revert blk-cgroup changs

revert blk-cgroup changs

[Christoph Hellwig]

Hi Jens,

this series reverts a bunch of blk-cgroup patches as one of them
caused a problem for which the time is running out to fix for this
merge window

[PATCH 1/5] Revert "blk-cgroup: move the cgroup information to struct gendisk"

[Christoph Hellwig]

This reverts commit 3f13ab7c80fdb0ada86a8e3e818960bc1ccbaa59 as a patch
it depends on caused a few problems.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 block/bfq-cgroup.c     |  4 +--
 block/blk-cgroup.c     | 66 +++++++++++++++++++++---------------------
 block/blk-cgroup.h     |  4 +--
 block/blk-iolatency.c  |  2 +-
 block/blk-throttle.c   | 16 ++++------
 include/linux/blkdev.h | 12 ++++----
 6 files changed, 50 insertions(+), 54 deletions(-)

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 624530643a05cd..935a497b5dedb3 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -999,7 +999,7 @@ void bfq_end_wr_async(struct bfq_data *bfqd)
 {
 	struct blkcg_gq *blkg;
 
-	list_for_each_entry(blkg, &bfqd->queue->disk->blkg_list, entry) {
+	list_for_each_entry(blkg, &bfqd->queue->blkg_list, q_node) {
 		struct bfq_group *bfqg = blkg_to_bfqg(blkg);
 
 		bfq_end_wr_async_queues(bfqd, bfqg);
@@ -1293,7 +1293,7 @@ struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
 	if (ret)
 		return NULL;
 
-	return blkg_to_bfqg(bfqd->queue->disk->root_blkg);
+	return blkg_to_bfqg(bfqd->queue->root_blkg);
 }
 
 struct blkcg_policy blkcg_policy_bfq = {
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 935028912e7abf..1653786644eab1 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -108,10 +108,10 @@ static struct cgroup_subsys_state *blkcg_css(void)
 	return task_css(current, io_cgrp_id);
 }
 
-static bool blkcg_policy_enabled(struct gendisk *disk,
+static bool blkcg_policy_enabled(struct request_queue *q,
 				 const struct blkcg_policy *pol)
 {
-	return pol && test_bit(pol->plid, disk->blkcg_pols);
+	return pol && test_bit(pol->plid, q->blkcg_pols);
 }
 
 static void blkg_free_workfn(struct work_struct *work)
@@ -123,18 +123,18 @@ static void blkg_free_workfn(struct work_struct *work)
 	/*
 	 * pd_free_fn() can also be called from blkcg_deactivate_policy(),
 	 * in order to make sure pd_free_fn() is called in order, the deletion
-	 * of the list blkg->entry is delayed to here from blkg_destroy(), and
+	 * of the list blkg->q_node is delayed to here from blkg_destroy(), and
 	 * blkcg_mutex is used to synchronize blkg_free_workfn() and
 	 * blkcg_deactivate_policy().
 	 */
-	mutex_lock(&blkg->disk->blkcg_mutex);
+	mutex_lock(&blkg->disk->queue->blkcg_mutex);
 	for (i = 0; i < BLKCG_MAX_POLS; i++)
 		if (blkg->pd[i])
 			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
 	if (blkg->parent)
 		blkg_put(blkg->parent);
-	list_del_init(&blkg->entry);
-	mutex_unlock(&blkg->disk->blkcg_mutex);
+	list_del_init(&blkg->q_node);
+	mutex_unlock(&blkg->disk->queue->blkcg_mutex);
 
 	put_disk(blkg->disk);
 	free_percpu(blkg->iostat_cpu);
@@ -269,7 +269,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 	get_device(disk_to_dev(disk));
 	blkg->disk = disk;
 
-	INIT_LIST_HEAD(&blkg->entry);
+	INIT_LIST_HEAD(&blkg->q_node);
 	spin_lock_init(&blkg->async_bio_lock);
 	bio_list_init(&blkg->async_bios);
 	INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn);
@@ -285,7 +285,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 		struct blkcg_policy *pol = blkcg_policy[i];
 		struct blkg_policy_data *pd;
 
-		if (!blkcg_policy_enabled(disk, pol))
+		if (!blkcg_policy_enabled(disk->queue, pol))
 			continue;
 
 		/* alloc per-policy data and attach it to blkg */
@@ -371,7 +371,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk,
 	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->entry, &disk->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];
@@ -444,7 +444,7 @@ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 	while (true) {
 		struct blkcg *pos = blkcg;
 		struct blkcg *parent = blkcg_parent(blkcg);
-		struct blkcg_gq *ret_blkg = disk->root_blkg;
+		struct blkcg_gq *ret_blkg = q->root_blkg;
 
 		while (parent) {
 			blkg = blkg_lookup(parent, disk);
@@ -526,7 +526,7 @@ static void blkg_destroy_all(struct gendisk *disk)
 
 restart:
 	spin_lock_irq(&q->queue_lock);
-	list_for_each_entry_safe(blkg, n, &disk->blkg_list, entry) {
+	list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) {
 		struct blkcg *blkcg = blkg->blkcg;
 
 		spin_lock(&blkcg->lock);
@@ -545,7 +545,7 @@ static void blkg_destroy_all(struct gendisk *disk)
 		}
 	}
 
-	disk->root_blkg = NULL;
+	q->root_blkg = NULL;
 	spin_unlock_irq(&q->queue_lock);
 }
 
@@ -620,7 +620,7 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
 		spin_lock_irq(&blkg->disk->queue->queue_lock);
-		if (blkcg_policy_enabled(blkg->disk, pol))
+		if (blkcg_policy_enabled(blkg->disk->queue, pol))
 			total += prfill(sf, blkg->pd[pol->plid], data);
 		spin_unlock_irq(&blkg->disk->queue->queue_lock);
 	}
@@ -728,7 +728,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	rcu_read_lock();
 	spin_lock_irq(&q->queue_lock);
 
-	if (!blkcg_policy_enabled(disk, pol)) {
+	if (!blkcg_policy_enabled(q, pol)) {
 		ret = -EOPNOTSUPP;
 		goto fail_unlock;
 	}
@@ -771,7 +771,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		rcu_read_lock();
 		spin_lock_irq(&q->queue_lock);
 
-		if (!blkcg_policy_enabled(disk, pol)) {
+		if (!blkcg_policy_enabled(q, pol)) {
 			blkg_free(new_blkg);
 			ret = -EOPNOTSUPP;
 			goto fail_preloaded;
@@ -951,7 +951,7 @@ 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 = bdev->bd_disk->root_blkg;
+		struct blkcg_gq *blkg = bdev->bd_disk->queue->root_blkg;
 		struct blkg_iostat tmp;
 		int cpu;
 		unsigned long flags;
@@ -1298,8 +1298,8 @@ int blkcg_init_disk(struct gendisk *disk)
 	bool preloaded;
 	int ret;
 
-	INIT_LIST_HEAD(&disk->blkg_list);
-	mutex_init(&disk->blkcg_mutex);
+	INIT_LIST_HEAD(&q->blkg_list);
+	mutex_init(&q->blkcg_mutex);
 
 	new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL);
 	if (!new_blkg)
@@ -1313,7 +1313,7 @@ int blkcg_init_disk(struct gendisk *disk)
 	blkg = blkg_create(&blkcg_root, disk, new_blkg);
 	if (IS_ERR(blkg))
 		goto err_unlock;
-	disk->root_blkg = blkg;
+	q->root_blkg = blkg;
 	spin_unlock_irq(&q->queue_lock);
 
 	if (preloaded)
@@ -1426,7 +1426,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 	struct blkcg_gq *blkg, *pinned_blkg = NULL;
 	int ret;
 
-	if (blkcg_policy_enabled(disk, pol))
+	if (blkcg_policy_enabled(q, pol))
 		return 0;
 
 	if (queue_is_mq(q))
@@ -1435,7 +1435,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 	spin_lock_irq(&q->queue_lock);
 
 	/* blkg_list is pushed at the head, reverse walk to allocate parents first */
-	list_for_each_entry_reverse(blkg, &disk->blkg_list, entry) {
+	list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) {
 		struct blkg_policy_data *pd;
 
 		if (blkg->pd[pol->plid])
@@ -1480,16 +1480,16 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 
 	/* all allocated, init in the same order */
 	if (pol->pd_init_fn)
-		list_for_each_entry_reverse(blkg, &disk->blkg_list, entry)
+		list_for_each_entry_reverse(blkg, &q->blkg_list, q_node)
 			pol->pd_init_fn(blkg->pd[pol->plid]);
 
-	list_for_each_entry_reverse(blkg, &disk->blkg_list, entry) {
+	list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) {
 		if (pol->pd_online_fn)
 			pol->pd_online_fn(blkg->pd[pol->plid]);
 		blkg->pd[pol->plid]->online = true;
 	}
 
-	__set_bit(pol->plid, disk->blkcg_pols);
+	__set_bit(pol->plid, q->blkcg_pols);
 	ret = 0;
 
 	spin_unlock_irq(&q->queue_lock);
@@ -1505,7 +1505,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 enomem:
 	/* alloc failed, nothing's initialized yet, free everything */
 	spin_lock_irq(&q->queue_lock);
-	list_for_each_entry(blkg, &disk->blkg_list, entry) {
+	list_for_each_entry(blkg, &q->blkg_list, q_node) {
 		struct blkcg *blkcg = blkg->blkcg;
 
 		spin_lock(&blkcg->lock);
@@ -1535,18 +1535,18 @@ void blkcg_deactivate_policy(struct gendisk *disk,
 	struct request_queue *q = disk->queue;
 	struct blkcg_gq *blkg;
 
-	if (!blkcg_policy_enabled(disk, pol))
+	if (!blkcg_policy_enabled(q, pol))
 		return;
 
 	if (queue_is_mq(q))
 		blk_mq_freeze_queue(q);
 
-	mutex_lock(&disk->blkcg_mutex);
+	mutex_lock(&q->blkcg_mutex);
 	spin_lock_irq(&q->queue_lock);
 
-	__clear_bit(pol->plid, disk->blkcg_pols);
+	__clear_bit(pol->plid, q->blkcg_pols);
 
-	list_for_each_entry(blkg, &disk->blkg_list, entry) {
+	list_for_each_entry(blkg, &q->blkg_list, q_node) {
 		struct blkcg *blkcg = blkg->blkcg;
 
 		spin_lock(&blkcg->lock);
@@ -1560,7 +1560,7 @@ void blkcg_deactivate_policy(struct gendisk *disk,
 	}
 
 	spin_unlock_irq(&q->queue_lock);
-	mutex_unlock(&disk->blkcg_mutex);
+	mutex_unlock(&q->blkcg_mutex);
 
 	if (queue_is_mq(q))
 		blk_mq_unfreeze_queue(q);
@@ -1957,7 +1957,7 @@ static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio,
  * Associate @bio with the blkg found by combining the css's blkg and the
  * request_queue of the @bio.  An association failure is handled by walking up
  * the blkg tree.  Therefore, the blkg associated can be anything between @blkg
- * and disk->root_blkg.  This situation only happens when a cgroup is dying and
+ * and q->root_blkg.  This situation only happens when a cgroup is dying and
  * then the remaining bios will spill to the closest alive blkg.
  *
  * A reference will be taken on the blkg and will be released when @bio is
@@ -1972,8 +1972,8 @@ void bio_associate_blkg_from_css(struct bio *bio,
 	if (css && css->parent) {
 		bio->bi_blkg = blkg_tryget_closest(bio, css);
 	} else {
-		blkg_get(bio->bi_bdev->bd_disk->root_blkg);
-		bio->bi_blkg = bio->bi_bdev->bd_disk->root_blkg;
+		blkg_get(bdev_get_queue(bio->bi_bdev)->root_blkg);
+		bio->bi_blkg = bdev_get_queue(bio->bi_bdev)->root_blkg;
 	}
 }
 EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css);
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index e442b406ca0da6..151f24de253985 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -54,7 +54,7 @@ struct blkg_iostat_set {
 /* association between a blk cgroup and a request queue */
 struct blkcg_gq {
 	struct gendisk			*disk;
-	struct list_head		entry;
+	struct list_head		q_node;
 	struct hlist_node		blkcg_node;
 	struct blkcg			*blkcg;
 
@@ -250,7 +250,7 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	if (blkcg == &blkcg_root)
-		return disk->root_blkg;
+		return disk->queue->root_blkg;
 
 	blkg = rcu_dereference(blkcg->blkg_hint);
 	if (blkg && blkg->disk == disk)
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index 5d5aa1e526b742..bc0d217f5c1723 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -665,7 +665,7 @@ static void blkiolatency_timer_fn(struct timer_list *t)
 
 	rcu_read_lock();
 	blkg_for_each_descendant_pre(blkg, pos_css,
-				     blkiolat->rqos.disk->root_blkg) {
+				     blkiolat->rqos.disk->queue->root_blkg) {
 		struct iolatency_grp *iolat;
 		struct child_latency_info *lat_info;
 		unsigned long flags;
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index e7bd7050d68402..21c8d5e871eac9 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -451,8 +451,7 @@ static void blk_throtl_update_limit_valid(struct throtl_data *td)
 	bool low_valid = false;
 
 	rcu_read_lock();
-	blkg_for_each_descendant_post(blkg, pos_css,
-			td->queue->disk->root_blkg) {
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
 		struct throtl_grp *tg = blkg_to_tg(blkg);
 
 		if (tg->bps[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] ||
@@ -1181,7 +1180,7 @@ static void throtl_pending_timer_fn(struct timer_list *t)
 
 	spin_lock_irq(&q->queue_lock);
 
-	if (!q->disk->root_blkg)
+	if (!q->root_blkg)
 		goto out_unlock;
 
 	if (throtl_can_upgrade(td, NULL))
@@ -1323,8 +1322,7 @@ static void tg_conf_updated(struct throtl_grp *tg, bool global)
 	 * blk-throttle.
 	 */
 	blkg_for_each_descendant_pre(blkg, pos_css,
-			global ? tg->td->queue->disk->root_blkg :
-			tg_to_blkg(tg)) {
+			global ? tg->td->queue->root_blkg : tg_to_blkg(tg)) {
 		struct throtl_grp *this_tg = blkg_to_tg(blkg);
 		struct throtl_grp *parent_tg;
 
@@ -1719,7 +1717,7 @@ void blk_throtl_cancel_bios(struct gendisk *disk)
 	 * path need RCU protection and to prevent warning from lockdep.
 	 */
 	rcu_read_lock();
-	blkg_for_each_descendant_post(blkg, pos_css, disk->root_blkg) {
+	blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) {
 		struct throtl_grp *tg = blkg_to_tg(blkg);
 		struct throtl_service_queue *sq = &tg->service_queue;
 
@@ -1873,8 +1871,7 @@ static bool throtl_can_upgrade(struct throtl_data *td,
 		return false;
 
 	rcu_read_lock();
-	blkg_for_each_descendant_post(blkg, pos_css,
-			td->queue->disk->root_blkg) {
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
 		struct throtl_grp *tg = blkg_to_tg(blkg);
 
 		if (tg == this_tg)
@@ -1920,8 +1917,7 @@ static void throtl_upgrade_state(struct throtl_data *td)
 	td->low_upgrade_time = jiffies;
 	td->scale = 0;
 	rcu_read_lock();
-	blkg_for_each_descendant_post(blkg, pos_css,
-			td->queue->disk->root_blkg) {
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
 		struct throtl_grp *tg = blkg_to_tg(blkg);
 		struct throtl_service_queue *sq = &tg->service_queue;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 79aec4ebadb9e0..b9637d63e6f024 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -163,12 +163,6 @@ struct gendisk {
 	struct timer_rand_state *random;
 	atomic_t sync_io;		/* RAID */
 	struct disk_events *ev;
-#ifdef CONFIG_BLK_CGROUP
-	DECLARE_BITMAP		(blkcg_pols, BLKCG_MAX_POLS);
-	struct blkcg_gq		*root_blkg;
-	struct list_head	blkg_list;
-	struct mutex		blkcg_mutex;
-#endif /* CONFIG_BLK_CGROUP */
 #ifdef  CONFIG_BLK_DEV_INTEGRITY
 	struct kobject integrity_kobj;
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
@@ -487,6 +481,12 @@ struct request_queue {
 	struct blk_mq_tags	*sched_shared_tags;
 
 	struct list_head	icq_list;
+#ifdef CONFIG_BLK_CGROUP
+	DECLARE_BITMAP		(blkcg_pols, BLKCG_MAX_POLS);
+	struct blkcg_gq		*root_blkg;
+	struct list_head	blkg_list;
+	struct mutex		blkcg_mutex;
+#endif
 
 	struct queue_limits	limits;
 
-- 
2.39.1

[PATCH 1/5] Revert "blk-cgroup: move the cgroup information to struct gendisk"

[Christoph Hellwig]

This reverts commit 3f13ab7c80fdb0ada86a8e3e818960bc1ccbaa59 as a patch
it depends on caused a few problems.

Signed-off-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 block/bfq-cgroup.c     |  4 +--
 block/blk-cgroup.c     | 66 +++++++++++++++++++++---------------------
 block/blk-cgroup.h     |  4 +--
 block/blk-iolatency.c  |  2 +-
 block/blk-throttle.c   | 16 ++++------
 include/linux/blkdev.h | 12 ++++----
 6 files changed, 50 insertions(+), 54 deletions(-)

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 624530643a05cd..935a497b5dedb3 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -999,7 +999,7 @@ void bfq_end_wr_async(struct bfq_data *bfqd)
 {
 	struct blkcg_gq *blkg;
 
-	list_for_each_entry(blkg, &bfqd->queue->disk->blkg_list, entry) {
+	list_for_each_entry(blkg, &bfqd->queue->blkg_list, q_node) {
 		struct bfq_group *bfqg = blkg_to_bfqg(blkg);
 
 		bfq_end_wr_async_queues(bfqd, bfqg);
@@ -1293,7 +1293,7 @@ struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
 	if (ret)
 		return NULL;
 
-	return blkg_to_bfqg(bfqd->queue->disk->root_blkg);
+	return blkg_to_bfqg(bfqd->queue->root_blkg);
 }
 
 struct blkcg_policy blkcg_policy_bfq = {
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 935028912e7abf..1653786644eab1 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -108,10 +108,10 @@ static struct cgroup_subsys_state *blkcg_css(void)
 	return task_css(current, io_cgrp_id);
 }
 
-static bool blkcg_policy_enabled(struct gendisk *disk,
+static bool blkcg_policy_enabled(struct request_queue *q,
 				 const struct blkcg_policy *pol)
 {
-	return pol && test_bit(pol->plid, disk->blkcg_pols);
+	return pol && test_bit(pol->plid, q->blkcg_pols);
 }
 
 static void blkg_free_workfn(struct work_struct *work)
@@ -123,18 +123,18 @@ static void blkg_free_workfn(struct work_struct *work)
 	/*
 	 * pd_free_fn() can also be called from blkcg_deactivate_policy(),
 	 * in order to make sure pd_free_fn() is called in order, the deletion
-	 * of the list blkg->entry is delayed to here from blkg_destroy(), and
+	 * of the list blkg->q_node is delayed to here from blkg_destroy(), and
 	 * blkcg_mutex is used to synchronize blkg_free_workfn() and
 	 * blkcg_deactivate_policy().
 	 */
-	mutex_lock(&blkg->disk->blkcg_mutex);
+	mutex_lock(&blkg->disk->queue->blkcg_mutex);
 	for (i = 0; i < BLKCG_MAX_POLS; i++)
 		if (blkg->pd[i])
 			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
 	if (blkg->parent)
 		blkg_put(blkg->parent);
-	list_del_init(&blkg->entry);
-	mutex_unlock(&blkg->disk->blkcg_mutex);
+	list_del_init(&blkg->q_node);
+	mutex_unlock(&blkg->disk->queue->blkcg_mutex);
 
 	put_disk(blkg->disk);
 	free_percpu(blkg->iostat_cpu);
@@ -269,7 +269,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 	get_device(disk_to_dev(disk));
 	blkg->disk = disk;
 
-	INIT_LIST_HEAD(&blkg->entry);
+	INIT_LIST_HEAD(&blkg->q_node);
 	spin_lock_init(&blkg->async_bio_lock);
 	bio_list_init(&blkg->async_bios);
 	INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn);
@@ -285,7 +285,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 		struct blkcg_policy *pol = blkcg_policy[i];
 		struct blkg_policy_data *pd;
 
-		if (!blkcg_policy_enabled(disk, pol))
+		if (!blkcg_policy_enabled(disk->queue, pol))
 			continue;
 
 		/* alloc per-policy data and attach it to blkg */
@@ -371,7 +371,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk,
 	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->entry, &disk->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];
@@ -444,7 +444,7 @@ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 	while (true) {
 		struct blkcg *pos = blkcg;
 		struct blkcg *parent = blkcg_parent(blkcg);
-		struct blkcg_gq *ret_blkg = disk->root_blkg;
+		struct blkcg_gq *ret_blkg = q->root_blkg;
 
 		while (parent) {
 			blkg = blkg_lookup(parent, disk);
@@ -526,7 +526,7 @@ static void blkg_destroy_all(struct gendisk *disk)
 
 restart:
 	spin_lock_irq(&q->queue_lock);
-	list_for_each_entry_safe(blkg, n, &disk->blkg_list, entry) {
+	list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) {
 		struct blkcg *blkcg = blkg->blkcg;
 
 		spin_lock(&blkcg->lock);
@@ -545,7 +545,7 @@ static void blkg_destroy_all(struct gendisk *disk)
 		}
 	}
 
-	disk->root_blkg = NULL;
+	q->root_blkg = NULL;
 	spin_unlock_irq(&q->queue_lock);
 }
 
@@ -620,7 +620,7 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
 		spin_lock_irq(&blkg->disk->queue->queue_lock);
-		if (blkcg_policy_enabled(blkg->disk, pol))
+		if (blkcg_policy_enabled(blkg->disk->queue, pol))
 			total += prfill(sf, blkg->pd[pol->plid], data);
 		spin_unlock_irq(&blkg->disk->queue->queue_lock);
 	}
@@ -728,7 +728,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	rcu_read_lock();
 	spin_lock_irq(&q->queue_lock);
 
-	if (!blkcg_policy_enabled(disk, pol)) {
+	if (!blkcg_policy_enabled(q, pol)) {
 		ret = -EOPNOTSUPP;
 		goto fail_unlock;
 	}
@@ -771,7 +771,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		rcu_read_lock();
 		spin_lock_irq(&q->queue_lock);
 
-		if (!blkcg_policy_enabled(disk, pol)) {
+		if (!blkcg_policy_enabled(q, pol)) {
 			blkg_free(new_blkg);
 			ret = -EOPNOTSUPP;
 			goto fail_preloaded;
@@ -951,7 +951,7 @@ 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 = bdev->bd_disk->root_blkg;
+		struct blkcg_gq *blkg = bdev->bd_disk->queue->root_blkg;
 		struct blkg_iostat tmp;
 		int cpu;
 		unsigned long flags;
@@ -1298,8 +1298,8 @@ int blkcg_init_disk(struct gendisk *disk)
 	bool preloaded;
 	int ret;
 
-	INIT_LIST_HEAD(&disk->blkg_list);
-	mutex_init(&disk->blkcg_mutex);
+	INIT_LIST_HEAD(&q->blkg_list);
+	mutex_init(&q->blkcg_mutex);
 
 	new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL);
 	if (!new_blkg)
@@ -1313,7 +1313,7 @@ int blkcg_init_disk(struct gendisk *disk)
 	blkg = blkg_create(&blkcg_root, disk, new_blkg);
 	if (IS_ERR(blkg))
 		goto err_unlock;
-	disk->root_blkg = blkg;
+	q->root_blkg = blkg;
 	spin_unlock_irq(&q->queue_lock);
 
 	if (preloaded)
@@ -1426,7 +1426,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 	struct blkcg_gq *blkg, *pinned_blkg = NULL;
 	int ret;
 
-	if (blkcg_policy_enabled(disk, pol))
+	if (blkcg_policy_enabled(q, pol))
 		return 0;
 
 	if (queue_is_mq(q))
@@ -1435,7 +1435,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 	spin_lock_irq(&q->queue_lock);
 
 	/* blkg_list is pushed at the head, reverse walk to allocate parents first */
-	list_for_each_entry_reverse(blkg, &disk->blkg_list, entry) {
+	list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) {
 		struct blkg_policy_data *pd;
 
 		if (blkg->pd[pol->plid])
@@ -1480,16 +1480,16 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 
 	/* all allocated, init in the same order */
 	if (pol->pd_init_fn)
-		list_for_each_entry_reverse(blkg, &disk->blkg_list, entry)
+		list_for_each_entry_reverse(blkg, &q->blkg_list, q_node)
 			pol->pd_init_fn(blkg->pd[pol->plid]);
 
-	list_for_each_entry_reverse(blkg, &disk->blkg_list, entry) {
+	list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) {
 		if (pol->pd_online_fn)
 			pol->pd_online_fn(blkg->pd[pol->plid]);
 		blkg->pd[pol->plid]->online = true;
 	}
 
-	__set_bit(pol->plid, disk->blkcg_pols);
+	__set_bit(pol->plid, q->blkcg_pols);
 	ret = 0;
 
 	spin_unlock_irq(&q->queue_lock);
@@ -1505,7 +1505,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 enomem:
 	/* alloc failed, nothing's initialized yet, free everything */
 	spin_lock_irq(&q->queue_lock);
-	list_for_each_entry(blkg, &disk->blkg_list, entry) {
+	list_for_each_entry(blkg, &q->blkg_list, q_node) {
 		struct blkcg *blkcg = blkg->blkcg;
 
 		spin_lock(&blkcg->lock);
@@ -1535,18 +1535,18 @@ void blkcg_deactivate_policy(struct gendisk *disk,
 	struct request_queue *q = disk->queue;
 	struct blkcg_gq *blkg;
 
-	if (!blkcg_policy_enabled(disk, pol))
+	if (!blkcg_policy_enabled(q, pol))
 		return;
 
 	if (queue_is_mq(q))
 		blk_mq_freeze_queue(q);
 
-	mutex_lock(&disk->blkcg_mutex);
+	mutex_lock(&q->blkcg_mutex);
 	spin_lock_irq(&q->queue_lock);
 
-	__clear_bit(pol->plid, disk->blkcg_pols);
+	__clear_bit(pol->plid, q->blkcg_pols);
 
-	list_for_each_entry(blkg, &disk->blkg_list, entry) {
+	list_for_each_entry(blkg, &q->blkg_list, q_node) {
 		struct blkcg *blkcg = blkg->blkcg;
 
 		spin_lock(&blkcg->lock);
@@ -1560,7 +1560,7 @@ void blkcg_deactivate_policy(struct gendisk *disk,
 	}
 
 	spin_unlock_irq(&q->queue_lock);
-	mutex_unlock(&disk->blkcg_mutex);
+	mutex_unlock(&q->blkcg_mutex);
 
 	if (queue_is_mq(q))
 		blk_mq_unfreeze_queue(q);
@@ -1957,7 +1957,7 @@ static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio,
  * Associate @bio with the blkg found by combining the css's blkg and the
  * request_queue of the @bio.  An association failure is handled by walking up
  * the blkg tree.  Therefore, the blkg associated can be anything between @blkg
- * and disk->root_blkg.  This situation only happens when a cgroup is dying and
+ * and q->root_blkg.  This situation only happens when a cgroup is dying and
  * then the remaining bios will spill to the closest alive blkg.
  *
  * A reference will be taken on the blkg and will be released when @bio is
@@ -1972,8 +1972,8 @@ void bio_associate_blkg_from_css(struct bio *bio,
 	if (css && css->parent) {
 		bio->bi_blkg = blkg_tryget_closest(bio, css);
 	} else {
-		blkg_get(bio->bi_bdev->bd_disk->root_blkg);
-		bio->bi_blkg = bio->bi_bdev->bd_disk->root_blkg;
+		blkg_get(bdev_get_queue(bio->bi_bdev)->root_blkg);
+		bio->bi_blkg = bdev_get_queue(bio->bi_bdev)->root_blkg;
 	}
 }
 EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css);
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index e442b406ca0da6..151f24de253985 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -54,7 +54,7 @@ struct blkg_iostat_set {
 /* association between a blk cgroup and a request queue */
 struct blkcg_gq {
 	struct gendisk			*disk;
-	struct list_head		entry;
+	struct list_head		q_node;
 	struct hlist_node		blkcg_node;
 	struct blkcg			*blkcg;
 
@@ -250,7 +250,7 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	if (blkcg == &blkcg_root)
-		return disk->root_blkg;
+		return disk->queue->root_blkg;
 
 	blkg = rcu_dereference(blkcg->blkg_hint);
 	if (blkg && blkg->disk == disk)
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index 5d5aa1e526b742..bc0d217f5c1723 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -665,7 +665,7 @@ static void blkiolatency_timer_fn(struct timer_list *t)
 
 	rcu_read_lock();
 	blkg_for_each_descendant_pre(blkg, pos_css,
-				     blkiolat->rqos.disk->root_blkg) {
+				     blkiolat->rqos.disk->queue->root_blkg) {
 		struct iolatency_grp *iolat;
 		struct child_latency_info *lat_info;
 		unsigned long flags;
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index e7bd7050d68402..21c8d5e871eac9 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -451,8 +451,7 @@ static void blk_throtl_update_limit_valid(struct throtl_data *td)
 	bool low_valid = false;
 
 	rcu_read_lock();
-	blkg_for_each_descendant_post(blkg, pos_css,
-			td->queue->disk->root_blkg) {
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
 		struct throtl_grp *tg = blkg_to_tg(blkg);
 
 		if (tg->bps[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] ||
@@ -1181,7 +1180,7 @@ static void throtl_pending_timer_fn(struct timer_list *t)
 
 	spin_lock_irq(&q->queue_lock);
 
-	if (!q->disk->root_blkg)
+	if (!q->root_blkg)
 		goto out_unlock;
 
 	if (throtl_can_upgrade(td, NULL))
@@ -1323,8 +1322,7 @@ static void tg_conf_updated(struct throtl_grp *tg, bool global)
 	 * blk-throttle.
 	 */
 	blkg_for_each_descendant_pre(blkg, pos_css,
-			global ? tg->td->queue->disk->root_blkg :
-			tg_to_blkg(tg)) {
+			global ? tg->td->queue->root_blkg : tg_to_blkg(tg)) {
 		struct throtl_grp *this_tg = blkg_to_tg(blkg);
 		struct throtl_grp *parent_tg;
 
@@ -1719,7 +1717,7 @@ void blk_throtl_cancel_bios(struct gendisk *disk)
 	 * path need RCU protection and to prevent warning from lockdep.
 	 */
 	rcu_read_lock();
-	blkg_for_each_descendant_post(blkg, pos_css, disk->root_blkg) {
+	blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) {
 		struct throtl_grp *tg = blkg_to_tg(blkg);
 		struct throtl_service_queue *sq = &tg->service_queue;
 
@@ -1873,8 +1871,7 @@ static bool throtl_can_upgrade(struct throtl_data *td,
 		return false;
 
 	rcu_read_lock();
-	blkg_for_each_descendant_post(blkg, pos_css,
-			td->queue->disk->root_blkg) {
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
 		struct throtl_grp *tg = blkg_to_tg(blkg);
 
 		if (tg == this_tg)
@@ -1920,8 +1917,7 @@ static void throtl_upgrade_state(struct throtl_data *td)
 	td->low_upgrade_time = jiffies;
 	td->scale = 0;
 	rcu_read_lock();
-	blkg_for_each_descendant_post(blkg, pos_css,
-			td->queue->disk->root_blkg) {
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
 		struct throtl_grp *tg = blkg_to_tg(blkg);
 		struct throtl_service_queue *sq = &tg->service_queue;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 79aec4ebadb9e0..b9637d63e6f024 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -163,12 +163,6 @@ struct gendisk {
 	struct timer_rand_state *random;
 	atomic_t sync_io;		/* RAID */
 	struct disk_events *ev;
-#ifdef CONFIG_BLK_CGROUP
-	DECLARE_BITMAP		(blkcg_pols, BLKCG_MAX_POLS);
-	struct blkcg_gq		*root_blkg;
-	struct list_head	blkg_list;
-	struct mutex		blkcg_mutex;
-#endif /* CONFIG_BLK_CGROUP */
 #ifdef  CONFIG_BLK_DEV_INTEGRITY
 	struct kobject integrity_kobj;
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
@@ -487,6 +481,12 @@ struct request_queue {
 	struct blk_mq_tags	*sched_shared_tags;
 
 	struct list_head	icq_list;
+#ifdef CONFIG_BLK_CGROUP
+	DECLARE_BITMAP		(blkcg_pols, BLKCG_MAX_POLS);
+	struct blkcg_gq		*root_blkg;
+	struct list_head	blkg_list;
+	struct mutex		blkcg_mutex;
+#endif
 
 	struct queue_limits	limits;
 
-- 
2.39.1

[PATCH 2/5] Revert "blk-cgroup: delay calling blkcg_exit_disk until disk_release"

[Christoph Hellwig]

This reverts commit c43332fe028c252a2a28e46be70a530f64fc3c9d as it is not
needed without moving to disk references in the blkg.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 block/blk-throttle.c | 3 +--
 block/genhd.c        | 4 ++--
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 21c8d5e871eac9..74bb1e753ea09d 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -2407,8 +2407,7 @@ void blk_throtl_exit(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
 
-	if (!q->td)
-		return;
+	BUG_ON(!q->td);
 	del_timer_sync(&q->td->service_queue.pending_timer);
 	throtl_shutdown_wq(q);
 	blkcg_deactivate_policy(disk, &blkcg_policy_throtl);
diff --git a/block/genhd.c b/block/genhd.c
index 65373738c70b02..7e031559bf514c 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -668,6 +668,8 @@ void del_gendisk(struct gendisk *disk)
 	rq_qos_exit(q);
 	blk_mq_unquiesce_queue(q);
 
+	blkcg_exit_disk(disk);
+
 	/*
 	 * If the disk does not own the queue, allow using passthrough requests
 	 * again.  Else leave the queue frozen to fail all I/O.
@@ -1164,8 +1166,6 @@ static void disk_release(struct device *dev)
 	might_sleep();
 	WARN_ON_ONCE(disk_live(disk));
 
-	blkcg_exit_disk(disk);
-
 	/*
 	 * To undo the all initialization from blk_mq_init_allocated_queue in
 	 * case of a probe failure where add_disk is never called we have to
-- 
2.39.1

[PATCH 3/5] Revert "blk-cgroup: delay blk-cgroup initialization until add_disk"

[Christoph Hellwig]

This reverts commit 178fa7d49815ea8001f43ade37a22072829fd8ab.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 block/genhd.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/block/genhd.c b/block/genhd.c
index 7e031559bf514c..093ef292e98f7f 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -466,13 +466,9 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 	 */
 	pm_runtime_set_memalloc_noio(ddev, true);
 
-	ret = blkcg_init_disk(disk);
-	if (ret)
-		goto out_del_block_link;
-
 	ret = blk_integrity_add(disk);
 	if (ret)
-		goto out_blkcg_exit;
+		goto out_del_block_link;
 
 	disk->part0->bd_holder_dir =
 		kobject_create_and_add("holders", &ddev->kobj);
@@ -538,8 +534,6 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 	kobject_put(disk->part0->bd_holder_dir);
 out_del_integrity:
 	blk_integrity_del(disk);
-out_blkcg_exit:
-	blkcg_exit_disk(disk);
 out_del_block_link:
 	if (!sysfs_deprecated)
 		sysfs_remove_link(block_depr, dev_name(ddev));
@@ -668,8 +662,6 @@ void del_gendisk(struct gendisk *disk)
 	rq_qos_exit(q);
 	blk_mq_unquiesce_queue(q);
 
-	blkcg_exit_disk(disk);
-
 	/*
 	 * If the disk does not own the queue, allow using passthrough requests
 	 * again.  Else leave the queue frozen to fail all I/O.
@@ -1178,6 +1170,8 @@ static void disk_release(struct device *dev)
 	    !test_bit(GD_ADDED, &disk->state))
 		blk_mq_exit_queue(disk->queue);
 
+	blkcg_exit_disk(disk);
+
 	bioset_exit(&disk->bio_split);
 
 	disk_release_events(disk);
@@ -1390,6 +1384,9 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 	if (xa_insert(&disk->part_tbl, 0, disk->part0, GFP_KERNEL))
 		goto out_destroy_part_tbl;
 
+	if (blkcg_init_disk(disk))
+		goto out_erase_part0;
+
 	rand_initialize_disk(disk);
 	disk_to_dev(disk)->class = &block_class;
 	disk_to_dev(disk)->type = &disk_type;
@@ -1402,6 +1399,8 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 #endif
 	return disk;
 
+out_erase_part0:
+	xa_erase(&disk->part_tbl, 0);
 out_destroy_part_tbl:
 	xa_destroy(&disk->part_tbl);
 	disk->part0->bd_disk = NULL;
-- 
2.39.1

[PATCH 3/5] Revert "blk-cgroup: delay blk-cgroup initialization until add_disk"

[Christoph Hellwig]

This reverts commit 178fa7d49815ea8001f43ade37a22072829fd8ab.

Signed-off-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 block/genhd.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/block/genhd.c b/block/genhd.c
index 7e031559bf514c..093ef292e98f7f 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -466,13 +466,9 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 	 */
 	pm_runtime_set_memalloc_noio(ddev, true);
 
-	ret = blkcg_init_disk(disk);
-	if (ret)
-		goto out_del_block_link;
-
 	ret = blk_integrity_add(disk);
 	if (ret)
-		goto out_blkcg_exit;
+		goto out_del_block_link;
 
 	disk->part0->bd_holder_dir =
 		kobject_create_and_add("holders", &ddev->kobj);
@@ -538,8 +534,6 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 	kobject_put(disk->part0->bd_holder_dir);
 out_del_integrity:
 	blk_integrity_del(disk);
-out_blkcg_exit:
-	blkcg_exit_disk(disk);
 out_del_block_link:
 	if (!sysfs_deprecated)
 		sysfs_remove_link(block_depr, dev_name(ddev));
@@ -668,8 +662,6 @@ void del_gendisk(struct gendisk *disk)
 	rq_qos_exit(q);
 	blk_mq_unquiesce_queue(q);
 
-	blkcg_exit_disk(disk);
-
 	/*
 	 * If the disk does not own the queue, allow using passthrough requests
 	 * again.  Else leave the queue frozen to fail all I/O.
@@ -1178,6 +1170,8 @@ static void disk_release(struct device *dev)
 	    !test_bit(GD_ADDED, &disk->state))
 		blk_mq_exit_queue(disk->queue);
 
+	blkcg_exit_disk(disk);
+
 	bioset_exit(&disk->bio_split);
 
 	disk_release_events(disk);
@@ -1390,6 +1384,9 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 	if (xa_insert(&disk->part_tbl, 0, disk->part0, GFP_KERNEL))
 		goto out_destroy_part_tbl;
 
+	if (blkcg_init_disk(disk))
+		goto out_erase_part0;
+
 	rand_initialize_disk(disk);
 	disk_to_dev(disk)->class = &block_class;
 	disk_to_dev(disk)->type = &disk_type;
@@ -1402,6 +1399,8 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 #endif
 	return disk;
 
+out_erase_part0:
+	xa_erase(&disk->part_tbl, 0);
 out_destroy_part_tbl:
 	xa_destroy(&disk->part_tbl);
 	disk->part0->bd_disk = NULL;
-- 
2.39.1

[PATCH 4/5] Revert "blk-cgroup: pass a gendisk to blkg_lookup"

[Christoph Hellwig]

This reverts commit 821e840c08ad83736eced4037cdad864e95e2584.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 block/blk-cgroup.c | 16 ++++++++--------
 block/blk-cgroup.h | 20 ++++++++++----------
 2 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1653786644eab1..1574566321245e 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -350,7 +350,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk,
 
 	/* link parent */
 	if (blkcg_parent(blkcg)) {
-		blkg->parent = blkg_lookup(blkcg_parent(blkcg), disk);
+		blkg->parent = blkg_lookup(blkcg_parent(blkcg), disk->queue);
 		if (WARN_ON_ONCE(!blkg->parent)) {
 			ret = -ENODEV;
 			goto err_put_css;
@@ -423,12 +423,12 @@ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
-	blkg = blkg_lookup(blkcg, disk);
+	blkg = blkg_lookup(blkcg, q);
 	if (blkg)
 		return blkg;
 
 	spin_lock_irqsave(&q->queue_lock, flags);
-	blkg = blkg_lookup(blkcg, disk);
+	blkg = blkg_lookup(blkcg, q);
 	if (blkg) {
 		if (blkcg != &blkcg_root &&
 		    blkg != rcu_dereference(blkcg->blkg_hint))
@@ -447,7 +447,7 @@ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 		struct blkcg_gq *ret_blkg = q->root_blkg;
 
 		while (parent) {
-			blkg = blkg_lookup(parent, disk);
+			blkg = blkg_lookup(parent, q);
 			if (blkg) {
 				/* remember closest blkg */
 				ret_blkg = blkg;
@@ -733,7 +733,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		goto fail_unlock;
 	}
 
-	blkg = blkg_lookup(blkcg, disk);
+	blkg = blkg_lookup(blkcg, q);
 	if (blkg)
 		goto success;
 
@@ -747,7 +747,7 @@ 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, disk)) {
+		while (parent && !blkg_lookup(parent, q)) {
 			pos = parent;
 			parent = blkcg_parent(parent);
 		}
@@ -777,7 +777,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 			goto fail_preloaded;
 		}
 
-		blkg = blkg_lookup(pos, disk);
+		blkg = blkg_lookup(pos, q);
 		if (blkg) {
 			blkg_free(new_blkg);
 		} else {
@@ -1852,7 +1852,7 @@ void blkcg_maybe_throttle_current(void)
 	blkcg = css_to_blkcg(blkcg_css());
 	if (!blkcg)
 		goto out;
-	blkg = blkg_lookup(blkcg, disk);
+	blkg = blkg_lookup(blkcg, disk->queue);
 	if (!blkg)
 		goto out;
 	if (!blkg_tryget(blkg))
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 151f24de253985..3d9e42c519db86 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -234,30 +234,30 @@ static inline bool bio_issue_as_root_blkg(struct bio *bio)
 }
 
 /**
- * blkg_lookup - lookup blkg for the specified blkcg - disk pair
+ * blkg_lookup - lookup blkg for the specified blkcg - q pair
  * @blkcg: blkcg of interest
- * @disk: gendisk of interest
+ * @q: request_queue of interest
  *
- * Lookup blkg for the @blkcg - @disk pair.
+ * 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 gendisk *disk)
+					   struct request_queue *q)
 {
 	struct blkcg_gq *blkg;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	if (blkcg == &blkcg_root)
-		return disk->queue->root_blkg;
+		return q->root_blkg;
 
 	blkg = rcu_dereference(blkcg->blkg_hint);
-	if (blkg && blkg->disk == disk)
+	if (blkg && blkg->disk->queue == q)
 		return blkg;
 
-	blkg = radix_tree_lookup(&blkcg->blkg_tree, disk->queue->id);
-	if (blkg && blkg->disk != disk)
+	blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id);
+	if (blkg && blkg->disk->queue != q)
 		blkg = NULL;
 	return blkg;
 }
@@ -357,7 +357,7 @@ static inline void blkg_put(struct blkcg_gq *blkg)
 #define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg)		\
 	css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css)	\
 		if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css),	\
-					    (p_blkg)->disk)))
+					    (p_blkg)->disk->queue)))
 
 /**
  * blkg_for_each_descendant_post - post-order walk of a blkg's descendants
@@ -372,7 +372,7 @@ static inline void blkg_put(struct blkcg_gq *blkg)
 #define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg)		\
 	css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css)	\
 		if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css),	\
-					    (p_blkg)->disk)))
+					    (p_blkg)->disk->queue)))
 
 bool __blkcg_punt_bio_submit(struct bio *bio);
 
-- 
2.39.1

[PATCH 5/5] Revert "blk-cgroup: pin the gendisk in struct blkcg_gq"

[Christoph Hellwig]

This reverts commit 84d7d462b16dd5f0bf7c7ca9254bf81db2c952a2.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 block/bfq-cgroup.c        |  6 +++---
 block/blk-cgroup-rwstat.c |  2 +-
 block/blk-cgroup.c        | 35 ++++++++++++++++++-----------------
 block/blk-cgroup.h        | 11 ++++++-----
 block/blk-iocost.c        |  2 +-
 block/blk-iolatency.c     |  4 ++--
 block/blk-throttle.c      |  4 ++--
 7 files changed, 33 insertions(+), 31 deletions(-)

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 935a497b5dedb3..ea3638e06e04b4 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -405,7 +405,7 @@ static void bfqg_stats_xfer_dead(struct bfq_group *bfqg)
 
 	parent = bfqg_parent(bfqg);
 
-	lockdep_assert_held(&bfqg_to_blkg(bfqg)->disk->queue->queue_lock);
+	lockdep_assert_held(&bfqg_to_blkg(bfqg)->q->queue_lock);
 
 	if (unlikely(!parent))
 		return;
@@ -536,7 +536,7 @@ static void bfq_pd_init(struct blkg_policy_data *pd)
 {
 	struct blkcg_gq *blkg = pd_to_blkg(pd);
 	struct bfq_group *bfqg = blkg_to_bfqg(blkg);
-	struct bfq_data *bfqd = blkg->disk->queue->elevator->elevator_data;
+	struct bfq_data *bfqd = blkg->q->elevator->elevator_data;
 	struct bfq_entity *entity = &bfqg->entity;
 	struct bfq_group_data *d = blkcg_to_bfqgd(blkg->blkcg);
 
@@ -1199,7 +1199,7 @@ static u64 bfqg_prfill_stat_recursive(struct seq_file *sf,
 	struct cgroup_subsys_state *pos_css;
 	u64 sum = 0;
 
-	lockdep_assert_held(&blkg->disk->queue->queue_lock);
+	lockdep_assert_held(&blkg->q->queue_lock);
 
 	rcu_read_lock();
 	blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
diff --git a/block/blk-cgroup-rwstat.c b/block/blk-cgroup-rwstat.c
index b8b8c82e667a3b..3304e841df7ce9 100644
--- a/block/blk-cgroup-rwstat.c
+++ b/block/blk-cgroup-rwstat.c
@@ -107,7 +107,7 @@ void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
 	struct cgroup_subsys_state *pos_css;
 	unsigned int i;
 
-	lockdep_assert_held(&blkg->disk->queue->queue_lock);
+	lockdep_assert_held(&blkg->q->queue_lock);
 
 	memset(sum, 0, sizeof(*sum));
 	rcu_read_lock();
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1574566321245e..981ebe003b1c63 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -118,6 +118,7 @@ static void blkg_free_workfn(struct work_struct *work)
 {
 	struct blkcg_gq *blkg = container_of(work, struct blkcg_gq,
 					     free_work);
+	struct request_queue *q = blkg->q;
 	int i;
 
 	/*
@@ -127,16 +128,16 @@ static void blkg_free_workfn(struct work_struct *work)
 	 * blkcg_mutex is used to synchronize blkg_free_workfn() and
 	 * blkcg_deactivate_policy().
 	 */
-	mutex_lock(&blkg->disk->queue->blkcg_mutex);
+	mutex_lock(&q->blkcg_mutex);
 	for (i = 0; i < BLKCG_MAX_POLS; i++)
 		if (blkg->pd[i])
 			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
 	if (blkg->parent)
 		blkg_put(blkg->parent);
 	list_del_init(&blkg->q_node);
-	mutex_unlock(&blkg->disk->queue->blkcg_mutex);
+	mutex_unlock(&q->blkcg_mutex);
 
-	put_disk(blkg->disk);
+	blk_put_queue(q);
 	free_percpu(blkg->iostat_cpu);
 	percpu_ref_exit(&blkg->refcnt);
 	kfree(blkg);
@@ -263,12 +264,10 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 	blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask);
 	if (!blkg->iostat_cpu)
 		goto out_exit_refcnt;
-
-	if (test_bit(GD_DEAD, &disk->state))
+	if (!blk_get_queue(disk->queue))
 		goto out_free_iostat;
-	get_device(disk_to_dev(disk));
-	blkg->disk = disk;
 
+	blkg->q = disk->queue;
 	INIT_LIST_HEAD(&blkg->q_node);
 	spin_lock_init(&blkg->async_bio_lock);
 	bio_list_init(&blkg->async_bios);
@@ -304,7 +303,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 	while (--i >= 0)
 		if (blkg->pd[i])
 			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
-	put_disk(blkg->disk);
+	blk_put_queue(disk->queue);
 out_free_iostat:
 	free_percpu(blkg->iostat_cpu);
 out_exit_refcnt:
@@ -476,7 +475,7 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 	struct blkcg *blkcg = blkg->blkcg;
 	int i;
 
-	lockdep_assert_held(&blkg->disk->queue->queue_lock);
+	lockdep_assert_held(&blkg->q->queue_lock);
 	lockdep_assert_held(&blkcg->lock);
 
 	/*
@@ -500,7 +499,7 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 
 	blkg->online = false;
 
-	radix_tree_delete(&blkcg->blkg_tree, blkg->disk->queue->id);
+	radix_tree_delete(&blkcg->blkg_tree, blkg->q->id);
 	hlist_del_init_rcu(&blkg->blkcg_node);
 
 	/*
@@ -587,7 +586,9 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 
 const char *blkg_dev_name(struct blkcg_gq *blkg)
 {
-	return bdi_dev_name(blkg->disk->bdi);
+	if (!blkg->q->disk)
+		return NULL;
+	return bdi_dev_name(blkg->q->disk->bdi);
 }
 
 /**
@@ -619,10 +620,10 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
 
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
-		spin_lock_irq(&blkg->disk->queue->queue_lock);
-		if (blkcg_policy_enabled(blkg->disk->queue, pol))
+		spin_lock_irq(&blkg->q->queue_lock);
+		if (blkcg_policy_enabled(blkg->q, pol))
 			total += prfill(sf, blkg->pd[pol->plid], data);
-		spin_unlock_irq(&blkg->disk->queue->queue_lock);
+		spin_unlock_irq(&blkg->q->queue_lock);
 	}
 	rcu_read_unlock();
 
@@ -1046,9 +1047,9 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
-		spin_lock_irq(&blkg->disk->queue->queue_lock);
+		spin_lock_irq(&blkg->q->queue_lock);
 		blkcg_print_one_stat(blkg, sf);
-		spin_unlock_irq(&blkg->disk->queue->queue_lock);
+		spin_unlock_irq(&blkg->q->queue_lock);
 	}
 	rcu_read_unlock();
 	return 0;
@@ -1118,7 +1119,7 @@ static void blkcg_destroy_blkgs(struct blkcg *blkcg)
 	while (!hlist_empty(&blkcg->blkg_list)) {
 		struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first,
 						struct blkcg_gq, blkcg_node);
-		struct request_queue *q = blkg->disk->queue;
+		struct request_queue *q = blkg->q;
 
 		if (need_resched() || !spin_trylock(&q->queue_lock)) {
 			/*
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 3d9e42c519db86..9c5078755e5e19 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -53,7 +53,8 @@ struct blkg_iostat_set {
 
 /* association between a blk cgroup and a request queue */
 struct blkcg_gq {
-	struct gendisk			*disk;
+	/* Pointer to the associated request_queue */
+	struct request_queue		*q;
 	struct list_head		q_node;
 	struct hlist_node		blkcg_node;
 	struct blkcg			*blkcg;
@@ -253,11 +254,11 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
 		return q->root_blkg;
 
 	blkg = rcu_dereference(blkcg->blkg_hint);
-	if (blkg && blkg->disk->queue == q)
+	if (blkg && blkg->q == q)
 		return blkg;
 
 	blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id);
-	if (blkg && blkg->disk->queue != q)
+	if (blkg && blkg->q != q)
 		blkg = NULL;
 	return blkg;
 }
@@ -357,7 +358,7 @@ static inline void blkg_put(struct blkcg_gq *blkg)
 #define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg)		\
 	css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css)	\
 		if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css),	\
-					    (p_blkg)->disk->queue)))
+					    (p_blkg)->q)))
 
 /**
  * blkg_for_each_descendant_post - post-order walk of a blkg's descendants
@@ -372,7 +373,7 @@ static inline void blkg_put(struct blkcg_gq *blkg)
 #define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg)		\
 	css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css)	\
 		if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css),	\
-					    (p_blkg)->disk->queue)))
+					    (p_blkg)->q)))
 
 bool __blkcg_punt_bio_submit(struct bio *bio);
 
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 7a2dc9dc8e3ba0..ff534e9d92dca2 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -2947,7 +2947,7 @@ static void ioc_pd_init(struct blkg_policy_data *pd)
 {
 	struct ioc_gq *iocg = pd_to_iocg(pd);
 	struct blkcg_gq *blkg = pd_to_blkg(&iocg->pd);
-	struct ioc *ioc = q_to_ioc(blkg->disk->queue);
+	struct ioc *ioc = q_to_ioc(blkg->q);
 	struct ioc_now now;
 	struct blkcg_gq *tblkg;
 	unsigned long flags;
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index bc0d217f5c1723..0dc910568b3145 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -967,12 +967,12 @@ static void iolatency_pd_init(struct blkg_policy_data *pd)
 {
 	struct iolatency_grp *iolat = pd_to_lat(pd);
 	struct blkcg_gq *blkg = lat_to_blkg(iolat);
-	struct rq_qos *rqos = blkcg_rq_qos(blkg->disk->queue);
+	struct rq_qos *rqos = blkcg_rq_qos(blkg->q);
 	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
 	u64 now = ktime_to_ns(ktime_get());
 	int cpu;
 
-	if (blk_queue_nonrot(blkg->disk->queue))
+	if (blk_queue_nonrot(blkg->q))
 		iolat->ssd = true;
 	else
 		iolat->ssd = false;
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 74bb1e753ea09d..47e9d8be68f300 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -387,7 +387,7 @@ static void throtl_pd_init(struct blkg_policy_data *pd)
 {
 	struct throtl_grp *tg = pd_to_tg(pd);
 	struct blkcg_gq *blkg = tg_to_blkg(tg);
-	struct throtl_data *td = blkg->disk->queue->td;
+	struct throtl_data *td = blkg->q->td;
 	struct throtl_service_queue *sq = &tg->service_queue;
 
 	/*
@@ -1174,7 +1174,7 @@ static void throtl_pending_timer_fn(struct timer_list *t)
 
 	/* throtl_data may be gone, so figure out request queue by blkg */
 	if (tg)
-		q = tg->pd.blkg->disk->queue;
+		q = tg->pd.blkg->q;
 	else
 		q = td->queue;
 
-- 
2.39.1

[PATCH 5/5] Revert "blk-cgroup: pin the gendisk in struct blkcg_gq"

[Christoph Hellwig]

This reverts commit 84d7d462b16dd5f0bf7c7ca9254bf81db2c952a2.

Signed-off-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 block/bfq-cgroup.c        |  6 +++---
 block/blk-cgroup-rwstat.c |  2 +-
 block/blk-cgroup.c        | 35 ++++++++++++++++++-----------------
 block/blk-cgroup.h        | 11 ++++++-----
 block/blk-iocost.c        |  2 +-
 block/blk-iolatency.c     |  4 ++--
 block/blk-throttle.c      |  4 ++--
 7 files changed, 33 insertions(+), 31 deletions(-)

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 935a497b5dedb3..ea3638e06e04b4 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -405,7 +405,7 @@ static void bfqg_stats_xfer_dead(struct bfq_group *bfqg)
 
 	parent = bfqg_parent(bfqg);
 
-	lockdep_assert_held(&bfqg_to_blkg(bfqg)->disk->queue->queue_lock);
+	lockdep_assert_held(&bfqg_to_blkg(bfqg)->q->queue_lock);
 
 	if (unlikely(!parent))
 		return;
@@ -536,7 +536,7 @@ static void bfq_pd_init(struct blkg_policy_data *pd)
 {
 	struct blkcg_gq *blkg = pd_to_blkg(pd);
 	struct bfq_group *bfqg = blkg_to_bfqg(blkg);
-	struct bfq_data *bfqd = blkg->disk->queue->elevator->elevator_data;
+	struct bfq_data *bfqd = blkg->q->elevator->elevator_data;
 	struct bfq_entity *entity = &bfqg->entity;
 	struct bfq_group_data *d = blkcg_to_bfqgd(blkg->blkcg);
 
@@ -1199,7 +1199,7 @@ static u64 bfqg_prfill_stat_recursive(struct seq_file *sf,
 	struct cgroup_subsys_state *pos_css;
 	u64 sum = 0;
 
-	lockdep_assert_held(&blkg->disk->queue->queue_lock);
+	lockdep_assert_held(&blkg->q->queue_lock);
 
 	rcu_read_lock();
 	blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
diff --git a/block/blk-cgroup-rwstat.c b/block/blk-cgroup-rwstat.c
index b8b8c82e667a3b..3304e841df7ce9 100644
--- a/block/blk-cgroup-rwstat.c
+++ b/block/blk-cgroup-rwstat.c
@@ -107,7 +107,7 @@ void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
 	struct cgroup_subsys_state *pos_css;
 	unsigned int i;
 
-	lockdep_assert_held(&blkg->disk->queue->queue_lock);
+	lockdep_assert_held(&blkg->q->queue_lock);
 
 	memset(sum, 0, sizeof(*sum));
 	rcu_read_lock();
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1574566321245e..981ebe003b1c63 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -118,6 +118,7 @@ static void blkg_free_workfn(struct work_struct *work)
 {
 	struct blkcg_gq *blkg = container_of(work, struct blkcg_gq,
 					     free_work);
+	struct request_queue *q = blkg->q;
 	int i;
 
 	/*
@@ -127,16 +128,16 @@ static void blkg_free_workfn(struct work_struct *work)
 	 * blkcg_mutex is used to synchronize blkg_free_workfn() and
 	 * blkcg_deactivate_policy().
 	 */
-	mutex_lock(&blkg->disk->queue->blkcg_mutex);
+	mutex_lock(&q->blkcg_mutex);
 	for (i = 0; i < BLKCG_MAX_POLS; i++)
 		if (blkg->pd[i])
 			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
 	if (blkg->parent)
 		blkg_put(blkg->parent);
 	list_del_init(&blkg->q_node);
-	mutex_unlock(&blkg->disk->queue->blkcg_mutex);
+	mutex_unlock(&q->blkcg_mutex);
 
-	put_disk(blkg->disk);
+	blk_put_queue(q);
 	free_percpu(blkg->iostat_cpu);
 	percpu_ref_exit(&blkg->refcnt);
 	kfree(blkg);
@@ -263,12 +264,10 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 	blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask);
 	if (!blkg->iostat_cpu)
 		goto out_exit_refcnt;
-
-	if (test_bit(GD_DEAD, &disk->state))
+	if (!blk_get_queue(disk->queue))
 		goto out_free_iostat;
-	get_device(disk_to_dev(disk));
-	blkg->disk = disk;
 
+	blkg->q = disk->queue;
 	INIT_LIST_HEAD(&blkg->q_node);
 	spin_lock_init(&blkg->async_bio_lock);
 	bio_list_init(&blkg->async_bios);
@@ -304,7 +303,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 	while (--i >= 0)
 		if (blkg->pd[i])
 			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
-	put_disk(blkg->disk);
+	blk_put_queue(disk->queue);
 out_free_iostat:
 	free_percpu(blkg->iostat_cpu);
 out_exit_refcnt:
@@ -476,7 +475,7 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 	struct blkcg *blkcg = blkg->blkcg;
 	int i;
 
-	lockdep_assert_held(&blkg->disk->queue->queue_lock);
+	lockdep_assert_held(&blkg->q->queue_lock);
 	lockdep_assert_held(&blkcg->lock);
 
 	/*
@@ -500,7 +499,7 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 
 	blkg->online = false;
 
-	radix_tree_delete(&blkcg->blkg_tree, blkg->disk->queue->id);
+	radix_tree_delete(&blkcg->blkg_tree, blkg->q->id);
 	hlist_del_init_rcu(&blkg->blkcg_node);
 
 	/*
@@ -587,7 +586,9 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 
 const char *blkg_dev_name(struct blkcg_gq *blkg)
 {
-	return bdi_dev_name(blkg->disk->bdi);
+	if (!blkg->q->disk)
+		return NULL;
+	return bdi_dev_name(blkg->q->disk->bdi);
 }
 
 /**
@@ -619,10 +620,10 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
 
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
-		spin_lock_irq(&blkg->disk->queue->queue_lock);
-		if (blkcg_policy_enabled(blkg->disk->queue, pol))
+		spin_lock_irq(&blkg->q->queue_lock);
+		if (blkcg_policy_enabled(blkg->q, pol))
 			total += prfill(sf, blkg->pd[pol->plid], data);
-		spin_unlock_irq(&blkg->disk->queue->queue_lock);
+		spin_unlock_irq(&blkg->q->queue_lock);
 	}
 	rcu_read_unlock();
 
@@ -1046,9 +1047,9 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
-		spin_lock_irq(&blkg->disk->queue->queue_lock);
+		spin_lock_irq(&blkg->q->queue_lock);
 		blkcg_print_one_stat(blkg, sf);
-		spin_unlock_irq(&blkg->disk->queue->queue_lock);
+		spin_unlock_irq(&blkg->q->queue_lock);
 	}
 	rcu_read_unlock();
 	return 0;
@@ -1118,7 +1119,7 @@ static void blkcg_destroy_blkgs(struct blkcg *blkcg)
 	while (!hlist_empty(&blkcg->blkg_list)) {
 		struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first,
 						struct blkcg_gq, blkcg_node);
-		struct request_queue *q = blkg->disk->queue;
+		struct request_queue *q = blkg->q;
 
 		if (need_resched() || !spin_trylock(&q->queue_lock)) {
 			/*
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 3d9e42c519db86..9c5078755e5e19 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -53,7 +53,8 @@ struct blkg_iostat_set {
 
 /* association between a blk cgroup and a request queue */
 struct blkcg_gq {
-	struct gendisk			*disk;
+	/* Pointer to the associated request_queue */
+	struct request_queue		*q;
 	struct list_head		q_node;
 	struct hlist_node		blkcg_node;
 	struct blkcg			*blkcg;
@@ -253,11 +254,11 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
 		return q->root_blkg;
 
 	blkg = rcu_dereference(blkcg->blkg_hint);
-	if (blkg && blkg->disk->queue == q)
+	if (blkg && blkg->q == q)
 		return blkg;
 
 	blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id);
-	if (blkg && blkg->disk->queue != q)
+	if (blkg && blkg->q != q)
 		blkg = NULL;
 	return blkg;
 }
@@ -357,7 +358,7 @@ static inline void blkg_put(struct blkcg_gq *blkg)
 #define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg)		\
 	css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css)	\
 		if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css),	\
-					    (p_blkg)->disk->queue)))
+					    (p_blkg)->q)))
 
 /**
  * blkg_for_each_descendant_post - post-order walk of a blkg's descendants
@@ -372,7 +373,7 @@ static inline void blkg_put(struct blkcg_gq *blkg)
 #define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg)		\
 	css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css)	\
 		if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css),	\
-					    (p_blkg)->disk->queue)))
+					    (p_blkg)->q)))
 
 bool __blkcg_punt_bio_submit(struct bio *bio);
 
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 7a2dc9dc8e3ba0..ff534e9d92dca2 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -2947,7 +2947,7 @@ static void ioc_pd_init(struct blkg_policy_data *pd)
 {
 	struct ioc_gq *iocg = pd_to_iocg(pd);
 	struct blkcg_gq *blkg = pd_to_blkg(&iocg->pd);
-	struct ioc *ioc = q_to_ioc(blkg->disk->queue);
+	struct ioc *ioc = q_to_ioc(blkg->q);
 	struct ioc_now now;
 	struct blkcg_gq *tblkg;
 	unsigned long flags;
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index bc0d217f5c1723..0dc910568b3145 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -967,12 +967,12 @@ static void iolatency_pd_init(struct blkg_policy_data *pd)
 {
 	struct iolatency_grp *iolat = pd_to_lat(pd);
 	struct blkcg_gq *blkg = lat_to_blkg(iolat);
-	struct rq_qos *rqos = blkcg_rq_qos(blkg->disk->queue);
+	struct rq_qos *rqos = blkcg_rq_qos(blkg->q);
 	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
 	u64 now = ktime_to_ns(ktime_get());
 	int cpu;
 
-	if (blk_queue_nonrot(blkg->disk->queue))
+	if (blk_queue_nonrot(blkg->q))
 		iolat->ssd = true;
 	else
 		iolat->ssd = false;
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 74bb1e753ea09d..47e9d8be68f300 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -387,7 +387,7 @@ static void throtl_pd_init(struct blkg_policy_data *pd)
 {
 	struct throtl_grp *tg = pd_to_tg(pd);
 	struct blkcg_gq *blkg = tg_to_blkg(tg);
-	struct throtl_data *td = blkg->disk->queue->td;
+	struct throtl_data *td = blkg->q->td;
 	struct throtl_service_queue *sq = &tg->service_queue;
 
 	/*
@@ -1174,7 +1174,7 @@ static void throtl_pending_timer_fn(struct timer_list *t)
 
 	/* throtl_data may be gone, so figure out request queue by blkg */
 	if (tg)
-		q = tg->pd.blkg->disk->queue;
+		q = tg->pd.blkg->q;
 	else
 		q = td->queue;
 
-- 
2.39.1

Re: [PATCH 1/5] Revert "blk-cgroup: move the cgroup information to struct gendisk"

[Jens Axboe]

On Tue, 14 Feb 2023 19:33:04 +0100, Christoph Hellwig wrote:
> This reverts commit 3f13ab7c80fdb0ada86a8e3e818960bc1ccbaa59 as a patch
> it depends on caused a few problems.
> 
> 

Applied, thanks!

[1/5] Revert "blk-cgroup: move the cgroup information to struct gendisk"
      commit: 1231039db31cf0703996d0b1797c2702e25a110a
[2/5] Revert "blk-cgroup: delay calling blkcg_exit_disk until disk_release"
      commit: b4e94f9c2c0822265a6942741d270aa16d229331
[3/5] Revert "blk-cgroup: delay blk-cgroup initialization until add_disk"
      commit: b6553bef8cdc2983943f60edb8dc5e49361ebb3b
[4/5] Revert "blk-cgroup: pass a gendisk to blkg_lookup"
      commit: 9a9c261e6b5512e0b8d9ae9b1c1746c743a15a48
[5/5] Revert "blk-cgroup: pin the gendisk in struct blkcg_gq"
      commit: a06377c5d01eeeaa52ad979b62c3c72efcc3eff0

Best regards,
-- 
Jens Axboe

Re: revert blk-cgroup changs

[Ming Lei]

On Tue, Feb 14, 2023 at 07:33:03PM +0100, Christoph Hellwig wrote:
> Hi Jens,
> 
> this series reverts a bunch of blk-cgroup patches as one of them
> caused a problem for which the time is running out to fix for this
> merge window

Thanks for fixing these issues!

Tested-by: Ming Lei <ming.lei@redhat.com>

Thanks,
Ming

Re: revert blk-cgroup changs

[Ming Lei]

On Tue, Feb 14, 2023 at 07:33:03PM +0100, Christoph Hellwig wrote:
> Hi Jens,
> 
> this series reverts a bunch of blk-cgroup patches as one of them
> caused a problem for which the time is running out to fix for this
> merge window

Thanks for fixing these issues!

Tested-by: Ming Lei <ming.lei-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>

Thanks,
Ming