Merge branch 'sched/locking' into sched/core

Merge reason: the rq locking changes are stable,
              propagate them into the .40 queue.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 353 insertions, 297 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 506cb81..0cfe031 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -312,6 +312,9 @@ struct cfs_rq {
 
 	u64 exec_clock;
 	u64 min_vruntime;
+#ifndef CONFIG_64BIT
+	u64 min_vruntime_copy;
+#endif
 
 	struct rb_root tasks_timeline;
 	struct rb_node *rb_leftmost;
@@ -554,6 +557,10 @@ struct rq {
 	unsigned int ttwu_count;
 	unsigned int ttwu_local;
 #endif
+
+#ifdef CONFIG_SMP
+	struct task_struct *wake_list;
+#endif
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
@@ -597,7 +604,7 @@ static inline int cpu_of(struct rq *rq)
  * Return the group to which this tasks belongs.
  *
  * We use task_subsys_state_check() and extend the RCU verification
- * with lockdep_is_held(&task_rq(p)->lock) because cpu_cgroup_attach()
+ * with lockdep_is_held(&p->pi_lock) because cpu_cgroup_attach()
  * holds that lock for each task it moves into the cgroup. Therefore
  * by holding that lock, we pin the task to the current cgroup.
  */
@@ -607,7 +614,7 @@ static inline struct task_group *task_group(struct task_struct *p)
 	struct cgroup_subsys_state *css;
 
 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
-			lockdep_is_held(&task_rq(p)->lock));
+			lockdep_is_held(&p->pi_lock));
 	tg = container_of(css, struct task_group, css);
 
 	return autogroup_task_group(p, tg);
@@ -839,18 +846,39 @@ static inline int task_current(struct rq *rq, struct task_struct *p)
 	return rq->curr == p;
 }
 
-#ifndef __ARCH_WANT_UNLOCKED_CTXSW
 static inline int task_running(struct rq *rq, struct task_struct *p)
 {
+#ifdef CONFIG_SMP
+	return p->on_cpu;
+#else
 	return task_current(rq, p);
+#endif
 }
 
+#ifndef __ARCH_WANT_UNLOCKED_CTXSW
 static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
 {
+#ifdef CONFIG_SMP
+	/*
+	 * We can optimise this out completely for !SMP, because the
+	 * SMP rebalancing from interrupt is the only thing that cares
+	 * here.
+	 */
+	next->on_cpu = 1;
+#endif
 }
 
 static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 {
+#ifdef CONFIG_SMP
+	/*
+	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
+	 * We must ensure this doesn't happen until the switch is completely
+	 * finished.
+	 */
+	smp_wmb();
+	prev->on_cpu = 0;
+#endif
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */
 	rq->lock.owner = current;
@@ -866,15 +894,6 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 }
 
 #else /* __ARCH_WANT_UNLOCKED_CTXSW */
-static inline int task_running(struct rq *rq, struct task_struct *p)
-{
-#ifdef CONFIG_SMP
-	return p->oncpu;
-#else
-	return task_current(rq, p);
-#endif
-}
-
 static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
 {
 #ifdef CONFIG_SMP
@@ -883,7 +902,7 @@ static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
 	 * SMP rebalancing from interrupt is the only thing that cares
 	 * here.
 	 */
-	next->oncpu = 1;
+	next->on_cpu = 1;
 #endif
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
 	raw_spin_unlock_irq(&rq->lock);
@@ -896,12 +915,12 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 {
 #ifdef CONFIG_SMP
 	/*
-	 * After ->oncpu is cleared, the task can be moved to a different CPU.
+	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
 	 * We must ensure this doesn't happen until the switch is completely
 	 * finished.
 	 */
 	smp_wmb();
-	prev->oncpu = 0;
+	prev->on_cpu = 0;
 #endif
 #ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
 	local_irq_enable();
@@ -910,23 +929,15 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 #endif /* __ARCH_WANT_UNLOCKED_CTXSW */
 
 /*
- * Check whether the task is waking, we use this to synchronize ->cpus_allowed
- * against ttwu().
- */
-static inline int task_is_waking(struct task_struct *p)
-{
-	return unlikely(p->state == TASK_WAKING);
-}
-
-/*
- * __task_rq_lock - lock the runqueue a given task resides on.
- * Must be called interrupts disabled.
+ * __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);
@@ -937,22 +948,22 @@ static inline struct rq *__task_rq_lock(struct task_struct *p)
 }
 
 /*
- * task_rq_lock - lock the runqueue a given task resides on and disable
- * interrupts. Note the ordering: we can safely lookup the task_rq without
- * explicitly disabling preemption.
+ * 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 (;;) {
-		local_irq_save(*flags);
+		raw_spin_lock_irqsave(&p->pi_lock, *flags);
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
 		if (likely(rq == task_rq(p)))
 			return rq;
-		raw_spin_unlock_irqrestore(&rq->lock, *flags);
+		raw_spin_unlock(&rq->lock);
+		raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
 	}
 }
 
@@ -962,10 +973,13 @@ static void __task_rq_unlock(struct rq *rq)
 	raw_spin_unlock(&rq->lock);
 }
 
-static inline void task_rq_unlock(struct rq *rq, unsigned long *flags)
+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_irqrestore(&rq->lock, *flags);
+	raw_spin_unlock(&rq->lock);
+	raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
 }
 
 /*
@@ -1774,7 +1788,6 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 	update_rq_clock(rq);
 	sched_info_queued(p);
 	p->sched_class->enqueue_task(rq, p, flags);
-	p->se.on_rq = 1;
 }
 
 static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
@@ -1782,7 +1795,6 @@ static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 	update_rq_clock(rq);
 	sched_info_dequeued(p);
 	p->sched_class->dequeue_task(rq, p, flags);
-	p->se.on_rq = 0;
 }
 
 /*
@@ -2117,7 +2129,7 @@ static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 	 * A queue event has occurred, and we're going to schedule.  In
 	 * this case, we can save a useless back to back clock update.
 	 */
-	if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr))
+	if (rq->curr->on_rq && test_tsk_need_resched(rq->curr))
 		rq->skip_clock_update = 1;
 }
 
@@ -2163,6 +2175,11 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 */
 	WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
 			!(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
+
+#ifdef CONFIG_LOCKDEP
+	WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
+				      lockdep_is_held(&task_rq(p)->lock)));
+#endif
 #endif
 
 	trace_sched_migrate_task(p, new_cpu);
@@ -2183,19 +2200,6 @@ struct migration_arg {
 static int migration_cpu_stop(void *data);
 
 /*
- * The task's runqueue lock must be held.
- * Returns true if you have to wait for migration thread.
- */
-static bool migrate_task(struct task_struct *p, struct rq *rq)
-{
-	/*
-	 * If the task is not on a runqueue (and not running), then
-	 * the next wake-up will properly place the task.
-	 */
-	return p->se.on_rq || task_running(rq, p);
-}
-
-/*
  * wait_task_inactive - wait for a thread to unschedule.
  *
  * If @match_state is nonzero, it's the @p->state value just checked and
@@ -2252,11 +2256,11 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		rq = task_rq_lock(p, &flags);
 		trace_sched_wait_task(p);
 		running = task_running(rq, p);
-		on_rq = p->se.on_rq;
+		on_rq = p->on_rq;
 		ncsw = 0;
 		if (!match_state || p->state == match_state)
 			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
-		task_rq_unlock(rq, &flags);
+		task_rq_unlock(rq, p, &flags);
 
 		/*
 		 * If it changed from the expected state, bail out now.
@@ -2331,7 +2335,7 @@ EXPORT_SYMBOL_GPL(kick_process);
 
 #ifdef CONFIG_SMP
 /*
- * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
+ * ->cpus_allowed is protected by both rq->lock and p->pi_lock
  */
 static int select_fallback_rq(int cpu, struct task_struct *p)
 {
@@ -2364,12 +2368,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 }
 
 /*
- * The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable.
+ * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
  */
 static inline
-int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags)
+int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
 {
-	int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags);
+	int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
 
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
@@ -2395,27 +2399,60 @@ static void update_avg(u64 *avg, u64 sample)
 }
 #endif
 
-static inline void ttwu_activate(struct task_struct *p, struct rq *rq,
-				 bool is_sync, bool is_migrate, bool is_local,
-				 unsigned long en_flags)
+static void
+ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 {
+#ifdef CONFIG_SCHEDSTATS
+	struct rq *rq = this_rq();
+
+#ifdef CONFIG_SMP
+	int this_cpu = smp_processor_id();
+
+	if (cpu == this_cpu) {
+		schedstat_inc(rq, ttwu_local);
+		schedstat_inc(p, se.statistics.nr_wakeups_local);
+	} else {
+		struct sched_domain *sd;
+
+		schedstat_inc(p, se.statistics.nr_wakeups_remote);
+		for_each_domain(this_cpu, sd) {
+			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
+				schedstat_inc(sd, ttwu_wake_remote);
+				break;
+			}
+		}
+	}
+#endif /* CONFIG_SMP */
+
+	schedstat_inc(rq, ttwu_count);
 	schedstat_inc(p, se.statistics.nr_wakeups);
-	if (is_sync)
+
+	if (wake_flags & WF_SYNC)
 		schedstat_inc(p, se.statistics.nr_wakeups_sync);
-	if (is_migrate)
+
+	if (cpu != task_cpu(p))
 		schedstat_inc(p, se.statistics.nr_wakeups_migrate);
-	if (is_local)
-		schedstat_inc(p, se.statistics.nr_wakeups_local);
-	else
-		schedstat_inc(p, se.statistics.nr_wakeups_remote);
 
+#endif /* CONFIG_SCHEDSTATS */
+}
+
+static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
+{
 	activate_task(rq, p, en_flags);
+	p->on_rq = 1;
+
+	/* if a worker is waking up, notify workqueue */
+	if (p->flags & PF_WQ_WORKER)
+		wq_worker_waking_up(p, cpu_of(rq));
 }
 
-static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq,
-					int wake_flags, bool success)
+/*
+ * Mark the task runnable and perform wakeup-preemption.
+ */
+static void
+ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 {
-	trace_sched_wakeup(p, success);
+	trace_sched_wakeup(p, true);
 	check_preempt_curr(rq, p, wake_flags);
 
 	p->state = TASK_RUNNING;
@@ -2434,9 +2471,99 @@ static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq,
 		rq->idle_stamp = 0;
 	}
 #endif
-	/* if a worker is waking up, notify workqueue */
-	if ((p->flags & PF_WQ_WORKER) && success)
-		wq_worker_waking_up(p, cpu_of(rq));
+}
+
+static void
+ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags)
+{
+#ifdef CONFIG_SMP
+	if (p->sched_contributes_to_load)
+		rq->nr_uninterruptible--;
+#endif
+
+	ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING);
+	ttwu_do_wakeup(rq, p, wake_flags);
+}
+
+/*
+ * Called in case the task @p isn't fully descheduled from its runqueue,
+ * in this case we must do a remote wakeup. Its a 'light' wakeup though,
+ * since all we need to do is flip p->state to TASK_RUNNING, since
+ * the task is still ->on_rq.
+ */
+static int ttwu_remote(struct task_struct *p, int wake_flags)
+{
+	struct rq *rq;
+	int ret = 0;
+
+	rq = __task_rq_lock(p);
+	if (p->on_rq) {
+		ttwu_do_wakeup(rq, p, wake_flags);
+		ret = 1;
+	}
+	__task_rq_unlock(rq);
+
+	return ret;
+}
+
+#ifdef CONFIG_SMP
+static void sched_ttwu_pending(void)
+{
+	struct rq *rq = this_rq();
+	struct task_struct *list = xchg(&rq->wake_list, NULL);
+
+	if (!list)
+		return;
+
+	raw_spin_lock(&rq->lock);
+
+	while (list) {
+		struct task_struct *p = list;
+		list = list->wake_entry;
+		ttwu_do_activate(rq, p, 0);
+	}
+
+	raw_spin_unlock(&rq->lock);
+}
+
+void scheduler_ipi(void)
+{
+	sched_ttwu_pending();
+}
+
+static void ttwu_queue_remote(struct task_struct *p, int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	struct task_struct *next = rq->wake_list;
+
+	for (;;) {
+		struct task_struct *old = next;
+
+		p->wake_entry = next;
+		next = cmpxchg(&rq->wake_list, old, p);
+		if (next == old)
+			break;
+	}
+
+	if (!next)
+		smp_send_reschedule(cpu);
+}
+#endif
+
+static void ttwu_queue(struct task_struct *p, int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+
+#if defined(CONFIG_SMP) && defined(CONFIG_SCHED_TTWU_QUEUE)
+	if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) {
+		ttwu_queue_remote(p, cpu);
+		return;
+	}
+#endif
+
+	raw_spin_lock(&rq->lock);
+	ttwu_do_activate(rq, p, 0);
+	raw_spin_unlock(&rq->lock);
 }
 
 /**
@@ -2454,92 +2581,64 @@ static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq,
  * Returns %true if @p was woken up, %false if it was already running
  * or @state didn't match @p's state.
  */
-static int try_to_wake_up(struct task_struct *p, unsigned int state,
-			  int wake_flags)
+static int
+try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 {
-	int cpu, orig_cpu, this_cpu, success = 0;
 	unsigned long flags;
-	unsigned long en_flags = ENQUEUE_WAKEUP;
-	struct rq *rq;
-
-	this_cpu = get_cpu();
+	int cpu, success = 0;
 
 	smp_wmb();
-	rq = task_rq_lock(p, &flags);
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	if (!(p->state & state))
 		goto out;
 
-	if (p->se.on_rq)
-		goto out_running;
-
+	success = 1; /* we're going to change ->state */
 	cpu = task_cpu(p);
-	orig_cpu = cpu;
 
-#ifdef CONFIG_SMP
-	if (unlikely(task_running(rq, p)))
-		goto out_activate;
+	if (p->on_rq && ttwu_remote(p, wake_flags))
+		goto stat;
 
+#ifdef CONFIG_SMP
 	/*
-	 * In order to handle concurrent wakeups and release the rq->lock
-	 * we put the task in TASK_WAKING state.
-	 *
-	 * First fix up the nr_uninterruptible count:
+	 * If the owning (remote) cpu is still in the middle of schedule() with
+	 * this task as prev, wait until its done referencing the task.
 	 */
-	if (task_contributes_to_load(p)) {
-		if (likely(cpu_online(orig_cpu)))
-			rq->nr_uninterruptible--;
-		else
-			this_rq()->nr_uninterruptible--;
-	}
-	p->state = TASK_WAKING;
-
-	if (p->sched_class->task_waking) {
-		p->sched_class->task_waking(rq, p);
-		en_flags |= ENQUEUE_WAKING;
+	while (p->on_cpu) {
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+		/*
+		 * If called from interrupt context we could have landed in the
+		 * middle of schedule(), in this case we should take care not
+		 * to spin on ->on_cpu if p is current, since that would
+		 * deadlock.
+		 */
+		if (p == current) {
+			ttwu_queue(p, cpu);
+			goto stat;
+		}
+#endif
+		cpu_relax();
 	}
-
-	cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags);
-	if (cpu != orig_cpu)
-		set_task_cpu(p, cpu);
-	__task_rq_unlock(rq);
-
-	rq = cpu_rq(cpu);
-	raw_spin_lock(&rq->lock);
-
 	/*
-	 * We migrated the task without holding either rq->lock, however
-	 * since the task is not on the task list itself, nobody else
-	 * will try and migrate the task, hence the rq should match the
-	 * cpu we just moved it to.
+	 * Pairs with the smp_wmb() in finish_lock_switch().
 	 */
-	WARN_ON(task_cpu(p) != cpu);
-	WARN_ON(p->state != TASK_WAKING);
+	smp_rmb();
 
-#ifdef CONFIG_SCHEDSTATS
-	schedstat_inc(rq, ttwu_count);
-	if (cpu == this_cpu)
-		schedstat_inc(rq, ttwu_local);
-	else {
-		struct sched_domain *sd;
-		for_each_domain(this_cpu, sd) {
-			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
-				schedstat_inc(sd, ttwu_wake_remote);
-				break;
-			}
-		}
-	}
-#endif /* CONFIG_SCHEDSTATS */
+	p->sched_contributes_to_load = !!task_contributes_to_load(p);
+	p->state = TASK_WAKING;
 
-out_activate:
+	if (p->sched_class->task_waking)
+		p->sched_class->task_waking(p);
+
+	cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
+	if (task_cpu(p) != cpu)
+		set_task_cpu(p, cpu);
 #endif /* CONFIG_SMP */
-	ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu,
-		      cpu == this_cpu, en_flags);
-	success = 1;
-out_running:
-	ttwu_post_activation(p, rq, wake_flags, success);
+
+	ttwu_queue(p, cpu);
+stat:
+	ttwu_stat(p, cpu, wake_flags);
 out:
-	task_rq_unlock(rq, &flags);
-	put_cpu();
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 	return success;
 }
@@ -2548,31 +2647,34 @@ out:
  * try_to_wake_up_local - try to wake up a local task with rq lock held
  * @p: the thread to be awakened
  *
- * Put @p on the run-queue if it's not already there.  The caller must
+ * Put @p on the run-queue if it's not already there. The caller must
  * ensure that this_rq() is locked, @p is bound to this_rq() and not
- * the current task.  this_rq() stays locked over invocation.
+ * the current task.
  */
 static void try_to_wake_up_local(struct task_struct *p)
 {
 	struct rq *rq = task_rq(p);
-	bool success = false;
 
 	BUG_ON(rq != this_rq());
 	BUG_ON(p == current);
 	lockdep_assert_held(&rq->lock);
 
+	if (!raw_spin_trylock(&p->pi_lock)) {
+		raw_spin_unlock(&rq->lock);
+		raw_spin_lock(&p->pi_lock);
+		raw_spin_lock(&rq->lock);
+	}
+
 	if (!(p->state & TASK_NORMAL))
-		return;
+		goto out;
 
-	if (!p->se.on_rq) {
-		if (likely(!task_running(rq, p))) {
-			schedstat_inc(rq, ttwu_count);
-			schedstat_inc(rq, ttwu_local);
-		}
-		ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP);
-		success = true;
-	}
-	ttwu_post_activation(p, rq, 0, success);
+	if (!p->on_rq)
+		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+
+	ttwu_do_wakeup(rq, p, 0);
+	ttwu_stat(p, smp_processor_id(), 0);
+out:
+	raw_spin_unlock(&p->pi_lock);
 }
 
 /**
@@ -2605,19 +2707,21 @@ int wake_up_state(struct task_struct *p, unsigned int state)
  */
 static void __sched_fork(struct task_struct *p)
 {
+	p->on_rq			= 0;
+
+	p->se.on_rq			= 0;
 	p->se.exec_start		= 0;
 	p->se.sum_exec_runtime		= 0;
 	p->se.prev_sum_exec_runtime	= 0;
 	p->se.nr_migrations		= 0;
 	p->se.vruntime			= 0;
+	INIT_LIST_HEAD(&p->se.group_node);
 
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 
 	INIT_LIST_HEAD(&p->rt.run_list);
-	p->se.on_rq = 0;
-	INIT_LIST_HEAD(&p->se.group_node);
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
@@ -2629,6 +2733,7 @@ static void __sched_fork(struct task_struct *p)
  */
 void sched_fork(struct task_struct *p, int clone_flags)
 {
+	unsigned long flags;
 	int cpu = get_cpu();
 
 	__sched_fork(p);
@@ -2679,16 +2784,16 @@ void sched_fork(struct task_struct *p, int clone_flags)
 	 *
 	 * Silence PROVE_RCU.
 	 */
-	rcu_read_lock();
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	set_task_cpu(p, cpu);
-	rcu_read_unlock();
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 	if (likely(sched_info_on()))
 		memset(&p->sched_info, 0, sizeof(p->sched_info));
 #endif
-#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
-	p->oncpu = 0;
+#if defined(CONFIG_SMP)
+	p->on_cpu = 0;
 #endif
 #ifdef CONFIG_PREEMPT
 	/* Want to start with kernel preemption disabled. */
@@ -2712,37 +2817,27 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 {
 	unsigned long flags;
 	struct rq *rq;
-	int cpu __maybe_unused = get_cpu();
 
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
 #ifdef CONFIG_SMP
-	rq = task_rq_lock(p, &flags);
-	p->state = TASK_WAKING;
-
 	/*
 	 * Fork balancing, do it here and not earlier because:
 	 *  - cpus_allowed can change in the fork path
 	 *  - any previously selected cpu might disappear through hotplug
-	 *
-	 * We set TASK_WAKING so that select_task_rq() can drop rq->lock
-	 * without people poking at ->cpus_allowed.
 	 */
-	cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0);
-	set_task_cpu(p, cpu);
-
-	p->state = TASK_RUNNING;
-	task_rq_unlock(rq, &flags);
+	set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0));
 #endif
 
-	rq = task_rq_lock(p, &flags);
+	rq = __task_rq_lock(p);
 	activate_task(rq, p, 0);
-	trace_sched_wakeup_new(p, 1);
+	p->on_rq = 1;
+	trace_sched_wakeup_new(p, true);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken)
 		p->sched_class->task_woken(rq, p);
 #endif
-	task_rq_unlock(rq, &flags);
-	put_cpu();
+	task_rq_unlock(rq, p, &flags);
 }
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -3451,27 +3546,22 @@ void sched_exec(void)
 {
 	struct task_struct *p = current;
 	unsigned long flags;
-	struct rq *rq;
 	int dest_cpu;
 
-	rq = task_rq_lock(p, &flags);
-	dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0);
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0);
 	if (dest_cpu == smp_processor_id())
 		goto unlock;
 
-	/*
-	 * select_task_rq() can race against ->cpus_allowed
-	 */
-	if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
-	    likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) {
+	if (likely(cpu_active(dest_cpu))) {
 		struct migration_arg arg = { p, dest_cpu };
 
-		task_rq_unlock(rq, &flags);
-		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
+		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+		stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
 		return;
 	}
 unlock:
-	task_rq_unlock(rq, &flags);
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 }
 
 #endif
@@ -3508,7 +3598,7 @@ unsigned long long task_delta_exec(struct task_struct *p)
 
 	rq = task_rq_lock(p, &flags);
 	ns = do_task_delta_exec(p, rq);
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, p, &flags);
 
 	return ns;
 }
@@ -3526,7 +3616,7 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 
 	rq = task_rq_lock(p, &flags);
 	ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq);
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, p, &flags);
 
 	return ns;
 }
@@ -3550,7 +3640,7 @@ unsigned long long thread_group_sched_runtime(struct task_struct *p)
 	rq = task_rq_lock(p, &flags);
 	thread_group_cputime(p, &totals);
 	ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq);
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, p, &flags);
 
 	return ns;
 }
@@ -4036,7 +4126,7 @@ static inline void schedule_debug(struct task_struct *prev)
 
 static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
-	if (prev->se.on_rq)
+	if (prev->on_rq)
 		update_rq_clock(rq);
 	prev->sched_class->put_prev_task(rq, prev);
 }
@@ -4098,11 +4188,13 @@ need_resched:
 		if (unlikely(signal_pending_state(prev->state, prev))) {
 			prev->state = TASK_RUNNING;
 		} else {
+			deactivate_task(rq, prev, DEQUEUE_SLEEP);
+			prev->on_rq = 0;
+
 			/*
-			 * If a worker is going to sleep, notify and
-			 * ask workqueue whether it wants to wake up a
-			 * task to maintain concurrency.  If so, wake
-			 * up the task.
+			 * If a worker went to sleep, notify and ask workqueue
+			 * whether it wants to wake up a task to maintain
+			 * concurrency.
 			 */
 			if (prev->flags & PF_WQ_WORKER) {
 				struct task_struct *to_wakeup;
@@ -4111,21 +4203,20 @@ need_resched:
 				if (to_wakeup)
 					try_to_wake_up_local(to_wakeup);
 			}
-			deactivate_task(rq, prev, DEQUEUE_SLEEP);
+
+			/*
+			 * If we are going to sleep and we have plugged IO
+			 * queued, make sure to submit it to avoid deadlocks.
+			 */
+			if (blk_needs_flush_plug(prev)) {
+				raw_spin_unlock(&rq->lock);
+				blk_flush_plug(prev);
+				raw_spin_lock(&rq->lock);
+			}
 		}
 		switch_count = &prev->nvcsw;
 	}
 
-	/*
-	 * If we are going to sleep and we have plugged IO queued, make
-	 * sure to submit it to avoid deadlocks.
-	 */
-	if (prev->state != TASK_RUNNING && blk_needs_flush_plug(prev)) {
-		raw_spin_unlock(&rq->lock);
-		blk_flush_plug(prev);
-		raw_spin_lock(&rq->lock);
-	}
-
 	pre_schedule(rq, prev);
 
 	if (unlikely(!rq->nr_running))
@@ -4162,70 +4253,53 @@ need_resched:
 EXPORT_SYMBOL(schedule);
 
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-/*
- * Look out! "owner" is an entirely speculative pointer
- * access and not reliable.
- */
-int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
-{
-	unsigned int cpu;
-	struct rq *rq;
 
-	if (!sched_feat(OWNER_SPIN))
-		return 0;
+static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
+{
+	bool ret = false;
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	/*
-	 * Need to access the cpu field knowing that
-	 * DEBUG_PAGEALLOC could have unmapped it if
-	 * the mutex owner just released it and exited.
-	 */
-	if (probe_kernel_address(&owner->cpu, cpu))
-		return 0;
-#else
-	cpu = owner->cpu;
-#endif
+	rcu_read_lock();
+	if (lock->owner != owner)
+		goto fail;
 
 	/*
-	 * Even if the access succeeded (likely case),
-	 * the cpu field may no longer be valid.
+	 * Ensure we emit the owner->on_cpu, dereference _after_ checking
+	 * lock->owner still matches owner, if that fails, owner might
+	 * point to free()d memory, if it still matches, the rcu_read_lock()
+	 * ensures the memory stays valid.
 	 */
-	if (cpu >= nr_cpumask_bits)
-		return 0;
+	barrier();
 
-	/*
-	 * We need to validate that we can do a
-	 * get_cpu() and that we have the percpu area.
-	 */
-	if (!cpu_online(cpu))
-		return 0;
+	ret = owner->on_cpu;
+fail:
+	rcu_read_unlock();
 
-	rq = cpu_rq(cpu);
+	return ret;
+}
 
-	for (;;) {
-		/*
-		 * Owner changed, break to re-assess state.
-		 */
-		if (lock->owner != owner) {
-			/*
-			 * If the lock has switched to a different owner,
-			 * we likely have heavy contention. Return 0 to quit
-			 * optimistic spinning and not contend further:
-			 */
-			if (lock->owner)
-				return 0;
-			break;
-		}
+/*
+ * Look out! "owner" is an entirely speculative pointer
+ * access and not reliable.
+ */
+int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
+{
+	if (!sched_feat(OWNER_SPIN))
+		return 0;
 
-		/*
-		 * Is that owner really running on that cpu?
-		 */
-		if (task_thread_info(rq->curr) != owner || need_resched())
+	while (owner_running(lock, owner)) {
+		if (need_resched())
 			return 0;
 
 		arch_mutex_cpu_relax();
 	}
 
+	/*
+	 * If the owner changed to another task there is likely
+	 * heavy contention, stop spinning.
+	 */
+	if (lock->owner)
+		return 0;
+
 	return 1;
 }
 #endif
@@ -4685,19 +4759,18 @@ EXPORT_SYMBOL(sleep_on_timeout);
  */
 void rt_mutex_setprio(struct task_struct *p, int prio)
 {
-	unsigned long flags;
 	int oldprio, on_rq, running;
 	struct rq *rq;
 	const struct sched_class *prev_class;
 
 	BUG_ON(prio < 0 || prio > MAX_PRIO);
 
-	rq = task_rq_lock(p, &flags);
+	rq = __task_rq_lock(p);
 
 	trace_sched_pi_setprio(p, prio);
 	oldprio = p->prio;
 	prev_class = p->sched_class;
-	on_rq = p->se.on_rq;
+	on_rq = p->on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
 		dequeue_task(rq, p, 0);
@@ -4717,7 +4790,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 		enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
 
 	check_class_changed(rq, p, prev_class, oldprio);
-	task_rq_unlock(rq, &flags);
+	__task_rq_unlock(rq);
 }
 
 #endif
@@ -4745,7 +4818,7 @@ void set_user_nice(struct task_struct *p, long nice)
 		p->static_prio = NICE_TO_PRIO(nice);
 		goto out_unlock;
 	}
-	on_rq = p->se.on_rq;
+	on_rq = p->on_rq;
 	if (on_rq)
 		dequeue_task(rq, p, 0);
 
@@ -4765,7 +4838,7 @@ void set_user_nice(struct task_struct *p, long nice)
 			resched_task(rq->curr);
 	}
 out_unlock:
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, p, &flags);
 }
 EXPORT_SYMBOL(set_user_nice);
 
@@ -4879,8 +4952,6 @@ static struct task_struct *find_process_by_pid(pid_t pid)
 static void
 __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
 {
-	BUG_ON(p->se.on_rq);
-
 	p->policy = policy;
 	p->rt_priority = prio;
 	p->normal_prio = normal_prio(p);
@@ -4995,20 +5066,17 @@ recheck:
 	/*
 	 * make sure no PI-waiters arrive (or leave) while we are
 	 * changing the priority of the task:
-	 */
-	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	/*
+	 *
 	 * To be able to change p->policy safely, the appropriate
 	 * runqueue lock must be held.
 	 */
-	rq = __task_rq_lock(p);
+	rq = task_rq_lock(p, &flags);
 
 	/*
 	 * Changing the policy of the stop threads its a very bad idea
 	 */
 	if (p == rq->stop) {
-		__task_rq_unlock(rq);
-		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+		task_rq_unlock(rq, p, &flags);
 		return -EINVAL;
 	}
 
@@ -5032,8 +5100,7 @@ recheck:
 		if (rt_bandwidth_enabled() && rt_policy(policy) &&
 				task_group(p)->rt_bandwidth.rt_runtime == 0 &&
 				!task_group_is_autogroup(task_group(p))) {
-			__task_rq_unlock(rq);
-			raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+			task_rq_unlock(rq, p, &flags);
 			return -EPERM;
 		}
 	}
@@ -5042,11 +5109,10 @@ recheck:
 	/* recheck policy now with rq lock held */
 	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
 		policy = oldpolicy = -1;
-		__task_rq_unlock(rq);
-		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+		task_rq_unlock(rq, p, &flags);
 		goto recheck;
 	}
-	on_rq = p->se.on_rq;
+	on_rq = p->on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
 		deactivate_task(rq, p, 0);
@@ -5065,8 +5131,7 @@ recheck:
 		activate_task(rq, p, 0);
 
 	check_class_changed(rq, p, prev_class, oldprio);
-	__task_rq_unlock(rq);
-	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+	task_rq_unlock(rq, p, &flags);
 
 	rt_mutex_adjust_pi(p);
 
@@ -5317,7 +5382,6 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
 {
 	struct task_struct *p;
 	unsigned long flags;
-	struct rq *rq;
 	int retval;
 
 	get_online_cpus();
@@ -5332,9 +5396,9 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
 	if (retval)
 		goto out_unlock;
 
-	rq = task_rq_lock(p, &flags);
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);
-	task_rq_unlock(rq, &flags);
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 out_unlock:
 	rcu_read_unlock();
@@ -5659,7 +5723,7 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
 
 	rq = task_rq_lock(p, &flags);
 	time_slice = p->sched_class->get_rr_interval(rq, p);
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, p, &flags);
 
 	rcu_read_unlock();
 	jiffies_to_timespec(time_slice, &t);
@@ -5777,8 +5841,8 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	rcu_read_unlock();
 
 	rq->curr = rq->idle = idle;
-#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
-	idle->oncpu = 1;
+#if defined(CONFIG_SMP)
+	idle->on_cpu = 1;
 #endif
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 
@@ -5882,18 +5946,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 	unsigned int dest_cpu;
 	int ret = 0;
 
-	/*
-	 * Serialize against TASK_WAKING so that ttwu() and wunt() can
-	 * drop the rq->lock and still rely on ->cpus_allowed.
-	 */
-again:
-	while (task_is_waking(p))
-		cpu_relax();
 	rq = task_rq_lock(p, &flags);
-	if (task_is_waking(p)) {
-		task_rq_unlock(rq, &flags);
-		goto again;
-	}
 
 	if (!cpumask_intersects(new_mask, cpu_active_mask)) {
 		ret = -EINVAL;
@@ -5918,16 +5971,16 @@ again:
 		goto out;
 
 	dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
-	if (migrate_task(p, rq)) {
+	if (p->on_rq) {
 		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */
-		task_rq_unlock(rq, &flags);
+		task_rq_unlock(rq, p, &flags);
 		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
 		tlb_migrate_finish(p->mm);
 		return 0;
 	}
 out:
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, p, &flags);
 
 	return ret;
 }
@@ -5955,6 +6008,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
 	rq_src = cpu_rq(src_cpu);
 	rq_dest = cpu_rq(dest_cpu);
 
+	raw_spin_lock(&p->pi_lock);
 	double_rq_lock(rq_src, rq_dest);
 	/* Already moved. */
 	if (task_cpu(p) != src_cpu)
@@ -5967,7 +6021,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
 	 * If we're not on a rq, the next wake-up will ensure we're
 	 * placed properly.
 	 */
-	if (p->se.on_rq) {
+	if (p->on_rq) {
 		deactivate_task(rq_src, p, 0);
 		set_task_cpu(p, dest_cpu);
 		activate_task(rq_dest, p, 0);
@@ -5977,6 +6031,7 @@ done:
 	ret = 1;
 fail:
 	double_rq_unlock(rq_src, rq_dest);
+	raw_spin_unlock(&p->pi_lock);
 	return ret;
 }
 
@@ -6317,6 +6372,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_DYING:
+		sched_ttwu_pending();
 		/* Update our root-domain */
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
@@ -7961,7 +8017,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 	int old_prio = p->prio;
 	int on_rq;
 
-	on_rq = p->se.on_rq;
+	on_rq = p->on_rq;
 	if (on_rq)
 		deactivate_task(rq, p, 0);
 	__setscheduler(rq, p, SCHED_NORMAL, 0);
@@ -8304,7 +8360,7 @@ void sched_move_task(struct task_struct *tsk)
 	rq = task_rq_lock(tsk, &flags);
 
 	running = task_current(rq, tsk);
-	on_rq = tsk->se.on_rq;
+	on_rq = tsk->on_rq;
 
 	if (on_rq)
 		dequeue_task(rq, tsk, 0);
@@ -8323,7 +8379,7 @@ void sched_move_task(struct task_struct *tsk)
 	if (on_rq)
 		enqueue_task(rq, tsk, 0);
 
-	task_rq_unlock(rq, &flags);
+	task_rq_unlock(rq, tsk, &flags);
 }
 #endif /* CONFIG_CGROUP_SCHED */