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

Pull scheduler fixes from Ingo Molnar:
 "Thiscontains misc fixes: preempt_schedule_common() and io_schedule()
  recursion fixes, sched/dl fixes, a completion_done() revert, two
  sched/rt fixes and a comment update patch"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/rt: Avoid obvious configuration fail
  sched/autogroup: Fix failure to set cpu.rt_runtime_us
  sched/dl: Do update_rq_clock() in yield_task_dl()
  sched: Prevent recursion in io_schedule()
  sched/completion: Serialize completion_done() with complete()
  sched: Fix preempt_schedule_common() triggering tracing recursion
  sched/dl: Prevent enqueue of a sleeping task in dl_task_timer()
  sched: Make dl_task_time() use task_rq_lock()
  sched: Clarify ordering between task_rq_lock() and move_queued_task()

5 files changed, 148 insertions, 99 deletions

diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 8a2e230fb86a..eae160dd669d 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -87,8 +87,7 @@ static inline struct autogroup *autogroup_create(void)
          * so we don't have to move tasks around upon policy change,
          * or flail around trying to allocate bandwidth on the fly.
          * A bandwidth exception in __sched_setscheduler() allows
-         * the policy change to proceed.  Thereafter, task_group()
-         * returns &root_task_group, so zero bandwidth is required.
+         * the policy change to proceed.
          */
         free_rt_sched_group(tg);
         tg->rt_se = root_task_group.rt_se;
@@ -115,9 +114,6 @@ bool task_wants_autogroup(struct task_struct *p, struct task_group *tg)
         if (tg != &root_task_group)
                 return false;
 
-        if (p->sched_class != &fair_sched_class)
-                return false;
-
         /*
          * We can only assume the task group can't go away on us if
          * autogroup_move_group() can see us on ->thread_group list.
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index 7052d3fd4e7b..8d0f35debf35 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -274,7 +274,7 @@ bool try_wait_for_completion(struct completion *x)
          * first without taking the lock so we can
          * return early in the blocking case.
          */
-        if (!ACCESS_ONCE(x->done))
+        if (!READ_ONCE(x->done))
                 return 0;
 
         spin_lock_irqsave(&x->wait.lock, flags);
@@ -297,6 +297,21 @@ EXPORT_SYMBOL(try_wait_for_completion);
  */
 bool completion_done(struct completion *x)
 {
-        return !!ACCESS_ONCE(x->done);
+        if (!READ_ONCE(x->done))
+                return false;
+
+        /*
+         * If ->done, we need to wait for complete() to release ->wait.lock
+         * otherwise we can end up freeing the completion before complete()
+         * is done referencing it.
+         *
+         * The RMB pairs with complete()'s RELEASE of ->wait.lock and orders
+         * the loads of ->done and ->wait.lock such that we cannot observe
+         * the lock before complete() acquires it while observing the ->done
+         * after it's acquired the lock.
+         */
+        smp_rmb();
+        spin_unlock_wait(&x->wait.lock);
+        return true;
 }
 EXPORT_SYMBOL(completion_done);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 13049aac05a6..f0f831e8a345 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -307,66 +307,6 @@ __read_mostly int scheduler_running;
 int sysctl_sched_rt_runtime = 950000;
 
 /*
- * __task_rq_lock - lock the rq @p resides on.
- */
-static inline struct rq *__task_rq_lock(struct task_struct *p)
-        __acquires(rq->lock)
-{
-        struct rq *rq;
-
-        lockdep_assert_held(&p->pi_lock);
-
-        for (;;) {
-                rq = task_rq(p);
-                raw_spin_lock(&rq->lock);
-                if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
-                        return rq;
-                raw_spin_unlock(&rq->lock);
-
-                while (unlikely(task_on_rq_migrating(p)))
-                        cpu_relax();
-        }
-}
-
-/*
- * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
- */
-static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
-        __acquires(p->pi_lock)
-        __acquires(rq->lock)
-{
-        struct rq *rq;
-
-        for (;;) {
-                raw_spin_lock_irqsave(&p->pi_lock, *flags);
-                rq = task_rq(p);
-                raw_spin_lock(&rq->lock);
-                if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
-                        return rq;
-                raw_spin_unlock(&rq->lock);
-                raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
-
-                while (unlikely(task_on_rq_migrating(p)))
-                        cpu_relax();
-        }
-}
-
-static void __task_rq_unlock(struct rq *rq)
-        __releases(rq->lock)
-{
-        raw_spin_unlock(&rq->lock);
-}
-
-static inline void
-task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags)
-        __releases(rq->lock)
-        __releases(p->pi_lock)
-{
-        raw_spin_unlock(&rq->lock);
-        raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
-}
-
-/*
  * this_rq_lock - lock this runqueue and disable interrupts.
  */
 static struct rq *this_rq_lock(void)
@@ -2899,7 +2839,7 @@ void __sched schedule_preempt_disabled(void)
         preempt_disable();
 }
 
-static void preempt_schedule_common(void)
+static void __sched notrace preempt_schedule_common(void)
 {
         do {
                 __preempt_count_add(PREEMPT_ACTIVE);
@@ -4418,36 +4358,29 @@ EXPORT_SYMBOL_GPL(yield_to);
  * This task is about to go to sleep on IO. Increment rq->nr_iowait so
  * that process accounting knows that this is a task in IO wait state.
  */
-void __sched io_schedule(void)
-{
-        struct rq *rq = raw_rq();
-
-        delayacct_blkio_start();
-        atomic_inc(&rq->nr_iowait);
-        blk_flush_plug(current);
-        current->in_iowait = 1;
-        schedule();
-        current->in_iowait = 0;
-        atomic_dec(&rq->nr_iowait);
-        delayacct_blkio_end();
-}
-EXPORT_SYMBOL(io_schedule);
-
 long __sched io_schedule_timeout(long timeout)
 {
-        struct rq *rq = raw_rq();
+        int old_iowait = current->in_iowait;
+        struct rq *rq;
         long ret;
 
+        current->in_iowait = 1;
+        if (old_iowait)
+                blk_schedule_flush_plug(current);
+        else
+                blk_flush_plug(current);
+
         delayacct_blkio_start();
+        rq = raw_rq();
         atomic_inc(&rq->nr_iowait);
-        blk_flush_plug(current);
-        current->in_iowait = 1;
         ret = schedule_timeout(timeout);
-        current->in_iowait = 0;
+        current->in_iowait = old_iowait;
         atomic_dec(&rq->nr_iowait);
         delayacct_blkio_end();
+
         return ret;
 }
+EXPORT_SYMBOL(io_schedule_timeout);
 
 /**
  * sys_sched_get_priority_max - return maximum RT priority.
@@ -7642,6 +7575,12 @@ static inline int tg_has_rt_tasks(struct task_group *tg)
 {