Merge tag 'for-5.18/block-2022-03-18' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - BFQ cleanups and fixes (Yu, Zhang, Yahu, Paolo)

 - blk-rq-qos completion fix (Tejun)

 - blk-cgroup merge fix (Tejun)

 - Add offline error return value to distinguish it from an IO error on
   the device (Song)

 - IO stats fixes (Zhang, Christoph)

 - blkcg refcount fixes (Ming, Yu)

 - Fix for indefinite dispatch loop softlockup (Shin'ichiro)

 - blk-mq hardware queue management improvements (Ming)

 - sbitmap dead code removal (Ming, John)

 - Plugging merge improvements (me)

 - Show blk-crypto capabilities in sysfs (Eric)

 - Multiple delayed queue run improvement (David)

 - Block throttling fixes (Ming)

 - Start deprecating auto module loading based on dev_t (Christoph)

 - bio allocation improvements (Christoph, Chaitanya)

 - Get rid of bio_devname (Christoph)

 - bio clone improvements (Christoph)

 - Block plugging improvements (Christoph)

 - Get rid of genhd.h header (Christoph)

 - Ensure drivers use appropriate flush helpers (Christoph)

 - Refcounting improvements (Christoph)

 - Queue initialization and teardown improvements (Ming, Christoph)

 - Misc fixes/improvements (Barry, Chaitanya, Colin, Dan, Jiapeng,
   Lukas, Nian, Yang, Eric, Chengming)

* tag 'for-5.18/block-2022-03-18' of git://git.kernel.dk/linux-block: (127 commits)
  block: cancel all throttled bios in del_gendisk()
  block: let blkcg_gq grab request queue's refcnt
  block: avoid use-after-free on throttle data
  block: limit request dispatch loop duration
  block/bfq-iosched: Fix spelling mistake "tenative" -> "tentative"
  sr: simplify the local variable initialization in sr_block_open()
  block: don't merge across cgroup boundaries if blkcg is enabled
  block: fix rq-qos breakage from skipping rq_qos_done_bio()
  block: flush plug based on hardware and software queue order
  block: ensure plug merging checks the correct queue at least once
  block: move rq_qos_exit() into disk_release()
  block: do more work in elevator_exit
  block: move blk_exit_queue into disk_release
  block: move q_usage_counter release into blk_queue_release
  block: don't remove hctx debugfs dir from blk_mq_exit_queue
  block: move blkcg initialization/destroy into disk allocation/release handler
  sr: implement ->free_disk to simplify refcounting
  sd: implement ->free_disk to simplify refcounting
  sd: delay calling free_opal_dev
  sd: call sd_zbc_release_disk before releasing the scsi_device reference
  ...

11 files changed, 370 insertions, 852 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 117d7f248ac9..4c21f6e69e18 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -405,21 +405,25 @@ extern void bioset_exit(struct bio_set *);
 extern int biovec_init_pool(mempool_t *pool, int pool_entries);
 extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src);
 
-struct bio *bio_alloc_bioset(gfp_t gfp, unsigned short nr_iovecs,
-		struct bio_set *bs);
-struct bio *bio_alloc_kiocb(struct kiocb *kiocb, unsigned short nr_vecs,
-		struct bio_set *bs);
+struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
+			     unsigned int opf, gfp_t gfp_mask,
+			     struct bio_set *bs);
+struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev,
+		unsigned short nr_vecs, unsigned int opf, struct bio_set *bs);
 struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs);
 extern void bio_put(struct bio *);
 
-extern void __bio_clone_fast(struct bio *, struct bio *);
-extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
+struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src,
+		gfp_t gfp, struct bio_set *bs);
+int bio_init_clone(struct block_device *bdev, struct bio *bio,
+		struct bio *bio_src, gfp_t gfp);
 
 extern struct bio_set fs_bio_set;
 
-static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned short nr_iovecs)
+static inline struct bio *bio_alloc(struct block_device *bdev,
+		unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask)
 {
-	return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set);
+	return bio_alloc_bioset(bdev, nr_vecs, opf, gfp_mask, &fs_bio_set);
 }
 
 void submit_bio(struct bio *bio);
@@ -454,10 +458,10 @@ static inline int bio_iov_vecs_to_alloc(struct iov_iter *iter, int max_segs)
 struct request_queue;
 
 extern int submit_bio_wait(struct bio *bio);
-extern void bio_init(struct bio *bio, struct bio_vec *table,
-		     unsigned short max_vecs);
+void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table,
+	      unsigned short max_vecs, unsigned int opf);
 extern void bio_uninit(struct bio *);
-extern void bio_reset(struct bio *);
+void bio_reset(struct bio *bio, struct block_device *bdev, unsigned int opf);
 void bio_chain(struct bio *, struct bio *);
 
 int bio_add_page(struct bio *, struct page *, unsigned len, unsigned off);
@@ -487,8 +491,6 @@ static inline void bio_release_pages(struct bio *bio, bool mark_dirty)
 		__bio_release_pages(bio, mark_dirty);
 }
 
-extern const char *bio_devname(struct bio *bio, char *buffer);
-
 #define bio_dev(bio) \
 	disk_devt((bio)->bi_bdev->bd_disk)
 
@@ -515,13 +517,6 @@ static inline void bio_set_dev(struct bio *bio, struct block_device *bdev)
 	bio_associate_blkg(bio);
 }
 
-static inline void bio_copy_dev(struct bio *dst, struct bio *src)
-{
-	bio_clear_flag(dst, BIO_REMAPPED);
-	dst->bi_bdev = src->bi_bdev;
-	bio_clone_blkg_association(dst, src);
-}
-
 /*
  * BIO list management for use by remapping drivers (e.g. DM or MD) and loop.
  *
@@ -790,6 +785,7 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
 		bio->bi_opf |= REQ_NOWAIT;
 }
 
-struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp);
+struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
+		unsigned int nr_pages, unsigned int opf, gfp_t gfp);
 
 #endif /* __LINUX_BIO_H */
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index b4de2010fba5..f2ad8ed8f777 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -25,14 +25,8 @@
 #include <linux/kthread.h>
 #include <linux/fs.h>
 
-/* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */
-#define BLKG_STAT_CPU_BATCH	(INT_MAX / 2)
-
-/* Max limits for throttle policy */
-#define THROTL_IOPS_MAX		UINT_MAX
 #define FC_APPID_LEN              129
 
-
 #ifdef CONFIG_BLK_CGROUP
 
 enum blkg_iostat_type {
@@ -44,6 +38,7 @@ enum blkg_iostat_type {
 };
 
 struct blkcg_gq;
+struct blkg_policy_data;
 
 struct blkcg {
 	struct cgroup_subsys_state	css;
@@ -76,36 +71,6 @@ struct blkg_iostat_set {
 	struct blkg_iostat		last;
 };
 
-/*
- * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a
- * request_queue (q).  This is used by blkcg policies which need to track
- * information per blkcg - q pair.
- *
- * There can be multiple active blkcg policies and each blkg:policy pair is
- * represented by a blkg_policy_data which is allocated and freed by each
- * policy's pd_alloc/free_fn() methods.  A policy can allocate private data
- * area by allocating larger data structure which embeds blkg_policy_data
- * at the beginning.
- */
-struct blkg_policy_data {
-	/* the blkg and policy id this per-policy data belongs to */
-	struct blkcg_gq			*blkg;
-	int				plid;
-};
-
-/*
- * Policies that need to keep per-blkcg data which is independent from any
- * request_queue associated to it should implement cpd_alloc/free_fn()
- * methods.  A policy can allocate private data area by allocating larger
- * data structure which embeds blkcg_policy_data at the beginning.
- * cpd_init() is invoked to let each policy handle per-blkcg data.
- */
-struct blkcg_policy_data {
-	/* the blkcg and policy id this per-policy data belongs to */
-	struct blkcg			*blkcg;
-	int				plid;
-};
-
 /* association between a blk cgroup and a request queue */
 struct blkcg_gq {
 	/* Pointer to the associated request_queue */
@@ -141,93 +106,11 @@ struct blkcg_gq {
 	struct rcu_head			rcu_head;
 };
 
-typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp);
-typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd);
-typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd);
-typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd);
-typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp,
-				struct request_queue *q, struct blkcg *blkcg);
-typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd);
-typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd);
-typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd);
-typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd);
-typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd);
-typedef bool (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd,
-				struct seq_file *s);
-
-struct blkcg_policy {
-	int				plid;
-	/* cgroup files for the policy */
-	struct cftype			*dfl_cftypes;
-	struct cftype			*legacy_cftypes;
-
-	/* operations */
-	blkcg_pol_alloc_cpd_fn		*cpd_alloc_fn;
-	blkcg_pol_init_cpd_fn		*cpd_init_fn;
-	blkcg_pol_free_cpd_fn		*cpd_free_fn;
-	blkcg_pol_bind_cpd_fn		*cpd_bind_fn;
-
-	blkcg_pol_alloc_pd_fn		*pd_alloc_fn;
-	blkcg_pol_init_pd_fn		*pd_init_fn;
-	blkcg_pol_online_pd_fn		*pd_online_fn;
-	blkcg_pol_offline_pd_fn		*pd_offline_fn;
-	blkcg_pol_free_pd_fn		*pd_free_fn;
-	blkcg_pol_reset_pd_stats_fn	*pd_reset_stats_fn;
-	blkcg_pol_stat_pd_fn		*pd_stat_fn;
-};
-
-extern struct blkcg blkcg_root;
 extern struct cgroup_subsys_state * const blkcg_root_css;
-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);
-
-/* Blkio controller policy registration */
-int blkcg_policy_register(struct blkcg_policy *pol);
-void blkcg_policy_unregister(struct blkcg_policy *pol);
-int blkcg_activate_policy(struct request_queue *q,
-			  const struct blkcg_policy *pol);
-void blkcg_deactivate_policy(struct request_queue *q,
-			     const struct blkcg_policy *pol);
-
-const char *blkg_dev_name(struct blkcg_gq *blkg);
-void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
-		       u64 (*prfill)(struct seq_file *,
-				     struct blkg_policy_data *, int),
-		       const struct blkcg_policy *pol, int data,
-		       bool show_total);
-u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v);
-
-struct blkg_conf_ctx {
-	struct block_device		*bdev;
-	struct blkcg_gq			*blkg;
-	char				*body;
-};
-
-struct block_device *blkcg_conf_open_bdev(char **inputp);
-int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
-		   char *input, struct blkg_conf_ctx *ctx);
-void blkg_conf_finish(struct blkg_conf_ctx *ctx);
 
-/**
- * blkcg_css - find the current css
- *
- * Find the css associated with either the kthread or the current task.
- * This may return a dying css, so it is up to the caller to use tryget logic
- * to confirm it is alive and well.
- */
-static inline struct cgroup_subsys_state *blkcg_css(void)
-{
-	struct cgroup_subsys_state *css;
-
-	css = kthread_blkcg();
-	if (css)
-		return css;
-	return task_css(current, io_cgrp_id);
-}
+void blkcg_destroy_blkgs(struct blkcg *blkcg);
+void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay);
+void blkcg_maybe_throttle_current(void);
 
 static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
 {
@@ -235,27 +118,6 @@ static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
 }
 
 /**
- * __bio_blkcg - internal, inconsistent version to get blkcg
- *
- * DO NOT USE.
- * This function is inconsistent and consequently is dangerous to use.  The
- * first part of the function returns a blkcg where a reference is owned by the
- * bio.  This means it does not need to be rcu protected as it cannot go away
- * with the bio owning a reference to it.  However, the latter potentially gets
- * it from task_css().  This can race against task migration and the cgroup
- * dying.  It is also semantically different as it must be called rcu protected
- * and is susceptible to failure when trying to get a reference to it.
- * Therefore, it is not ok to assume that *_get() will always succeed on the
- * blkcg returned here.
- */
-static inline struct blkcg *__bio_blkcg(struct bio *bio)
-{
-	if (bio && bio->bi_blkg)
-		return bio->bi_blkg->blkcg;
-	return css_to_blkcg(blkcg_css());
-}
-
-/**
  * bio_blkcg - grab the blkcg associated with a bio
  * @bio: target bio
  *
@@ -291,22 +153,6 @@ static inline bool blk_cgroup_congested(void)
 }
 
 /**
- * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg
- * @return: true if this bio needs to be submitted with the root blkg context.
- *
- * In order to avoid priority inversions we sometimes need to issue a bio as if
- * it were attached to the root blkg, and then backcharge to the actual owning
- * blkg.  The idea is we do bio_blkcg() to look up the actual context for the
- * bio and attach the appropriate blkg to the bio.  Then we call this helper and
- * if it is true run with the root blkg for that queue and then do any
- * backcharging to the originating cgroup once the io is complete.
- */
-static inline bool bio_issue_as_root_blkg(struct bio *bio)
-{
-	return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0;
-}
-
-/**
  * blkcg_parent - get the parent of a blkcg
  * @blkcg: blkcg of interest
  *
@@ -318,96 +164,6 @@ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg)
 }
 
 /**
- * __blkg_lookup - internal version of blkg_lookup()
- * @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.
- */
-static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg,
-					     struct request_queue *q,
-					     bool update_hint)
-{
-	struct blkcg_gq *blkg;
-
-	if (blkcg == &blkcg_root)
-		return q->root_blkg;
-
-	blkg = rcu_dereference(blkcg->blkg_hint);
-	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_to_pdata - get policy private data
- * @blkg: blkg of interest
- * @pol: policy of interest
- *
- * Return pointer to private data associated with the @blkg-@pol pair.
- */
-static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
-						  struct blkcg_policy *pol)
-{
-	return blkg ? blkg->pd[pol->plid] : NULL;
-}
-
-static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg,
-						     struct blkcg_policy *pol)
-{
-	return blkcg ? blkcg->cpd[pol->plid] : NULL;
-}
-
-/**
- * pdata_to_blkg - get blkg associated with policy private data
- * @pd: policy private data of interest
- *
- * @pd is policy private data.  Determine the blkg it's associated with.
- */
-static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd)
-{
-	return pd ? pd->blkg : NULL;
-}
-
-static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd)
-{
-	return cpd ? cpd->blkcg : NULL;
-}
-
-extern void blkcg_destroy_blkgs(struct blkcg *blkcg);
-
-/**
  * blkcg_pin_online - pin online state
  * @blkcg: blkcg of interest
  *
@@ -439,231 +195,24 @@ static inline void blkcg_unpin_online(struct blkcg *blkcg)
 	} while (blkcg);
 }
 
-/**
- * blkg_path - format cgroup path of blkg
- * @blkg: blkg of interest
- * @buf: target buffer
- * @buflen: target buffer length
- *
- * Format the path of the cgroup of @blkg into @buf.
- */
-static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
-{
-	return cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
-}
-
-/**
- * blkg_get - get a blkg reference
- * @blkg: blkg to get
- *
- * The caller should be holding an existing reference.
- */
-static inline void blkg_get(struct blkcg_gq *blkg)
-{
-	percpu_ref_get(&blkg->refcnt);
-}
-
-/**
- * blkg_tryget - try and get a blkg reference
- * @blkg: blkg to get
- *
- * This is for use when doing an RCU lookup of the blkg.  We may be in the midst
- * of freeing this blkg, so we can only use it if the refcnt is not zero.
- */
-static inline bool blkg_tryget(struct blkcg_gq *blkg)
-{
-	return blkg && percpu_ref_tryget(&blkg->refcnt);
-}
-
-/**
- * blkg_put - put a blkg reference
- * @blkg: blkg to put
- */
-static inline void blkg_put(struct blkcg_gq *blkg)
-{
-	percpu_ref_put(&blkg->refcnt);
-}
-
-/**
- * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants
- * @d_blkg: loop cursor pointing to the current descendant
- * @pos_css: used for iteration
- * @p_blkg: target blkg to walk descendants of
- *
- * Walk @c_blkg through the descendants of @p_blkg.  Must be used with RCU
- * read locked.  If called under either blkcg or queue lock, the iteration
- * is guaranteed to include all and only online blkgs.  The caller may
- * update @pos_css by calling css_rightmost_descendant() to skip subtree.
- * @p_blkg is included in the iteration and the first node to be visited.
- */
-#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)->q, false)))
-
-/**
- * blkg_for_each_descendant_post - post-order walk of a blkg's descendants
- * @d_blkg: loop cursor pointing to the current descendant
- * @pos_css: used for iteration
- * @p_blkg: target blkg to walk descendants of
- *
- * Similar to blkg_for_each_descendant_pre() but performs post-order
- * traversal instead.  Synchronization rules are the same.  @p_blkg is
- * included in the iteration and the last node to be visited.
- */
-#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)->q, false)))
-
-bool __blkcg_punt_bio_submit(struct bio *bio);
-
-static inline bool blkcg_punt_bio_submit(struct bio *bio)
-{
-	if (bio->bi_opf & REQ_CGROUP_PUNT)
-		return __blkcg_punt_bio_submit(bio);
-	else
-		return false;
-}
-
-static inline void blkcg_bio_issue_init(struct bio *bio)
-{
-	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
-}
-
-static inline void blkcg_use_delay(struct blkcg_gq *blkg)
-{
-	if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0))
-		return;
-	if (atomic_add_return(1, &blkg->use_delay) == 1)
-		atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
-}
-
-static inline int blkcg_unuse_delay(struct blkcg_gq *blkg)
-{
-	int old = atomic_read(&blkg->use_delay);
-
-	if (WARN_ON_ONCE(old < 0))
-		return 0;
-	if (old == 0)
-		return 0;
-
-	/*
-	 * We do this song and dance because we can race with somebody else
-	 * adding or removing delay.  If we just did an atomic_dec we'd end up
-	 * negative and we'd already be in trouble.  We need to subtract 1 and
-	 * then check to see if we were the last delay so we can drop the
-	 * congestion count on the cgroup.
-	 */
-	while (old) {
-		int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1);
-		if (cur == old)
-			break;
-		old = cur;
-	}
-
-	if (old == 0)
-		return 0;
-	if (old == 1)
-		atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
-	return 1;
-}
-
-/**
- * blkcg_set_delay - Enable allocator delay mechanism with the specified delay amount
- * @blkg: target blkg
- * @delay: delay duration in nsecs
- *
- * When enabled with this function, the delay is not decayed and must be
- * explicitly cleared with blkcg_clear_delay(). Must not be mixed with
- * blkcg_[un]use_delay() and blkcg_add_delay() usages.
- */
-static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay)
-{
-	int old = atomic_read(&blkg->use_delay);
-
-	/* We only want 1 person setting the congestion count for this blkg. */
-	if (!old && atomic_cmpxchg(&blkg->use_delay, old, -1) == old)
-		atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
-
-	atomic64_set(&blkg->delay_nsec, delay);
-}
-
-/**
- * blkcg_clear_delay - Disable allocator delay mechanism
- * @blkg: target blkg
- *
- * Disable use_delay mechanism. See blkcg_set_delay().
- */
-static inline void blkcg_clear_delay(struct blkcg_gq *blkg)
-{
-	int old = atomic_read(&blkg->use_delay);
-
-	/* We only want 1 person clearing the congestion count for this blkg. */
-	if (old && atomic_cmpxchg(&blkg->use_delay, old, 0) == old)
-		atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
-}
-
-void blk_cgroup_bio_start(struct bio *bio);
-void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta);
-void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay);
-void blkcg_maybe_throttle_current(void);
 #else	/* CONFIG_BLK_CGROUP */
 
 struct blkcg {
 };
 
-struct blkg_policy_data {
-};
-
-struct blkcg_policy_data {
-};
-
 struct blkcg_gq {
 };
 
-struct blkcg_policy {
-};
-
 #define blkcg_root_css	((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))
 
 static inline void blkcg_maybe_throttle_current(void) { }
 static inline bool blk_cgroup_congested(void) { return false; }
 
 #ifdef CONFIG_BLOCK
-
 static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { }
-
-static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
-static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
-{ return NULL; }
-static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
-static inline void blkcg_exit_queue(struct request_queue *q) { }
-static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; }
-static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { }
-static inline int blkcg_activate_policy(struct request_queue *q,
-					const struct blkcg_policy *pol) { return 0; }
-static inline void blkcg_deactivate_policy(struct request_queue *q,
-					   const struct blkcg_policy *pol) { }
-
-static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; }
 static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; }
+#endif /* CONFIG_BLOCK */
 
-static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
-						  struct blkcg_policy *pol) { return NULL; }
-static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; }
-static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; }
-static inline void blkg_get(struct blkcg_gq *blkg) { }
-static inline void blkg_put(struct blkcg_gq *blkg) { }
-
-static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; }
-static inline void blkcg_bio_issue_init(struct bio *bio) { }
-static inline void blk_cgroup_bio_start(struct bio *bio) { }
-
-#define blk_queue_for_each_rl(rl, q)	\
-	for ((rl) = &(q)->root_rl; (rl); (rl) = NULL)
-
-#endif	/* CONFIG_BLOCK */
 #endif	/* CONFIG_BLK_CGROUP */
 
 #ifdef CONFIG_BLK_CGROUP_FC_APPID
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index d319ffa59354..7aa5c54901a9 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -917,8 +917,7 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq)
 }
 
 #define queue_for_each_hw_ctx(q, hctx, i)				\
-	for ((i) = 0; (i) < (q)->nr_hw_queues &&			\
-	     ({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++)
+	xa_for_each(&(q)->hctx_table, (i), (hctx))
 
 #define hctx_for_each_ctx(hctx, ctx, i)					\
 	for ((i) = 0; (i) < (hctx)->nr_ctx &&				\
@@ -952,8 +951,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 		struct bio_set *bs, gfp_t gfp_mask,
 		int (*bio_ctr)(struct bio *, struct bio *, void *), void *data);
 void blk_rq_unprep_clone(struct request *rq);
-blk_status_t blk_insert_cloned_request(struct request_queue *q,
-		struct request *rq);
+blk_status_t blk_insert_cloned_request(struct request *rq);
 
 struct rq_map_data {
 	struct page **pages;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index fe065c394fff..0c3563b45fe9 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -153,6 +153,13 @@ typedef u8 __bitwise blk_status_t;
  */
 #define BLK_STS_ZONE_ACTIVE_RESOURCE	((__force blk_status_t)16)
 
+/*
+ * BLK_STS_OFFLINE is returned from the driver when the target device is offline
+ * or is being taken offline. This could help differentiate the case where a
+ * device is intentionally being shut down from a real I/O error.
+ */
+#define BLK_STS_OFFLINE		((__force blk_status_t)17)
+
 /**
  * blk_path_error - returns true if error may be path related
  * @error: status the request was completed with
@@ -317,7 +324,8 @@ enum {
 	BIO_TRACE_COMPLETION,	/* bio_endio() should trace the final completion
 				 * of this bio. */
 	BIO_CGROUP_ACCT,	/* has been accounted to a cgroup */
-	BIO_TRACKED,		/* set if bio goes through the rq_qos path */
+	BIO_QOS_THROTTLED,	/* bio went through rq_qos throttle path */
+	BIO_QOS_MERGED,		/* but went through rq_qos merge path */
 	BIO_REMAPPED,
 	BIO_ZONE_WRITE_LOCKED,	/* Owns a zoned device zone write lock */
 	BIO_PERCPU_CACHE,	/* can participate in per-cpu alloc cache */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 16b47035e4b0..eb27312a1b8f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1,9 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Portions Copyright (C) 1992 Drew Eckhardt
+ */
 #ifndef _LINUX_BLKDEV_H
 #define _LINUX_BLKDEV_H
 
-#include <linux/sched.h>
-#include <linux/genhd.h>
+#include <linux/types.h>
+#include <linux/blk_types.h>
+#include <linux/device.h>
 #include <linux/list.h>
 #include <linux/llist.h>
 #include <linux/minmax.h>
@@ -12,11 +16,15 @@
 #include <linux/wait.h>
 #include <linux/bio.h>
 #include <linux/gfp.h>
+#include <linux/kdev_t.h>
 #include <linux/rcupdate.h>
 #include <linux/percpu-refcount.h>
 #include <linux/blkzoned.h>
+#include <linux/sched.h>
 #include <linux/sbitmap.h>
 #include <linux/srcu.h>
+#include <linux/uuid.h>
+#include <linux/xarray.h>
 
 struct module;
 struct request_queue;
@@ -33,6 +41,10 @@ struct blk_queue_stats;
 struct blk_stat_callback;
 struct blk_crypto_profile;
 
+extern const struct device_type disk_type;
+extern struct device_type part_type;
+extern struct class block_class;
+
 /* Must be consistent with blk_mq_poll_stats_bkt() */
 #define BLK_MQ_POLL_STATS_BKTS 16
 
@@ -45,6 +57,145 @@ struct blk_crypto_profile;
  */
 #define BLKCG_MAX_POLS		6
 
+#define DISK_MAX_PARTS			256
+#define DISK_NAME_LEN			32
+
+#define PARTITION_META_INFO_VOLNAMELTH	64
+/*
+ * Enough for the string representation of any kind of UUID plus NULL.
+ * EFI UUID is 36 characters. MSDOS UUID is 11 characters.
+ */
+#define PARTITION_META_INFO_UUIDLTH	(UUID_STRING_LEN + 1)
+
+struct partition_meta_info {
+	char uuid[PARTITION_META_INFO_UUIDLTH];
+	u8 volname[PARTITION_META_INFO_VOLNAMELTH];
+};
+
+/**
+ * DOC: genhd capability flags
+ *
+ * ``GENHD_FL_REMOVABLE``: indicates that the block device gives access to
+ * removable media.  When set, the device remains present even when media is not
+ * inserted.  Shall not be set for devices which are removed entirely when the
+ * media is removed.
+ *
+ * ``GENHD_FL_HIDDEN``: the block device is hidden; it doesn't produce events,
+ * doesn't appear in sysfs, and can't be opened from userspace or using
+ * blkdev_get*. Used for the underlying components of multipath devices.
+ *
+ * ``GENHD_FL_NO_PART``: partition support is disabled.  The kernel will not
+ * scan for partitions from add_disk, and users can't add partitions manually.
+ *
+ */
+enum {
+	GENHD_FL_REMOVABLE			= 1 << 0,
+	GENHD_FL_HIDDEN				= 1 << 1,
+	GENHD_FL_NO_PART			= 1 << 2,
+};
+
+enum {
+	DISK_EVENT_MEDIA_CHANGE			= 1 << 0, /* media changed */
+	DISK_EVENT_EJECT_REQUEST		= 1 << 1, /* eject requested */
+};
+
+enum {
+	/* Poll even if events_poll_msecs is unset */
+	DISK_EVENT_FLAG_POLL			= 1 << 0,
+	/* Forward events to udev */
+	DISK_EVENT_FLAG_UEVENT			= 1 << 1,
+	/* Block event polling when open for exclusive write */
+	DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE	= 1 << 2,
+};
+
+struct disk_events;
+struct badblocks;
+
+struct blk_integrity {
+	const struct blk_integrity_profile	*profile;
+	unsigned char				flags;
+	unsigned char				tuple_size;
+	unsigned char				interval_exp;
+	unsigned char				tag_size;
+};
+
+struct gendisk {
+	/*
+	 * major/first_minor/minors should not be set by any new driver, the
+	 * block core will take care of allocating them automatically.
+	 */
+	int major;
+	int first_minor;
+	int minors;
+
+	char disk_name[DISK_NAME_LEN];	/* name of major driver */
+
+	unsigned short events;		/* supported events */
+	unsigned short event_flags;	/* flags related to event processing */
+
+	struct xarray part_tbl;
+	struct block_device *part0;
+
+	const struct block_device_operations *fops;
+	struct request_queue *queue;
+	void *private_data;
+
+	int flags;
+	unsigned long state;
+#define GD_NEED_PART_SCAN		0
+#define GD_READ_ONLY			1
+#define GD_DEAD				2
+#define GD_NATIVE_CAPACITY		3
+#define GD_ADDED			4
+
+	struct mutex open_mutex;	/* open/close mutex */
+	unsigned open_partitions;	/* number of open partitions */
+
+	struct backing_dev_info	*bdi;
+	struct kobject *slave_dir;
+#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED
+	struct list_head slave_bdevs;
+#endif
+	struct timer_rand_state *random;
+	atomic_t sync_io;		/* RAID */
+	struct disk_events *ev;
+#ifdef  CONFIG_BLK_DEV_INTEGRITY
+	struct kobject integrity_kobj;
+#endif	/* CONFIG_BLK_DEV_INTEGRITY */
+#if IS_ENABLED(CONFIG_CDROM)
+	struct cdrom_device_info *cdi;
+#endif
+	int node_id;
+	struct badblocks *bb;
+	struct lockdep_map lockdep_map;
+	u64 diskseq;
+};
+
+static inline bool disk_live(struct gendisk *disk)
+{
+	return !inode_unhashed(disk->part0->bd_inode);
+}
+
+/*
+ * The gendisk is refcounted by the part0 block_device, and the bd_device
+ * therein is also used for device model presentation in sysfs.
+ */
+#define dev_to_disk(device) \
+	(dev_to_bdev(device)->bd_disk)
+#define disk_to_dev(disk) \
+	(&((disk)->part0->bd_device))
+
+#if IS_REACHABLE(CONFIG_CDROM)
+#define disk_to_cdi(disk)	((disk)->cdi)
+#else
+#define disk_to_cdi(disk)	NULL
+#endif
+
+static inline dev_t disk_devt(struct gendisk *disk)
+{
+	return MKDEV(disk->major, disk->first_minor);
+}
+
 static inline int blk_validate_block_size(unsigned long bsize)
 {
 	if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
@@ -204,7 +355,7 @@ struct request_queue {
 	unsigned int		queue_depth;
 
 	/* hw dispatch queues */
-	struct blk_mq_hw_ctx	**queue_hw_ctx;
+	struct xarray		hctx_table;
 	unsigned int		nr_hw_queues;
 
 	/*
@@ -262,6 +413,7 @@ struct request_queue {
 
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	struct blk_crypto_profile *crypto_profile;
+	struct kobject *crypto_kobject;
 #endif
 
 	unsigned int		rq_timeout;
@@ -596,6 +748,118 @@ static inline unsigned int blk_queue_depth(struct request_queue *q)
 #define for_each_bio(_bio)		\
 	for (; _bio; _bio = _bio->bi_next)
 
+int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
+				 const struct attribute_group **groups);
+static inline int __must_check add_disk(struct gendisk *disk)
+{
+	return device_add_disk(NULL, disk, NULL);
+}
+void del_gendisk(struct gendisk *gp);
+void invalidate_disk(struct gendisk *disk);
+void set_disk_ro(struct gendisk *disk, bool read_only);
+void disk_uevent(struct gendisk *disk, enum kobject_action action);
+
+static inline int get_disk_ro(struct gendisk *disk)
+{
+	return disk->part0->bd_read_only ||
+		test_bit(GD_READ_ONLY, &disk->state);
+}
+
+static inline int bdev_read_only(struct block_device *bdev)
+{
+	return bdev->bd_read_only || get_disk_ro(bdev->bd_disk);
+}
+
+bool set_capacity_and_notify(struct gendisk *disk, sector_t size);
+bool disk_force_media_change(struct gendisk *disk, unsigned int events);
+
+void add_disk_randomness(struct gendisk *disk) __latent_entropy;
+void rand_initialize_disk(struct gendisk *disk);
+
+static inline sector_t get_start_sect(struct block_device *bdev)
+{
+	return bdev->bd_start_sect;
+}
+
+static inline sector_t bdev_nr_sectors(struct block_device *bdev)
+{
+	return bdev->bd_nr_sectors;
+}
+
+static inline loff_t bdev_nr_bytes(struct block_device *bdev)
+{
+	return (loff_t)bdev_nr_sectors(bdev) << SECTOR_SHIFT;
+}
+
+static inline sector_t get_capacity(struct gendisk *disk)
+{
+	return bdev_nr_sectors(disk->part0);
+}
+
+static inline u64 sb_bdev_nr_blocks(struct super_block *sb)
+{
+	return bdev_nr_sectors(sb->s_bdev) >>
+		(sb->s_blocksize_bits - SECTOR_SHIFT);
+}
+
+int bdev_disk_changed(struct gendisk *disk, bool invalidate);
+
+struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
+		struct lock_class_key *lkclass);
+void put_disk(struct gendisk *disk);
+struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass);
+
+/**
+ * blk_alloc_disk - allocate a gendisk structure
+ * @node_id: numa node to allocate on
+ *
+ * Allocate and pre-initialize a gendisk structure for use with BIO based
+ * drivers.
+ *
+ * Context: can sleep
+ */
+#define blk_alloc_disk(node_id)						\
+({									\
+	static struct lock_class_key __key;				\
+									\
+	__blk_alloc_disk(node_id, &__key);				\
+})
+void blk_cleanup_disk(struct gendisk *disk);
+
+int __register_blkdev(unsigned int major, const char *name,
+		void (*probe)(dev_t devt));
+#define register_blkdev(major, name) \
+	__register_blkdev(major, name, NULL)
+void unregister_blkdev(unsigned int major, const char *name);
+
+bool bdev_check_media_change(struct block_device *bdev);
+int __invalidate_device(struct block_device *bdev, bool kill_dirty);
+void set_capacity(struct gendisk *disk, sector_t size);
+
+#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED
+int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
+void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk);
+int bd_register_pending_holders(struct gendisk *disk);
+#else
+static inline int bd_link_disk_holder(struct block_device *bdev,
+				      struct gendisk *disk)
+{
+	return 0;
+}
+static inline void bd_unlink_disk_holder(struct block_device *bdev,
+					 struct gendisk *disk)
+{
+}
+static inline int bd_register_pending_holders(struct gendisk *disk)
+{
+	return 0;
+}
+#endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */
+
+dev_t part_devt(struct gendisk *disk, u8 partno);
+void inc_diskseq(struct gendisk *disk);
+dev_t blk_lookup_devt(const char *name, int partno);
+void blk_request_module(dev_t devt);
 
 extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
@@ -792,14 +1056,11 @@ extern void blk_start_plug(struct blk_plug *);
 extern void blk_start_plug_nr_ios(struct blk_plug *, unsigned short);
 extern void blk_finish_plug(struct blk_plug *);
 
-void blk_flush_plug(struct blk_plug *plug, bool from_schedule);
-
-static inline bool blk_needs_flush_plug(struct task_struct *tsk)
+void __blk_flush_plug(struct blk_plug *plug, bool from_schedule);
+static inline void blk_flush_plug(struct blk_plug *plug, bool async)
 {
-	struct blk_plug *plug = tsk->plug;
-
-	return plug &&
-		 (plug->mq_list || !list_empty(&plug->cb_list));
+	if (plug)
+		__blk_flush_plug(plug, async);
 }
 
 int blkdev_issue_flush(struct block_device *bdev);
@@ -825,11 +1086,6 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async)
 {
 }
 
-static inline bool blk_needs_flush_plug(struct task_struct *tsk)
-{
-	return false;
-}
-
 static inline int blkdev_issue_flush(struct block_device *bdev)
 {
 	return 0;
@@ -1211,6 +1467,7 @@ struct block_device_operations {
 	void (*unlock_native_capacity) (struct gendisk *);
 	int (*getgeo)(struct block_device *, struct hd_geometry *);
 	int (*set_read_only)(struct block_device *bdev, bool ro);
+	void (*free_disk)(struct gendisk *disk);
 	/* this callback is with swap_lock and sometimes page table lock held */
 	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
 	int (*report_zones)(struct gendisk *, sector_t sector,
@@ -1267,7 +1524,7 @@ void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time,
 /**
  * bio_end_io_acct - end I/O accounting for bio based drivers
  * @bio:	bio to end account for
- * @start:	start time returned by bio_start_io_acct()
+ * @start_time:	start time returned by bio_start_io_acct()
  */
 static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
 {
@@ -1312,6 +1569,7 @@ void invalidate_bdev(struct block_device *bdev);
 int sync_blockdev(struct block_device *bdev);
 int sync_blockdev_nowait(struct block_device *bdev);
 void sync_bdevs(bool wait);
+void printk_all_partitions(void);
 #else
 static inline void invalidate_bdev(struct block_device *bdev)
 {
@@ -1327,7 +1585,11 @@ static inline int sync_blockdev_nowait(struct block_device *bdev)
 static inline void sync_bdevs(bool wait)
 {
 }
-#endif
+static inline void printk_all_partitions(void)
+{
+}
+#endif /* CONFIG_BLOCK */
+
 int fsync_bdev(struct block_device *bdev);
 
 int freeze_bdev(struct block_device *bdev);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
deleted file mode 100644
index 6906a45bc761..000000000000
--- a/include/linux/genhd.h
+++ /dev/null
@@ -1,291 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_GENHD_H
-#define _LINUX_GENHD_H
-
-/*
- * 	genhd.h Copyright (C) 1992 Drew Eckhardt
- *	Generic hard disk header file by  
- * 		Drew Eckhardt
- *
- *		<drew@colorado.edu>
- */
-
-#include <linux/types.h>
-#include <linux/kdev_t.h>
-#include <linux/uuid.h>
-#include <linux/blk_types.h>
-#include <linux/device.h>
-#include <linux/xarray.h>
-
-extern const struct device_type disk_type;
-extern struct device_type part_type;
-extern struct class block_class;
-
-#define DISK_MAX_PARTS			256
-#define DISK_NAME_LEN			32
-
-#define PARTITION_META_INFO_VOLNAMELTH	64
-/*
- * Enough for the string representation of any kind of UUID plus NULL.
- * EFI UUID is 36 characters. MSDOS UUID is 11 characters.
- */
-#define PARTITION_META_INFO_UUIDLTH	(UUID_STRING_LEN + 1)
-
-struct partition_meta_info {
-	char uuid[PARTITION_META_INFO_UUIDLTH];
-	u8 volname[PARTITION_META_INFO_VOLNAMELTH];
-};
-
-/**
- * DOC: genhd capability flags
- *
- * ``GENHD_FL_REMOVABLE``: indicates that the block device gives access to
- * removable media.  When set, the device remains present even when media is not
- * inserted.  Shall not be set for devices which are removed entirely when the
- * media is removed.
- *
- * ``GENHD_FL_HIDDEN``: the block device is hidden; it doesn't produce events,
- * doesn't appear in sysfs, and can't be opened from userspace or using
- * blkdev_get*. Used for the underlying components of multipath devices.
- *
- * ``GENHD_FL_NO_PART``: partition support is disabled.  The kernel will not
- * scan for partitions from add_disk, and users can't add partitions manually.
- *
- */
-enum {
-	GENHD_FL_REMOVABLE			= 1 << 0,
-	GENHD_FL_HIDDEN				= 1 << 1,
-	GENHD_FL_NO_PART			= 1 << 2,
-};
-
-enum {
-	DISK_EVENT_MEDIA_CHANGE			= 1 << 0, /* media changed */
-	DISK_EVENT_EJECT_REQUEST		= 1 << 1, /* eject requested */
-};
-
-enum {
-	/* Poll even if events_poll_msecs is unset */
-	DISK_EVENT_FLAG_POLL			= 1 << 0,
-	/* Forward events to udev */
-	DISK_EVENT_FLAG_UEVENT			= 1 << 1,
-	/* Block event polling when open for exclusive write */
-	DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE	= 1 << 2,
-};
-
-struct disk_events;
-struct badblocks;
-
-struct blk_integrity {
-	const struct blk_integrity_profile	*profile;
-	unsigned char				flags;
-	unsigned char				tuple_size;
-	unsigned char				interval_exp;
-	unsigned char				tag_size;
-};
-
-struct gendisk {
-	/*
-	 * major/first_minor/minors should not be set by any new driver, the
-	 * block core will take care of allocating them automatically.
-	 */
-	int major;
-	int first_minor;
-	int minors;
-
-	char disk_name[DISK_NAME_LEN];	/* name of major driver */
-
-	unsigned short events;		/* supported events */
-	unsigned short event_flags;	/* flags related to event processing */
-
-	struct xarray part_tbl;
-	struct block_device *part0;
-
-	const struct block_device_operations *fops;
-	struct request_queue *queue;
-	void *private_data;
-
-	int flags;
-	unsigned long state;
-#define GD_NEED_PART_SCAN		0
-#define GD_READ_ONLY			1
-#define GD_DEAD				2
-#define GD_NATIVE_CAPACITY		3
-
-	struct mutex open_mutex;	/* open/close mutex */
-	unsigned open_partitions;	/* number of open partitions */
-
-	struct backing_dev_info	*bdi;
-	struct kobject *slave_dir;
-#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED
-	struct list_head slave_bdevs;
-#endif
-	struct timer_rand_state *random;
-	atomic_t sync_io;		/* RAID */
-	struct disk_events *ev;
-#ifdef  CONFIG_BLK_DEV_INTEGRITY
-	struct kobject integrity_kobj;
-#endif	/* CONFIG_BLK_DEV_INTEGRITY */
-#if IS_ENABLED(CONFIG_CDROM)
-	struct cdrom_device_info *cdi;
-#endif
-	int node_id;
-	struct badblocks *bb;
-	struct lockdep_map lockdep_map;
-	u64 diskseq;
-};
-
-static inline bool disk_live(struct gendisk *disk)
-{
-	return !inode_unhashed(disk->part0->bd_inode);
-}
-
-/*
- * The gendisk is refcounted by the part0 block_device, and the bd_device
- * therein is also used for device model presentation in sysfs.
- */
-#define dev_to_disk(device) \
-	(dev_to_bdev(device)->bd_disk)
-#define disk_to_dev(disk) \
-	(&((disk)->part0->bd_device))
-
-#if IS_REACHABLE(CONFIG_CDROM)
-#define disk_to_cdi(disk)	((disk)->cdi)
-#else
-#define disk_to_cdi(disk)	NULL
-#endif
-
-static inline dev_t disk_devt(struct gendisk *disk)
-{
-	return MKDEV(disk->major, disk->first_minor);
-}
-
-void disk_uevent(struct gendisk *disk, enum kobject_action action);
-
-/* block/genhd.c */
-int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
-				 const struct attribute_group **groups);
-static inline int __must_check add_disk(struct gendisk *disk)
-{
-	return device_add_disk(NULL, disk, NULL);
-}
-extern void del_gendisk(struct gendisk *gp);
-
-void invalidate_disk(struct gendisk *disk);
-
-void set_disk_ro(struct gendisk *disk, bool read_only);
-
-static inline int get_disk_ro(struct gendisk *disk)
-{
-	return disk->part0->bd_read_only ||
-		test_bit(GD_READ_ONLY, &disk->state);
-}
-
-static inline int bdev_read_only(struct block_device *bdev)
-{
-	return bdev->bd_read_only || get_disk_ro(bdev->bd_disk);
-}
-
-extern void disk_block_events(struct gendisk *disk);
-extern void disk_unblock_events(struct gendisk *disk);
-extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
-bool set_capacity_and_notify(struct gendisk *disk, sector_t size);
-bool disk_force_media_change(struct gendisk *disk, unsigned int events);
-
-/* drivers/char/random.c */
-extern void add_disk_randomness(struct gendisk *disk) __latent_entropy;
-extern void rand_initialize_disk(struct gendisk *disk);
-
-static inline sector_t get_start_sect(struct block_device *bdev)
-{
-	return bdev->bd_start_sect;
-}
-
-static inline sector_t bdev_nr_sectors(struct block_device *bdev)
-{
-	return bdev->bd_nr_sectors;
-}
-
-static inline loff_t bdev_nr_bytes(struct block_device *bdev)
-{
-	return (loff_t)bdev_nr_sectors(bdev) << SECTOR_SHIFT;
-}
-
-static inline sector_t get_capacity(struct gendisk *disk)
-{
-	return bdev_nr_sectors(disk->part0);
-}
-
-static inline u64 sb_bdev_nr_blocks(struct super_block *sb)
-{
-	return bdev_nr_sectors(sb->s_bdev) >>
-		(sb->s_blocksize_bits - SECTOR_SHIFT);
-}
-
-int bdev_disk_changed(struct gendisk *disk, bool invalidate);
-void blk_drop_partitions(struct gendisk *disk);
-
-struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
-		struct lock_class_key *lkclass);
-extern void put_disk(struct gendisk *disk);
-struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass);
-
-/**
- * blk_alloc_disk - allocate a gendisk structure
- * @node_id: numa node to allocate on
- *
- * Allocate and pre-initialize a gendisk structure for use with BIO based
- * drivers.
- *
- * Context: can sleep
- */
-#define blk_alloc_disk(node_id)						\
-({									\
-	static struct lock_class_key __key;				\
-									\
-	__blk_alloc_disk(node_id, &__key);				\
-})
-void blk_cleanup_disk(struct gendisk *disk);
-
-int __register_blkdev(unsigned int major, const char *name,
-		void (*probe)(dev_t devt));
-#define register_blkdev(major, name) \
-	__register_blkdev(major, name, NULL)
-void unregister_blkdev(unsigned int major, const char *name);
-
-bool bdev_check_media_change(struct block_device *bdev);
-int __invalidate_device(struct block_device *bdev, bool kill_dirty);
-void set_capacity(struct gendisk *disk, sector_t size);
-
-#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED
-int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
-void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk);
-int bd_register_pending_holders(struct gendisk *disk);
-#else
-static inline int bd_link_disk_holder(struct block_device *bdev,
-				      struct gendisk *disk)
-{
-	return 0;
-}
-static inline void bd_unlink_disk_holder(struct block_device *bdev,
-					 struct gendisk *disk)
-{
-}
-static inline int bd_register_pending_holders(struct gendisk *disk)
-{
-	return 0;
-}
-#endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */
-
-dev_t part_devt(struct gendisk *disk, u8 partno);
-void inc_diskseq(struct gendisk *disk);
-dev_t blk_lookup_devt(const char *name, int partno);
-void blk_request_module(dev_t devt);
-#ifdef CONFIG_BLOCK
-void printk_all_partitions(void);
-#else /* CONFIG_BLOCK */
-static inline void printk_all_partitions(void)
-{
-}
-#endif /* CONFIG_BLOCK */
-
-#endif /* _LINUX_GENHD_H */
diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h
index 6f7949b2fd8d..abeba356bc3f 100644
--- a/include/linux/part_stat.h
+++ b/include/linux/part_stat.h
@@ -2,7 +2,7 @@
 #ifndef _LINUX_PART_STAT_H
 #define _LINUX_PART_STAT_H
 
-#include <linux/genhd.h>
+#include <linux/blkdev.h>
 #include <asm/local.h>
 
 struct disk_stats {
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 95df357ec009..dffeb8281c2d 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -28,14 +28,9 @@ struct seq_file;
  */
 struct sbitmap_word {
 	/**
-	 * @depth: Number of bits being used in @word/@cleared
-	 */
-	unsigned long depth;
-
-	/**
 	 * @word: word holding free bits
 	 */
-	unsigned long word ____cacheline_aligned_in_smp;
+	unsigned long word;
 
 	/**
 	 * @cleared: word holding cleared bits
@@ -140,7 +135,7 @@ struct sbitmap_queue {
 
 	/**
 	 * @min_shallow_depth: The minimum shallow depth which may be passed to
-	 * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow().
+	 * sbitmap_queue_get_shallow()
 	 */
 	unsigned int min_shallow_depth;
 };
@@ -164,6 +159,14 @@ struct sbitmap_queue {
 int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
 		      gfp_t flags, int node, bool round_robin, bool alloc_hint);
 
+/* sbitmap internal helper */
+static inline unsigned int __map_depth(const struct sbitmap *sb, int index)
+{
+	if (index == sb->map_nr - 1)
+		return sb->depth - (index << sb->shift);
+	return 1U << sb->shift;
+}
+
 /**
  * sbitmap_free() - Free memory used by a &struct sbitmap.
  * @sb: Bitmap to free.
@@ -251,7 +254,7 @@ static inline void __sbitmap_for_each_set(struct sbitmap *sb,
 	while (scanned < sb->depth) {
 		unsigned long word;
 		unsigned int depth = min_t(unsigned int,
-					   sb->map[index].depth - nr,
+					   __map_depth(sb, index) - nr,
 					   sb->depth - scanned);
 
 		scanned += depth;
@@ -460,7 +463,7 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
 					unsigned int *offset);
 
 /**
- * __sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct
+ * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct
  * sbitmap_queue, limiting the depth used from each word, with preemption
  * already disabled.
  * @sbq: Bitmap queue to allocate from.
@@ -472,8 +475,8 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
  *
  * Return: Non-negative allocated bit number if successful, -1 otherwise.
  */
-int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
-				unsigned int shallow_depth);
+int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
+			      unsigned int shallow_depth);
 
 /**
  * sbitmap_queue_get() - Try to allocate a free bit from a &struct
@@ -496,32 +499,6 @@ static inline int sbitmap_queue_get(struct sbitmap_queue *sbq,
 }
 
 /**
- * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct
- * sbitmap_queue, limiting the depth used from each word.
- * @sbq: Bitmap queue to allocate from.
- * @cpu: Output parameter; will contain the CPU we ran on (e.g., to be passed to
- *       sbitmap_queue_clear()).
- * @shallow_depth: The maximum number of bits to allocate from a single word.
- * See sbitmap_get_shallow().
- *
- * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after
- * initializing @sbq.
- *
- * Return: Non-negative allocated bit number if successful, -1 otherwise.
- */
-static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
-					    unsigned int *cpu,
-					    unsigned int shallow_depth)
-{
-	int nr;
-
-	*cpu = get_cpu();
-	nr = __sbitmap_queue_get_shallow(sbq, shallow_depth);
-	put_cpu();
-	return nr;
-}
-
-/**
  * sbitmap_queue_min_shallow_depth() - Inform a &struct sbitmap_queue of the
  * minimum shallow depth that will be used.
  * @sbq: Bitmap queue in question.
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 6794d7322cbd..e3a4c67794b1 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -13,7 +13,6 @@
 #include <scsi/scsi_request.h>
 
 struct Scsi_Host;
-struct scsi_driver;
 
 /*
  * MAX_COMMAND_SIZE is:
@@ -159,14 +158,6 @@ static inline void *scsi_cmd_priv(struct scsi_cmnd *cmd)
 	return cmd + 1;
 }
 
-/* make sure not to use it with passthrough commands */
-static inline struct scsi_driver *scsi_cmd_to_driver(struct scsi_cmnd *cmd)
-{
-	struct request *rq = scsi_cmd_to_rq(cmd);
-
-	return *(struct scsi_driver **)rq->q->disk->private_data;
-}
-
 void scsi_done(struct scsi_cmnd *cmd);
 
 extern void scsi_finish_command(struct scsi_cmnd *cmd);
diff --git a/include/scsi/scsi_driver.h b/include/scsi/scsi_driver.h
index 6dffa8555a39..4ce1988b2ba0 100644
--- a/include/scsi/scsi_driver.h
+++ b/include/scsi/scsi_driver.h
@@ -4,11 +4,10 @@
 
 #include <linux/blk_types.h>
 #include <linux/device.h>
+#include <scsi/scsi_cmnd.h>
 
 struct module;
 struct request;
-struct scsi_cmnd;
-struct scsi_device;
 
 struct scsi_driver {
 	struct device_driver	gendrv;
@@ -31,4 +30,10 @@ extern int scsi_register_interface(struct class_interface *);
 #define scsi_unregister_interface(intf) \
 	class_interface_unregister(intf)
 
+/* make sure not to use it with passthrough commands */
+static inline struct scsi_driver *scsi_cmd_to_driver(struct scsi_cmnd *cmd)
+{
+	return to_scsi_driver(cmd->device->sdev_gendev.driver);
+}
+
 #endif /* _SCSI_SCSI_DRIVER_H */
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 27170e40e8c9..7f4dfbdf12a6 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -100,19 +100,7 @@ TRACE_EVENT(block_rq_requeue,
 		  __entry->nr_sector, 0)
 );
 
-/**
- * block_rq_complete - block IO operation completed by device driver
- * @rq: block operations request
- * @error: status code
- * @nr_bytes: number of completed bytes
- *
- * The block_rq_complete tracepoint event indicates that some portion
- * of operation request has been completed by the device driver.  If
- * the @rq->bio is %NULL, then there is absolutely no additional work to
- * do for the request. If @rq->bio is non-NULL then there is
- * additional work required to complete the request.
- */
-TRACE_EVENT(block_rq_complete,
+DECLARE_EVENT_CLASS(block_rq_completion,
 
 	TP_PROTO(struct request *rq, blk_status_t error, unsigned int nr_bytes),
 
@@ -144,6 +132,41 @@ TRACE_EVENT(block_rq_complete,
 		  __entry->nr_sector, __entry->error)
 );
 
+/**
+ * block_rq_complete - block IO operation completed by device driver
+ * @rq: block operations request
+ * @error: status code
+ * @nr_bytes: number of completed bytes
+ *
+ * The block_rq_complete tracepoint event indicates that some portion
+ * of operation request has been completed by the device driver.  If
+ * the @rq->bio is %NULL, then there is absolutely no additional work to
+ * do for the request. If @rq->bio is non-NULL then there is
+ * additional work required to complete the request.
+ */
+DEFINE_EVENT(block_rq_completion, block_rq_complete,
+
+	TP_PROTO(struct request *rq, blk_status_t error, unsigned int nr_bytes),
+
+	TP_ARGS(rq, error, nr_bytes)
+);
+
+/**
+ * block_rq_error - block IO operation error reported by device driver
+ * @rq: block operations request
+ * @error: status code
+ * @nr_bytes: number of completed bytes
+ *
+ * The block_rq_error tracepoint event indicates that some portion
+ * of operation request has failed as reported by the device driver.
+ */
+DEFINE_EVENT(block_rq_completion, block_rq_error,
+
+	TP_PROTO(struct request *rq, blk_status_t error, unsigned int nr_bytes),
+
+	TP_ARGS(rq, error, nr_bytes)
+);
+
 DECLARE_EVENT_CLASS(block_rq,
 
 	TP_PROTO(struct request *rq),