diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 627476bc64957d5b0c89f2182ffb4a2f172d5701..1b2829e99dad02cab2b04a417d87f9481023053e 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -724,19 +724,19 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
  * sure that the reference to cgroup is valid across the call (see
  * comments in bfq_bic_update_cgroup on this issue)
  */
-static void *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
-				     struct bfq_io_cq *bic,
-				     struct bfq_group *bfqg)
+static void __bfq_bic_change_cgroup(struct bfq_data *bfqd,
+				    struct bfq_io_cq *bic,
+				    struct bfq_group *bfqg)
 {
-	struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0);
-	struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1);
+	struct bfq_queue *async_bfqq = bic_to_bfqq(bic, false);
+	struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, true);
 	struct bfq_entity *entity;
 
 	if (async_bfqq) {
 		entity = &async_bfqq->entity;
 
 		if (entity->sched_data != &bfqg->sched_data) {
-			bic_set_bfqq(bic, NULL, 0);
+			bic_set_bfqq(bic, NULL, false);
 			bfq_release_process_ref(bfqd, async_bfqq);
 		}
 	}
@@ -772,12 +772,10 @@ static void *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
 				 */
 				bfq_put_cooperator(sync_bfqq);
 				bfq_release_process_ref(bfqd, sync_bfqq);
-				bic_set_bfqq(bic, NULL, 1);
+				bic_set_bfqq(bic, NULL, true);
 			}
 		}
 	}
-
-	return bfqg;
 }
 
 void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index a72304c728fce0753bc463c0bdcdee82ffe8c823..16f43bbc575a0aa167bfc2268057dda90cb85e51 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -386,6 +386,12 @@ static void bfq_put_stable_ref(struct bfq_queue *bfqq);
 
 void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync)
 {
+	struct bfq_queue *old_bfqq = bic->bfqq[is_sync];
+
+	/* Clear bic pointer if bfqq is detached from this bic */
+	if (old_bfqq && old_bfqq->bic == bic)
+		old_bfqq->bic = NULL;
+
 	/*
 	 * If bfqq != NULL, then a non-stable queue merge between
 	 * bic->bfqq and bfqq is happening here. This causes troubles
@@ -3108,7 +3114,7 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
 	/*
 	 * Merge queues (that is, let bic redirect its requests to new_bfqq)
 	 */
-	bic_set_bfqq(bic, new_bfqq, 1);
+	bic_set_bfqq(bic, new_bfqq, true);
 	bfq_mark_bfqq_coop(new_bfqq);
 	/*
 	 * new_bfqq now belongs to at least two bics (it is a shared queue):
@@ -5311,7 +5317,6 @@ static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
 		unsigned long flags;
 
 		spin_lock_irqsave(&bfqd->lock, flags);
-		bfqq->bic = NULL;
 		bfq_exit_bfqq(bfqd, bfqq);
 		bic_set_bfqq(bic, NULL, is_sync);
 		spin_unlock_irqrestore(&bfqd->lock, flags);
@@ -6557,7 +6562,7 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
 		return bfqq;
 	}
 
-	bic_set_bfqq(bic, NULL, 1);
+	bic_set_bfqq(bic, NULL, true);
 
 	bfq_put_cooperator(bfqq);
 
@@ -7058,7 +7063,9 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
 
 	bfqd->queue_weights_tree = RB_ROOT_CACHED;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	bfqd->num_groups_with_pending_reqs = 0;
+#endif
 
 	INIT_LIST_HEAD(&bfqd->active_list);
 	INIT_LIST_HEAD(&bfqd->idle_list);
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 9fa89577322d4a7a1cc5de4616d6843f0b7066f4..41aa151ccc223457621abb30e24ec8a02701346b 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -197,8 +197,10 @@ struct bfq_entity {
 	/* flag, set to request a weight, ioprio or ioprio_class change  */
 	int prio_changed;
 
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	/* flag, set if the entity is counted in groups_with_pending_reqs */
 	bool in_groups_with_pending_reqs;
+#endif
 
 	/* last child queue of entity created (for non-leaf entities) */
 	struct bfq_queue *last_bfqq_created;
@@ -491,6 +493,7 @@ struct bfq_data {
 	 */
 	struct rb_root_cached queue_weights_tree;
 
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	/*
 	 * Number of groups with at least one process that
 	 * has at least one request waiting for completion. Note that
@@ -538,6 +541,7 @@ struct bfq_data {
 	 * with no request waiting for completion.
 	 */
 	unsigned int num_groups_with_pending_reqs;
+#endif
 
 	/*
 	 * Per-class (RT, BE, IDLE) number of bfq_queues containing
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index b02b53658ed467836cd6c788ebbc62ab27015d62..ea4c3d757fdd1755adfd850b06e1d44ac37b8a09 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -1612,28 +1612,28 @@ void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 
 void bfq_add_bfqq_in_groups_with_pending_reqs(struct bfq_queue *bfqq)
 {
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	struct bfq_entity *entity = &bfqq->entity;
 
 	if (!entity->in_groups_with_pending_reqs) {
 		entity->in_groups_with_pending_reqs = true;
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
 		if (!(bfqq_group(bfqq)->num_queues_with_pending_reqs++))
 			bfqq->bfqd->num_groups_with_pending_reqs++;
-#endif
 	}
+#endif
 }
 
 void bfq_del_bfqq_in_groups_with_pending_reqs(struct bfq_queue *bfqq)
 {
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	struct bfq_entity *entity = &bfqq->entity;
 
 	if (entity->in_groups_with_pending_reqs) {
 		entity->in_groups_with_pending_reqs = false;
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
 		if (!(--bfqq_group(bfqq)->num_queues_with_pending_reqs))
 			bfqq->bfqd->num_groups_with_pending_reqs--;
-#endif
 	}
+#endif
 }
 
 /*
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 50ac0dce95b84f3a66e60300b4217444260e7807..ce6a2b7d3dfb2b405e013393ffe8e90e92be504e 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -33,6 +33,7 @@
 #include "blk-cgroup.h"
 #include "blk-ioprio.h"
 #include "blk-throttle.h"
+#include "blk-rq-qos.h"
 
 /*
  * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation.
@@ -1322,6 +1323,7 @@ int blkcg_init_disk(struct gendisk *disk)
 void blkcg_exit_disk(struct gendisk *disk)
 {
 	blkg_destroy_all(disk);
+	rq_qos_exit(disk->queue);
 	blk_throtl_exit(disk);
 }
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 3866b6c4cd889e2bf608245fbbedf01588d472f2..9321767470dc5f5b3bcfd2939851a15a6dffe2c2 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -254,14 +254,15 @@ EXPORT_SYMBOL_GPL(blk_clear_pm_only);
 
 static void blk_free_queue_rcu(struct rcu_head *rcu_head)
 {
-	kmem_cache_free(blk_requestq_cachep,
-			container_of(rcu_head, struct request_queue, rcu_head));
+	struct request_queue *q = container_of(rcu_head,
+			struct request_queue, rcu_head);
+
+	percpu_ref_exit(&q->q_usage_counter);
+	kmem_cache_free(blk_requestq_cachep, q);
 }
 
 static void blk_free_queue(struct request_queue *q)
 {
-	percpu_ref_exit(&q->q_usage_counter);
-
 	if (q->poll_stat)
 		blk_stat_remove_callback(q, q->poll_cb);
 	blk_stat_free_callback(q->poll_cb);
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index d1bdc12deaa70f6f20c8cd8ab254b5a325845061..549ddc9e0c6f4d7b7ac241728d1b8b6714a8b8bb 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -232,7 +232,9 @@ enum {
 
 	/* 1/64k is granular enough and can easily be handled w/ u32 */
 	WEIGHT_ONE		= 1 << 16,
+};
 
+enum {
 	/*
 	 * As vtime is used to calculate the cost of each IO, it needs to
 	 * be fairly high precision.  For example, it should be able to
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 1f8f3b87bdfa869cb41c35d63fe89f5bedb70b21..df628e30bca41684accd154175c0e39677e92fb4 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1773,7 +1773,16 @@ static const struct block_device_operations lo_fops = {
 /*
  * And now the modules code and kernel interface.
  */
-static int max_loop;
+
+/*
+ * If max_loop is specified, create that many devices upfront.
+ * This also becomes a hard limit. If max_loop is not specified,
+ * create CONFIG_BLK_DEV_LOOP_MIN_COUNT loop devices at module
+ * init time. Loop devices can be requested on-demand with the
+ * /dev/loop-control interface, or be instantiated by accessing
+ * a 'dead' device node.
+ */
+static int max_loop = CONFIG_BLK_DEV_LOOP_MIN_COUNT;
 module_param(max_loop, int, 0444);
 MODULE_PARM_DESC(max_loop, "Maximum number of loop devices");
 module_param(max_part, int, 0444);
@@ -2181,7 +2190,7 @@ MODULE_ALIAS("devname:loop-control");
 
 static int __init loop_init(void)
 {
-	int i, nr;
+	int i;
 	int err;
 
 	part_shift = 0;
@@ -2209,19 +2218,6 @@ static int __init loop_init(void)
 		goto err_out;
 	}
 
-	/*
-	 * If max_loop is specified, create that many devices upfront.
-	 * This also becomes a hard limit. If max_loop is not specified,
-	 * create CONFIG_BLK_DEV_LOOP_MIN_COUNT loop devices at module
-	 * init time. Loop devices can be requested on-demand with the
-	 * /dev/loop-control interface, or be instantiated by accessing
-	 * a 'dead' device node.
-	 */
-	if (max_loop)
-		nr = max_loop;
-	else
-		nr = CONFIG_BLK_DEV_LOOP_MIN_COUNT;
-
 	err = misc_register(&loop_misc);
 	if (err < 0)
 		goto err_out;
@@ -2233,7 +2229,7 @@ static int __init loop_init(void)
 	}
 
 	/* pre-create number of devices given by config or max_loop */
-	for (i = 0; i < nr; i++)
+	for (i = 0; i < max_loop; i++)
 		loop_add(i);
 
 	printk(KERN_INFO "loop: module loaded\n");
diff --git a/include/linux/bio.h b/include/linux/bio.h
index b231a665682a3ffab9508425342172f11eb45238..22078a28d7cb1316ddb800bed8c5c28242c8d1ba 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -782,8 +782,7 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
 
 static inline void bio_clear_polled(struct bio *bio)
 {
-	/* can't support alloc cache if we turn off polling */
-	bio->bi_opf &= ~(REQ_POLLED | REQ_ALLOC_CACHE);
+	bio->bi_opf &= ~REQ_POLLED;
 }
 
 struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,