1 files changed, 163 insertions, 60 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c56fb57f2991..d01f9d047397 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -102,9 +102,12 @@ void update_rq_clock(struct rq *rq)
 
 	lockdep_assert_held(&rq->lock);
 
-	if (rq->clock_skip_update & RQCF_ACT_SKIP)
+	if (rq->clock_update_flags & RQCF_ACT_SKIP)
 		return;
 
+#ifdef CONFIG_SCHED_DEBUG
+	rq->clock_update_flags |= RQCF_UPDATED;
+#endif
 	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
 	if (delta < 0)
 		return;
@@ -185,7 +188,7 @@ struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
 		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
-			rf->cookie = lockdep_pin_lock(&rq->lock);
+			rq_pin_lock(rq, rf);
 			return rq;
 		}
 		raw_spin_unlock(&rq->lock);
@@ -225,7 +228,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 		 * pair with the WMB to ensure we must then also see migrating.
 		 */
 		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
-			rf->cookie = lockdep_pin_lock(&rq->lock);
+			rq_pin_lock(rq, rf);
 			return rq;
 		}
 		raw_spin_unlock(&rq->lock);
@@ -1195,9 +1198,9 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		 * OK, since we're going to drop the lock immediately
 		 * afterwards anyway.
 		 */
-		lockdep_unpin_lock(&rq->lock, rf.cookie);
+		rq_unpin_lock(rq, &rf);
 		rq = move_queued_task(rq, p, dest_cpu);
-		lockdep_repin_lock(&rq->lock, rf.cookie);
+		rq_repin_lock(rq, &rf);
 	}
 out:
 	task_rq_unlock(rq, p, &rf);
@@ -1690,7 +1693,7 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl
  * Mark the task runnable and perform wakeup-preemption.
  */
 static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
-			   struct pin_cookie cookie)
+			   struct rq_flags *rf)
 {
 	check_preempt_curr(rq, p, wake_flags);
 	p->state = TASK_RUNNING;
@@ -1702,9 +1705,9 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
 		 * Our task @p is fully woken up and running; so its safe to
 		 * drop the rq->lock, hereafter rq is only used for statistics.
 		 */
-		lockdep_unpin_lock(&rq->lock, cookie);
+		rq_unpin_lock(rq, rf);
 		p->sched_class->task_woken(rq, p);
-		lockdep_repin_lock(&rq->lock, cookie);
+		rq_repin_lock(rq, rf);
 	}
 
 	if (rq->idle_stamp) {
@@ -1723,7 +1726,7 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
 
 static void
 ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
-		 struct pin_cookie cookie)
+		 struct rq_flags *rf)
 {
 	int en_flags = ENQUEUE_WAKEUP;
 
@@ -1738,7 +1741,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 #endif
 
 	ttwu_activate(rq, p, en_flags);
-	ttwu_do_wakeup(rq, p, wake_flags, cookie);
+	ttwu_do_wakeup(rq, p, wake_flags, rf);
 }
 
 /*
@@ -1757,7 +1760,7 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
 	if (task_on_rq_queued(p)) {
 		/* check_preempt_curr() may use rq clock */
 		update_rq_clock(rq);
-		ttwu_do_wakeup(rq, p, wake_flags, rf.cookie);
+		ttwu_do_wakeup(rq, p, wake_flags, &rf);
 		ret = 1;
 	}
 	__task_rq_unlock(rq, &rf);
@@ -1770,15 +1773,15 @@ void sched_ttwu_pending(void)
 {
 	struct rq *rq = this_rq();
 	struct llist_node *llist = llist_del_all(&rq->wake_list);
-	struct pin_cookie cookie;
 	struct task_struct *p;
 	unsigned long flags;
+	struct rq_flags rf;
 
 	if (!llist)
 		return;
 
 	raw_spin_lock_irqsave(&rq->lock, flags);
-	cookie = lockdep_pin_lock(&rq->lock);
+	rq_pin_lock(rq, &rf);
 
 	while (llist) {
 		int wake_flags = 0;
@@ -1789,10 +1792,10 @@ void sched_ttwu_pending(void)
 		if (p->sched_remote_wakeup)
 			wake_flags = WF_MIGRATED;
 
-		ttwu_do_activate(rq, p, wake_flags, cookie);
+		ttwu_do_activate(rq, p, wake_flags, &rf);
 	}
 
-	lockdep_unpin_lock(&rq->lock, cookie);
+	rq_unpin_lock(rq, &rf);
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 
@@ -1881,7 +1884,7 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
 static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 {
 	struct rq *rq = cpu_rq(cpu);
-	struct pin_cookie cookie;
+	struct rq_flags rf;
 
 #if defined(CONFIG_SMP)
 	if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
@@ -1892,9 +1895,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 #endif
 
 	raw_spin_lock(&rq->lock);
-	cookie = lockdep_pin_lock(&rq->lock);
-	ttwu_do_activate(rq, p, wake_flags, cookie);
-	lockdep_unpin_lock(&rq->lock, cookie);
+	rq_pin_lock(rq, &rf);
+	ttwu_do_activate(rq, p, wake_flags, &rf);
+	rq_unpin_lock(rq, &rf);
 	raw_spin_unlock(&rq->lock);
 }
 
@@ -2086,11 +2089,24 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	p->sched_contributes_to_load = !!task_contributes_to_load(p);
 	p->state = TASK_WAKING;
 
+	if (p->in_iowait) {
+		delayacct_blkio_end();
+		atomic_dec(&task_rq(p)->nr_iowait);
+	}
+
 	cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
 	if (task_cpu(p) != cpu) {
 		wake_flags |= WF_MIGRATED;
 		set_task_cpu(p, cpu);
 	}
+
+#else /* CONFIG_SMP */
+
+	if (p->in_iowait) {
+		delayacct_blkio_end();
+		atomic_dec(&task_rq(p)->nr_iowait);
+	}
+
 #endif /* CONFIG_SMP */
 
 	ttwu_queue(p, cpu, wake_flags);
@@ -2111,7 +2127,7 @@ out:
  * ensure that this_rq() is locked, @p is bound to this_rq() and not
  * the current task.
  */
-static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie)
+static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
 {
 	struct rq *rq = task_rq(p);
 
@@ -2128,11 +2144,11 @@ static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie
 		 * disabled avoiding further scheduler activity on it and we've
 		 * not yet picked a replacement task.
 		 */
-		lockdep_unpin_lock(&rq->lock, cookie);
+		rq_unpin_lock(rq, rf);
 		raw_spin_unlock(&rq->lock);
 		raw_spin_lock(&p->pi_lock);
 		raw_spin_lock(&rq->lock);
-		lockdep_repin_lock(&rq->lock, cookie);
+		rq_repin_lock(rq, rf);
 	}
 
 	if (!(p->state & TASK_NORMAL))
@@ -2140,10 +2156,15 @@ static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie
 
 	trace_sched_waking(p);
 
-	if (!task_on_rq_queued(p))
+	if (!task_on_rq_queued(p)) {
+		if (p->in_iowait) {
+			delayacct_blkio_end();
+			atomic_dec(&rq->nr_iowait);
+		}
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+	}
 
-	ttwu_do_wakeup(rq, p, 0, cookie);
+	ttwu_do_wakeup(rq, p, 0, rf);
 	ttwu_stat(p, smp_processor_id(), 0);
 out:
 	raw_spin_unlock(&p->pi_lock);
@@ -2578,6 +2599,7 @@ void wake_up_new_task(struct task_struct *p)
 	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 	rq = __task_rq_lock(p, &rf);
+	update_rq_clock(rq);
 	post_init_entity_util_avg(&p->se);
 
 	activate_task(rq, p, 0);
@@ -2590,9 +2612,9 @@ void wake_up_new_task(struct task_struct *p)
 		 * Nothing relies on rq->lock after this, so its fine to
 		 * drop it.
 		 */
-		lockdep_unpin_lock(&rq->lock, rf.cookie);
+		rq_unpin_lock(rq, &rf);
 		p->sched_class->task_woken(rq, p);
-		lockdep_repin_lock(&rq->lock, rf.cookie);
+		rq_repin_lock(rq, &rf);
 	}
 #endif
 	task_rq_unlock(rq, p, &rf);
@@ -2861,7 +2883,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
  */
 static __always_inline struct rq *
 context_switch(struct rq *rq, struct task_struct *prev,
-	       struct task_struct *next, struct pin_cookie cookie)
+	       struct task_struct *next, struct rq_flags *rf)
 {
 	struct mm_struct *mm, *oldmm;
 
@@ -2887,13 +2909,16 @@ context_switch(struct rq *rq, struct task_struct *prev,
 		prev->active_mm = NULL;
 		rq->prev_mm = oldmm;
 	}
+
+	rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
+
 	/*
 	 * Since the runqueue lock will be released by the next
 	 * task (which is an invalid locking op but in the case
 	 * of the scheduler it's an obvious special-case), so we
 	 * do an early lockdep release here:
 	 */
-	lockdep_unpin_lock(&rq->lock, cookie);
+	rq_unpin_lock(rq, rf);
 	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
 
 	/* Here we just switch the register state and the stack. */
@@ -2949,6 +2974,36 @@ unsigned long long nr_context_switches(void)
 	return sum;
 }
 
+/*
+ * IO-wait accounting, and how its mostly bollocks (on SMP).
+ *
+ * The idea behind IO-wait account is to account the idle time that we could
+ * have spend running if it were not for IO. That is, if we were to improve the
+ * storage performance, we'd have a proportional reduction in IO-wait time.
+ *
+ * This all works nicely on UP, where, when a task blocks on IO, we account
+ * idle time as IO-wait, because if the storage were faster, it could've been
+ * running and we'd not be idle.
+ *
+ * This has been extended to SMP, by doing the same for each CPU. This however
+ * is broken.
+ *
+ * Imagine for instance the case where two tasks block on one CPU, only the one
+ * CPU will have IO-wait accounted, while the other has regular idle. Even
+ * though, if the storage were faster, both could've ran at the same time,
+ * utilising both CPUs.
+ *
+ * This means, that when looking globally, the current IO-wait accounting on
+ * SMP is a lower bound, by reason of under accounting.
+ *
+ * Worse, since the numbers are provided per CPU, they are sometimes
+ * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly
+ * associated with any one particular CPU, it can wake to another CPU than it
+ * blocked on. This means the per CPU IO-wait number is meaningless.
+ *
+ * Task CPU affinities can make all that even more 'interesting'.
+ */
+
 unsigned long nr_iowait(void)
 {
 	unsigned long i, sum = 0;
@@ -2959,6 +3014,13 @@ unsigned long nr_iowait(void)
 	return sum;
 }
 
+/*
+ * Consumers of these two interfaces, like for example the cpufreq menu
+ * governor are using nonsensical data. Boosting frequency for a CPU that has
+ * IO-wait which might not even end up running the task when it does become
+ * runnable.
+ */
+
 unsigned long nr_iowait_cpu(int cpu)
 {
 	struct rq *this = cpu_rq(cpu);
@@ -3257,31 +3319,30 @@ static inline void schedule_debug(struct task_struct *prev)
  * Pick up the highest-prio task:
  */
 static inline struct task_struct *
-pick_next_task(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
-	const struct sched_class *class = &fair_sched_class;
+	const struct sched_class *class;
 	struct task_struct *p;
 
 	/*
 	 * Optimization: we know that if all tasks are in
 	 * the fair class we can call that function directly:
 	 */
-	if (likely(prev->sched_class == class &&
-		   rq->nr_running == rq->cfs.h_nr_running)) {
-		p = fair_sched_class.pick_next_task(rq, prev, cookie);
+	if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
+		p = fair_sched_class.pick_next_task(rq, prev, rf);
 		if (unlikely(p == RETRY_TASK))
 			goto again;
 
 		/* assumes fair_sched_class->next == idle_sched_class */
 		if (unlikely(!p))
-			p = idle_sched_class.pick_next_task(rq, prev, cookie);
+			p = idle_sched_class.pick_next_task(rq, prev, rf);
 
 		return p;
 	}
 
 again:
 	for_each_class(class) {
-		p = class->pick_next_task(rq, prev, cookie);
+		p = class->pick_next_task(rq, prev, rf);
 		if (p) {
 			if (unlikely(p == RETRY_TASK))
 				goto again;
@@ -3335,7 +3396,7 @@ static void __sched notrace __schedule(bool preempt)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
-	struct pin_cookie cookie;
+	struct rq_flags rf;
 	struct rq *rq;
 	int cpu;
 
@@ -3358,9 +3419,9 @@ static void __sched notrace __schedule(bool preempt)
 	 */
 	smp_mb__before_spinlock();
 	raw_spin_lock(&rq->lock);
-	cookie = lockdep_pin_lock(&rq->lock);
+	rq_pin_lock(rq, &rf);
 
-	rq->clock_skip_update <<= 1; /* promote REQ to ACT */
+	rq->clock_update_flags <<= 1; /* promote REQ to ACT */
 
 	switch_count = &prev->nivcsw;
 	if (!preempt && prev->state) {
@@ -3370,6 +3431,11 @@ static void __sched notrace __schedule(bool preempt)
 			deactivate_task(rq, prev, DEQUEUE_SLEEP);
 			prev->on_rq = 0;
 
+			if (prev->in_iowait) {
+				atomic_inc(&rq->nr_iowait);
+				delayacct_blkio_start();
+			}
+
 			/*
 			 * If a worker went to sleep, notify and ask workqueue
 			 * whether it wants to wake up a task to maintain
@@ -3380,7 +3446,7 @@ static void __sched notrace __schedule(bool preempt)
 
 				to_wakeup = wq_worker_sleeping(prev);
 				if (to_wakeup)
-					try_to_wake_up_local(to_wakeup, cookie);
+					try_to_wake_up_local(to_wakeup, &rf);
 			}
 		}
 		switch_count = &prev->nvcsw;
@@ -3389,10 +3455,9 @@ static void __sched notrace __schedule(bool preempt)
 	if (task_on_rq_queued(prev))
 		update_rq_clock(rq);
 
-	next = pick_next_task(rq, prev, cookie);
+	next = pick_next_task(rq, prev, &rf);
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
-	rq->clock_skip_update = 0;
 
 	if (likely(prev != next)) {
 		rq->nr_switches++;
@@ -3400,9 +3465,10 @@ static void __sched notrace __schedule(bool preempt)
 		++*switch_count;
 
 		trace_sched_switch(preempt, prev, next);
-		rq = context_switch(rq, prev, next, cookie); /* unlocks the rq */
+		rq = context_switch(rq, prev, next, &rf); /* unlocks the rq */
 	} else {
-		lockdep_unpin_lock(&rq->lock, cookie);
+		rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
+		rq_unpin_lock(rq, &rf);
 		raw_spin_unlock_irq(&rq->lock);
 	}
 
@@ -3651,6 +3717,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	BUG_ON(prio > MAX_PRIO);
 
 	rq = __task_rq_lock(p, &rf);
+	update_rq_clock(rq);
 
 	/*
 	 * Idle task boosting is a nono in general. There is one
@@ -3747,6 +3814,8 @@ void set_user_nice(struct task_struct *p, long nice)
 	 * the task might be in the middle of scheduling on another CPU.
 	 */
 	rq = task_rq_lock(p, &rf);
+	update_rq_clock(rq);
+
 	/*
 	 * The RT priorities are set via sched_setscheduler(), but we still
 	 * allow the 'normal' nice value to be set - but as expected
@@ -4179,6 +4248,7 @@ recheck:
 	 * runqueue lock must be held.
 	 */
 	rq = task_rq_lock(p, &rf);
+	update_rq_clock(rq);
 
 	/*
 	 * Changing the policy of the stop threads its a very bad idea
@@ -5057,31 +5127,48 @@ out_irq:
 }
 EXPORT_SYMBOL_GPL(yield_to);
 
+int io_schedule_prepare(void)
+{
+	int old_iowait = current->in_iowait;
+
+	current->in_iowait = 1;
+	blk_schedule_flush_plug(current);
+
+	return old_iowait;
+}
+
+void io_schedule_finish(int token)
+{
+	current->in_iowait = token;
+}
+
 /*
  * 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.
  */
 long __sched io_schedule_timeout(long timeout)
 {
-	int old_iowait = current->in_iowait;
-	struct rq *rq;
+	int token;
 	long ret;
 
-	current->in_iowait = 1;
-	blk_schedule_flush_plug(current);
-
-	delayacct_blkio_start();
-	rq = raw_rq();
-	atomic_inc(&rq->nr_iowait);
+	token = io_schedule_prepare();
 	ret = schedule_timeout(timeout);
-	current->in_iowait = old_iowait;
-	atomic_dec(&rq->nr_iowait);
-	delayacct_blkio_end();
+	io_schedule_finish(token);
 
 	return ret;
 }
 EXPORT_SYMBOL(io_schedule_timeout);
 
+void io_schedule(void)
+{
+	int token;
+
+	token = io_schedule_prepare();
+	schedule();
+	io_schedule_finish(token);
+}
+EXPORT_SYMBOL(io_schedule);
+
 /**
  * sys_sched_get_priority_max - return maximum RT priority.
  * @policy: scheduling class.
@@ -5521,7 +5608,7 @@ static void migrate_tasks(struct rq *dead_rq)
 {
 	struct rq *rq = dead_rq;
 	struct task_struct *next, *stop = rq->stop;
-	struct pin_cookie cookie;
+	struct rq_flags rf, old_rf;
 	int dest_cpu;
 
 	/*
@@ -5553,8 +5640,8 @@ static void migrate_tasks(struct rq *dead_rq)
 		/*
 		 * pick_next_task assumes pinned rq->lock.
 		 */
-		cookie = lockdep_pin_lock(&rq->lock);
-		next = pick_next_task(rq, &fake_task, cookie);
+		rq_pin_lock(rq, &rf);
+		next = pick_next_task(rq, &fake_task, &rf);
 		BUG_ON(!next);
 		next->sched_class->put_prev_task(rq, next);
 
@@ -5567,7 +5654,7 @@ static void migrate_tasks(struct rq *dead_rq)
 		 * because !cpu_active at this point, which means load-balance
 		 * will not interfere. Also, stop-machine.
 		 */
-		lockdep_unpin_lock(&rq->lock, cookie);
+		rq_unpin_lock(rq, &rf);
 		raw_spin_unlock(&rq->lock);
 		raw_spin_lock(&next->pi_lock);
 		raw_spin_lock(&rq->lock);
@@ -5582,6 +5669,13 @@ static void migrate_tasks(struct rq *dead_rq)
 			continue;
 		}
 
+		/*
+		 * __migrate_task() may return with a different
+		 * rq->lock held and a new cookie in 'rf', but we need
+		 * to preserve rf::clock_update_flags for 'dead_rq'.
+		 */
+		old_rf = rf;
+
 		/* Find suitable destination for @next, with force if needed. */
 		dest_cpu = select_fallback_rq(dead_rq->cpu, next);
 
@@ -5590,6 +5684,7 @@ static void migrate_tasks(struct rq *dead_rq)
 			raw_spin_unlock(&rq->lock);
 			rq = dead_rq;
 			raw_spin_lock(&rq->lock);
+			rf = old_rf;
 		}
 		raw_spin_unlock(&next->pi_lock);
 	}
@@ -5881,12 +5976,14 @@ static int init_rootdomain(struct root_domain *rd)
 
 	init_dl_bw(&rd->dl_bw);
 	if (cpudl_init(&rd->cpudl) != 0)
-		goto free_dlo_mask;
+		goto free_rto_mask;
 
 	if (cpupri_init(&rd->cpupri) != 0)
-		goto free_rto_mask;
+		goto free_cpudl;
 	return 0;
 
+free_cpudl:
+	cpudl_cleanup(&rd->cpudl);
 free_rto_mask:
 	free_cpumask_var(rd->rto_mask);
 free_dlo_mask:
@@ -7487,6 +7584,7 @@ void __init sched_init_smp(void)
 	init_sched_dl_class();
 
 	sched_init_smt();
+	sched_clock_init_late();
 
 	sched_smp_initialized = true;
 }
@@ -7502,6 +7600,7 @@ early_initcall(migration_init);
 void __init sched_init_smp(void)
 {
 	sched_init_granularity();
+	sched_clock_init_late();
 }
 #endif /* CONFIG_SMP */
 
@@ -7545,6 +7644,8 @@ void __init sched_init(void)
 	int i, j;
 	unsigned long alloc_size = 0, ptr;
 
+	sched_clock_init();
+
 	for (i = 0; i < WAIT_TABLE_SIZE; i++)
 		init_waitqueue_head(bit_wait_table + i);
 
@@ -7983,6 +8084,7 @@ void sched_move_task(struct task_struct *tsk)
 	struct rq *rq;
 
 	rq = task_rq_lock(tsk, &rf);
+	update_rq_clock(rq);
 
 	running = task_current(rq, tsk);
 	queued = task_on_rq_queued(tsk);
@@ -8431,6 +8533,7 @@ static void cpu_cgroup_fork(struct task_struct *task)
 
 	rq = task_rq_lock(task, &rf);
 
+	update_rq_clock(rq);
 	sched_change_group(task, TASK_SET_GROUP);
 
 	task_rq_unlock(rq, task, &rf);