Merge tag 'for-5.9/block-20200802' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:
 "Good amount of cleanups and tech debt removals in here, and as a
  result, the diffstat shows a nice net reduction in code.

   - Softirq completion cleanups (Christoph)

   - Stop using ->queuedata (Christoph)

   - Cleanup bd claiming (Christoph)

   - Use check_events, moving away from the legacy media change
     (Christoph)

   - Use inode i_blkbits consistently (Christoph)

   - Remove old unused writeback congestion bits (Christoph)

   - Cleanup/unify submission path (Christoph)

   - Use bio_uninit consistently, instead of bio_disassociate_blkg
     (Christoph)

   - sbitmap cleared bits handling (John)

   - Request merging blktrace event addition (Jan)

   - sysfs add/remove race fixes (Luis)

   - blk-mq tag fixes/optimizations (Ming)

   - Duplicate words in comments (Randy)

   - Flush deferral cleanup (Yufen)

   - IO context locking/retry fixes (John)

   - struct_size() usage (Gustavo)

   - blk-iocost fixes (Chengming)

   - blk-cgroup IO stats fixes (Boris)

   - Various little fixes"

* tag 'for-5.9/block-20200802' of git://git.kernel.dk/linux-block: (135 commits)
  block: blk-timeout: delete duplicated word
  block: blk-mq-sched: delete duplicated word
  block: blk-mq: delete duplicated word
  block: genhd: delete duplicated words
  block: elevator: delete duplicated word and fix typos
  block: bio: delete duplicated words
  block: bfq-iosched: fix duplicated word
  iocost_monitor: start from the oldest usage index
  iocost: Fix check condition of iocg abs_vdebt
  block: Remove callback typedefs for blk_mq_ops
  block: Use non _rcu version of list functions for tag_set_list
  blk-cgroup: show global disk stats in root cgroup io.stat
  blk-cgroup: make iostat functions visible to stat printing
  block: improve discard bio alignment in __blkdev_issue_discard()
  block: change REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL to be odd numbers
  block: defer flush request no matter whether we have elevator
  block: make blk_timeout_init() static
  block: remove retry loop in ioc_release_fn()
  block: remove unnecessary ioc nested locking
  block: integrate bd_start_claiming into __blkdev_get
  ...

16 files changed, 219 insertions, 478 deletions

diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 90a7e844a098..fff9367a6348 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -33,8 +33,6 @@ enum wb_congested_state {
 	WB_sync_congested,	/* The sync queue is getting full */
 };
 
-typedef int (congested_fn)(void *, int);
-
 enum wb_stat_item {
 	WB_RECLAIMABLE,
 	WB_WRITEBACK,
@@ -88,26 +86,6 @@ struct wb_completion {
 	struct wb_completion cmpl = WB_COMPLETION_INIT(bdi)
 
 /*
- * For cgroup writeback, multiple wb's may map to the same blkcg.  Those
- * wb's can operate mostly independently but should share the congested
- * state.  To facilitate such sharing, the congested state is tracked using
- * the following struct which is created on demand, indexed by blkcg ID on
- * its bdi, and refcounted.
- */
-struct bdi_writeback_congested {
-	unsigned long state;		/* WB_[a]sync_congested flags */
-	refcount_t refcnt;		/* nr of attached wb's and blkg */
-
-#ifdef CONFIG_CGROUP_WRITEBACK
-	struct backing_dev_info *__bdi;	/* the associated bdi, set to NULL
-					 * on bdi unregistration. For memcg-wb
-					 * internal use only! */
-	int blkcg_id;			/* ID of the associated blkcg */
-	struct rb_node rb_node;		/* on bdi->cgwb_congestion_tree */
-#endif
-};
-
-/*
  * Each wb (bdi_writeback) can perform writeback operations, is measured
  * and throttled, independently.  Without cgroup writeback, each bdi
  * (bdi_writeback) is served by its embedded bdi->wb.
@@ -140,7 +118,7 @@ struct bdi_writeback {
 
 	struct percpu_counter stat[NR_WB_STAT_ITEMS];
 
-	struct bdi_writeback_congested *congested;
+	unsigned long congested;	/* WB_[a]sync_congested flags */
 
 	unsigned long bw_time_stamp;	/* last time write bw is updated */
 	unsigned long dirtied_stamp;
@@ -190,8 +168,6 @@ struct backing_dev_info {
 	struct list_head bdi_list;
 	unsigned long ra_pages;	/* max readahead in PAGE_SIZE units */
 	unsigned long io_pages;	/* max allowed IO size */
-	congested_fn *congested_fn; /* Function pointer if device is md/dm */
-	void *congested_data;	/* Pointer to aux data for congested func */
 
 	struct kref refcnt;	/* Reference counter for the structure */
 	unsigned int capabilities; /* Device capabilities */
@@ -208,11 +184,8 @@ struct backing_dev_info {
 	struct list_head wb_list; /* list of all wbs */
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
-	struct rb_root cgwb_congested_tree; /* their congested states */
 	struct mutex cgwb_release_mutex;  /* protect shutdown of wb structs */
 	struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */
-#else
-	struct bdi_writeback_congested *wb_congested;
 #endif
 	wait_queue_head_t wb_waitq;
 
@@ -232,18 +205,8 @@ enum {
 	BLK_RW_SYNC	= 1,
 };
 
-void clear_wb_congested(struct bdi_writeback_congested *congested, int sync);
-void set_wb_congested(struct bdi_writeback_congested *congested, int sync);
-
-static inline void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
-{
-	clear_wb_congested(bdi->wb.congested, sync);
-}
-
-static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync)
-{
-	set_wb_congested(bdi->wb.congested, sync);
-}
+void clear_bdi_congested(struct backing_dev_info *bdi, int sync);
+void set_bdi_congested(struct backing_dev_info *bdi, int sync);
 
 struct wb_lock_cookie {
 	bool locked;
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 6b3504bf7a42..0b06b2d26c9a 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -169,11 +169,7 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
 
 static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
 {
-	struct backing_dev_info *bdi = wb->bdi;
-
-	if (bdi->congested_fn)
-		return bdi->congested_fn(bdi->congested_data, cong_bits);
-	return wb->congested->state & cong_bits;
+	return wb->congested & cong_bits;
 }
 
 long congestion_wait(int sync, long timeout);
@@ -224,9 +220,6 @@ static inline int bdi_sched_wait(void *word)
 
 #ifdef CONFIG_CGROUP_WRITEBACK
 
-struct bdi_writeback_congested *
-wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp);
-void wb_congested_put(struct bdi_writeback_congested *congested);
 struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi,
 				    struct cgroup_subsys_state *memcg_css);
 struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi,
@@ -404,19 +397,6 @@ static inline bool inode_cgwb_enabled(struct inode *inode)
 	return false;
 }
 
-static inline struct bdi_writeback_congested *
-wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp)
-{
-	refcount_inc(&bdi->wb_congested->refcnt);
-	return bdi->wb_congested;
-}
-
-static inline void wb_congested_put(struct bdi_writeback_congested *congested)
-{
-	if (refcount_dec_and_test(&congested->refcnt))
-		kfree(congested);
-}
-
 static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi)
 {
 	return &bdi->wb;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 91676d4b2dfe..c6d765382926 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -8,8 +8,6 @@
 #include <linux/highmem.h>
 #include <linux/mempool.h>
 #include <linux/ioprio.h>
-
-#ifdef CONFIG_BLOCK
 /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */
 #include <linux/blk_types.h>
 
@@ -491,21 +489,12 @@ do {						\
 #define bio_dev(bio) \
 	disk_devt((bio)->bi_disk)
 
-#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
-void bio_associate_blkg_from_page(struct bio *bio, struct page *page);
-#else
-static inline void bio_associate_blkg_from_page(struct bio *bio,
-						struct page *page) { }
-#endif
-
 #ifdef CONFIG_BLK_CGROUP
-void bio_disassociate_blkg(struct bio *bio);
 void bio_associate_blkg(struct bio *bio);
 void bio_associate_blkg_from_css(struct bio *bio,
 				 struct cgroup_subsys_state *css);
 void bio_clone_blkg_association(struct bio *dst, struct bio *src);
 #else	/* CONFIG_BLK_CGROUP */
-static inline void bio_disassociate_blkg(struct bio *bio) { }
 static inline void bio_associate_blkg(struct bio *bio) { }
 static inline void bio_associate_blkg_from_css(struct bio *bio,
 					       struct cgroup_subsys_state *css)
@@ -824,5 +813,4 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
 		bio->bi_opf |= REQ_NOWAIT;
 }
 
-#endif /* CONFIG_BLOCK */
 #endif /* __LINUX_BIO_H */
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index a57ebe2f00ab..c8fc9792ac77 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -109,12 +109,6 @@ struct blkcg_gq {
 	struct hlist_node		blkcg_node;
 	struct blkcg			*blkcg;
 
-	/*
-	 * Each blkg gets congested separately and the congestion state is
-	 * propagated to the matching bdi_writeback_congested.
-	 */
-	struct bdi_writeback_congested	*wb_congested;
-
 	/* all non-root blkcg_gq's are guaranteed to have access to parent */
 	struct blkcg_gq			*parent;
 
@@ -183,10 +177,6 @@ extern bool blkcg_debug_stats;
 
 struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
 				      struct request_queue *q, bool update_hint);
-struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
-				      struct request_queue *q);
-struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
-				    struct request_queue *q);
 int blkcg_init_queue(struct request_queue *q);
 void blkcg_exit_queue(struct request_queue *q);
 
@@ -481,32 +471,6 @@ static inline bool blkg_tryget(struct blkcg_gq *blkg)
 }
 
 /**
- * blkg_tryget_closest - try and get a blkg ref on the closet blkg
- * @blkg: blkg to get
- *
- * This needs to be called rcu protected.  As the failure mode here is to walk
- * up the blkg tree, this ensure that the blkg->parent pointers are always
- * valid.  This returns the blkg that it ended up taking a reference on or %NULL
- * if no reference was taken.
- */
-static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg)
-{
-	struct blkcg_gq *ret_blkg = NULL;
-
-	WARN_ON_ONCE(!rcu_read_lock_held());
-
-	while (blkg) {
-		if (blkg_tryget(blkg)) {
-			ret_blkg = blkg;
-			break;
-		}
-		blkg = blkg->parent;
-	}
-
-	return ret_blkg;
-}
-
-/**
  * blkg_put - put a blkg reference
  * @blkg: blkg to put
  */
@@ -547,14 +511,6 @@ static inline void blkg_put(struct blkcg_gq *blkg)
 		if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css),	\
 					      (p_blkg)->q, false)))
 
-#ifdef CONFIG_BLK_DEV_THROTTLING
-extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
-			   struct bio *bio);
-#else
-static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
-				  struct bio *bio) { return false; }
-#endif
-
 bool __blkcg_punt_bio_submit(struct bio *bio);
 
 static inline bool blkcg_punt_bio_submit(struct bio *bio)
@@ -570,65 +526,6 @@ static inline void blkcg_bio_issue_init(struct bio *bio)
 	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
 }
 
-static inline bool blkcg_bio_issue_check(struct request_queue *q,
-					 struct bio *bio)
-{
-	struct blkcg_gq *blkg;
-	bool throtl = false;
-
-	rcu_read_lock();
-
-	if (!bio->bi_blkg) {
-		char b[BDEVNAME_SIZE];
-
-		WARN_ONCE(1,
-			  "no blkg associated for bio on block-device: %s\n",
-			  bio_devname(bio, b));
-		bio_associate_blkg(bio);
-	}
-
-	blkg = bio->bi_blkg;
-
-	throtl = blk_throtl_bio(q, blkg, bio);
-
-	if (!throtl) {
-		struct blkg_iostat_set *bis;
-		int rwd, cpu;
-
-		if (op_is_discard(bio->bi_opf))
-			rwd = BLKG_IOSTAT_DISCARD;
-		else if (op_is_write(bio->bi_opf))
-			rwd = BLKG_IOSTAT_WRITE;
-		else
-			rwd = BLKG_IOSTAT_READ;
-
-		cpu = get_cpu();
-		bis = per_cpu_ptr(blkg->iostat_cpu, cpu);
-		u64_stats_update_begin(&bis->sync);
-
-		/*
-		 * If the bio is flagged with BIO_CGROUP_ACCT it means this is a
-		 * split bio and we would have already accounted for the size of
-		 * the bio.
-		 */
-		if (!bio_flagged(bio, BIO_CGROUP_ACCT)) {
-			bio_set_flag(bio, BIO_CGROUP_ACCT);
-			bis->cur.bytes[rwd] += bio->bi_iter.bi_size;
-		}
-		bis->cur.ios[rwd]++;
-
-		u64_stats_update_end(&bis->sync);
-		if (cgroup_subsys_on_dfl(io_cgrp_subsys))
-			cgroup_rstat_updated(blkg->blkcg->css.cgroup, cpu);
-		put_cpu();
-	}
-
-	blkcg_bio_issue_init(bio);
-
-	rcu_read_unlock();
-	return !throtl;
-}
-
 static inline void blkcg_use_delay(struct blkcg_gq *blkg)
 {
 	if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0))
@@ -702,6 +599,7 @@ static inline void blkcg_clear_delay(struct blkcg_gq *blkg)
 		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);
@@ -755,8 +653,7 @@ 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 bool blkcg_bio_issue_check(struct request_queue *q,
-					 struct bio *bio) { return true; }
+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)
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index d6fcae17da5a..9d2d5ad367a4 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -267,27 +267,9 @@ struct blk_mq_queue_data {
 	bool last;
 };
 
-typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *,
-		const struct blk_mq_queue_data *);
-typedef void (commit_rqs_fn)(struct blk_mq_hw_ctx *);
-typedef bool (get_budget_fn)(struct blk_mq_hw_ctx *);
-typedef void (put_budget_fn)(struct blk_mq_hw_ctx *);
-typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool);
-typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
-typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
-typedef int (init_request_fn)(struct blk_mq_tag_set *set, struct request *,
-		unsigned int, unsigned int);
-typedef void (exit_request_fn)(struct blk_mq_tag_set *set, struct request *,
-		unsigned int);
-
 typedef bool (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
 		bool);
 typedef bool (busy_tag_iter_fn)(struct request *, void *, bool);
-typedef int (poll_fn)(struct blk_mq_hw_ctx *);
-typedef int (map_queues_fn)(struct blk_mq_tag_set *set);
-typedef bool (busy_fn)(struct request_queue *);
-typedef void (complete_fn)(struct request *);
-typedef void (cleanup_rq_fn)(struct request *);
 
 /**
  * struct blk_mq_ops - Callback functions that implements block driver
@@ -297,7 +279,8 @@ struct blk_mq_ops {
 	/**
 	 * @queue_rq: Queue a new request from block IO.
 	 */
-	queue_rq_fn		*queue_rq;
+	blk_status_t (*queue_rq)(struct blk_mq_hw_ctx *,
+				 const struct blk_mq_queue_data *);
 
 	/**
 	 * @commit_rqs: If a driver uses bd->last to judge when to submit
@@ -306,7 +289,7 @@ struct blk_mq_ops {
 	 * purpose of kicking the hardware (which the last request otherwise
 	 * would have done).
 	 */
-	commit_rqs_fn		*commit_rqs;
+	void (*commit_rqs)(struct blk_mq_hw_ctx *);
 
 	/**
 	 * @get_budget: Reserve budget before queue request, once .queue_rq is
@@ -314,37 +297,38 @@ struct blk_mq_ops {
 	 * reserved budget. Also we have to handle failure case
 	 * of .get_budget for avoiding I/O deadlock.
 	 */
-	get_budget_fn		*get_budget;
+	bool (*get_budget)(struct request_queue *);
+
 	/**
 	 * @put_budget: Release the reserved budget.
 	 */
-	put_budget_fn		*put_budget;
+	void (*put_budget)(struct request_queue *);
 
 	/**
 	 * @timeout: Called on request timeout.
 	 */
-	timeout_fn		*timeout;
+	enum blk_eh_timer_return (*timeout)(struct request *, bool);
 
 	/**
 	 * @poll: Called to poll for completion of a specific tag.
 	 */
-	poll_fn			*poll;
+	int (*poll)(struct blk_mq_hw_ctx *);
 
 	/**
 	 * @complete: Mark the request as complete.
 	 */
-	complete_fn		*complete;
+	void (*complete)(struct request *);
 
 	/**
 	 * @init_hctx: Called when the block layer side of a hardware queue has
 	 * been set up, allowing the driver to allocate/init matching
 	 * structures.
 	 */
-	init_hctx_fn		*init_hctx;
+	int (*init_hctx)(struct blk_mq_hw_ctx *, void *, unsigned int);
 	/**
 	 * @exit_hctx: Ditto for exit/teardown.
 	 */
-	exit_hctx_fn		*exit_hctx;
+	void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int);
 
 	/**
 	 * @init_request: Called for every command allocated by the block layer
@@ -353,11 +337,13 @@ struct blk_mq_ops {
 	 * Tag greater than or equal to queue_depth is for setting up
 	 * flush request.
 	 */
-	init_request_fn		*init_request;
+	int (*init_request)(struct blk_mq_tag_set *set, struct request *,
+			    unsigned int, unsigned int);
 	/**
 	 * @exit_request: Ditto for exit/teardown.
 	 */
-	exit_request_fn		*exit_request;
+	void (*exit_request)(struct blk_mq_tag_set *set, struct request *,
+			     unsigned int);
 
 	/**
 	 * @initialize_rq_fn: Called from inside blk_get_request().
@@ -368,18 +354,18 @@ struct blk_mq_ops {
 	 * @cleanup_rq: Called before freeing one request which isn't completed
 	 * yet, and usually for freeing the driver private data.
 	 */
-	cleanup_rq_fn		*cleanup_rq;
+	void (*cleanup_rq)(struct request *);
 
 	/**
 	 * @busy: If set, returns whether or not this queue currently is busy.
 	 */
-	busy_fn			*busy;
+	bool (*busy)(struct request_queue *);
 
 	/**
 	 * @map_queues: This allows drivers specify their own queue mapping by
 	 * overriding the setup-time function that builds the mq_map.
 	 */
-	map_queues_fn		*map_queues;
+	int (*map_queues)(struct blk_mq_tag_set *set);
 
 #ifdef CONFIG_BLK_DEBUG_FS
 	/**
@@ -447,8 +433,6 @@ enum {
 	BLK_MQ_REQ_NOWAIT	= (__force blk_mq_req_flags_t)(1 << 0),
 	/* allocate from reserved pool */
 	BLK_MQ_REQ_RESERVED	= (__force blk_mq_req_flags_t)(1 << 1),
-	/* allocate internal/sched tag */
-	BLK_MQ_REQ_INTERNAL	= (__force blk_mq_req_flags_t)(1 << 2),
 	/* set RQF_PREEMPT */
 	BLK_MQ_REQ_PREEMPT	= (__force blk_mq_req_flags_t)(1 << 3),
 };
@@ -503,8 +487,8 @@ void __blk_mq_end_request(struct request *rq, blk_status_t error);
 void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list);
 void blk_mq_kick_requeue_list(struct request_queue *q);
 void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
-bool blk_mq_complete_request(struct request *rq);
-void blk_mq_force_complete_rq(struct request *rq);
+void blk_mq_complete_request(struct request *rq);
+bool blk_mq_complete_request_remote(struct request *rq);
 bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
 			   struct bio *bio, unsigned int nr_segs);
 bool blk_mq_queue_stopped(struct request_queue *q);
@@ -537,6 +521,15 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q);
 
 unsigned int blk_mq_rq_cpu(struct request *rq);
 
+bool __blk_should_fake_timeout(struct request_queue *q);
+static inline bool blk_should_fake_timeout(struct request_queue *q)
+{
+	if (IS_ENABLED(CONFIG_FAIL_IO_TIMEOUT) &&
+	    test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags))
+		return __blk_should_fake_timeout(q);
+	return false;
+}
+
 /**
  * blk_mq_rq_from_pdu - cast a PDU to a request
  * @pdu: the PDU (Protocol Data Unit) to be casted
@@ -589,6 +582,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq)
 		rq->q->mq_ops->cleanup_rq(rq);
 }
 
-blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio);
+blk_qc_t blk_mq_submit_bio(struct bio *bio);
 
 #endif
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index ccb895f911b1..4ecf4fed171f 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -14,12 +14,39 @@ struct bio_set;
 struct bio;
 struct bio_integrity_payload;
 struct page;
-struct block_device;
 struct io_context;
 struct cgroup_subsys_state;
 typedef void (bio_end_io_t) (struct bio *);
 struct bio_crypt_ctx;
 
+struct block_device {
+	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
+	int			bd_openers;
+	struct inode *		bd_inode;	/* will die */
+	struct super_block *	bd_super;
+	struct mutex		bd_mutex;	/* open/close mutex */
+	void *			bd_claiming;
+	void *			bd_holder;
+	int			bd_holders;
+	bool			bd_write_holder;
+#ifdef CONFIG_SYSFS
+	struct list_head	bd_holder_disks;
+#endif
+	struct block_device *	bd_contains;
+	u8			bd_partno;
+	struct hd_struct *	bd_part;
+	/* number of times partitions within this device have been opened. */
+	unsigned		bd_part_count;
+	int			bd_invalidated;
+	struct gendisk *	bd_disk;
+	struct backing_dev_info *bd_bdi;
+
+	/* The counter of freeze processes */
+	int			bd_fsfreeze_count;
+	/* Mutex for freeze */
+	struct mutex		bd_fsfreeze_mutex;
+} __randomize_layout;
+
 /*
  * Block error status values.  See block/blk-core:blk_errors for the details.
  * Alpha cannot write a byte atomically, so we need to use 32-bit value.
@@ -300,12 +327,8 @@ enum req_opf {
 	REQ_OP_DISCARD		= 3,
 	/* securely erase sectors */
 	REQ_OP_SECURE_ERASE	= 5,
-	/* reset a zone write pointer */
-	REQ_OP_ZONE_RESET	= 6,
 	/* write the same sector many times */
 	REQ_OP_WRITE_SAME	= 7,
-	/* reset all the zone present on the device */
-	REQ_OP_ZONE_RESET_ALL	= 8,
 	/* write the zero filled sector many times */
 	REQ_OP_WRITE_ZEROES	= 9,
 	/* Open a zone */
@@ -316,6 +339,10 @@ enum req_opf {
 	REQ_OP_ZONE_FINISH	= 12,
 	/* write data at the current zone write pointer */
 	REQ_OP_ZONE_APPEND	= 13,
+	/* reset a zone write pointer */
+	REQ_OP_ZONE_RESET	= 15,
+	/* reset all the zone present on the device */
+	REQ_OP_ZONE_RESET_ALL	= 17,
 
 	/* SCSI passthrough using struct scsi_request */
 	REQ_OP_SCSI_IN		= 32,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 57241417ff2f..9ab06ea26894 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -4,9 +4,6 @@
 
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
-
-#ifdef CONFIG_BLOCK
-
 #include <linux/major.h>
 #include <linux/genhd.h>
 #include <linux/list.h>
@@ -289,8 +286,6 @@ static inline unsigned short req_get_ioprio(struct request *req)
 
 struct blk_queue_ctx;
 
-typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio);
-
 struct bio_vec;
 
 enum blk_eh_timer_return {
@@ -401,8 +396,6 @@ struct request_queue {
 	struct blk_queue_stats	*stats;
 	struct rq_qos		*rq_qos;
 
-	make_request_fn		*make_request_fn;
-
 	const struct blk_mq_ops	*mq_ops;
 
 	/* sw queues */
@@ -528,9 +521,9 @@ struct request_queue {
 	unsigned int		sg_timeout;
 	unsigned int		sg_reserved_size;
 	int			node;
+	struct mutex		debugfs_mutex;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	struct blk_trace __rcu	*blk_trace;
-	struct mutex		blk_trace_mutex;
 #endif
 	/*
 	 * for flush operations
@@ -574,8 +567,9 @@ struct request_queue {
 	struct list_head	tag_set_list;
 	struct bio_set		bio_split;
 
-#ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*debugfs_dir;
+
+#ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*sched_debugfs_dir;
 	struct dentry		*rqos_debugfs_dir;
 #endif
@@ -584,8 +578,6 @@ struct request_queue {
 
 	size_t			cmd_size;
 
-	struct work_struct	release_work;
-
 #define BLK_MAX_WRITE_HINTS	5
 	u64			write_hints[BLK_MAX_WRITE_HINTS];
 };
@@ -861,8 +853,7 @@ static inline void rq_flush_dcache_pages(struct request *rq)
 
 extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
-extern blk_qc_t generic_make_request(struct bio *bio);
-extern blk_qc_t direct_make_request(struct bio *bio);
+blk_qc_t submit_bio_noacct(struct bio *bio);
 extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_put_request(struct request *);
 extern struct request *blk_get_request(struct request_queue *, unsigned int op,
@@ -876,7 +867,7 @@ extern void blk_rq_unprep_clone(struct request *rq);
 extern blk_status_t blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
 extern int blk_rq_append_bio(struct request *rq, struct bio **bio);
-extern void blk_queue_split(struct request_queue *, struct bio **);
+extern void blk_queue_split(struct bio **);
 extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int);
 extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t,
 			      unsigned int, void __user *);
@@ -1079,7 +1070,6 @@ void blk_steal_bios(struct bio_list *list, struct request *rq);
 extern bool blk_update_request(struct request *rq, blk_status_t error,
 			       unsigned int nr_bytes);
 
-extern void __blk_complete_request(struct request *);
 extern void blk_abort_request(struct request *);
 
 /*
@@ -1166,13 +1156,13 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	return __blk_rq_map_sg(q, rq, sglist, &last_sg);
 }
 extern void blk_dump_rq_flags(struct request *, char *);
-extern long nr_blockdev_pages(void);
 
 bool __must_check blk_get_queue(struct request_queue *);
-struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id);
+struct request_queue *blk_alloc_queue(int node_id);
 extern void blk_put_queue(struct request_queue *);
 extern void blk_set_queue_dying(struct request_queue *);
 
+#ifdef CONFIG_BLOCK
 /*
  * blk_plug permits building a queue of related requests by holding the I/O
  * fragments for a short period. This allows merging of sequential requests
@@ -1232,9 +1222,47 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk)
 		 !list_empty(&plug->cb_list));
 }
 
+int blkdev_issue_flush(struct block_device *, gfp_t);
+long nr_blockdev_pages(void);
+#else /* CONFIG_BLOCK */
+struct blk_plug {
+};
+
+static inline void blk_start_plug(struct blk_plug *plug)
+{
+}
+
+static inline void blk_finish_plug(struct blk_plug *plug)
+{
+}
+
+static inline void blk_flush_plug(struct task_struct *task)
+{
+}
+
+static inline void blk_schedule_flush_plug(struct task_struct *task)
+{
+}
+
+
+static inline bool blk_needs_flush_plug(struct task_struct *tsk)
+{
+	return false;
+}
+
+static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask)
+{
+	return 0;
+}
+
+static inline long nr_blockdev_pages(void)
+{
+	return 0;
+}
+#endif /* CONFIG_BLOCK */
+
 extern void blk_io_schedule(void);
 
-int blkdev_issue_flush(struct block_device *, gfp_t);
 extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct page *page);
 
@@ -1516,7 +1544,7 @@ static inline unsigned int blksize_bits(unsigned int size)
 
 static inline unsigned int block_size(struct block_device *bdev)
 {
-	return bdev->bd_block_size;
+	return 1 << bdev->bd_inode->i_blkbits;
 }
 
 int kblockd_schedule_work(struct work_struct *work);
@@ -1746,6 +1774,7 @@ static inline void blk_ksm_unregister(struct request_queue *q) { }
 
 
 struct block_device_operations {
+	blk_qc_t (*submit_bio) (struct bio *bio);
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
 	int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
@@ -1753,8 +1782,6 @@ struct block_device_operations {
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
-	/* ->media_changed() is DEPRECATED, use ->check_events() instead */
-	int (*media_changed) (struct gendisk *);
 	void (*unlock_native_capacity) (struct gendisk *);
 	int (*revalidate_disk) (struct gendisk *);
 	int (*getgeo)(struct block_device *, struct hd_geometry *);
@@ -1834,52 +1861,6 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
 }
 #endif /* CONFIG_BLK_DEV_ZONED */
 
-#else /* CONFIG_BLOCK */
-
-struct block_device;
-
-/*
- * stubs for when the block layer is configured out
- */
-#define buffer_heads_over_limit 0
-
-static inline long nr_blockdev_pages(void)
-{
-	return 0;
-}
-
-struct blk_plug {
-};
-
-static inline void blk_start_plug(struct blk_plug *plug)
-{
-}
-
-static inline void blk_finish_plug(struct blk_plug *plug)
-{
-}
-
-static inline void blk_flush_plug(struct task_struct *task)
-{
-}
-
-static inline void blk_schedule_flush_plug(struct task_struct *task)
-{
-}
-
-
-static inline bool blk_needs_flush_plug(struct task_struct *tsk)
-{
-	return false;
-}
-
-static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask)
-{
-	return 0;
-}
-
-#endif /* CONFIG_BLOCK */
-
 static inline void blk_wake_io_task(struct task_struct *waiter)
 {
 	/*
@@ -1893,7 +1874,6 @@ static inline void blk_wake_io_task(struct task_struct *waiter)
 		wake_up_process(waiter);
 }
 
-#ifdef CONFIG_BLOCK
 unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 		unsigned int op);
 void disk_end_io_acct(struct gendisk *disk, unsigned int op,
@@ -1919,6 +1899,53 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
 {
 	return disk_end_io_acct(bio->bi_disk, bio_op(bio), start_time);
 }
-#endif /* CONFIG_BLOCK */
 
+int bdev_read_only(struct block_device *bdev);
+int set_blocksize(struct block_device *bdev, int size);
+
+const char *bdevname(struct block_device *bdev, char *buffer);
+struct block_device *lookup_bdev(const char *);
+
+void blkdev_show(struct seq_file *seqf, off_t offset);
+
+#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
+#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
+#ifdef CONFIG_BLOCK
+#define BLKDEV_MAJOR_MAX	512
+#else
+#define BLKDEV_MAJOR_MAX	0
+#endif
+
+int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
+struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
+		void *holder);
+struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder);
+int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole,
+		void *holder);
+void bd_abort_claiming(struct block_device *bdev, struct block_device *whole,
+		void *holder);
+void blkdev_put(struct block_device *bdev, fmode_t mode);
+
+struct block_device *I_BDEV(struct inode *inode);
+struct block_device *bdget(dev_t);
+struct block_device *bdgrab(struct block_device *bdev);
+void bdput(struct block_device *);
+
+#ifdef CONFIG_BLOCK
+void invalidate_bdev(struct block_device *bdev);
+int sync_blockdev(struct block_device *bdev);
+#else
+static inline void invalidate_bdev(struct block_device *bdev)
+{
+}
+static inline int sync_blockdev(struct block_device *bdev)
+{
+	return 0;
+}
 #endif
+int fsync_bdev(struct block_device *bdev);
+
+struct super_block *freeze_bdev(struct block_device *bdev);
+int thaw_bdev(struct block_device *bdev, struct super_block *sb);
+
+#endif /* _LINUX_BLKDEV_H */
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 22fb11e2d2e0..6b47f94378c5 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -406,6 +406,7 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; }
 static inline void invalidate_inode_buffers(struct inode *inode) {}
 static inline int remove_inode_buffers(struct inode *inode) { return 1; }
 static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
+#define buffer_heads_over_limit 0
 
 #endif /* CONFIG_BLOCK */
 #endif /* _LINUX_BUFFER_HEAD_H */
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index 8543fa59da72..f48d0a31deae 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -73,7 +73,6 @@ struct cdrom_device_ops {
 	int (*drive_status) (struct cdrom_device_info *, int);
 	unsigned int (*check_events) (struct cdrom_device_info *cdi,
 				      unsigned int clearing, int slot);
-	int (*media_changed) (struct cdrom_device_info *, int);
 	int (*tray_move) (struct cdrom_device_info *, int);
 	int (*lock_door) (struct cdrom_device_info *, int);
 	int (*select_speed) (struct cdrom_device_info *, int);
@@ -107,7 +106,6 @@ extern int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev,
 		       fmode_t mode, unsigned int cmd, unsigned long arg);
 extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi,
 				       unsigned int clearing);
-extern int cdrom_media_changed(struct cdrom_device_info *);
 
 extern int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi);
 extern void unregister_cdrom(struct cdrom_device_info *cdi);
diff --git a/include/linux/dasd_mod.h b/include/linux/dasd_mod.h
index d39abad2ff6e..14e6cf8c6267 100644
--- a/include/linux/dasd_mod.h
+++ b/include/linux/dasd_mod.h
@@ -4,6 +4,8 @@
 
 #include <asm/dasd.h>
 
+struct gendisk;
+
 extern int dasd_biodasdinfo(struct gendisk *disk, dasd_information2_t *info);
 
 #endif
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 73dec4b5d5be..93096e524e43 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -322,12 +322,6 @@ struct dm_target {
 	bool discards_supported:1;
 };
 
-/* Each target can link one of these into the table */
-struct dm_target_callbacks {
-	struct list_head list;
-	int (*congested_fn) (struct dm_target_callbacks *, int);
-};
-
 void *dm_per_bio_data(struct bio *bio, size_t data_size);
 struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size);
 unsigned dm_bio_get_target_bio_nr(const struct bio *bio);
@@ -479,11 +473,6 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 			sector_t start, sector_t len, char *params);
 
 /*
- * Target_ctr should call this if it needs to add any callbacks.
- */
-void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb);
-
-/*
  * Target can use this to set the table's type.
  * Can only ever be called from a target's ctr.
  * Useful for "hybrid" target (supports both bio-based
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0a6394178360..cdfed8c99750 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -471,45 +471,6 @@ struct address_space {
 	 * must be enforced here for CRIS, to let the least significant bit
 	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
 	 */
-struct request_queue;
-
-struct block_device {
-	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
-	int			bd_openers;
-	struct inode *		bd_inode;	/* will die */
-	struct super_block *	bd_super;
-	struct mutex		bd_mutex;	/* open/close mutex */
-	void *			bd_claiming;
-	void *			bd_holder;
-	int			bd_holders;
-	bool			bd_write_holder;
-#ifdef CONFIG_SYSFS
-	struct list_head	bd_holder_disks;
-#endif
-	struct block_device *	bd_contains;
-	unsigned		bd_block_size;
-	u8			bd_partno;
-	struct hd_struct *	bd_part;
-	/* number of times partitions within this device have been opened. */
-	unsigned		bd_part_count;
-	int			bd_invalidated;
-	struct gendisk *	bd_disk;
-	struct request_queue *  bd_queue;
-	struct backing_dev_info *bd_bdi;
-	struct list_head	bd_list;
-	/*
-	 * Private data.  You must have bd_claim'ed the block_device
-	 * to use this.  NOTE:  bd_claim allows an owner to claim
-	 * the same device multiple times, the owner must take special
-	 * care to not mess up bd_private for that case.
-	 */
-	unsigned long		bd_private;
-
-	/* The counter of freeze processes */
-	int			bd_fsfreeze_count;
-	/* Mutex for freeze */
-	struct mutex		bd_fsfreeze_mutex;
-} __randomize_layout;
 
 /* XArray tags, for tagging dirty and writeback pages in the pagecache. */
 #define PAGECACHE_TAG_DIRTY	XA_MARK_0
@@ -908,8 +869,6 @@ static inline unsigned imajor(const struct inode *inode)
 	return MAJOR(inode->i_rdev);
 }
 
-extern struct block_device *I_BDEV(struct inode *inode);
-
 struct fown_struct {
 	rwlock_t lock;          /* protects pid, uid, euid fields */
 	struct pid *pid;	/* pid or -pgrp where SIGIO should be sent */
@@ -1776,14 +1735,6 @@ struct dir_context {
 	loff_t pos;
 };
 
-struct block_device_operations;
-
-/* These macros are for out of kernel modules to test that
- * the kernel supports the unlocked_ioctl and compat_ioctl
- * fields in struct file_operations. */
-#define HAVE_COMPAT_IOCTL 1
-#define HAVE_UNLOCKED_IOCTL 1
-
 /*
  * These flags let !MMU mmap() govern direct device mapping vs immediate
  * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
@@ -2265,18 +2216,9 @@ struct file_system_type {
 
 #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)
 
-#ifdef CONFIG_BLOCK
 extern struct dentry *mount_bdev(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data,
 	int (*fill_super)(struct super_block *, void *, int));
-#else
-static inline struct dentry *mount_bdev(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data,
-	int (*fill_super)(struct super_block *, void *, int))
-{
-	return ERR_PTR(-ENODEV);
-}
-#endif
 extern struct dentry *mount_single(struct file_system_type *fs_type,
 	int flags, void *data,
 	int (*fill_super)(struct super_block *, void *, int));
@@ -2285,14 +2227,7 @@ extern struct dentry *mount_nodev(struct file_system_type *fs_type,
 	int (*fill_super)(struct super_block *, void *, int));
 extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
 void generic_shutdown_super(struct super_block *sb);
-#ifdef CONFIG_BLOCK
 void kill_block_super(struct super_block *sb);
-#else
-static inline void kill_block_super(struct super_block *sb)
-{
-	BUG();
-}
-#endif
 void kill_anon_super(struct super_block *sb);
 void kill_litter_super(struct super_block *sb);
 void deactivate_super(struct super_block *sb);
@@ -2582,93 +2517,16 @@ extern struct kmem_cache *names_cachep;
 #define __getname()		kmem_cache_alloc(names_cachep, GFP_KERNEL)
 #define __putname(name)		kmem_cache_free(names_cachep, (void *)(name))
 
-#ifdef CONFIG_BLOCK
-extern int register_blkdev(unsigned int, const char *);
-extern void unregister_blkdev(unsigned int, const char *);
-extern struct block_device *bdget(dev_t);
-extern struct block_device *bdgrab(struct block_device *bdev);
-extern void bd_set_size(struct block_device *, loff_t size);
-extern void bd_forget(struct inode *inode);
-extern void bdput(struct block_device *);
-extern void invalidate_bdev(struct block_device *);
-extern void iterate_bdevs(void (*)(struct block_device *, void *), void *);
-extern int sync_blockdev(struct block_device *bdev);
-extern struct super_block *freeze_bdev(struct block_device *);
-extern void emergency_thaw_all(void);
-extern void emergency_thaw_bdev(struct super_block *sb);
-extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
-extern int fsync_bdev(struct block_device *);
-
 extern struct super_block *blockdev_superblock;
-
 static inline bool sb_is_blkdev_sb(struct super_block *sb)
 {
-	return sb == blockdev_superblock;
-}
-#else
-static inline void bd_forget(struct inode *inode) {}
-static inline int sync_blockdev(struct block_device *bdev) { return 0; }
-static inline void invalidate_bdev(struct block_device *bdev) {}
-
-static inline struct super_block *freeze_bdev(struct block_device *sb)
-{
-	return NULL;
-}
-
-static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
-{
-	return 0;
+	return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock;
 }
 
-static inline int emergency_thaw_bdev(struct super_block *sb)
-{
-	return 0;
-}
-
-static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg)
-{
-}
-
-static inline bool sb_is_blkdev_sb(struct super_block *sb)
-{
-	return false;
-}
-#endif
+void emergency_thaw_all(void);
 extern int sync_filesystem(struct super_block *);
 extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
-#ifdef CONFIG_BLOCK
-extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
-extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
-extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
-extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
-					       void *holder);
-extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode,
-					      void *holder);
-extern struct block_device *bd_start_claiming(struct block_device *bdev,
-					      void *holder);
-extern void bd_finish_claiming(struct block_device *bdev,
-			       struct block_device *whole, void *holder);
-extern void bd_abort_claiming(struct block_device *bdev,
-			      struct block_device *whole, void *holder);
-extern void blkdev_put(struct block_device *bdev, fmode_t mode);
-
-#ifdef CONFIG_SYSFS
-extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
-extern void bd_unlink_disk_holder(struct block_device *bdev,
-				  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)
-{
-}
-#endif
-#endif
 
 /* fs/char_dev.c */
 #define CHRDEV_MAJOR_MAX 512
@@ -2699,31 +2557,12 @@ static inline void unregister_chrdev(unsigned int major, const char *name)
 	__unregister_chrdev(major, 0, 256, name);
 }
 
-/* fs/block_dev.c */
-#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
-#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
-
-#ifdef CONFIG_BLOCK
-#define BLKDEV_MAJOR_MAX	512
-extern const char *bdevname(struct block_device *bdev, char *buffer);
-extern struct block_device *lookup_bdev(const char *);
-extern void blkdev_show(struct seq_file *,off_t);
-
-#else
-#define BLKDEV_MAJOR_MAX	0
-#endif
-
 extern void init_special_inode(struct inode *, umode_t, dev_t);
 
 /* Invalid inode operations -- fs/bad_inode.c */
 extern void make_bad_inode(struct inode *);
 extern bool is_bad_inode(struct inode *);
 
-#ifdef CONFIG_BLOCK
-extern int revalidate_disk(struct gendisk *);
-extern int check_disk_change(struct block_device *);
-extern int __invalidate_device(struct block_device *, bool);
-#endif
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 					pgoff_t start, pgoff_t end);
 
@@ -3124,10 +2963,6 @@ static inline void remove_inode_hash(struct inode *inode)
 
 extern void inode_sb_list_add(struct inode *inode);
 
-#ifdef CONFIG_BLOCK
-extern int bdev_read_only(struct block_device *);
-#endif
-extern int set_blocksize(struct block_device *, int);
 extern int sb_set_blocksize(struct super_block *, int);
 extern int sb_min_blocksize(struct super_block *, int);
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 392aad5e29a2..4ab853461dff 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -19,13 +19,12 @@
 #include <linux/blk_types.h>
 #include <asm/local.h>
 
-#ifdef CONFIG_BLOCK
-
 #define dev_to_disk(device)	container_of((device), struct gendisk, part0.__dev)
 #define dev_to_part(device)	container_of((device), struct hd_struct, __dev)
 #define disk_to_dev(disk)	(&(disk)->part0.__dev)
 #define part_to_dev(part)	(&((part)->__dev))
 
+extern const struct device_type disk_type;
 extern struct device_type part_type;
 extern struct class block_class;
 
@@ -337,12 +336,9 @@ static inline void set_capacity(struct gendisk *disk, sector_t size)
 	disk->part0.nr_sects = size;
 }
 
-extern dev_t blk_lookup_devt(const char *name, int partno);
-
 int bdev_disk_changed(struct block_device *bdev, bool invalidate);
 int blk_add_partitions(struct gendisk *disk, struct block_device *bdev);
 int blk_drop_partitions(struct block_device *bdev);
-extern void printk_all_partitions(void);
 
 extern struct gendisk *__alloc_disk_node(int minors, int node_id);
 extern struct kobject *get_disk_and_module(struct gendisk *disk);
@@ -373,10 +369,40 @@ extern void blk_unregister_region(dev_t devt, unsigned long range);
 
 #define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE)
 
-#else /* CONFIG_BLOCK */
+int register_blkdev(unsigned int major, const char *name);
+void unregister_blkdev(unsigned int major, const char *name);
 
-static inline void printk_all_partitions(void) { }
+int revalidate_disk(struct gendisk *disk);
+int check_disk_change(struct block_device *bdev);
+int __invalidate_device(struct block_device *bdev, bool kill_dirty);
+void bd_set_size(struct block_device *bdev, loff_t size);
 
+/* for drivers/char/raw.c: */
+int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
+long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
+
+#ifdef CONFIG_SYSFS
+int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
+void bd_unlink_disk_holder(struct block_device *bdev, 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)
+{
+}
+#endif /* CONFIG_SYSFS */
+
+#ifdef CONFIG_BLOCK
+void printk_all_partitions(void);
+dev_t blk_lookup_devt(const char *name, int partno);
+#else /* CONFIG_BLOCK */
+static inline void printk_all_partitions(void)
+{
+}
 static inline dev_t blk_lookup_devt(const char *name, int partno)
 {
 	dev_t devt = MKDEV(0, 0);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index d56128df2aff..4aaa29772bb0 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -27,6 +27,7 @@
 #include <linux/timer.h>
 #include <linux/slab.h>
 #include <linux/bit_spinlock.h>
+#include <linux/blkdev.h>
 #include <crypto/hash.h>
 #endif
 
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index ee8ec2e68055..1db223710b28 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -631,7 +631,6 @@ static inline int nvm_next_ppa_in_chk(struct nvm_tgt_dev *dev,
 	return last;
 }
 
-typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *);
 typedef sector_t (nvm_tgt_capacity_fn)(void *);
 typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *,
 				int flags);
@@ -650,7 +649,7 @@ struct nvm_tgt_type {
 	int flags;
 
 	/* target entry points */
-	nvm_tgt_make_rq_fn *make_rq;
+	const struct block_device_operations *bops;
 	nvm_tgt_capacity_fn *capacity;
 
 	/* module-specific init/teardown */
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 93b114226af8..34d64ca306b1 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -212,6 +212,21 @@ DEFINE_EVENT(block_rq, block_rq_issue,
 );
 
 /**
+ * block_rq_merge - merge request with another one in the elevator
+ * @q: queue holding operation
+ * @rq: block IO operation operation request
+ *
+ * Called when block operation request @rq from queue @q is merged to another
+ * request queued in the elevator.
+ */
+DEFINE_EVENT(block_rq, block_rq_merge,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq)
+);
+
+/**
  * block_bio_bounce - used bounce buffer when processing block operation
  * @q: queue holding the block operation
  * @bio: block operation