() annotation
  locking/lockdep/selftests: Add mixed read-write ABBA tests
  mm, locking/barriers: Clarify tlb_flush_pending() barriers
  locking/lockdep: Make CONFIG_LOCKDEP_CROSSRELEASE and CONFIG_LOCKDEP_COMPLETIONS truly non-interactive
  locking/lockdep: Explicitly initialize wq_barrier::done::map
  locking/lockdep: Rename CONFIG_LOCKDEP_COMPLETE to CONFIG_LOCKDEP_COMPLETIONS
  locking/lockdep: Reword title of LOCKDEP_CROSSRELEASE config
  locking/lockdep: Make CONFIG_LOCKDEP_CROSSRELEASE part of CONFIG_PROVE_LOCKING
  locking/refcounts, x86/asm: Implement fast refcount overflow protection
  locking/lockdep: Fix the rollback and overwrite detection logic in crossrelease
  ...

kernel/locking/lockdep_internals.h

@@ -143,6 +143,8 @@ struct lockdep_stats {
 	int	redundant_softirqs_on;
 	int	redundant_softirqs_off;
 	int	nr_unused_locks;
+	int	nr_redundant_checks;
+	int	nr_redundant;
 	int	nr_cyclic_checks;
 	int	nr_cyclic_check_recursions;
 	int	nr_find_usage_forwards_checks;

kernel/locking/lockdep_proc.c

@@ -201,6 +201,10 @@ static void lockdep_stats_debug_show(struct seq_file *m)
 		debug_atomic_read(chain_lookup_hits));
 	seq_printf(m, " cyclic checks:                 %11llu\n",
 		debug_atomic_read(nr_cyclic_checks));
+	seq_printf(m, " redundant checks:              %11llu\n",
+		debug_atomic_read(nr_redundant_checks));
+	seq_printf(m, " redundant links:               %11llu\n",
+		debug_atomic_read(nr_redundant));
 	seq_printf(m, " find-mask forwards checks:     %11llu\n",
 		debug_atomic_read(nr_find_usage_forwards_checks));
 	seq_printf(m, " find-mask backwards checks:    %11llu\n",

kernel/locking/lockdep_states.h

@@ -6,4 +6,3 @@
  */
 LOCKDEP_STATE(HARDIRQ)
 LOCKDEP_STATE(SOFTIRQ)
-LOCKDEP_STATE(RECLAIM_FS)

kernel/locking/osq_lock.c

@@ -109,6 +109,19 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 
 	prev = decode_cpu(old);
 	node->prev = prev;
+
+	/*
+	 * osq_lock()			unqueue
+	 *
+	 * node->prev = prev		osq_wait_next()
+	 * WMB				MB
+	 * prev->next = node		next->prev = prev // unqueue-C
+	 *
+	 * Here 'node->prev' and 'next->prev' are the same variable and we need
+	 * to ensure these stores happen in-order to avoid corrupting the list.
+	 */
+	smp_wmb();
+
 	WRITE_ONCE(prev->next, node);
 
 	/*

kernel/locking/qspinlock_paravirt.h

@@ -72,7 +72,7 @@ static inline bool pv_queued_spin_steal_lock(struct qspinlock *lock)
 	struct __qspinlock *l = (void *)lock;
 
 	if (!(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) &&
-	    (cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0)) {
+	    (cmpxchg_acquire(&l->locked, 0, _Q_LOCKED_VAL) == 0)) {
 		qstat_inc(qstat_pv_lock_stealing, true);
 		return true;
 	}
@@ -101,16 +101,16 @@ static __always_inline void clear_pending(struct qspinlock *lock)
 
 /*
  * The pending bit check in pv_queued_spin_steal_lock() isn't a memory
- * barrier. Therefore, an atomic cmpxchg() is used to acquire the lock
- * just to be sure that it will get it.
+ * barrier. Therefore, an atomic cmpxchg_acquire() is used to acquire the
+ * lock just to be sure that it will get it.
  */
 static __always_inline int trylock_clear_pending(struct qspinlock *lock)
 {
 	struct __qspinlock *l = (void *)lock;
 
 	return !READ_ONCE(l->locked) &&
-	       (cmpxchg(&l->locked_pending, _Q_PENDING_VAL, _Q_LOCKED_VAL)
-			== _Q_PENDING_VAL);
+	       (cmpxchg_acquire(&l->locked_pending, _Q_PENDING_VAL,
+				_Q_LOCKED_VAL) == _Q_PENDING_VAL);
 }
 #else /* _Q_PENDING_BITS == 8 */
 static __always_inline void set_pending(struct qspinlock *lock)
@@ -138,7 +138,7 @@ static __always_inline int trylock_clear_pending(struct qspinlock *lock)
 		 */
 		old = val;
 		new = (val & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL;
-		val = atomic_cmpxchg(&lock->val, old, new);
+		val = atomic_cmpxchg_acquire(&lock->val, old, new);
 
 		if (val == old)
 			return 1;
@@ -362,8 +362,18 @@ static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 	 * observe its next->locked value and advance itself.
 	 *
 	 * Matches with smp_store_mb() and cmpxchg() in pv_wait_node()
+	 *
+	 * The write to next->locked in arch_mcs_spin_unlock_contended()
+	 * must be ordered before the read of pn->state in the cmpxchg()
+	 * below for the code to work correctly. To guarantee full ordering
+	 * irrespective of the success or failure of the cmpxchg(),
+	 * a relaxed version with explicit barrier is used. The control
+	 * dependency will order the reading of pn->state before any
+	 * subsequent writes.
 	 */
-	if (cmpxchg(&pn->state, vcpu_halted, vcpu_hashed) != vcpu_halted)
+	smp_mb__before_atomic();
+	if (cmpxchg_relaxed(&pn->state, vcpu_halted, vcpu_hashed)
+	    != vcpu_halted)
 		return;
 
 	/*

kernel/locking/rtmutex_common.h

@@ -40,6 +40,9 @@ struct rt_mutex_waiter {
 /*
  * Various helpers to access the waiters-tree:
  */
+
+#ifdef CONFIG_RT_MUTEXES
+
 static inline int rt_mutex_has_waiters(struct rt_mutex *lock)
 {
 	return !RB_EMPTY_ROOT(&lock->waiters);
@@ -69,6 +72,32 @@ task_top_pi_waiter(struct task_struct *p)
 			pi_tree_entry);
 }
 
+#else
+
+static inline int rt_mutex_has_waiters(struct rt_mutex *lock)
+{
+	return false;
+}
+
+static inline struct rt_mutex_waiter *
+rt_mutex_top_waiter(struct rt_mutex *lock)
+{
+	return NULL;
+}
+
+static inline int task_has_pi_waiters(struct task_struct *p)
+{
+	return false;
+}
+
+static inline struct rt_mutex_waiter *
+task_top_pi_waiter(struct task_struct *p)
+{
+	return NULL;
+}
+
+#endif
+
 /*
  * lock->owner state tracking:
  */

kernel/locking/rwsem-spinlock.c

@@ -126,7 +126,7 @@ __rwsem_wake_one_writer(struct rw_semaphore *sem)
 /*
  * get a read lock on the semaphore
  */
-void __sched __down_read(struct rw_semaphore *sem)
+int __sched __down_read_common(struct rw_semaphore *sem, int state)
 {
 	struct rwsem_waiter waiter;
 	unsigned long flags;
@@ -140,8 +140,6 @@ void __sched __down_read(struct rw_semaphore *sem)
 		goto out;
 	}
 
-	set_current_state(TASK_UNINTERRUPTIBLE);
-
 	/* set up my own style of waitqueue */
 	waiter.task = current;
 	waiter.type = RWSEM_WAITING_FOR_READ;
@@ -149,20 +147,41 @@ void __sched __down_read(struct rw_semaphore *sem)
 
 	list_add_tail(&waiter.list, &sem->wait_list);
 
-	/* we don't need to touch the semaphore struct anymore */
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
 	/* wait to be given the lock */
 	for (;;) {
 		if (!waiter.task)
 			break;
+		if (signal_pending_state(state, current))
+			goto out_nolock;
+		set_current_state(state);
+		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 		schedule();
-		set_current_state(TASK_UNINTERRUPTIBLE);
+		raw_spin_lock_irqsave(&sem->wait_lock, flags);
 	}
 
-	__set_current_state(TASK_RUNNING);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
  out:
-	;
+	return 0;
+
+out_nolock:
+	/*
+	 * We didn't take the lock, so that there is a writer, which
+	 * is owner or the first waiter of the sem. If it's a waiter,
+	 * it will be woken by current owner. Not need to wake anybody.
+	 */
+	list_del(&waiter.list);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+	return -EINTR;
+}
+
+void __sched __down_read(struct rw_semaphore *sem)
+{
+	__down_read_common(sem, TASK_UNINTERRUPTIBLE);
+}
+
+int __sched __down_read_killable(struct rw_semaphore *sem)
+{
+	return __down_read_common(sem, TASK_KILLABLE);
 }
 
 /*

kernel/locking/rwsem-xadd.c

@@ -221,8 +221,8 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 /*
  * Wait for the read lock to be granted
  */
-__visible
-struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
+static inline struct rw_semaphore __sched *
+__rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
 {
 	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
 	struct rwsem_waiter waiter;
@@ -255,17 +255,44 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 
 	/* wait to be given the lock */
 	while (true) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
+		set_current_state(state);
 		if (!waiter.task)
 			break;
+		if (signal_pending_state(state, current)) {
+			raw_spin_lock_irq(&sem->wait_lock);
+			if (waiter.task)
+				goto out_nolock;
+			raw_spin_unlock_irq(&sem->wait_lock);
+			break;
+		}
 		schedule();
 	}
 
 	__set_current_state(TASK_RUNNING);
 	return sem;
+out_nolock:
+	list_del(&waiter.list);
+	if (list_empty(&sem->wait_list))
+		atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
+	raw_spin_unlock_irq(&sem->wait_lock);
+	__set_current_state(TASK_RUNNING);
+	return ERR_PTR(-EINTR);
+}
+
+__visible struct rw_semaphore * __sched
+rwsem_down_read_failed(struct rw_semaphore *sem)
+{
+	return __rwsem_down_read_failed_common(sem, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(rwsem_down_read_failed);
 
+__visible struct rw_semaphore * __sched
+rwsem_down_read_failed_killable(struct rw_semaphore *sem)
+{
+	return __rwsem_down_read_failed_common(sem, TASK_KILLABLE);
+}
+EXPORT_SYMBOL(rwsem_down_read_failed_killable);
+
 /*
  * This function must be called with the sem->wait_lock held to prevent
  * race conditions between checking the rwsem wait list and setting the