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

Pull locking updates from Ingo Molnar:
 "The biggest part of this tree is the new auto-generated atomics API
  wrappers by Mark Rutland.

  The primary motivation was to allow instrumentation without uglifying
  the primary source code.

  The linecount increase comes from adding the auto-generated files to
  the Git space as well:

    include/asm-generic/atomic-instrumented.h     | 1689 ++++++++++++++++--
    include/asm-generic/atomic-long.h             | 1174 ++++++++++---
    include/linux/atomic-fallback.h               | 2295 +++++++++++++++++++++++++
    include/linux/atomic.h                        | 1241 +------------

  I preferred this approach, so that the full call stack of the (already
  complex) locking APIs is still fully visible in 'git grep'.

  But if this is excessive we could certainly hide them.

  There's a separate build-time mechanism to determine whether the
  headers are out of date (they should never be stale if we do our job
  right).

  Anyway, nothing from this should be visible to regular kernel
  developers.

  Other changes:

   - Add support for dynamic keys, which removes a source of false
     positives in the workqueue code, among other things (Bart Van
     Assche)

   - Updates to tools/memory-model (Andrea Parri, Paul E. McKenney)

   - qspinlock, wake_q and lockdep micro-optimizations (Waiman Long)

   - misc other updates and enhancements"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits)
  locking/lockdep: Shrink struct lock_class_key
  locking/lockdep: Add module_param to enable consistency checks
  lockdep/lib/tests: Test dynamic key registration
  lockdep/lib/tests: Fix run_tests.sh
  kernel/workqueue: Use dynamic lockdep keys for workqueues
  locking/lockdep: Add support for dynamic keys
  locking/lockdep: Verify whether lock objects are small enough to be used as class keys
  locking/lockdep: Check data structure consistency
  locking/lockdep: Reuse lock chains that have been freed
  locking/lockdep: Fix a comment in add_chain_cache()
  locking/lockdep: Introduce lockdep_next_lockchain() and lock_chain_count()
  locking/lockdep: Reuse list entries that are no longer in use
  locking/lockdep: Free lock classes that are no longer in use
  locking/lockdep: Update two outdated comments
  locking/lockdep: Make it easy to detect whether or not inside a selftest
  locking/lockdep: Split lockdep_free_key_range() and lockdep_reset_lock()
  locking/lockdep: Initialize the locks_before and locks_after lists earlier
  locking/lockdep: Make zap_class() remove all matching lock order entries
  locking/lockdep: Reorder struct lock_class members
  locking/lockdep: Avoid that add_chain_cache() adds an invalid chain to the cache
  ...

1 files changed, 46 insertions, 21 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 43f44539b88f..0002995570db 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -396,19 +396,7 @@ static bool set_nr_if_polling(struct task_struct *p)
 #endif
 #endif
 
-/**
- * wake_q_add() - queue a wakeup for 'later' waking.
- * @head: the wake_q_head to add @task to
- * @task: the task to queue for 'later' wakeup
- *
- * Queue a task for later wakeup, most likely by the wake_up_q() call in the
- * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
- * instantly.
- *
- * This function must be used as-if it were wake_up_process(); IOW the task
- * must be ready to be woken at this location.
- */
-void wake_q_add(struct wake_q_head *head, struct task_struct *task)
+static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
 {
 	struct wake_q_node *node = &task->wake_q;
 
@@ -421,16 +409,56 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
 	 * state, even in the failed case, an explicit smp_mb() must be used.
 	 */
 	smp_mb__before_atomic();
-	if (cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL))
-		return;
-
-	get_task_struct(task);
+	if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)))
+		return false;
 
 	/*
 	 * The head is context local, there can be no concurrency.
 	 */
 	*head->lastp = node;
 	head->lastp = &node->next;
+	return true;
+}
+
+/**
+ * wake_q_add() - queue a wakeup for 'later' waking.
+ * @head: the wake_q_head to add @task to
+ * @task: the task to queue for 'later' wakeup
+ *
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
+ * instantly.
+ *
+ * This function must be used as-if it were wake_up_process(); IOW the task
+ * must be ready to be woken at this location.
+ */
+void wake_q_add(struct wake_q_head *head, struct task_struct *task)
+{
+	if (__wake_q_add(head, task))
+		get_task_struct(task);
+}
+
+/**
+ * wake_q_add_safe() - safely queue a wakeup for 'later' waking.
+ * @head: the wake_q_head to add @task to
+ * @task: the task to queue for 'later' wakeup
+ *
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
+ * instantly.
+ *
+ * This function must be used as-if it were wake_up_process(); IOW the task
+ * must be ready to be woken at this location.
+ *
+ * This function is essentially a task-safe equivalent to wake_q_add(). Callers
+ * that already hold reference to @task can call the 'safe' version and trust
+ * wake_q to do the right thing depending whether or not the @task is already
+ * queued for wakeup.
+ */
+void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task)
+{
+	if (!__wake_q_add(head, task))
+		put_task_struct(task);
 }
 
 void wake_up_q(struct wake_q_head *head)
@@ -5866,14 +5894,11 @@ void __init sched_init_smp(void)
 	/*
 	 * There's no userspace yet to cause hotplug operations; hence all the
 	 * CPU masks are stable and all blatant races in the below code cannot
-	 * happen. The hotplug lock is nevertheless taken to satisfy lockdep,
-	 * but there won't be any contention on it.
+	 * happen.
 	 */
-	cpus_read_lock();
 	mutex_lock(&sched_domains_mutex);
 	sched_init_domains(cpu_active_mask);
 	mutex_unlock(&sched_domains_mutex);
-	cpus_read_unlock();
 
 	/* Move init over to a non-isolated CPU */
 	if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)