Merge branch 'for-6.1/block' into for-6.1/passthrough

* for-6.1/block: (162 commits)
  sbitmap: fix lockup while swapping
  block: add rationale for not using blk_mq_plug() when applicable
  block: adapt blk_mq_plug() to not plug for writes that require a zone lock
  s390/dasd: use blk_mq_alloc_disk
  blk-cgroup: don't update the blkg lookup hint in blkg_conf_prep
  nvmet: don't look at the request_queue in nvmet_bdev_set_limits
  nvmet: don't look at the request_queue in nvmet_bdev_zone_mgmt_emulate_all
  blk-mq: use quiesced elevator switch when reinitializing queues
  block: replace blk_queue_nowait with bdev_nowait
  nvme: remove nvme_ctrl_init_connect_q
  nvme-loop: use the tagset alloc/free helpers
  nvme-loop: store the generic nvme_ctrl in set->driver_data
  nvme-loop: initialize sqsize later
  nvme-fc: use the tagset alloc/free helpers
  nvme-fc: store the generic nvme_ctrl in set->driver_data
  nvme-fc: keep ctrl->sqsize in sync with opts->queue_size
  nvme-rdma: use the tagset alloc/free helpers
  nvme-rdma: store the generic nvme_ctrl in set->driver_data
  nvme-tcp: use the tagset alloc/free helpers
  nvme-tcp: store the generic nvme_ctrl in set->driver_data
  ...

Signed-off-by: Jens Axboe <axboe@kernel.dk>

32 files changed, 532 insertions, 456 deletions

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 30b15a9a47c4..144bca006463 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -254,17 +254,12 @@ void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
 
 #else /* CONFIG_BFQ_CGROUP_DEBUG */
 
-void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
-			      blk_opf_t opf) { }
 void bfqg_stats_update_io_remove(struct bfq_group *bfqg, blk_opf_t opf) { }
 void bfqg_stats_update_io_merged(struct bfq_group *bfqg, blk_opf_t opf) { }
 void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
 				  u64 io_start_time_ns, blk_opf_t opf) { }
 void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
-void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
-void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
 void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { }
-void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { }
 
 #endif /* CONFIG_BFQ_CGROUP_DEBUG */
 
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index c740b41fe0a4..7ea427817f7f 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -1925,7 +1925,7 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
 	bfqq->service_from_backlogged = 0;
 	bfq_clear_bfqq_softrt_update(bfqq);
 
-	bfq_add_bfqq_busy(bfqd, bfqq);
+	bfq_add_bfqq_busy(bfqq);
 
 	/*
 	 * Expire in-service queue if preemption may be needed for
@@ -2419,7 +2419,7 @@ static void bfq_remove_request(struct request_queue *q,
 		bfqq->next_rq = NULL;
 
 		if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) {
-			bfq_del_bfqq_busy(bfqd, bfqq, false);
+			bfq_del_bfqq_busy(bfqq, false);
 			/*
 			 * bfqq emptied. In normal operation, when
 			 * bfqq is empty, bfqq->entity.service and
@@ -3098,7 +3098,7 @@ void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 	 */
 	if (bfq_bfqq_busy(bfqq) && RB_EMPTY_ROOT(&bfqq->sort_list) &&
 	    bfqq != bfqd->in_service_queue)
-		bfq_del_bfqq_busy(bfqd, bfqq, false);
+		bfq_del_bfqq_busy(bfqq, false);
 
 	bfq_reassign_last_bfqq(bfqq, NULL);
 
@@ -3908,7 +3908,7 @@ static bool __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 			 */
 			bfqq->budget_timeout = jiffies;
 
-		bfq_del_bfqq_busy(bfqd, bfqq, true);
+		bfq_del_bfqq_busy(bfqq, true);
 	} else {
 		bfq_requeue_bfqq(bfqd, bfqq, true);
 		/*
@@ -5255,9 +5255,7 @@ void bfq_put_queue(struct bfq_queue *bfqq)
 	struct hlist_node *n;
 	struct bfq_group *bfqg = bfqq_group(bfqq);
 
-	if (bfqq->bfqd)
-		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d",
-			     bfqq, bfqq->ref);
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d", bfqq, bfqq->ref);
 
 	bfqq->ref--;
 	if (bfqq->ref)
@@ -5321,7 +5319,7 @@ void bfq_put_queue(struct bfq_queue *bfqq)
 		hlist_del_init(&item->woken_list_node);
 	}
 
-	if (bfqq->bfqd && bfqq->bfqd->last_completed_rq_bfqq == bfqq)
+	if (bfqq->bfqd->last_completed_rq_bfqq == bfqq)
 		bfqq->bfqd->last_completed_rq_bfqq = NULL;
 
 	kmem_cache_free(bfq_pool, bfqq);
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index ad8e513d7e87..64ee618064ba 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -993,20 +993,23 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
 /* ---------------- cgroups-support interface ---------------- */
 
 void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq);
-void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
-			      blk_opf_t opf);
 void bfqg_stats_update_io_remove(struct bfq_group *bfqg, blk_opf_t opf);
 void bfqg_stats_update_io_merged(struct bfq_group *bfqg, blk_opf_t opf);
 void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
 				  u64 io_start_time_ns, blk_opf_t opf);
 void bfqg_stats_update_dequeue(struct bfq_group *bfqg);
-void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
-void bfqg_stats_update_idle_time(struct bfq_group *bfqg);
 void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg);
-void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg);
 void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		   struct bfq_group *bfqg);
 
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+			      blk_opf_t opf);
+void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
+void bfqg_stats_update_idle_time(struct bfq_group *bfqg);
+void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg);
+#endif
+
 void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg);
 void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio);
 void bfq_end_wr_async(struct bfq_data *bfqd);
@@ -1077,9 +1080,8 @@ void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
 void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		      bool expiration);
-void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
-		       bool expiration);
-void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_del_bfqq_busy(struct bfq_queue *bfqq, bool expiration);
+void bfq_add_bfqq_busy(struct bfq_queue *bfqq);
 
 /* --------------- end of interface of B-WF2Q+ ---------------- */
 
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index 983413cdefad..8fc3da4c23bb 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -1651,9 +1651,10 @@ void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
  * the service tree. As a special case, it can be invoked during an
  * expiration.
  */
-void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
-		       bool expiration)
+void bfq_del_bfqq_busy(struct bfq_queue *bfqq, bool expiration)
 {
+	struct bfq_data *bfqd = bfqq->bfqd;
+
 	bfq_log_bfqq(bfqd, bfqq, "del from busy");
 
 	bfq_clear_bfqq_busy(bfqq);
@@ -1674,8 +1675,10 @@ void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 /*
  * Called when an inactive queue receives a new request.
  */
-void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+void bfq_add_bfqq_busy(struct bfq_queue *bfqq)
 {
+	struct bfq_data *bfqd = bfqq->bfqd;
+
 	bfq_log_bfqq(bfqd, bfqq, "add to busy");
 
 	bfq_activate_bfqq(bfqd, bfqq);
diff --git a/block/bio.c b/block/bio.c
index 3d3a2678fea2..7cb7d2ff139b 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -760,8 +760,6 @@ EXPORT_SYMBOL(bio_put);
 static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp)
 {
 	bio_set_flag(bio, BIO_CLONED);
-	if (bio_flagged(bio_src, BIO_THROTTLED))
-		bio_set_flag(bio, BIO_THROTTLED);
 	bio->bi_ioprio = bio_src->bi_ioprio;
 	bio->bi_iter = bio_src->bi_iter;
 
@@ -1065,9 +1063,6 @@ void __bio_add_page(struct bio *bio, struct page *page,
 
 	bio->bi_iter.bi_size += len;
 	bio->bi_vcnt++;
-
-	if (!bio_flagged(bio, BIO_WORKINGSET) && unlikely(PageWorkingset(page)))
-		bio_set_flag(bio, BIO_WORKINGSET);
 }
 EXPORT_SYMBOL_GPL(__bio_add_page);
 
@@ -1276,9 +1271,6 @@ out:
  * fit into the bio, or are requested in @iter, whatever is smaller. If
  * MM encounters an error pinning the requested pages, it stops. Error
  * is returned only if 0 pages could be pinned.
- *
- * It's intended for direct IO, so doesn't do PSI tracking, the caller is
- * responsible for setting BIO_WORKINGSET if necessary.
  */
 int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 {
@@ -1294,8 +1286,6 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 		ret = __bio_iov_iter_get_pages(bio, iter);
 	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
 
-	/* don't account direct I/O as memory stall */
-	bio_clear_flag(bio, BIO_WORKINGSET);
 	return bio->bi_vcnt ? 0 : ret;
 }
 EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
@@ -1754,7 +1744,8 @@ static int __init init_bio(void)
 	cpuhp_setup_state_multi(CPUHP_BIO_DEAD, "block/bio:dead", NULL,
 					bio_cpu_dead);
 
-	if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS))
+	if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0,
+			BIOSET_NEED_BVECS | BIOSET_PERCPU_CACHE))
 		panic("bio: can't allocate bios\n");
 
 	if (bioset_integrity_create(&fs_bio_set, BIO_POOL_SIZE))
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 869af9d72bcf..6a5c849ee061 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -202,19 +202,19 @@ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg)
 /**
  * blkg_alloc - allocate a blkg
  * @blkcg: block cgroup the new blkg is associated with
- * @q: request_queue the new blkg is associated with
+ * @disk: gendisk the new blkg is associated with
  * @gfp_mask: allocation mask to use
  *
  * Allocate a new blkg assocating @blkcg and @q.
  */
-static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
+static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 				   gfp_t gfp_mask)
 {
 	struct blkcg_gq *blkg;
 	int i, cpu;
 
 	/* alloc and init base part */
-	blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node);
+	blkg = kzalloc_node(sizeof(*blkg), gfp_mask, disk->queue->node);
 	if (!blkg)
 		return NULL;
 
@@ -225,10 +225,10 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 	if (!blkg->iostat_cpu)
 		goto err_free;
 
-	if (!blk_get_queue(q))
+	if (!blk_get_queue(disk->queue))
 		goto err_free;
 
-	blkg->q = q;
+	blkg->q = disk->queue;
 	INIT_LIST_HEAD(&blkg->q_node);
 	spin_lock_init(&blkg->async_bio_lock);
 	bio_list_init(&blkg->async_bios);
@@ -243,11 +243,11 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 		struct blkcg_policy *pol = blkcg_policy[i];
 		struct blkg_policy_data *pd;
 
-		if (!blkcg_policy_enabled(q, pol))
+		if (!blkcg_policy_enabled(disk->queue, pol))
 			continue;
 
 		/* alloc per-policy data and attach it to blkg */
-		pd = pol->pd_alloc_fn(gfp_mask, q, blkcg);
+		pd = pol->pd_alloc_fn(gfp_mask, disk->queue, blkcg);
 		if (!pd)
 			goto err_free;
 
@@ -263,45 +263,20 @@ err_free:
 	return NULL;
 }
 
-struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
-				      struct request_queue *q, bool update_hint)
-{
-	struct blkcg_gq *blkg;
-
-	/*
-	 * Hint didn't match.  Look up from the radix tree.  Note that the
-	 * hint can only be updated under queue_lock as otherwise @blkg
-	 * could have already been removed from blkg_tree.  The caller is
-	 * responsible for grabbing queue_lock if @update_hint.
-	 */
-	blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id);
-	if (blkg && blkg->q == q) {
-		if (update_hint) {
-			lockdep_assert_held(&q->queue_lock);
-			rcu_assign_pointer(blkcg->blkg_hint, blkg);
-		}
-		return blkg;
-	}
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(blkg_lookup_slowpath);
-
 /*
  * If @new_blkg is %NULL, this function tries to allocate a new one as
  * necessary using %GFP_NOWAIT.  @new_blkg is always consumed on return.
  */
-static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
-				    struct request_queue *q,
+static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk,
 				    struct blkcg_gq *new_blkg)
 {
 	struct blkcg_gq *blkg;
 	int i, ret;
 
-	lockdep_assert_held(&q->queue_lock);
+	lockdep_assert_held(&disk->queue->queue_lock);
 
 	/* request_queue is dying, do not create/recreate a blkg */
-	if (blk_queue_dying(q)) {
+	if (blk_queue_dying(disk->queue)) {
 		ret = -ENODEV;
 		goto err_free_blkg;
 	}
@@ -314,7 +289,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 
 	/* allocate */
 	if (!new_blkg) {
-		new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT | __GFP_NOWARN);
+		new_blkg = blkg_alloc(blkcg, disk, GFP_NOWAIT | __GFP_NOWARN);
 		if (unlikely(!new_blkg)) {
 			ret = -ENOMEM;
 			goto err_put_css;
@@ -324,7 +299,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 
 	/* link parent */
 	if (blkcg_parent(blkcg)) {
-		blkg->parent = __blkg_lookup(blkcg_parent(blkcg), q, false);
+		blkg->parent = blkg_lookup(blkcg_parent(blkcg), disk->queue);
 		if (WARN_ON_ONCE(!blkg->parent)) {
 			ret = -ENODEV;
 			goto err_put_css;
@@ -342,10 +317,10 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 
 	/* insert */
 	spin_lock(&blkcg->lock);
-	ret = radix_tree_insert(&blkcg->blkg_tree, q->id, blkg);
+	ret = radix_tree_insert(&blkcg->blkg_tree, disk->queue->id, blkg);
 	if (likely(!ret)) {
 		hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
-		list_add(&blkg->q_node, &q->blkg_list);
+		list_add(&blkg->q_node, &disk->queue->blkg_list);
 
 		for (i = 0; i < BLKCG_MAX_POLS; i++) {
 			struct blkcg_policy *pol = blkcg_policy[i];
@@ -374,19 +349,20 @@ err_free_blkg:
 /**
  * blkg_lookup_create - lookup blkg, try to create one if not there
  * @blkcg: blkcg of interest
- * @q: request_queue of interest
+ * @disk: gendisk of interest
  *
- * Lookup blkg for the @blkcg - @q pair.  If it doesn't exist, try to
+ * Lookup blkg for the @blkcg - @disk pair.  If it doesn't exist, try to
  * create one.  blkg creation is performed recursively from blkcg_root such
  * that all non-root blkg's have access to the parent blkg.  This function
- * should be called under RCU read lock and takes @q->queue_lock.
+ * should be called under RCU read lock and takes @disk->queue->queue_lock.
  *
  * Returns the blkg or the closest blkg if blkg_create() fails as it walks
  * down from root.
  */
 static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
-		struct request_queue *q)
+		struct gendisk *disk)
 {
+	struct request_queue *q = disk->queue;
 	struct blkcg_gq *blkg;
 	unsigned long flags;
 
@@ -397,9 +373,13 @@ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 		return blkg;
 
 	spin_lock_irqsave(&q->queue_lock, flags);
-	blkg = __blkg_lookup(blkcg, q, true);
-	if (blkg)
+	blkg = blkg_lookup(blkcg, q);
+	if (blkg) {
+		if (blkcg != &blkcg_root &&
+		    blkg != rcu_dereference(blkcg->blkg_hint))
+			rcu_assign_pointer(blkcg->blkg_hint, blkg);
 		goto found;
+	}
 
 	/*
 	 * Create blkgs walking down from blkcg_root to @blkcg, so that all
@@ -412,7 +392,7 @@ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 		struct blkcg_gq *ret_blkg = q->root_blkg;
 
 		while (parent) {
-			blkg = __blkg_lookup(parent, q, false);
+			blkg = blkg_lookup(parent, q);
 			if (blkg) {
 				/* remember closest blkg */
 				ret_blkg = blkg;
@@ -422,7 +402,7 @@ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 			parent = blkcg_parent(parent);
 		}
 
-		blkg = blkg_create(pos, q, NULL);
+		blkg = blkg_create(pos, disk, NULL);
 		if (IS_ERR(blkg)) {
 			blkg = ret_blkg;
 			break;
@@ -476,14 +456,9 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 	percpu_ref_kill(&blkg->refcnt);
 }
 
-/**
- * blkg_destroy_all - destroy all blkgs associated with a request_queue
- * @q: request_queue of interest
- *
- * Destroy all blkgs associated with @q.
- */
-static void blkg_destroy_all(struct request_queue *q)
+static void blkg_destroy_all(struct gendisk *disk)
 {
+	struct request_queue *q = disk->queue;
 	struct blkcg_gq *blkg, *n;
 	int count = BLKG_DESTROY_BATCH_SIZE;
 
@@ -616,19 +591,6 @@ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v)
 }
 EXPORT_SYMBOL_GPL(__blkg_prfill_u64);
 
-/* Performs queue bypass and policy enabled checks then looks up blkg. */
-static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg,
-					  const struct blkcg_policy *pol,
-					  struct request_queue *q)
-{
-	WARN_ON_ONCE(!rcu_read_lock_held());
-	lockdep_assert_held(&q->queue_lock);
-
-	if (!blkcg_policy_enabled(q, pol))
-		return ERR_PTR(-EOPNOTSUPP);
-	return __blkg_lookup(blkcg, q, true /* update_hint */);
-}
-
 /**
  * blkcg_conf_open_bdev - parse and open bdev for per-blkg config update
  * @inputp: input string pointer
@@ -684,6 +646,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	__acquires(rcu) __acquires(&bdev->bd_queue->queue_lock)
 {
 	struct block_device *bdev;
+	struct gendisk *disk;
 	struct request_queue *q;
 	struct blkcg_gq *blkg;
 	int ret;
@@ -691,8 +654,8 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	bdev = blkcg_conf_open_bdev(&input);
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
-
-	q = bdev_get_queue(bdev);
+	disk = bdev->bd_disk;
+	q = disk->queue;
 
 	/*
 	 * blkcg_deactivate_policy() requires queue to be frozen, we can grab
@@ -705,12 +668,12 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	rcu_read_lock();
 	spin_lock_irq(&q->queue_lock);
 
-	blkg = blkg_lookup_check(blkcg, pol, q);
-	if (IS_ERR(blkg)) {
-		ret = PTR_ERR(blkg);
+	if (!blkcg_policy_enabled(q, pol)) {
+		ret = -EOPNOTSUPP;
 		goto fail_unlock;
 	}
 
+	blkg = blkg_lookup(blkcg, q);
 	if (blkg)
 		goto success;
 
@@ -724,7 +687,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		struct blkcg_gq *new_blkg;
 
 		parent = blkcg_parent(blkcg);
-		while (parent && !__blkg_lookup(parent, q, false)) {
+		while (parent && !blkg_lookup(parent, q)) {
 			pos = parent;
 			parent = blkcg_parent(parent);
 		}
@@ -733,7 +696,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		spin_unlock_irq(&q->queue_lock);
 		rcu_read_unlock();
 
-		new_blkg = blkg_alloc(pos, q, GFP_KERNEL);
+		new_blkg = blkg_alloc(pos, disk, GFP_KERNEL);
 		if (unlikely(!new_blkg)) {
 			ret = -ENOMEM;
 			goto fail_exit_queue;
@@ -748,17 +711,17 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		rcu_read_lock();
 		spin_lock_irq(&q->queue_lock);
 
-		blkg = blkg_lookup_check(pos, pol, q);
-		if (IS_ERR(blkg)) {
-			ret = PTR_ERR(blkg);
+		if (!blkcg_policy_enabled(q, pol)) {
 			blkg_free(new_blkg);
+			ret = -EOPNOTSUPP;
 			goto fail_preloaded;
 		}
 
+		blkg = blkg_lookup(pos, q);
 		if (blkg) {
 			blkg_free(new_blkg);
 		} else {
-			blkg = blkg_create(pos, q, new_blkg);
+			blkg = blkg_create(pos, disk, new_blkg);
 			if (IS_ERR(blkg)) {
 				ret = PTR_ERR(blkg);
 				goto fail_preloaded;
@@ -915,8 +878,7 @@ static void blkcg_fill_root_iostats(void)
 	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
 	while ((dev = class_dev_iter_next(&iter))) {
 		struct block_device *bdev = dev_to_bdev(dev);
-		struct blkcg_gq *blkg =
-			blk_queue_root_blkg(bdev_get_queue(bdev));
+		struct blkcg_gq *blkg = bdev->bd_disk->queue->root_blkg;
 		struct blkg_iostat tmp;
 		int cpu;
 		unsigned long flags;
@@ -1255,25 +1217,16 @@ static int blkcg_css_online(struct cgroup_subsys_state *css)
 	return 0;
 }
 
-/**
- * blkcg_init_queue - initialize blkcg part of request queue
- * @q: request_queue to initialize
- *
- * Called from blk_alloc_queue(). Responsible for initializing blkcg
- * part of new request_queue @q.
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int blkcg_init_queue(struct request_queue *q)
+int blkcg_init_disk(struct gendisk *disk)
 {
+	struct request_queue *q = disk->queue;
 	struct blkcg_gq *new_blkg, *blkg;
 	bool preloaded;
 	int ret;
 
 	INIT_LIST_HEAD(&q->blkg_list);
 
-	new_blkg = blkg_alloc(&blkcg_root, q, GFP_KERNEL);
+	new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL);
 	if (!new_blkg)
 		return -ENOMEM;
 
@@ -1282,7 +1235,7 @@ int blkcg_init_queue(struct request_queue *q)
 	/* Make sure the root blkg exists. */
 	/* spin_lock_irq can serve as RCU read-side critical section. */
 	spin_lock_irq(&q->queue_lock);
-	blkg = blkg_create(&blkcg_root, q, new_blkg);
+	blkg = blkg_create(&blkcg_root, disk, new_blkg);
 	if (IS_ERR(blkg))
 		goto err_unlock;
 	q->root_blkg = blkg;
@@ -1291,25 +1244,26 @@ int blkcg_init_queue(struct request_queue *q)
 	if (preloaded)
 		radix_tree_preload_end();
 
-	ret = blk_ioprio_init(q);
+	ret = blk_ioprio_init(disk);
 	if (ret)
 		goto err_destroy_all;
 
-	ret = blk_throtl_init(q);
+	ret = blk_throtl_init(disk);
 	if (ret)
-		goto err_destroy_all;
+		goto err_ioprio_exit;
 
-	ret = blk_iolatency_init(q);
-	if (ret) {
-		blk_throtl_exit(q);
-		blk_ioprio_exit(q);
-		goto err_destroy_all;
-	}
+	ret = blk_iolatency_init(disk);
+	if (ret)
+		goto err_throtl_exit;
 
 	return 0;
 
+err_throtl_exit:
+	blk_throtl_exit(disk);
+err_ioprio_exit:
+	blk_ioprio_exit(disk);
 err_destroy_all:
-	blkg_destroy_all(q);
+	blkg_destroy_all(disk);
 	return ret;
 err_unlock:
 	spin_unlock_irq(&q->queue_lock);
@@ -1318,16 +1272,10 @@ err_unlock:
 	return PTR_ERR(blkg);
 }
 
-/**
- * blkcg_exit_queue - exit and release blkcg part of request_queue
- * @q: request_queue being released
- *
- * Called from blk_exit_queue().  Responsible for exiting blkcg part.
- */
-void blkcg_exit_queue(struct request_queue *q)
+void blkcg_exit_disk(struct gendisk *disk)
 {
-	blkg_destroy_all(q);
-	blk_throtl_exit(q);
+	blkg_destroy_all(disk);
+	blk_throtl_exit(disk);
 }
 
 static void blkcg_bind(struct cgroup_subsys_state *root_css)
@@ -1836,13 +1784,13 @@ out:
 
 /**
  * blkcg_schedule_throttle - this task needs to check for throttling
- * @q: the request queue IO was submitted on
+ * @gendisk: disk to throttle
  * @use_memdelay: do we charge this to memory delay for PSI
  *
  * This is called by the IO controller when we know there's delay accumulated
  * for the blkg for this task.  We do not pass the blkg because there are places
  * we call this that may not have that information, the swapping code for
- * instance will only have a request_queue at that point.  This set's the
+ * instance will only have a block_device at that point.  This set's the
  * notify_resume for the task to check and see if it requires throttling before
  * returning to user space.
  *
@@ -1851,8 +1799,10 @@ out:
  * throttle once.  If the task needs to be throttled again it'll need to be
  * re-set at the next time we see the task.
  */
-void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay)
+void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay)
 {
+	struct request_queue *q = disk->queue;
+
 	if (unlikely(current->flags & PF_KTHREAD))
 		return;
 
@@ -1902,8 +1852,7 @@ static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio,
 	struct blkcg_gq *blkg, *ret_blkg = NULL;
 
 	rcu_read_lock();
-	blkg = blkg_lookup_create(css_to_blkcg(css),
-				  bdev_get_queue(bio->bi_bdev));
+	blkg = blkg_lookup_create(css_to_blkcg(css), bio->bi_bdev->bd_disk);
 	while (blkg) {
 		if (blkg_tryget(blkg)) {
 			ret_blkg = blkg;
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index d2724d1dd7c9..aa2b286bc825 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -178,10 +178,8 @@ struct blkcg_policy {
 extern struct blkcg blkcg_root;
 extern bool blkcg_debug_stats;
 
-struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
-				      struct request_queue *q, bool update_hint);
-int blkcg_init_queue(struct request_queue *q);
-void blkcg_exit_queue(struct request_queue *q);
+int blkcg_init_disk(struct gendisk *disk);
+void blkcg_exit_disk(struct gendisk *disk);
 
 /* Blkio controller policy registration */
 int blkcg_policy_register(struct blkcg_policy *pol);
@@ -227,22 +225,21 @@ static inline bool bio_issue_as_root_blkg(struct bio *bio)
 }
 
 /**
- * __blkg_lookup - internal version of blkg_lookup()
+ * blkg_lookup - lookup blkg for the specified blkcg - q pair
  * @blkcg: blkcg of interest
  * @q: request_queue of interest
- * @update_hint: whether to update lookup hint with the result or not
  *
- * This is internal version and shouldn't be used by policy
- * implementations.  Looks up blkgs for the @blkcg - @q pair regardless of
- * @q's bypass state.  If @update_hint is %true, the caller should be
- * holding @q->queue_lock and lookup hint is updated on success.
+ * Lookup blkg for the @blkcg - @q pair.
+
+ * Must be called in a RCU critical section.
  */
-static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg,
-					     struct request_queue *q,
-					     bool update_hint)
+static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
+					   struct request_queue *q)
 {
 	struct blkcg_gq *blkg;
 
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
 	if (blkcg == &blkcg_root)
 		return q->root_blkg;
 
@@ -250,33 +247,10 @@ static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg,
 	if (blkg && blkg->q == q)
 		return blkg;
 
-	return blkg_lookup_slowpath(blkcg, q, update_hint);
-}
-
-/**
- * blkg_lookup - lookup blkg for the specified blkcg - q pair
- * @blkcg: blkcg of interest
- * @q: request_queue of interest
- *
- * Lookup blkg for the @blkcg - @q pair.  This function should be called
- * under RCU read lock.
- */
-static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
-					   struct request_queue *q)
-{
-	WARN_ON_ONCE(!rcu_read_lock_held());
-	return __blkg_lookup(blkcg, q, false);
-}
-
-/**
- * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair
- * @q: request_queue of interest
- *
- * Lookup blkg for @q at the root level. See also blkg_lookup().
- */
-static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
-{
-	return q->root_blkg;
+	blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id);
+	if (blkg && blkg->q != q)
+		blkg = NULL;
+	return blkg;