@@ -2085,11 +2085,24 @@ try_to_wake_up(struct task_struct *p, un
 	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);

@@ -2139,8 +2152,13 @@ static void try_to_wake_up_local(struct
 
 	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_stat(p, smp_processor_id(), 0);

@@ -2948,6 +2966,36 @@ unsigned long long nr_context_switches(v
 	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;

@@ -2958,6 +3006,13 @@ 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);

@@ -3369,6 +3424,11 @@ static void __sched notrace __schedule(b
 			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

@@ -5063,19 +5123,13 @@ EXPORT_SYMBOL_GPL(yield_to);
 long __sched io_schedule_timeout(long timeout)
 {
 	int old_iowait = current->in_iowait;
-	struct rq *rq;
 	long ret;
 
 	current->in_iowait = 1;
 	blk_schedule_flush_plug(current);
 
-	delayacct_blkio_start();
-	rq = raw_rq();
-	atomic_inc(&rq->nr_iowait);
 	ret = schedule_timeout(timeout);
 	current->in_iowait = old_iowait;
-	atomic_dec(&rq->nr_iowait);
-	delayacct_blkio_end();
 
 	return ret;
 }