@@ -2736,30 +2736,6 @@ void blk_account_io_done(struct request *req, u64 now)
 	}
 }
 
-#ifdef CONFIG_PM
-/*
- * Don't process normal requests when queue is suspended
- * or in the process of suspending/resuming
- */
-static bool blk_pm_allow_request(struct request *rq)
-{
-	switch (rq->q->rpm_status) {
-	case RPM_RESUMING:
-	case RPM_SUSPENDING:
-		return rq->rq_flags & RQF_PM;
-	case RPM_SUSPENDED:
-		return false;
-	default:
-		return true;
-	}
-}
-#else
-static bool blk_pm_allow_request(struct request *rq)
-{
-	return true;
-}
-#endif
-
 void blk_account_io_start(struct request *rq, bool new_io)
 {
 	struct hd_struct *part;

@@ -2805,11 +2781,14 @@ static struct request *elv_next_request(struct request_queue *q)
 
 	while (1) {
 		list_for_each_entry(rq, &q->queue_head, queuelist) {
-			if (blk_pm_allow_request(rq))
-				return rq;
-
-			if (rq->rq_flags & RQF_SOFTBARRIER)
-				break;
+#ifdef CONFIG_PM
+			/*
+			 * If a request gets queued in state RPM_SUSPENDED
+			 * then that's a kernel bug.
+			 */
+			WARN_ON_ONCE(q->rpm_status == RPM_SUSPENDED);
+#endif
+			return rq;
 		}
 
 		/*

@@ -332,7 +332,6 @@ static const char *const rqf_name[] = {
 	RQF_NAME(ELVPRIV),
 	RQF_NAME(IO_STAT),
 	RQF_NAME(ALLOCED),
-	RQF_NAME(PM),
 	RQF_NAME(HASHED),
 	RQF_NAME(STATS),
 	RQF_NAME(SPECIAL_PAYLOAD),

@@ -107,17 +107,31 @@ int blk_pre_runtime_suspend(struct request_queue *q)
 	if (!q->dev)
 		return ret;
 
+	WARN_ON_ONCE(q->rpm_status != RPM_ACTIVE);
+
 	blk_pm_runtime_lock(q);
+	/*
+	 * Switch to preempt-only mode before calling synchronize_rcu() such
+	 * that later blk_queue_enter() calls see the preempt-only state. See
+	 * also http://lwn.net/Articles/573497/.
+	 */
+	blk_set_pm_only(q);
+	ret = -EBUSY;
+	if (percpu_ref_read(&q->q_usage_counter) == 1) {
+		synchronize_rcu();
+		if (percpu_ref_read(&q->q_usage_counter) == 1)
+			ret = 0;
+	}
 
 	spin_lock_irq(q->queue_lock);
-	if (q->nr_pending) {
-		ret = -EBUSY;
+	if (ret < 0)
 		pm_runtime_mark_last_busy(q->dev);
-	} else {
+	else
 		q->rpm_status = RPM_SUSPENDING;
-	}
 	spin_unlock_irq(q->queue_lock);
 
+	if (ret)
+		blk_clear_pm_only(q);
 	blk_pm_runtime_unlock(q);
 
 	return ret;

@@ -150,6 +164,9 @@ void blk_post_runtime_suspend(struct request_queue *q, int err)
 		pm_runtime_mark_last_busy(q->dev);
 	}
 	spin_unlock_irq(q->queue_lock);
+
+	if (err)
+		blk_clear_pm_only(q);
 }
 EXPORT_SYMBOL(blk_post_runtime_suspend);
 

@@ -197,13 +214,15 @@ void blk_post_runtime_resume(struct request_queue *q, int err)
 	spin_lock_irq(q->queue_lock);
 	if (!err) {
 		q->rpm_status = RPM_ACTIVE;
-		__blk_run_queue(q);
 		pm_runtime_mark_last_busy(q->dev);
 		pm_request_autosuspend(q->dev);
 	} else {
 		q->rpm_status = RPM_SUSPENDED;
 	}
 	spin_unlock_irq(q->queue_lock);
+
+	if (!err)
+		blk_clear_pm_only(q);
 }
 EXPORT_SYMBOL(blk_post_runtime_resume);
 

@@ -8,21 +8,23 @@
 #ifdef CONFIG_PM
 static inline void blk_pm_requeue_request(struct request *rq)
 {
-	if (rq->q->dev && !(rq->rq_flags & RQF_PM))
-		rq->q->nr_pending--;
 }
 
 static inline void blk_pm_add_request(struct request_queue *q,
 				      struct request *rq)
 {
-	if (q->dev && !(rq->rq_flags & RQF_PM) && q->nr_pending++ == 0 &&
-	    (q->rpm_status == RPM_SUSPENDED || q->rpm_status == RPM_SUSPENDING))
-		pm_request_resume(q->dev);
+	if (!q->dev || (rq->rq_flags & RQF_PREEMPT))
+		return;
+	/*
+	 * If the below warning is triggered then that means that the caller
+	 * did not use pm_runtime_get*().
+	 */
+	WARN_ON_ONCE(atomic_read(&q->dev->power.usage_count) == 0);
 }
 
 static inline void blk_pm_put_request(struct request *rq)
 {
-	if (rq->q->dev && !(rq->rq_flags & RQF_PM) && !--rq->q->nr_pending)
+	if (rq->q->dev && !(rq->rq_flags & RQF_PREEMPT))
 		pm_runtime_mark_last_busy(rq->q->dev);
 }
 #else

@@ -547,7 +547,6 @@ struct request_queue {
 #ifdef CONFIG_PM
 	struct device		*dev;
 	int			rpm_status;
-	unsigned int		nr_pending;
 	wait_queue_head_t	rpm_wq;
 	/* rpm_lock protects rpm_owner and rpm_nesting_level */
 	spinlock_t		rpm_lock;