Merge tag 'for-5.16/block-2021-10-29' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - mq-deadline accounting improvements (Bart)

 - blk-wbt timer fix (Andrea)

 - Untangle the block layer includes (Christoph)

 - Rework the poll support to be bio based, which will enable adding
   support for polling for bio based drivers (Christoph)

 - Block layer core support for multi-actuator drives (Damien)

 - blk-crypto improvements (Eric)

 - Batched tag allocation support (me)

 - Request completion batching support (me)

 - Plugging improvements (me)

 - Shared tag set improvements (John)

 - Concurrent queue quiesce support (Ming)

 - Cache bdev in ->private_data for block devices (Pavel)

 - bdev dio improvements (Pavel)

 - Block device invalidation and block size improvements (Xie)

 - Various cleanups, fixes, and improvements (Christoph, Jackie,
   Masahira, Tejun, Yu, Pavel, Zheng, me)

* tag 'for-5.16/block-2021-10-29' of git://git.kernel.dk/linux-block: (174 commits)
  blk-mq-debugfs: Show active requests per queue for shared tags
  block: improve readability of blk_mq_end_request_batch()
  virtio-blk: Use blk_validate_block_size() to validate block size
  loop: Use blk_validate_block_size() to validate block size
  nbd: Use blk_validate_block_size() to validate block size
  block: Add a helper to validate the block size
  block: re-flow blk_mq_rq_ctx_init()
  block: prefetch request to be initialized
  block: pass in blk_mq_tags to blk_mq_rq_ctx_init()
  block: add rq_flags to struct blk_mq_alloc_data
  block: add async version of bio_set_polled
  block: kill DIO_MULTI_BIO
  block: kill unused polling bits in __blkdev_direct_IO()
  block: avoid extra iter advance with async iocb
  block: Add independent access ranges support
  blk-mq: don't issue request directly in case that current is to be blocked
  sbitmap: silence data race warning
  blk-cgroup: synchronize blkg creation against policy deactivation
  block: refactor bio_iov_bvec_set()
  block: add single bio async direct IO helper
  ...

22 files changed, 1164 insertions, 1307 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index a62e72dd829f..9c14f0a8dbe5 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -12,13 +12,13 @@
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
-#include <linux/blkdev.h>
 #include <linux/device.h>
 #include <linux/writeback.h>
-#include <linux/blk-cgroup.h>
 #include <linux/backing-dev-defs.h>
 #include <linux/slab.h>
 
+struct blkcg;
+
 static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi)
 {
 	kref_get(&bdi->refcnt);
@@ -133,20 +133,7 @@ static inline bool writeback_in_progress(struct bdi_writeback *wb)
 	return test_bit(WB_writeback_running, &wb->state);
 }
 
-static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
-{
-	struct super_block *sb;
-
-	if (!inode)
-		return &noop_backing_dev_info;
-
-	sb = inode->i_sb;
-#ifdef CONFIG_BLOCK
-	if (sb_is_blkdev_sb(sb))
-		return I_BDEV(inode)->bd_disk->bdi;
-#endif
-	return sb->s_bdi;
-}
+struct backing_dev_info *inode_to_bdi(struct inode *inode);
 
 static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
 {
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 00952e92eae1..fe6bdfbbef66 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -6,19 +6,10 @@
 #define __LINUX_BIO_H
 
 #include <linux/mempool.h>
-#include <linux/ioprio.h>
 /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */
 #include <linux/blk_types.h>
 #include <linux/uio.h>
 
-#define BIO_DEBUG
-
-#ifdef BIO_DEBUG
-#define BIO_BUG_ON	BUG_ON
-#else
-#define BIO_BUG_ON
-#endif
-
 #define BIO_MAX_VECS		256U
 
 static inline unsigned int bio_max_segs(unsigned int nr_segs)
@@ -78,22 +69,6 @@ static inline bool bio_no_advance_iter(const struct bio *bio)
 	       bio_op(bio) == REQ_OP_WRITE_ZEROES;
 }
 
-static inline bool bio_mergeable(struct bio *bio)
-{
-	if (bio->bi_opf & REQ_NOMERGE_FLAGS)
-		return false;
-
-	return true;
-}
-
-static inline unsigned int bio_cur_bytes(struct bio *bio)
-{
-	if (bio_has_data(bio))
-		return bio_iovec(bio).bv_len;
-	else /* dataless requests such as discard */
-		return bio->bi_iter.bi_size;
-}
-
 static inline void *bio_data(struct bio *bio)
 {
 	if (bio_has_data(bio))
@@ -102,25 +77,6 @@ static inline void *bio_data(struct bio *bio)
 	return NULL;
 }
 
-/**
- * bio_full - check if the bio is full
- * @bio:	bio to check
- * @len:	length of one segment to be added
- *
- * Return true if @bio is full and one segment with @len bytes can't be
- * added to the bio, otherwise return false
- */
-static inline bool bio_full(struct bio *bio, unsigned len)
-{
-	if (bio->bi_vcnt >= bio->bi_max_vecs)
-		return true;
-
-	if (bio->bi_iter.bi_size > UINT_MAX - len)
-		return true;
-
-	return false;
-}
-
 static inline bool bio_next_segment(const struct bio *bio,
 				    struct bvec_iter_all *iter)
 {
@@ -163,6 +119,28 @@ static inline void bio_advance_iter_single(const struct bio *bio,
 		bvec_iter_advance_single(bio->bi_io_vec, iter, bytes);
 }
 
+void __bio_advance(struct bio *, unsigned bytes);
+
+/**
+ * bio_advance - increment/complete a bio by some number of bytes
+ * @bio:	bio to advance
+ * @bytes:	number of bytes to complete
+ *
+ * This updates bi_sector, bi_size and bi_idx; if the number of bytes to
+ * complete doesn't align with a bvec boundary, then bv_len and bv_offset will
+ * be updated on the last bvec as well.
+ *
+ * @bio will then represent the remaining, uncompleted portion of the io.
+ */
+static inline void bio_advance(struct bio *bio, unsigned int nbytes)
+{
+	if (nbytes == bio->bi_iter.bi_size) {
+		bio->bi_iter.bi_size = 0;
+		return;
+	}
+	__bio_advance(bio, nbytes);
+}
+
 #define __bio_for_each_segment(bvl, bio, iter, start)			\
 	for (iter = (start);						\
 	     (iter).bi_size &&						\
@@ -265,37 +243,6 @@ static inline void bio_clear_flag(struct bio *bio, unsigned int bit)
 	bio->bi_flags &= ~(1U << bit);
 }
 
-static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv)
-{
-	*bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
-}
-
-static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv)
-{
-	struct bvec_iter iter = bio->bi_iter;
-	int idx;
-
-	bio_get_first_bvec(bio, bv);
-	if (bv->bv_len == bio->bi_iter.bi_size)
-		return;		/* this bio only has a single bvec */
-
-	bio_advance_iter(bio, &iter, iter.bi_size);
-
-	if (!iter.bi_bvec_done)
-		idx = iter.bi_idx - 1;
-	else	/* in the middle of bvec */
-		idx = iter.bi_idx;
-
-	*bv = bio->bi_io_vec[idx];
-
-	/*
-	 * iter.bi_bvec_done records actual length of the last bvec
-	 * if this bio ends in the middle of one io vector
-	 */
-	if (iter.bi_bvec_done)
-		bv->bv_len = iter.bi_bvec_done;
-}
-
 static inline struct bio_vec *bio_first_bvec_all(struct bio *bio)
 {
 	WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
@@ -424,7 +371,7 @@ static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned short nr_iovecs)
 	return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set);
 }
 
-extern blk_qc_t submit_bio(struct bio *);
+void submit_bio(struct bio *bio);
 
 extern void bio_endio(struct bio *);
 
@@ -456,8 +403,6 @@ 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_advance(struct bio *, unsigned);
-
 extern void bio_init(struct bio *bio, struct bio_vec *table,
 		     unsigned short max_vecs);
 extern void bio_uninit(struct bio *);
@@ -469,12 +414,11 @@ extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
 			   unsigned int, unsigned int);
 int bio_add_zone_append_page(struct bio *bio, struct page *page,
 			     unsigned int len, unsigned int offset);
-bool __bio_try_merge_page(struct bio *bio, struct page *page,
-		unsigned int len, unsigned int off, bool *same_page);
 void __bio_add_page(struct bio *bio, struct page *page,
 		unsigned int len, unsigned int off);
 int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter);
-void bio_release_pages(struct bio *bio, bool mark_dirty);
+void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter);
+void __bio_release_pages(struct bio *bio, bool mark_dirty);
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
 
@@ -482,27 +426,16 @@ extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
 			       struct bio *src, struct bvec_iter *src_iter);
 extern void bio_copy_data(struct bio *dst, struct bio *src);
 extern void bio_free_pages(struct bio *bio);
-void bio_truncate(struct bio *bio, unsigned new_size);
 void guard_bio_eod(struct bio *bio);
 void zero_fill_bio(struct bio *bio);
 
-extern const char *bio_devname(struct bio *bio, char *buffer);
+static inline void bio_release_pages(struct bio *bio, bool mark_dirty)
+{
+	if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+		__bio_release_pages(bio, mark_dirty);
+}
 
-#define bio_set_dev(bio, bdev) 				\
-do {							\
-	bio_clear_flag(bio, BIO_REMAPPED);		\
-	if ((bio)->bi_bdev != (bdev))			\
-		bio_clear_flag(bio, BIO_THROTTLED);	\
-	(bio)->bi_bdev = (bdev);			\
-	bio_associate_blkg(bio);			\
-} while (0)
-
-#define bio_copy_dev(dst, src)			\
-do {						\
-	bio_clear_flag(dst, BIO_REMAPPED);		\
-	(dst)->bi_bdev = (src)->bi_bdev;	\
-	bio_clone_blkg_association(dst, src);	\
-} while (0)
+extern const char *bio_devname(struct bio *bio, char *buffer);
 
 #define bio_dev(bio) \
 	disk_devt((bio)->bi_bdev->bd_disk)
@@ -521,6 +454,22 @@ static inline void bio_clone_blkg_association(struct bio *dst,
 					      struct bio *src) { }
 #endif	/* CONFIG_BLK_CGROUP */
 
+static inline void bio_set_dev(struct bio *bio, struct block_device *bdev)
+{
+	bio_clear_flag(bio, BIO_REMAPPED);
+	if (bio->bi_bdev != bdev)
+		bio_clear_flag(bio, BIO_THROTTLED);
+	bio->bi_bdev = 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.
  *
@@ -784,7 +733,7 @@ static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
  */
 static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
 {
-	bio->bi_opf |= REQ_HIPRI;
+	bio->bi_opf |= REQ_POLLED;
 	if (!is_sync_kiocb(kiocb))
 		bio->bi_opf |= REQ_NOWAIT;
 }
diff --git a/include/linux/blk-crypto-profile.h b/include/linux/blk-crypto-profile.h
new file mode 100644
index 000000000000..bbab65bd5428
--- /dev/null
+++ b/include/linux/blk-crypto-profile.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2019 Google LLC
+ */
+
+#ifndef __LINUX_BLK_CRYPTO_PROFILE_H
+#define __LINUX_BLK_CRYPTO_PROFILE_H
+
+#include <linux/bio.h>
+#include <linux/blk-crypto.h>
+
+struct blk_crypto_profile;
+
+/**
+ * struct blk_crypto_ll_ops - functions to control inline encryption hardware
+ *
+ * Low-level operations for controlling inline encryption hardware.  This
+ * interface must be implemented by storage drivers that support inline
+ * encryption.  All functions may sleep, are serialized by profile->lock, and
+ * are never called while profile->dev (if set) is runtime-suspended.
+ */
+struct blk_crypto_ll_ops {
+
+	/**
+	 * @keyslot_program: Program a key into the inline encryption hardware.
+	 *
+	 * Program @key into the specified @slot in the inline encryption
+	 * hardware, overwriting any key that the keyslot may already contain.
+	 * The keyslot is guaranteed to not be in-use by any I/O.
+	 *
+	 * This is required if the device has keyslots.  Otherwise (i.e. if the
+	 * device is a layered device, or if the device is real hardware that
+	 * simply doesn't have the concept of keyslots) it is never called.
+	 *
+	 * Must return 0 on success, or -errno on failure.
+	 */
+	int (*keyslot_program)(struct blk_crypto_profile *profile,
+			       const struct blk_crypto_key *key,
+			       unsigned int slot);
+
+	/**
+	 * @keyslot_evict: Evict a key from the inline encryption hardware.
+	 *
+	 * If the device has keyslots, this function must evict the key from the
+	 * specified @slot.  The slot will contain @key, but there should be no
+	 * need for the @key argument to be used as @slot should be sufficient.
+	 * The keyslot is guaranteed to not be in-use by any I/O.
+	 *
+	 * If the device doesn't have keyslots itself, this function must evict
+	 * @key from any underlying devices.  @slot won't be valid in this case.
+	 *
+	 * If there are no keyslots and no underlying devices, this function
+	 * isn't required.
+	 *
+	 * Must return 0 on success, or -errno on failure.
+	 */
+	int (*keyslot_evict)(struct blk_crypto_profile *profile,
+			     const struct blk_crypto_key *key,
+			     unsigned int slot);
+};
+
+/**
+ * struct blk_crypto_profile - inline encryption profile for a device
+ *
+ * This struct contains a storage device's inline encryption capabilities (e.g.
+ * the supported crypto algorithms), driver-provided functions to control the
+ * inline encryption hardware (e.g. programming and evicting keys), and optional
+ * device-independent keyslot management data.
+ */
+struct blk_crypto_profile {
+
+	/* public: Drivers must initialize the following fields. */
+
+	/**
+	 * @ll_ops: Driver-provided functions to control the inline encryption
+	 * hardware, e.g. program and evict keys.
+	 */
+	struct blk_crypto_ll_ops ll_ops;
+
+	/**
+	 * @max_dun_bytes_supported: The maximum number of bytes supported for
+	 * specifying the data unit number (DUN).  Specifically, the range of
+	 * supported DUNs is 0 through (1 << (8 * max_dun_bytes_supported)) - 1.
+	 */
+	unsigned int max_dun_bytes_supported;
+
+	/**
+	 * @modes_supported: Array of bitmasks that specifies whether each
+	 * combination of crypto mode and data unit size is supported.
+	 * Specifically, the i'th bit of modes_supported[crypto_mode] is set if
+	 * crypto_mode can be used with a data unit size of (1 << i).  Note that
+	 * only data unit sizes that are powers of 2 can be supported.
+	 */
+	unsigned int modes_supported[BLK_ENCRYPTION_MODE_MAX];
+
+	/**
+	 * @dev: An optional device for runtime power management.  If the driver
+	 * provides this device, it will be runtime-resumed before any function
+	 * in @ll_ops is called and will remain resumed during the call.
+	 */
+	struct device *dev;
+
+	/* private: The following fields shouldn't be accessed by drivers. */
+
+	/* Number of keyslots, or 0 if not applicable */
+	unsigned int num_slots;
+
+	/*
+	 * Serializes all calls to functions in @ll_ops as well as all changes
+	 * to @slot_hashtable.  This can also be taken in read mode to look up
+	 * keyslots while ensuring that they can't be changed concurrently.
+	 */
+	struct rw_semaphore lock;
+
+	/* List of idle slots, with least recently used slot at front */
+	wait_queue_head_t idle_slots_wait_queue;
+	struct list_head idle_slots;
+	spinlock_t idle_slots_lock;
+
+	/*
+	 * Hash table which maps struct *blk_crypto_key to keyslots, so that we
+	 * can find a key's keyslot in O(1) time rather than O(num_slots).
+	 * Protected by 'lock'.
+	 */
+	struct hlist_head *slot_hashtable;
+	unsigned int log_slot_ht_size;
+
+	/* Per-keyslot data */
+	struct blk_crypto_keyslot *slots;
+};
+
+int blk_crypto_profile_init(struct blk_crypto_profile *profile,
+			    unsigned int num_slots);
+
+int devm_blk_crypto_profile_init(struct device *dev,
+				 struct blk_crypto_profile *profile,
+				 unsigned int num_slots);
+
+unsigned int blk_crypto_keyslot_index(struct blk_crypto_keyslot *slot);
+
+blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile,
+				    const struct blk_crypto_key *key,
+				    struct blk_crypto_keyslot **slot_ptr);
+
+void blk_crypto_put_keyslot(struct blk_crypto_keyslot *slot);
+
+bool __blk_crypto_cfg_supported(struct blk_crypto_profile *profile,
+				const struct blk_crypto_config *cfg);
+
+int __blk_crypto_evict_key(struct blk_crypto_profile *profile,
+			   const struct blk_crypto_key *key);
+
+void blk_crypto_reprogram_all_keys(struct blk_crypto_profile *profile);
+
+void blk_crypto_profile_destroy(struct blk_crypto_profile *profile);
+
+void blk_crypto_intersect_capabilities(struct blk_crypto_profile *parent,
+				       const struct blk_crypto_profile *child);
+
+bool blk_crypto_has_capabilities(const struct blk_crypto_profile *target,
+				 const struct blk_crypto_profile *reference);
+
+void blk_crypto_update_capabilities(struct blk_crypto_profile *dst,
+				    const struct blk_crypto_profile *src);
+
+#endif /* __LINUX_BLK_CRYPTO_PROFILE_H */
diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
new file mode 100644
index 000000000000..8a038ea0717e
--- /dev/null
+++ b/include/linux/blk-integrity.h
@@ -0,0 +1,183 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_BLK_INTEGRITY_H
+#define _LINUX_BLK_INTEGRITY_H
+
+#include <linux/blk-mq.h>
+
+struct request;
+
+enum blk_integrity_flags {
+	BLK_INTEGRITY_VERIFY		= 1 << 0,
+	BLK_INTEGRITY_GENERATE		= 1 << 1,
+	BLK_INTEGRITY_DEVICE_CAPABLE	= 1 << 2,
+	BLK_INTEGRITY_IP_CHECKSUM	= 1 << 3,
+};
+
+struct blk_integrity_iter {
+	void			*prot_buf;
+	void			*data_buf;
+	sector_t		seed;
+	unsigned int		data_size;
+	unsigned short		interval;
+	const char		*disk_name;
+};
+
+typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *);
+typedef void (integrity_prepare_fn) (struct request *);
+typedef void (integrity_complete_fn) (struct request *, unsigned int);
+
+struct blk_integrity_profile {
+	integrity_processing_fn		*generate_fn;
+	integrity_processing_fn		*verify_fn;
+	integrity_prepare_fn		*prepare_fn;
+	integrity_complete_fn		*complete_fn;
+	const char			*name;
+};
+
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+void blk_integrity_register(struct gendisk *, struct blk_integrity *);
+void blk_integrity_unregister(struct gendisk *);
+int blk_integrity_compare(struct gendisk *, struct gendisk *);
+int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
+				   struct scatterlist *);
+int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
+
+static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
+{
+	struct blk_integrity *bi = &disk->queue->integrity;
+
+	if (!bi->profile)
+		return NULL;
+
+	return bi;
+}
+
+static inline struct blk_integrity *
+bdev_get_integrity(struct block_device *bdev)
+{
+	return blk_get_integrity(bdev->bd_disk);
+}
+
+static inline bool
+blk_integrity_queue_supports_integrity(struct request_queue *q)
+{
+	return q->integrity.profile;
+}
+
+static inline void blk_queue_max_integrity_segments(struct request_queue *q,
+						    unsigned int segs)
+{
+	q->limits.max_integrity_segments = segs;
+}
+
+static inline unsigned short
+queue_max_integrity_segments(const struct request_queue *q)
+{
+	return q->limits.max_integrity_segments;
+}
+
+/**
+ * bio_integrity_intervals - Return number of integrity intervals for a bio
+ * @bi:		blk_integrity profile for device
+ * @sectors:	Size of the bio in 512-byte sectors
+ *
+ * Description: The block layer calculates everything in 512 byte
+ * sectors but integrity metadata is done in terms of the data integrity
+ * interval size of the storage device.  Convert the block layer sectors
+ * to the appropriate number of integrity intervals.
+ */
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
+{
+	return sectors >> (bi->interval_exp - 9);
+}
+
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+					       unsigned int sectors)
+{
+	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
+}
+
+static inline bool blk_integrity_rq(struct request *rq)
+{
+	return rq->cmd_flags & REQ_INTEGRITY;
+}
+
+/*
+ * Return the first bvec that contains integrity data.  Only drivers that are
+ * limited to a single integrity segment should use this helper.
+ */
+static inline struct bio_vec *rq_integrity_vec(struct request *rq)
+{
+	if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1))
+		return NULL;
+	return rq->bio->bi_integrity->bip_vec;
+}
+#else /* CONFIG_BLK_DEV_INTEGRITY */
+static inline int blk_rq_count_integrity_sg(struct request_queue *q,
+					    struct bio *b)
+{
+	return 0;
+}
+static inline int blk_rq_map_integrity_sg(struct request_queue *q,
+					  struct bio *b,
+					  struct scatterlist *s)
+{
+	return 0;
+}
+static inline struct blk_integrity *bdev_get_integrity(struct block_device *b)
+{
+	return NULL;
+}
+static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
+{
+	return NULL;
+}
+static inline bool
+blk_integrity_queue_supports_integrity(struct request_queue *q)
+{
+	return false;
+}
+static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b)
+{
+	return 0;
+}
+static inline void blk_integrity_register(struct gendisk *d,
+					 struct blk_integrity *b)
+{
+}
+static inline void blk_integrity_unregister(struct gendisk *d)
+{
+}
+static inline void blk_queue_max_integrity_segments(struct request_queue *q,
+						    unsigned int segs)
+{
+}
+static inline unsigned short
+queue_max_integrity_segments(const struct request_queue *q)
+{
+	return 0;
+}
+
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
+{
+	return 0;
+}
+
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+					       unsigned int sectors)
+{
+	return 0;
+}
+static inline int blk_integrity_rq(struct request *rq)
+{
+	return 0;
+}
+
+static inline struct bio_vec *rq_integrity_vec(struct request *rq)
+{
+	return NULL;
+}
+#endif /* CONFIG_BLK_DEV_INTEGRITY */
+#endif /* _LINUX_BLK_INTEGRITY_H */
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 13ba1861e688..b4039fdf1b04 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -6,10 +6,226 @@
 #include <linux/sbitmap.h>
 #include <linux/srcu.h>
 #include <linux/lockdep.h>
+#include <linux/scatterlist.h>
+#include <linux/prefetch.h>
 
 struct blk_mq_tags;
 struct blk_flush_queue;
 
+#define BLKDEV_MIN_RQ	4
+#define BLKDEV_DEFAULT_RQ	128
+
+typedef void (rq_end_io_fn)(struct request *, blk_status_t);
+
+/*
+ * request flags */
+typedef __u32 __bitwise req_flags_t;
+
+/* drive already may have started this one */
+#define RQF_STARTED		((__force req_flags_t)(1 << 1))
+/* may not be passed by ioscheduler */
+#define RQF_SOFTBARRIER		((__force req_flags_t)(1 << 3))
+/* request for flush sequence */
+#define RQF_FLUSH_SEQ		((__force req_flags_t)(1 << 4))
+/* merge of different types, fail separately */
+#define RQF_MIXED_MERGE		((__force req_flags_t)(1 << 5))
+/* track inflight for MQ */
+#define RQF_MQ_INFLIGHT		((__force req_flags_t)(1 << 6))
+/* don't call prep for this one */
+#define RQF_DONTPREP		((__force req_flags_t)(1 << 7))
+/* vaguely specified driver internal error.  Ignored by the block layer */
+#define RQF_FAILED		((__force req_flags_t)(1 << 10))
+/* don't warn about errors */
+#define RQF_QUIET		((__force req_flags_t)(1 << 11))
+/* elevator private data attached */
+#define RQF_ELVPRIV		((__force req_flags_t)(1 << 12))
+/* account into disk and partition IO statistics */
+#define RQF_IO_STAT		((__force req_flags_t)(1 << 13))
+/* runtime pm request */
+#define RQF_PM			((__force req_flags_t)(1 << 15))
+/* on IO scheduler merge hash */
+#define RQF_HASHED		((__force req_flags_t)(1 << 16))
+/* track IO completion time */
+#define RQF_STATS		((__force req_flags_t)(1 << 17))
+/* Look at ->special_vec for the actual data payload instead of the
+   bio chain. */
+#define RQF_SPECIAL_PAYLOAD	((__force req_flags_t)(1 << 18))
+/* The per-zone write lock is held for this request */
+#define RQF_ZONE_WRITE_LOCKED	((__force req_flags_t)(1 << 19))
+/* already slept for hybrid poll */
+#define RQF_MQ_POLL_SLEPT	((__force req_flags_t)(1 << 20))
+/* ->timeout has been called, don't expire again */
+#define RQF_TIMED_OUT		((__force req_flags_t)(1 << 21))
+/* queue has elevator attached */
+#define RQF_ELV			((__force req_flags_t)(1 << 22))
+
+/* flags that prevent us from merging requests: */
+#define RQF_NOMERGE_FLAGS \
+	(RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
+
+enum mq_rq_state {
+	MQ_RQ_IDLE		= 0,
+	MQ_RQ_IN_FLIGHT		= 1,
+	MQ_RQ_COMPLETE		= 2,
+};
+
+/*
+ * Try to put the fields that are referenced together in the same cacheline.
+ *
+ * If you modify this structure, make sure to update blk_rq_init() and
+ * especially blk_mq_rq_ctx_init() to take care of the added fields.
+ */
+struct request {
+	struct request_queue *q;
+	struct blk_mq_ctx *mq_ctx;
+	struct blk_mq_hw_ctx *mq_hctx;
+
+	unsigned int cmd_flags;		/* op and common flags */
+	req_flags_t rq_flags;
+
+	int tag;
+	int internal_tag;
+
+	unsigned int timeout;
+
+	/* the following two fields are internal, NEVER access directly */
+	unsigned int __data_len;	/* total data len */
+	sector_t __sector;		/* sector cursor */
+
+	struct bio *bio;
+	struct bio *biotail;
+
+	union {
+		struct list_head queuelist;
+		struct request *rq_next;
+	};
+
+	struct gendisk *rq_disk;
+	struct block_device *part;
+#ifdef CONFIG_BLK_RQ_ALLOC_TIME
+	/* Time that the first bio started allocating this request. */
+	u64 alloc_time_ns;
+#endif
+	/* Time that this request was allocated for this IO. */
+	u64 start_time_ns;
+	/* Time that I/O was submitted to the device. */
+	u64 io_start_time_ns;
+
+#ifdef CONFIG_BLK_WBT
+	unsigned short wbt_flags;
+#endif
+	/*
+	 * rq sectors used for blk stats. It has the same value
+	 * with blk_rq_sectors(rq), except that it never be zeroed
+	 * by completion.
+	 */
+	unsigned short stats_sectors;
+
+	/*
+	 * Number of scatter-gather DMA addr+len pairs after
+	 * physical address coalescing is performed.
+	 */
+	unsigned short nr_phys_segments;
+
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+	unsigned short nr_integrity_segments;
+#endif
+
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+	struct bio_crypt_ctx *crypt_ctx;
+	struct blk_crypto_keyslot *crypt_keyslot;
+#endif
+
+	unsigned short write_hint;
+	unsigned short ioprio;
+
+	enum mq_rq_state state;
+	refcount_t ref;
+
+	unsigned long deadline;
+
+	/*
+	 * The hash is used inside the scheduler, and killed once the
+	 * request reaches the dispatch list. The ipi_list is only used
+	 * to queue the request for softirq completion, which is long
+	 * after the request has been unhashed (and even removed from
+	 * the dispatch list).
+	 */
+	union {
+		struct hlist_node hash;	/* merge hash */
+		struct llist_node ipi_list;
+	};
+
+	/*
+	 * The rb_node is only used inside the io scheduler, requests
+	 * are pruned when moved to the dispatch queue. So let the
+	 * completion_data share space with the rb_node.
+	 */
+	union {
+		struct rb_node rb_node;	/* sort/lookup */
+		struct bio_vec special_vec;
+		void *completion_data;
+		int error_count; /* for legacy drivers, don't use */
+	};
+
+
+	/*
+	 * Three pointers are available for the IO schedulers, if they need
+	 * more they have to dynamically allocate it.  Flush requests are
+	 * never put on the IO scheduler. So let the flush fields share
+	 * space with the elevator data.
+	 */
+	union {
+		struct {
+			struct io_cq		*icq;
+			void			*priv[2];
+		} elv;
+
+		struct {
+			unsigned int		seq;
+			struct list_head	list;
+			rq_end_io_fn		*saved_end_io;
+		} flush;
+	};
+
+	union {
+		struct __call_single_data csd;
+		u64 fifo_time;
+	};
+
+	/*
+	 * completion callback.
+	 */
+	rq_end_io_fn *end_io;
+	void *end_io_data;
+};
+
+#define req_op(req) \
+	((req)->cmd_flags & REQ_OP_MASK)
+
+static inline bool blk_rq_is_passthrough(struct request *rq)
+{
+	return blk_op_is_passthrough(req_op(rq));
+}
+
+static inline unsigned short req_get_ioprio(struct request *req)
+{
+	return req->ioprio;
+}
+
+#define rq_data_dir(rq)		(op_is_write(req_op(rq)) ? WRITE : READ)
+
+#define rq_dma_dir(rq) \
+	(op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE)
+
+enum blk_eh_timer_return {
+	BLK_EH_DONE,		/* drivers has completed the command */
+	BLK_EH_RESET_TIMER,	/* reset timer and try again */
+};
+
+#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */
+#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */
+
 /**
  * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware
  * block device
@@ -126,9 +342,6 @@ struct blk_mq_hw_ctx {
 	unsigned long		queued;
 	/** @run: Number of dispatched requests. */
 	unsigned long		run;
-#define BLK_MQ_MAX_DISPATCH_ORDER	7
-	/** @dispatched: Number of dispatch requests by queue. */
-	unsigned long		dispatched[BLK_MQ_MAX_DISPATCH_ORDER];
 
 	/** @numa_node: NUMA node the storage adapter has been connected to. */
 	unsigned int		numa_node;
@@ -148,13 +361,6 @@ struct blk_mq_hw_ctx {
 	/** @kobj: Kernel object for sysfs. */
 	struct kobject		kobj;
 
-	/** @poll_considered: Count times blk_poll() was called. */
-	unsigned long		poll_considered;
-	/** @poll_invoked: Count how many requests blk_poll() polled. */
-	unsigned long		poll_invoked;
-	/** @poll_success: Count how many polled requests were completed. */
-	unsigned long		poll_success;
-
 #ifdef CONFIG_BLK_DEBUG_FS
 	/**
 	 * @debugfs_dir: debugfs directory for this hardware queue. Named
@@ -232,13 +438,11 @@ enum hctx_type {
  * @flags:	   Zero or more BLK_MQ_F_* flags.
  * @driver_data:   Pointer to data owned by the block driver that created this
  *		   tag set.
- * @active_queues_shared_sbitmap:
- * 		   number of active request queues per tag set.
- * @__bitmap_tags: A shared tags sbitmap, used over all hctx's
- * @__breserved_tags:
- *		   A shared reserved tags sbitmap, used over all hctx's
  * @tags:	   Tag sets. One tag set per hardware queue. Has @nr_hw_queues
  *		   elements.
+ * @shared_tags:
+ *		   Shared set of tags. Has @nr_hw_queues elements. If set,
+ *		   shared by all @tags.
  * @tag_list_lock: Serializes tag_list accesses.
  * @tag_list:	   List of the request queues that use this tag set. See also
  *		   request_queue.tag_set_list.
@@ -255,12 +459,11 @@ struct blk_mq_tag_set {
 	unsigned int		timeout;
 	unsigned int		flags;
 	void			*driver_data;
-	atomic_t		active_queues_shared_sbitmap;
 
-	struct sbitmap_queue	__bitmap_tags;
-	struct sbitmap_queue	__breserved_tags;
 	struct blk_mq_tags	**tags;
 
+	struct blk_mq_tags	*shared_tags;
+
 	struct mutex		tag_list_lock;
 	struct list_head	tag_list;
 };
@@ -330,7 +533,7 @@ struct blk_mq_ops {
 	/**
 	 * @poll: Called to poll for completion of a specific tag.
 	 */
-	int (*poll)(struct blk_mq_hw_ctx *);
+	int (*poll)(struct blk_mq_hw_ctx *, struct io_comp_batch *);
 
 	/**
 	 * @complete: Mark the request as complete.
@@ -432,6 +635,8 @@ enum {
 	((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \
 		<< BLK_MQ_F_ALLOC_POLICY_START_BIT)
 
+#define BLK_MQ_NO_HCTX_IDX	(-1U)
+
 struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata,
 		struct lock_class_key *lkclass);
 #define blk_mq_alloc_disk(set, queuedata)				\
@@ -451,8 +656,6 @@ int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set,
 		unsigned int set_flags);
 void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
 
-void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
-
 void blk_mq_free_request(struct request *rq);
 
 bool blk_mq_queue_inflight(struct request_queue *q);
@@ -471,7 +674,40 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
 struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 		unsigned int op, blk_mq_req_flags_t flags,
 		unsigned int hctx_idx);
-struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
+
+/*
+ * Tag address space map.
+ */
+struct blk_mq_tags {
+	unsigned int nr_tags;
+	unsigned int nr_reserved_tags;
+
+	atomic_t active_queues;
+
+	struct sbitmap_queue bitmap_tags;
+	struct sbitmap_queue breserved_tags;
+
+	struct request **rqs;
+	struct request **static_rqs;
+	struct list_head page_list;
+
+	/*
+	 * used to clear request reference in rqs[] before freeing one
+	 * request pool
+	 */
+	spinlock_t lock;
+};
+
+static inline struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags,
+					       unsigned int tag)
+{
+	if (tag < tags->nr_tags) {
+		prefetch(tags->rqs[tag]);
+		return tags->rqs[tag];
+	}
+
+	return NULL;
+}
 
 enum {
 	BLK_MQ_UNIQUE_TAG_BITS = 16,
@@ -524,6 +760,35 @@ static inline void blk_mq_set_request_complete(struct request *rq)
 void blk_mq_start_request(struct request *rq);
 void blk_mq_end_request(struct request *rq, blk_status_t error);
 void __blk_mq_end_request(struct request *rq, blk_status_t error);
+void blk_mq_end_request_batch(struct io_comp_batch *ib);
+
+/*
+ * Only need start/end time stamping if we have iostat or
+ * blk stats enabled, or using an IO scheduler.
+ */
+static inline bool blk_mq_need_time_stamp(struct request *rq)
+{
+	return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV));
+}
+
+/*
+ * Batched completions only work when there is no I/O error and no special
+ * ->end_io handler.
+ */
+static inline bool blk_mq_add_to_batch(struct request *req,
+				       struct io_comp_batch *iob, int ioerror,
+				       void (*complete)(struct io_comp_batch *))
+{
+	if (!iob || (req->rq_flags & RQF_ELV) || req->end_io || ioerror)
+		return false;
+	if (!iob->complete)
+		iob->complete = complete;
+	else if (iob->complete != complete)
+		return false;
+	iob->need_ts |= blk_mq_need_time_stamp(req);
+	rq_list_add(&iob->req_list, req);
+	return true;
+}
 
 void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list);
 void blk_mq_kick_requeue_list(struct request_queue *q);
@@ -605,16 +870,6 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq)
 	for ((i) = 0; (i) < (hctx)->nr_ctx &&				\
 	     ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++)
 
-static inline blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx,
-		struct request *rq)
-{
-	if (rq->tag != -1)
-		return rq->tag | (hctx->queue_num << BLK_QC_T_SHIFT);
-
-	return rq->internal_tag | (hctx->queue_num << BLK_QC_T_SHIFT) |
-			BLK_QC_T_INTERNAL;
-}
-
 static inline void blk_mq_cleanup_rq(struct request *rq)
 {
 	if (rq->q->mq_ops->cleanup_rq)
@@ -633,8 +888,268 @@ static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
 		rq->rq_disk = bio->bi_bdev->bd_disk;
 }
 
-blk_qc_t blk_mq_submit_bio(struct bio *bio);
 void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx,
 		struct lock_class_key *key);
 
+static inline bool rq_is_sync(struct request *rq)
+{
+	return op_is_sync(rq->cmd_flags);
+}
+
+void blk_rq_init(struct request_queue *q, struct request *rq);
+void blk_put_request(struct request *rq);
+struct request *blk_get_request(struct request_queue *q, unsigned int op,
+		blk_mq_req_flags_t flags);
+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);
+
+struct rq_map_data {
+	struct page **pages;
+	int page_order;
+	int nr_entries;
+	unsigned long offset;
+	int null_mapped;
+	int from_user;
+};
+
+int blk_rq_map_user(struct request_queue *, struct request *,
+		struct rq_map_data *, void __user *, unsigned long, gfp_t);
+int blk_rq_map_user_iov(struct request_queue *, struct request *,
+		struct rq_map_data *, const struct iov_iter *, gfp_t);
+int blk_rq_unmap_user(struct bio *);
+int blk_rq_map_kern(struct request_queue *, struct request *, void *,
+		unsigned int, gfp_t);
+int blk_rq_append_bio(struct request *rq, struct bio *bio);
+void blk_execute_rq_nowait(struct gendisk *, struct request *, int,
+		rq_end_io_fn *);
+blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq,
+		int at_head);
+
+struct req_iterator {
+	struct bvec_iter iter;
+	struct bio *bio;
+};
+
+#define __rq_for_each_bio(_bio, rq)	\
+	if ((rq->bio))			\
+		for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next)
+
+#define rq_for_each_segment(bvl, _rq, _iter)			\
+	__rq_for_each_bio(_iter.bio, _rq)			\
+		bio_for_each_segment(bvl, _iter.bio, _iter.iter)
+
+#define rq_for_each_bvec(bvl, _rq, _iter)			\
+	__rq_for_each_bio(_iter.bio, _rq)			\
+		bio_for_each_bvec(bvl, _iter.bio, _iter.iter)
+
+#define rq_iter_last(bvec, _iter)				\
+		(_iter.bio->bi_next == NULL &&			\
+		 bio_iter_last(bvec, _iter.iter))
+
+/*
+ * blk_rq_pos()			: the current sector
+ * blk_rq_bytes()		: bytes left in the entire request
+ * blk_rq_cur_bytes()		: bytes left in the current segment
+ * blk_rq_err_bytes()		: bytes left till the next error boundary
+ * blk_rq_sectors()		: sectors left in the entire request
+ * blk_rq_cur_sectors()		: sectors left in the current segment
+ * blk_rq_stats_sectors()	: sectors of the entire request used for stats
+ */
+static inline sector_t blk_rq_pos(const struct request *rq)
+{
+	return rq->__sector;
+}
+
+static inline unsigned int blk_rq_bytes(const struct request *rq)
+{
+	return rq->__data_len;
+}
+
+static inline int blk_rq_cur_bytes(const struct request *rq)
+{
+	if (!rq->bio)
+		return 0;
+	if (!bio_has_data(rq->bio))	/* dataless requests such as discard */
+		return rq->bio->bi_iter.bi_size;
+	return bio_iovec(rq->bio).bv_len;
+}
+
+unsigned int blk_rq_err_bytes(const struct request *rq);
+
+static inline unsigned int blk_rq_sectors(const struct request *rq)
+{
+	return blk_rq_bytes(rq) >> SECTOR_SHIFT;
+}
+
+static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
+{
+	return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
+}
+
+static inline unsigned int blk_rq_stats_sectors(const struct request *rq)
+{
+	return rq->stats_sectors;
+}
+
+/*
+ * Some commands like WRITE SAME have a payload or data transfer size which
+ * is different from the size of the request.  Any driver that supports such
+ * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to
+ * calculate the data transfer size.
+ */
+static inline unsigned int blk_rq_payload_bytes(struct request *rq)
+{
+	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
+		return rq->special_vec.bv_len;
+	return blk_rq_bytes(rq);
+}
+
+/*
+ * Return the first full biovec in the request.  The caller needs to check that
+ * there are any bvecs before calling this helper.
+ */
+static inline struct bio_vec req_bvec(struct request *rq)
+{
+	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
+		return rq->special_vec;
+	return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter);
+}
+
+static inline unsigned int blk_rq_count_bios(struct request *rq)
+{
+	unsigned int nr_bios = 0;
+	struct bio *bio;
+
+	__rq_for_each_bio(bio, rq)
+		nr_bios++;
+
+	return nr_bios;
+}
+
+void blk_steal_bios(struct bio_list *list, struct request *rq);
+
+/*
+ * Request completion related functions.
+ *
+ * blk_update_request() completes given number of bytes and updates
+ * the request without completing it.
+ */
+bool blk_update_request(struct request *rq, blk_status_t error,
+			       unsigned int nr_bytes);
+void blk_abort_request(struct request *);
+
+/*
+ * Number of physical segments as sent to the device.
+ *
+ * Normally this is the number of discontiguous data segments sent by the
+ * submitter.  But for data-less command like discard we might have no
+ * actual data segments submitted, but the driver might have to add it's
+ * own special payload.  In that case we still return 1 here so that this
+ * special payload will be mapped.
+ */
+static inline unsigned short blk_rq_nr_phys_segments(struct request *rq)
+{
+	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
+		return 1;
+	return rq->nr_phys_segments;
+}
+
+/*
+ * Number of discard segments (or ranges) the driver needs to fill in.
+ * Each discard bio merged into a request is counted as one segment.
+ */
+static inline unsigned short blk_rq_nr_discard_segments(struct request *rq)
+{
+	return max_t(unsigned short, rq->nr_phys_segments, 1);
+}
+
+int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
+		struct scatterlist *sglist, struct scatterlist **last_sg);
+static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq,
+		struct scatterlist *sglist)
+{
+	struct scatterlist *last_sg = NULL;
+
+	return __blk_rq_map_sg(q, rq, sglist, &last_sg);
+}
+void blk_dump_rq_flags(struct request *, char *);
+
+#ifdef CONFIG_BLK_DEV_ZONED
+static inline unsigned int blk_rq_zone_no(struct request *rq)
+{
+	return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
+}
+
+static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
+{
+	return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
+}
+
+bool blk_req_needs_zone_write_lock(struct request *rq);
+bool blk_req_zone_write_trylock(struct request *rq);
+void __blk_req_zone_write_lock(struct request *rq);
+void __blk_req_zone_write_unlock(struct request *rq);
+
+static inline void blk_req_zone_write_lock(struct request *rq)
+{
+	if (blk_req_needs_zone_write_lock(rq))
+		__blk_req_zone_write_lock(rq);
+}
+
+static inline void blk_req_zone_write_unlock(struct request *rq)
+{
+	if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED)
+		__blk_req_zone_write_unlock(rq);
+}
+
+static inline bool blk_req_zone_is_write_locked(struct request *rq)
+{
+	return rq->q->seq_zones_wlock &&
+		test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock);
+}
+
+static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
+{
+	if (!blk_req_needs_zone_write_lock(rq))
+		return true;
+	return !blk_req_zone_is_write_locked(rq);
+}
+#else /* CONFIG_BLK_DEV_ZONED */
+static inline bool blk_req_needs_zone_write_lock(struct request *rq)
+{
+	return false;
+}
+
+static inline void blk_req_zone_write_lock(struct request *rq)
+{
+}
+
+static inline void blk_req_zone_write_unlock(struct request *rq)
+{
+}
+static inline bool blk_req_zone_is_write_locked(struct request *rq)
+{
+	return false;
+}
+
+static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
+{
+	return true;
+}
+#endif /* CONFIG_BLK_DEV_ZONED */
+
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+# error	"You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform"
 #endif
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+void rq_flush_dcache_pages(struct request *rq);
+#else
+static inline void rq_flush_dcache_pages(struct request *rq)
+{
+}
+#endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */
+#endif /* BLK_MQ_H */
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index be622b5a21ed..1e370929c89e 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -38,6 +38,7 @@ struct block_device {
 	u8			bd_partno;
 	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
 	struct gendisk *	bd_disk;
+	struct request_queue *	bd_queue;
 
 	/* The counter of freeze processes */
 	int			bd_fsfreeze_count;
@@ -208,6 +209,9 @@ static inline void bio_issue_init(struct bio_issue *issue,
 			((u64)size << BIO_ISSUE_SIZE_SHIFT));
 }
 
+typedef unsigned int blk_qc_t;
+#define BLK_QC_T_NONE		-1U
+
 /*
  * main unit of I/O for the block layer and lower layers (ie drivers and
  * stacking drivers)
@@ -227,8 +231,8 @@ struct bio {
 
 	struct bvec_iter	bi_iter;
 
+	blk_qc_t		bi_cookie;
 	bio_end_io_t		*bi_end_io;
-
 	void			*bi_private;
 #ifdef CONFIG_BLK_CGROUP
 	/*
@@ -384,7 +388,7 @@ enum req_flag_bits {
 	/* command specific flags for REQ_OP_WRITE_ZEROES: */
 	__REQ_NOUNMAP,		/* do not free blocks when zeroing */
 
-	__REQ_HIPRI,
+	__REQ_POLLED,		/* caller polls for completion using bio_poll */
 
 	/* for driver use */
 	__REQ_DRV,
@@ -409,7 +413,7 @@ enum req_flag_bits {
 #define REQ_CGROUP_PUNT		(1ULL << __REQ_CGROUP_PUNT)
 
 #define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
-#define REQ_HIPRI		(1ULL << __REQ_HIPRI)
+#define REQ_POLLED		(1ULL << __REQ_POLLED)
 
 #define REQ_DRV			(1ULL << __REQ_DRV)
 #define REQ_SWAP		(1ULL << __REQ_SWAP)
@@ -431,8 +435,6 @@ enum stat_group {
 
 #define bio_op(bio) \
 	((bio)->bi_opf & REQ_OP_MASK)
-#define req_op(req) \
-	((req)->cmd_flags & REQ_OP_MASK)
 
 /* obsolete, don't use in new code */
 static inline void bio_set_op_attrs(struct bio *bio, unsigned op,
@@ -497,31 +499,6 @@ static inline int op_stat_group(unsigned int op)
 	return op_is_write(op);
 }
 
-typedef unsigned int blk_qc_t;
-#define BLK_QC_T_NONE		-1U
-#define BLK_QC_T_SHIFT		16
-#define BLK_QC_T_INTERNAL	(1U << 31)
-
-static inline bool blk_qc_t_valid(blk_qc_t cookie)
-{
-	return cookie != BLK_QC_T_NONE;
-}
-
-static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie)
-{
-	return (cookie & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT;
-}
-
-static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie)
-{
-	return cookie & ((1u << BLK_QC_T_SHIFT) - 1);
-}
-
-static inline bool blk_qc_t_is_internal(blk_qc_t cookie)
-{
-	return (cookie & BLK_QC_T_INTERNAL) != 0;
-}
-
 struct blk_rq_stat {
 	u64 mean;
 	u64 min;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 12b9dbcc980e..d2d627e2c782 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -3,8 +3,6 @@
 #define _LINUX_BLKDEV_H
 
 #include <linux/sched.h>
-#include <linux/sched/clock.h>
-#include <linux/major.h>
 #include <linux/genhd.h>
 #include <linux/list.h>
 #include <linux/llist.h>
@@ -12,17 +10,11 @@
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/wait.h>
-#include <linux/mempool.h>
-#include <linux/pfn.h>
 #include <linux/bio.h>
-#include <linux/stringify.h>
 #include <linux/gfp.h>
-#include <linux/smp.h>
 #include <linux/rcupdate.h>
 #include <linux/percpu-refcount.h>
-#include <linux/scatterlist.h>
 #include <linux/blkzoned.h>
-#include <linux/pm.h>
 #include <linux/sbitmap.h>
 
 struct module;
@@ -33,14 +25,12 @@ struct request;
 struct sg_io_hdr;
 struct blkcg_gq;
 struct blk_flush_queue;
+struct kiocb;
 struct pr_ops;
 struct rq_qos;
 struct blk_queue_stats;
 struct blk_stat_callback;
-struct blk_keyslot_manager;
-
-#define BLKDEV_MIN_RQ	4
-#define BLKDEV_MAX_RQ	128	/* Default maximum */
+struct blk_crypto_profile;
 
 /* Must be consistent with blk_mq_poll_stats_bkt() */
 #define BLK_MQ_POLL_STATS_BKTS 16
@@ -54,186 +44,13 @@ struct blk_keyslot_manager;
  */
 #define BLKCG_MAX_POLS		6
 
-typedef void (rq_end_io_fn)(struct request *, blk_status_t);
-
-/*
- * request flags */
-typedef __u32 __bitwise req_flags_t;
-
-/* drive already may have started this one */
-#define RQF_STARTED		((__force req_flags_t)(1 << 1))
-/* may not be passed by ioscheduler */
-#define RQF_SOFTBARRIER		((__force req_flags_t)(1 << 3))
-/* request for flush sequence */
-#define RQF_FLUSH_SEQ		((__force req_flags_t)(1 << 4))
-/* merge of different types, fail separately */
-#define RQF_MIXED_MERGE		((__force req_flags_t)(1 << 5))
-/* track inflight for MQ */
-#define RQF_MQ_INFLIGHT		((__force req_flags_t)(1 << 6))
-/* don't call prep for this one */
-#define RQF_DONTPREP		((__force req_flags_t)(1 << 7))
-/* vaguely specified driver internal error.  Ignored by the block layer */
-#define RQF_FAILED		((__force req_flags_t)(1 << 10))
-/* don't warn about errors */
-#define RQF_QUIET		((__force req_flags_t)(1 << 11))
-/* elevator private data attached */
-#define RQF_ELVPRIV		((__force req_flags_t)(1 << 12))
-/* account into disk and partition IO statistics */
-#define RQF_IO_STAT		((__force req_flags_t)(1 << 13))
-/* runtime pm request */
-#define RQF_PM			((__force req_flags_t)(1 << 15))
-/* on IO scheduler merge hash */
-#define RQF_HASHED		((__force req_flags_t)(1 << 16))
-/* track IO completion time */
-#define RQF_STATS		((__force req_flags_t)(1 << 17))
-/* Look at ->special_vec for the actual data payload instead of the
-   bio chain. */
-#define RQF_SPECIAL_PAYLOAD	((__force req_flags_t)(1 << 18))
-/* The per-zone write lock is held for this request */
-#define RQF_ZONE_WRITE_LOCKED	((__force req_flags_t)(1 << 19))
-/* already slept for hybrid poll */
-#define RQF_MQ_POLL_SLEPT	((__force req_flags_t)(1 << 20))
-/* ->timeout has been called, don't expire again */
-#define RQF_TIMED_OUT		((__force req_flags_t)(1 << 21))
-
-/* flags that prevent us from merging requests: */
-#define RQF_NOMERGE_FLAGS \
-	(RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
-
-/*
- * Request state for blk-mq.
- */
-enum mq_rq_state {
-	MQ_RQ_IDLE		= 0,
-	MQ_RQ_IN_FLIGHT		= 1,
-	MQ_RQ_COMPLETE		= 2,
-};
-
-/*
- * Try to put the fields that are referenced together in the same cacheline.
- *
- * If you modify this structure, make sure to update blk_rq_init() and
- * especially blk_mq_rq_ctx_init() to take care of the added fields.
- */
-struct request {
-	struct request_queue *q;
-	struct blk_mq_ctx *mq_ctx;
-	struct blk_mq_hw_ctx *mq_hctx;
-
-	unsigned int cmd_flags;		/* op and common flags */
-	req_flags_t rq_flags;
-
-	int tag;
-	int internal_tag;
-
-	/* the following two fields are internal, NEVER access directly */
-	unsigned int __data_len;	/* total data len */
-	sector_t __sector;		/* sector cursor */
-
-	struct bio *bio;
-	struct bio *biotail;
-
-	struct list_head queuelist;
-
-	/*
-	 * The hash is used inside the scheduler, and killed once the
-	 * request reaches the dispatch list. The ipi_list is only used
-	 * to queue the request for softirq completion, which is long
-	 * after the request has been unhashed (and even removed from
-	 * the dispatch list).
-	 */
-	union {
-		struct hlist_node hash;	/* merge hash */
-		struct llist_node ipi_list;
-	};
-
-	/*
-	 * The rb_node is only used inside the io scheduler, requests
-	 * are pruned when moved to the dispatch queue. So let the
-	 * completion_data share space with the rb_node.
-	 */
-	union {
-		struct rb_node rb_node;	/* sort/lookup */
-		struct bio_vec special_vec;
-		void *completion_data;
-		int error_count; /* for legacy drivers, don't use */
-	};
-
-	/*
-	 * Three pointers are available for the IO schedulers, if they need
-	 * more they have to dynamically allocate it.  Flush requests are
-	 * never put on the IO scheduler. So let the flush fields share
-	 * space with the elevator data.
-	 */
-	union {
-		struct {
-			struct io_cq		*icq;
-			void			*priv[2];
-		} elv;
-
-		struct {
-			unsigned int		seq;
-			struct list_head	list;
-			rq_end_io_fn		*saved_end_io;
-		} flush;
-	};
-
-	struct gendisk *rq_disk;
-	struct block_device *part;
-#ifdef CONFIG_BLK_RQ_ALLOC_TIME
-	/* Time that the first bio started allocating this request. */
-	u64 alloc_time_ns;
-#endif
-	/* Time that this request was allocated for this IO. */
-	u64 start_time_ns;
-	/* Time that I/O was submitted to the device. */
-	u64 io_start_time_ns;
-
-#ifdef CONFIG_BLK_WBT
-	unsigned short wbt_flags;
-#endif
-	/*
-	 * rq sectors used for blk stats. It has the same value
-	 * with blk_rq_sectors(rq), except that it never be zeroed
-	 * by completion.
-	 */
-	unsigned short stats_sectors;
-
-	/*
-	 * Number of scatter-gather DMA addr+len pairs after
-	 * physical address coalescing is performed.
-	 */
-	unsigned short nr_phys_segments;
-
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-	unsigned short nr_integrity_segments;
-#endif
-
-#ifdef CONFIG_BLK_INLINE_ENCRYPTION
-	struct bio_crypt_ctx *crypt_ctx;
-	struct blk_ksm_keyslot *crypt_keyslot;
-#endif
-
-	unsigned short write_hint;
-	unsigned short ioprio;
-
-	enum mq_rq_state state;
-	refcount_t ref;
-
-	unsigned int timeout;
-	unsigned long deadline;
-
-	union {
-		struct __call_single_data csd;
-		u64 fifo_time;
-	};
+static inline int blk_validate_block_size(unsigned int bsize)
+{
+	if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
+		return -EINVAL;
 
-	/*
-	 * completion callback.
-	 */
-	rq_end_io_fn *end_io;
-	void *end_io_data;
-};
+	return 0;
+}
 
 static inline bool blk_op_is_passthrough(unsigned int op)
 {
@@ -241,35 +58,6 @@ static inline bool blk_op_is_passthrough(unsigned int op)
 	return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
 }
 
-static inline bool blk_rq_is_passthrough(struct request *rq)
-{
-	return blk_op_is_passthrough(req_op(rq));
-}
-
-static inline unsigned short req_get_ioprio(struct request *req)
-{
-	return req->ioprio;
-}
-
-#include <linux/elevator.h>
-
-struct blk_queue_ctx;
-
-struct bio_vec;
-
-enum blk_eh_timer_return {
-	BLK_EH_DONE,		/* drivers has completed the command */
-	BLK_EH_RESET_TIMER,	/* reset timer and try again */
-};
-
-enum blk_queue_state {
-	Queue_down,
-	Queue_up,
-};
-
-#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */
-#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */
-
 /*
  * Zoned block device models (zoned limit).
  *
@@ -370,6 +158,34 @@ static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev,
 
 #endif /* CONFIG_BLK_DEV_ZONED */
 
+/*
+ * Independent access ranges: struct blk_independent_access_range describes
+ * a range of contiguous sectors that can be accessed using device command
+ * execution resources that are independent from the resources used for
+ * other access ranges. This is typically found with single-LUN multi-actuator
+ * HDDs where each access range is served by a different set of heads.
+ * The set of independent ranges supported by the device is defined using
+ * struct blk_independent_access_ranges. The independent ranges must not overlap
+ * and must include all sectors within the disk capacity (no sector holes
+ * allowed).
+ * For a device with multiple ranges, requests targeting sectors in different
+ * ranges can be executed in parallel. A request can straddle an access range
+ * boundary.
+ */
+struct blk_independent_access_range {
+	struct kobject		kobj;
+	struct request_queue	*queue;
+	sector_t		sector;
+	sector_t		nr_sectors;
+};
+
+struct blk_independent_access_ranges {
+	struct kobject				kobj;
+	bool					sysfs_registered;
+	unsigned int				nr_ia_ranges;
+	struct blk_independent_access_range	ia_range[];
+};
+
 struct request_queue {
 	struct request		*last_merge;
 	struct elevator_queue	*elevator;
@@ -444,8 +260,7 @@ struct request_queue {
 	unsigned int		dma_alignment;
 
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
-	/* Inline crypto capabilities */
-	struct blk_keyslot_manager *ksm;
+	struct blk_crypto_profile *crypto_profile;
 #endif
 
 	unsigned int		rq_timeout;
@@ -457,10 +272,9 @@ struct request_queue {
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
 
-	atomic_t		nr_active_requests_shared_sbitmap;
+	atomic_t		nr_active_requests_shared_tags;
 
-	struct sbitmap_queue	sched_bitmap_tags;
-	struct sbitmap_queue	sched_breserved_tags;
+	struct blk_mq_tags	*sched_shared_tags;
 
 	struct list_head	icq_list;
 #ifdef CONFIG_BLK_CGROUP
@@ -536,6 +350,8 @@ struct request_queue {
 	 */
 	struct mutex		mq_freeze_lock;
 
+	int			quiesce_depth;
+
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
 	struct bio_set		bio_split;
@@ -549,10 +365,14 @@ struct request_queue {
 
 	bool			mq_sysfs_init_done;
 
-	size_t			cmd_size;
-
 #define BLK_MAX_WRITE_HINTS	5
 	u64			write_hints[BLK_MAX_WRITE_HINTS];
+
+	/*
+	 * Independent sector access ranges. This is always NULL for
+	 * devices that do not have multiple independent access ranges.
+	 */
+	struct blk_independent_access_ranges *ia_ranges;
 };
 
 /* Keep blk_queue_flag_name[] in sync with the definitions below */
@@ -638,11 +458,6 @@ extern void blk_clear_pm_only(struct request_queue *q);
 
 #define list_entry_rq(ptr)	list_entry((ptr), struct request, queuelist)
 
-#define rq_data_dir(rq)		(op_is_write(req_op(rq)) ? WRITE : READ)
-
-#define rq_dma_dir(rq) \
-	(op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE)
-
 #define dma_map_bvec(dev, bv, dir, attrs) \
 	dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \
 	(dir), (attrs))
@@ -758,42 +573,6 @@ static inline unsigned int queue_max_active_zones(const struct request_queue *q)
 }
 #endif /* CONFIG_BLK_DEV_ZONED */
 
-static inline bool rq_is_sync(struct request *rq)
-{
-	return op_is_sync(rq->cmd_flags);
-}
-
-static inline bool rq_mergeable(struct request *rq)
-{
-	if (blk_rq_is_passthrough(rq))
-		return false;
-
-	if (req_op(rq) == REQ_OP_FLUSH)
-		return false;
-
-	if (req_op(rq) == REQ_OP_WRITE_ZEROES)
-		return false;
-
-	if (req_op(rq) == REQ_OP_ZONE_APPEND)
-		return false;
-
-	if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
-		return false;
-	if (rq->rq_flags & RQF_NOMERGE_FLAGS)
-		return false;
-
-	return true;
-}
-
-static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b)
-{
-	if (bio_page(a) == bio_page(b) &&
-	    bio_offset(a) == bio_offset(b))
-		return true;
-
-	return false;
-}
-
 static inline unsigned int blk_queue_depth(struct request_queue *q)
 {
 	if (q->queue_depth)
@@ -808,83 +587,20 @@ static inline unsigned int blk_queue_depth(struct request_queue *q)
 #define BLK_DEFAULT_SG_TIMEOUT	(60 * HZ)
 #define BLK_MIN_SG_TIMEOUT	(7 * HZ)
 
-struct rq_map_data {
-	struct page **pages;
-	int page_order;
-	int nr_entries;
-	unsigned long offset;
-	int null_mapped;
-	int from_user;
-};
-
-struct req_iterator {
-	struct bvec_iter iter;
-	struct bio *bio;
-};
-
 /* This should not be used directly - use rq_for_each_segment */
 #define for_each_bio(_bio)		\
 	for (; _bio; _bio = _bio->bi_next)
-#define __rq_for_each_bio(_bio, rq)	\
-	if ((rq->bio))			\
-		for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next)
-
-#define rq_for_each_segment(bvl, _rq, _iter)			\
-	__rq_for_each_bio(_iter.bio, _rq)			\
-		bio_for_each_segment(bvl, _iter.bio, _iter.iter)
 
-#define rq_for_each_bvec(bvl, _rq, _iter)			\
-	__rq_for_each_bio(_iter.bio, _rq)			\
-		bio_for_each_bvec(bvl, _iter.bio, _iter.iter)
-
-#define rq_iter_last(bvec, _iter)				\
-		(_iter.bio->bi_next == NULL &&			\
-		 bio_iter_last(bvec, _iter.iter))
-
-#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
-# error	"You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform"
-#endif
-#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
-extern void rq_flush_dcache_pages(struct request *rq);
-#else
-static inline void rq_flush_dcache_pages(struct request *rq)
-{
-}
-#endif
 
 extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
-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,
-				       blk_mq_req_flags_t flags);
+void submit_bio_noacct(struct bio *bio);
+
 extern int blk_lld_busy(struct request_queue *q);
-extern 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);
-extern void blk_rq_unprep_clone(struct request *rq);
-extern blk_status_t blk_insert_cloned_request(struct request_queue *q,
-				     struct request *rq);
-int blk_rq_append_bio(struct request *rq, struct bio *bio);
 extern void blk_queue_split(struct bio **);
 extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags);
 extern void blk_queue_exit(struct request_queue *q);
 extern void blk_sync_queue(struct request_queue *q);
-extern int blk_rq_map_user(struct request_queue *, struct request *,
-			   struct rq_map_data *, void __user *, unsigned long,
-			   gfp_t);
-extern int blk_rq_unmap_user(struct bio *);
-extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t);
-extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
-			       struct rq_map_data *, const struct iov_iter *,
-			       gfp_t);
-extern void blk_execute_rq_nowait(struct gendisk *,
-				  struct request *, int, rq_end_io_fn *);
-
-blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq,
-			    int at_head);
 
 /* Helper to convert REQ_OP_XXX to its string format XXX */
 extern const char *blk_op_str(unsigned int op);
@@ -892,11 +608,17 @@ extern const char *blk_op_str(unsigned int op);
 int blk_status_to_errno(blk_status_t status);
 blk_status_t errno_to_blk_status(int errno);
 
-int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin);
+/* only poll the hardware once, don't continue until a completion was found */
+#define BLK_POLL_ONESHOT		(1 << 0)
+/* do not sleep to wait for the expected completion time */
+#define BLK_POLL_NOSLEEP		(1 << 1)
+int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags);
+int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob,
+			unsigned int flags);
 
 static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 {
-	return bdev->bd_disk->queue;	/* this is never NULL */
+	return bdev->bd_queue;	/* this is never NULL */
 }
 
 /*
@@ -916,47 +638,6 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 #define PAGE_SECTORS		(1 << PAGE_SECTORS_SHIFT)
 #define SECTOR_MASK		(PAGE_SECTORS - 1)
 
-/*
- * blk_rq_pos()			: the current sector
- * blk_rq_bytes()		: bytes left in the entire request
- * blk_rq_cur_bytes()		: bytes left in the current segment
- * blk_rq_err_bytes()		: bytes left till the next error boundary
- * blk_rq_sectors()		: sectors left in the entire request
- * blk_rq_cur_sectors()		: sectors left in the current segment
- * blk_rq_stats_sectors()	: sectors of the entire request used for stats
- */
-static inline sector_t blk_rq_pos(const struct request *rq)
-{
-	return rq->__sector;
-}
-
-static inline unsigned int blk_rq_bytes(const struct request *rq)
-{
-	return rq->__data_len;
-}
-
-static inline int blk_rq_cur_bytes(const struct request *rq)
-{
-	return rq->bio ? bio_cur_bytes(rq->bio) : 0;
-}
-
-extern unsigned int blk_rq_err_bytes(const struct request *rq);
-
-static inline unsigned int blk_rq_sectors(const struct request *rq)
-{
-	return blk_rq_bytes(rq) >> SECTOR_SHIFT;
-}
-
-static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
-{
-	return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
-}
-
-static inline unsigned int blk_rq_stats_sectors(const struct request *rq)
-{
-	return rq->stats_sectors;
-}
-
 #ifdef CONFIG_BLK_DEV_ZONED
 
 /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */
@@ -973,42 +654,8 @@ static inline unsigned int bio_zone_is_seq(struct bio *bio)
 	return blk_queue_zone_is_seq(bdev_get_queue(bio->bi_bdev),
 				     bio->bi_iter.bi_sector);
 }
-
-static inline unsigned int blk_rq_zone_no(struct request *rq)
-{
-	return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
-}
-
-static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
-{
-	return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
-}
 #endif /* CONFIG_BLK_DEV_ZONED */
 
-/*
- * Some commands like WRITE SAME have a payload or data transfer size which
- * is different from the size of the request.  Any driver that supports such
- * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to
- * calculate the data transfer size.
- */
-static inline unsigned int blk_rq_payload_bytes(struct request *rq)
-{
-	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
-		return rq->special_vec.bv_len;
-	return blk_rq_bytes(rq);
-}
-
-/*
- * Return the first full biovec in the request.  The caller needs to check that
- * there are any bvecs before calling this helper.
- */
-static inline struct bio_vec req_bvec(struct request *rq)
-{
-	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
-		return rq->special_vec;
-	return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter);
-}
-
 static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 						     int op)
 {
@@ -1048,47 +695,6 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q,
 	return min(q->limits.max_sectors, chunk_sectors);
 }
 
-static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
-						  sector_t offset)
-{
-	struct request_queue *q = rq->q;
-
-	if (blk_rq_is_passthrough(rq))
-		return q->limits.max_hw_sectors;
-
-	if (!q->limits.chunk_sectors ||
-	    req_op(rq) == REQ_OP_DISCARD ||
-	    req_op(rq) == REQ_OP_SECURE_ERASE)
-		return blk_queue_get_max_sectors(q, req_op(rq));
-
-	return min(blk_max_size_offset(q, offset, 0),
-			blk_queue_get_max_sectors(q, req_op(rq)));
-}
-
-static inline unsigned int blk_rq_count_bios(struct request *rq)
-{
-	unsigned int nr_bios = 0;
-	struct bio *bio;
-
-	__rq_for_each_bio(bio, rq)
-		nr_bios++;
-
-	return nr_bios;
-}
-
-void blk_steal_bios(struct bio_list *list, struct request *rq);
-
-/*
- * Request completion related functions.
- *
- * blk_update_request() completes given number of bytes and updates
- * the request without completing it.
- */
-extern bool blk_update_request(struct request *rq, blk_status_t error,
-			       unsigned int nr_bytes);
-
-extern void blk_abort_request(struct request *);
-
 /*
  * Access functions for manipulating queue properties
  */
@@ -1133,46 +739,24 @@ extern void blk_queue_dma_alignment(struct request_queue *, int);
 extern void blk_queue_update_dma_alignment(struct request_queue *, int);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
 extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
-extern void blk_queue_required_elevator_features(struct request_queue *q,
-						 unsigned int features);
-extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
-					      struct device *dev);
 
-/*
- * Number of physical segments as sent to the device.
- *
- * Normally this is the number of discontiguous data segments sent by the
- * submitter.  But for data-less command like discard we might have no
- * actual data segments submitted, but the driver might have to add it's
- * own special payload.  In that case we still return 1 here so that this
- * special payload will be mapped.
- */
-static inline unsigned short blk_rq_nr_phys_segments(struct request *rq)
-{
-	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
-		return 1;
-	return rq->nr_phys_segments;
-}
+struct blk_independent_access_ranges *
+disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges);
+void disk_set_independent_access_ranges(struct gendisk *disk,
+				struct blk_independent_access_ranges *iars);
 
 /*
- * Number of discard segments (or ranges) the driver needs to fill in.
- * Each discard bio merged into a request is counted as one segment.
+ * Elevator features for blk_queue_required_elevator_features:
  */
-static inline unsigned short blk_rq_nr_discard_segments(struct request *rq)
-{
-	return max_t(unsigned short, rq->nr_phys_segments, 1);
-}
+/* Supports zoned block devices sequential write constraint */
+#define ELEVATOR_F_ZBD_SEQ_WRITE	(1U << 0)
+/* Supports scheduling on multiple hardware queues */
+#define ELEVATOR_F_MQ_AWARE		(1U << 1)
 
-int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
-		struct scatterlist *sglist, struct scatterlist **last_sg);
-static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq,
-		struct scatterlist *sglist)
-{
-	struct scatterlist *last_sg = NULL;
-
-	return __blk_rq_map_sg(q, rq, sglist, &last_sg);
-}
-extern void blk_dump_rq_flags(struct request *, char *);
+extern void blk_queue_required_elevator_features(struct request_queue *q,
+						 unsigned int features);
+extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
+					      struct device *dev);
 
 bool __must_check blk_get_queue(struct request_queue *);
 extern void blk_put_queue(struct request_queue *);
@@ -1187,19 +771,24 @@ extern void blk_set_queue_dying(struct request_queue *);
  * as the lock contention for request_queue lock is reduced.
  *
  * It is ok not to disable preemption when adding the request to the plug list
- * or when attempting a merge, because blk_schedule_flush_list() will only flush
- * the plug list when the task sleeps by itself. For details, please see
- * schedule() where blk_schedule_flush_plug() is called.
+ * or when attempting a merge. For details, please see schedule() where
+ * blk_flush_plug() is called.
  */
 struct blk_plug {
-	struct list_head mq_list; /* blk-mq requests */
-	struct list_head cb_list; /* md requires an unplug callback */
+	struct request *mq_list; /* blk-mq requests */
+
+	/* if ios_left is > 1, we can batch tag/rq allocations */
+	struct request *cached_rq;
+	unsigned short nr_ios;
+
 	unsigned short rq_count;
+
 	bool multiple_queues;
+	bool has_elevator;
 	bool nowait;
+
+	struct list_head cb_list; /* md requires an unplug callback */
 };
-#define BLK_MAX_REQUEST_COUNT 16
-#define BLK_PLUG_FLUSH_SIZE (128 * 1024)
 
 struct blk_plug_cb;
 typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool);
@@ -1211,32 +800,17 @@ struct blk_plug_cb {
 extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug,
 					     void *data, int size);
 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 *);
-extern void blk_flush_plug_list(struct blk_plug *, bool);
 
-static inline void blk_flush_plug(struct task_struct *tsk)
-{
-	struct blk_plug *plug = tsk->plug;
-
-	if (plug)
-		blk_flush_plug_list(plug, false);
-}
-
-static inline void blk_schedule_flush_plug(struct task_struct *tsk)
-{
-	struct blk_plug *plug = tsk->plug;
-
-	if (plug)
-		blk_flush_plug_list(plug, true);
-}
+void blk_flush_plug(struct blk_plug *plug, bool from_schedule);
 
 static inline bool blk_needs_flush_plug(struct task_struct *tsk)
 {
 	struct blk_plug *plug = tsk->plug;
 
 	return plug &&
-		 (!list_empty(&plug->mq_list) ||
-		 !list_empty(&plug->cb_list));
+		 (plug->mq_list || !list_empty(&plug->cb_list));
 }
 
 int blkdev_issue_flush(struct block_device *bdev);
@@ -1245,23 +819,23 @@ long nr_blockdev_pages(void);
 struct blk_plug {
 };
 
-static inline void blk_start_plug(struct blk_plug *plug)
+static inline void blk_start_plug_nr_ios(struct blk_plug *plug,
+					 unsigned short nr_ios)
 {
 }
 
-static inline void blk_finish_plug(struct blk_plug *plug)
+static inline void blk_start_plug(struct blk_plug *plug)
 {
 }
 
-static inline void blk_flush_plug(struct task_struct *task)
+static inline void blk_finish_plug(struct blk_plug *plug)
 {
 }
 
-static inline void blk_schedule_flush_plug(struct task_struct *task)
+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;
@@ -1499,22 +1073,6 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector
 	return offset << SECTOR_SHIFT;
 }
 
-/*
- * Two cases of handling DISCARD merge:
- * If max_discard_segments > 1, the driver takes every bio
- * as a range and send them to controller together. The ranges
- * needn't to be contiguous.
- * Otherwise, the bios/requests will be handled as same as
- * others which should be contiguous.
- */
-static inline bool blk_discard_mergable(struct request *req)
-{
-	if (req_op(req) == REQ_OP_DISCARD &&
-	    queue_max_discard_segments(req->q) > 1)
-		return true;
-	return false;
-}
-
 static inline int bdev_discard_alignment(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
@@ -1628,210 +1186,28 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned lo
 #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
 	MODULE_ALIAS("block-major-" __stringify(major) "-*")
 
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-
-enum blk_integrity_flags {
-	BLK_INTEGRITY_VERIFY		= 1 << 0,
-	BLK_INTEGRITY_GENERATE		= 1 << 1,
-	BLK_INTEGRITY_DEVICE_CAPABLE	= 1 << 2,
-	BLK_INTEGRITY_IP_CHECKSUM	= 1 << 3,
-};
-
-struct blk_integrity_iter {
-	void			*prot_buf;
-	void			*data_buf;
-	sector_t		seed;
-	unsigned int		data_size;
-	unsigned short		interval;
-	const char		*disk_name;
-};
-
-typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *);
-typedef void (integrity_prepare_fn) (struct request *);
-typedef void (integrity_complete_fn) (struct request *, unsigned int);
-
-struct blk_integrity_profile {
-	integrity_processing_fn		*generate_fn;
-	integrity_processing_fn		*verify_fn;
-	integrity_prepare_fn		*prepare_fn;
-	integrity_complete_fn		*complete_fn;
-	const char			*name;
-};
-
-extern void blk_integrity_register(struct gendisk *, struct blk_integrity *);
-extern void blk_integrity_unregister(struct gendisk *);
-extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
-extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
-				   struct scatterlist *);
-extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
-
-static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
-{
-	struct blk_integrity *bi = &disk->queue->integrity;
-
-	if (!bi->profile)
-		return NULL;
-
-	return bi;
-}
-
-static inline
-struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
-{
-	return blk_get_integrity(bdev->bd_disk);
-}
-
-static inline bool
-blk_integrity_queue_supports_integrity(struct request_queue *q)
-{
-	return q->integrity.profile;
-}
-
-static inline bool blk_integrity_rq(struct request *rq)
-{
-	return rq->cmd_flags & REQ_INTEGRITY;
-}
-
-static inline void blk_queue_max_integrity_segments(struct request_queue *q,
-						    unsigned int segs)
-{
-	q->limits.max_integrity_segments = segs;
-}
-
-static inline unsigned short
-queue_max_integrity_segments(const struct request_queue *q)
-{
-	return q->limits.max_integrity_segments;
-}
-
-/**
- * bio_integrity_intervals - Return number of integrity intervals for a bio
- * @bi:		blk_integrity profile for device
- * @sectors:	Size of the bio in 512-byte sectors
- *
- * Description: The block layer calculates everything in 512 byte
- * sectors but integrity metadata is done in terms of the data integrity
- * interval size of the storage device.  Convert the block layer sectors
- * to the appropriate number of integrity intervals.
- */
-static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
-						   unsigned int sectors)
-{
-	return sectors >> (bi->interval_exp - 9);
-}
-
-static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
-					       unsigned int sectors)
-{
-	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
-}
-
-/*
- * Return the first bvec that contains integrity data.  Only drivers that are
- * limited to a single integrity segment should use this helper.
- */
-static inline struct bio_vec *rq_integrity_vec(struct request *rq)
-{
-	if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1))
-		return NULL;
-	return rq->bio->bi_integrity->bip_vec;
-}
-
-#else /* CONFIG_BLK_DEV_INTEGRITY */
-
-struct bio;
-struct block_device;
-struct gendisk;
-struct blk_integrity;
-
-static inline int blk_integrity_rq(struct request *rq)
-{
-	return 0;
-}
-static inline int blk_rq_count_integrity_sg(struct request_queue *q,
-					    struct bio *b)
-{
-	return 0;
-}
-static inline int blk_rq_map_integrity_sg(struct request_queue *q,
-					  struct bio *b,
-					  struct scatterlist *s)
-{
-	return 0;
-}
-static inline struct blk_integrity *bdev_get_integrity(struct block_device *b)
-{
-	return NULL;
-}
-static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
-{
-	return NULL;
-}
-static inline bool
-blk_integrity_queue_supports_integrity(struct request_queue *q)
-{
-	return false;
-}
-static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b)
-{
-	return 0;
-}
-static inline void blk_integrity_register(struct gendisk *d,
-					 struct blk_integrity *b)
-{
-}
-static inline void blk_integrity_unregister(struct gendisk *d)
-{
-}
-static inline void blk_queue_max_integrity_segments(struct request_queue *q,
-						    unsigned int segs)
-{
-}
-static inline unsigned short queue_max_integrity_segments(const struct request_queue *q)
-{
-	return 0;
-}
-
-static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
-						   unsigned int sectors)
-{
-	return 0;
-}
-
-static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
-					       unsigned int sectors)
-{
-	return 0;
-}
-
-static inline struct bio_vec *rq_integrity_vec(struct request *rq)
-{
-	return NULL;
-}
-
-#endif /* CONFIG_BLK_DEV_INTEGRITY */
-
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 
-bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q);
+bool blk_crypto_register(struct blk_crypto_profile *profile,
+			 struct request_queue *q);
 
-void blk_ksm_unregister(struct request_queue *q);
+void blk_crypto_unregister(struct request_queue *q);
 
 #else /* CONFIG_BLK_INLINE_ENCRYPTION */
 
-static inline bool blk_ksm_register(struct blk_keyslot_manager *ksm,
-				    struct request_queue *q)
+static inline bool blk_crypto_register(struct blk_crypto_profile *profile,
+				       struct request_queue *q)
 {
 	return true;
 }
 
-static inline void blk_ksm_unregister(struct request_queue *q) { }
+static inline void blk_crypto_unregister(struct request_queue *q) { }
 
 #endif /* CONFIG_BLK_INLINE_ENCRYPTION */
 
 
 struct block_device_operations {
-	blk_qc_t (*submit_bio) (struct bio *bio);
+	void (*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);
@@ -1869,60 +1245,6 @@ extern int bdev_read_page(struct block_device *, sector_t, struct page *);
 extern int bdev_write_page(struct block_device *, sector_t, struct page *,
 						struct writeback_control *);
 
-#ifdef CONFIG_BLK_DEV_ZONED
-bool blk_req_needs_zone_write_lock(struct request *rq);
-bool blk_req_zone_write_trylock(struct request *rq);
-void __blk_req_zone_write_lock(struct request *rq);
-void __blk_req_zone_write_unlock(struct request *rq);
-
-static inline void blk_req_zone_write_lock(struct request *rq)
-{
-	if (blk_req_needs_zone_write_lock(rq))
-		__blk_req_zone_write_lock(rq);
-}
-
-static inline void blk_req_zone_write_unlock(struct request *rq)
-{
-	if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED)
-		__blk_req_zone_write_unlock(rq);
-}
-
-static inline bool blk_req_zone_is_write_locked(struct request *rq)
-{
-	return rq->q->seq_zones_wlock &&
-		test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock);
-}
-
-static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
-{
-	if (!blk_req_needs_zone_write_lock(rq))
-		return true;
-	return !blk_req_zone_is_write_locked(rq);
-}
-#else
-static inline bool blk_req_needs_zone_write_lock(struct request *rq)
-{
-	return false;
-}
-
-static inline void blk_req_zone_write_lock(struct request *rq)
-{
-}
-
-static inline void blk_req_zone_write_unlock(struct request *rq)
-{
-}
-static inline bool blk_req_zone_is_write_locked(struct request *rq)
-{
-	return false;
-}
-
-static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
-{
-	return true;
-}
-#endif /* CONFIG_BLK_DEV_ZONED */
-
 static inline void blk_wake_io_task(struct task_struct *waiter)
 {
 	/*
@@ -2005,4 +1327,41 @@ int fsync_bdev(struct block_device *bdev);
 int freeze_bdev(struct block_device *bdev);
 int thaw_bdev(struct block_device *bdev);
 
+struct io_comp_batch {
+	struct request *req_list;
+	bool need_ts;
+	void (*complete)(struct io_comp_batch *);
+};
+
+#define DEFINE_IO_COMP_BATCH(name)	struct io_comp_batch name = { }
+
+#define rq_list_add(listptr, rq)	do {		\
+	(rq)->rq_next = *(listptr);			\
+	*(listptr) = rq;				\
+} while (0)
+
+#define rq_list_pop(listptr)				\
+({							\
+	struct request *__req = NULL;			\
+	if ((listptr) && *(listptr))	{		\
+		__req = *(listptr);			\
+		*(listptr) = __req->rq_next;		\
+	}						\
+	__req;						\
+})
+
+#define rq_list_peek(listptr)				\
+({							\
+	struct request *__req = NULL;			\
+	if ((listptr) && *(listptr))			\
+		__req = *(listptr);			\
+	__req;						\
+})
+
+#define rq_list_for_each(listptr, pos)			\
+	for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) \
+
+#define rq_list_next(rq)	(rq)->rq_next
+#define rq_list_empty(list)	((list) == (struct request *) NULL)
+
 #endif /* _LINUX_BLKDEV_H */
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index a083e15df608..22501a293fa5 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -2,7 +2,7 @@
 #ifndef BLKTRACE_H
 #define BLKTRACE_H
 
-#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/relay.h>
 #include <linux/compat.h>
 #include <uapi/linux/blktrace_api.h>
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index 0e9bdd42dafb..35c25dff651a 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -44,7 +44,7 @@ struct bvec_iter {
 
 	unsigned int            bi_bvec_done;	/* number of bytes completed in
 						   current bvec */
-};
+} __packed;
 
 struct bvec_iter_all {
 	struct bio_vec	bv;
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 114553b487ef..a7df155ea49b 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -576,9 +576,9 @@ struct dm_table *dm_swap_table(struct mapped_device *md,
 			       struct dm_table *t);
 
 /*
- * Table keyslot manager functions
+ * Table blk_crypto_profile functions
  */
-void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm);
+void dm_destroy_crypto_profile(struct blk_crypto_profile *profile);
 
 /*-----------------------------------------------------------------
  * Macros.
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
deleted file mode 100644
index ef9ceead3db1..000000000000
--- a/include/linux/elevator.h
+++ /dev/null
@@ -1,181 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_ELEVATOR_H
-#define _LINUX_ELEVATOR_H
-
-#include <linux/percpu.h>
-#include <linux/hashtable.h>
-
-#ifdef CONFIG_BLOCK
-
-struct io_cq;
-struct elevator_type;
-#ifdef CONFIG_BLK_DEBUG_FS
-struct blk_mq_debugfs_attr;
-#endif
-
-/*
- * Return values from elevator merger
- */
-enum elv_merge {
-	ELEVATOR_NO_MERGE	= 0,
-	ELEVATOR_FRONT_MERGE	= 1,
-	ELEVATOR_BACK_MERGE	= 2,
-	ELEVATOR_DISCARD_MERGE	= 3,
-};
-
-struct blk_mq_alloc_data;
-struct blk_mq_hw_ctx;
-
-struct elevator_mq_ops {
-	int (*init_sched)(struct request_queue *, struct elevator_type *);
-	void (*exit_sched)(struct elevator_queue *);
-	int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int);
-	void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int);
-	void (*depth_updated)(struct blk_mq_hw_ctx *);
-
-	bool (*allow_merge)(struct request_queue *, struct request *, struct bio *);
-	bool (*bio_merge)(struct request_queue *, struct bio *, unsigned int);
-	int (*request_merge)(struct request_queue *q, struct request **, struct bio *);
-	void (*request_merged)(struct request_queue *, struct request *, enum elv_merge);
-	void (*requests_merged)(struct request_queue *, struct request *, struct request *);
-	void (*limit_depth)(unsigned int, struct blk_mq_alloc_data *);
-	void (*prepare_request)(struct request *);
-	void (*finish_request)(struct request *);
-	void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool);
-	struct request *(*dispatch_request)(struct blk_mq_hw_ctx *);
-	bool (*has_work)(struct blk_mq_hw_ctx *);
-	void (*completed_request)(struct request *, u64);
-	void (*requeue_request)(struct request *);
-	struct request *(*former_request)(struct request_queue *, struct request *);
-	struct request *(*next_request)(struct request_queue *, struct request *);
-	void (*init_icq)(struct io_cq *);
-	void (*exit_icq)(struct io_cq *);
-};
-
-#define ELV_NAME_MAX	(16)
-
-struct elv_fs_entry {
-	struct attribute attr;
-	ssize_t (*show)(struct elevator_queue *, char *);
-	ssize_t (*store)(struct elevator_queue *, const char *, size_t);
-};
-
-/*
- * identifies an elevator type, such as AS or deadline
- */
-struct elevator_type
-{
-	/* managed by elevator core */
-	struct kmem_cache *icq_cache;
-
-	/* fields provided by elevator implementation */
-	struct elevator_mq_ops ops;
-
-	size_t icq_size;	/* see iocontext.h */
-	size_t icq_align;	/* ditto */
-	struct elv_fs_entry *elevator_attrs;
-	const char *elevator_name;
-	const char *elevator_alias;
-	const unsigned int elevator_features;
-	struct module *elevator_owner;
-#ifdef CONFIG_BLK_DEBUG_FS
-	const struct blk_mq_debugfs_attr *queue_debugfs_attrs;
-	const struct blk_mq_debugfs_attr *hctx_debugfs_attrs;
-#endif
-
-	/* managed by elevator core */
-	char icq_cache_name[ELV_NAME_MAX + 6];	/* elvname + "_io_cq" */
-	struct list_head list;
-};
-
-#define ELV_HASH_BITS 6
-
-void elv_rqhash_del(struct request_queue *q, struct request *rq);
-void elv_rqhash_add(struct request_queue *q, struct request *rq);
-void elv_rqhash_reposition(struct request_queue *q, struct request *rq);
-struct request *elv_rqhash_find(struct request_queue *q, sector_t offset);
-
-/*
- * each queue has an elevator_queue associated with it
- */
-struct elevator_queue
-{
-	struct elevator_type *type;
-	void *elevator_data;
-	struct kobject kobj;
-	struct mutex sysfs_lock;
-	unsigned int registered:1;
-	DECLARE_HASHTABLE(hash, ELV_HASH_BITS);
-};
-
-/*
- * block elevator interface
- */
-extern enum elv_merge elv_merge(struct request_queue *, struct request **,
-		struct bio *);
-extern void elv_merge_requests(struct request_queue *, struct request *,
-			       struct request *);
-extern void elv_merged_request(struct request_queue *, struct request *,
-		enum elv_merge);
-extern bool elv_attempt_insert_merge(struct request_queue *, struct request *,
-				     struct list_head *);
-extern struct request *elv_former_request(struct request_queue *, struct request *);
-extern struct request *elv_latter_request(struct request_queue *, struct request *);
-void elevator_init_mq(struct request_queue *q);
-
-/*
- * io scheduler registration
- */
-extern int elv_register(struct elevator_type *);
-extern void elv_unregister(struct elevator_type *);
-
-/*
- * io scheduler sysfs switching
- */
-extern ssize_t elv_iosched_show(struct request_queue *, char *);
-extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
-
-extern bool elv_bio_merge_ok(struct request *, struct bio *);
-extern struct elevator_queue *elevator_alloc(struct request_queue *,
-					struct elevator_type *);
-
-/*
- * Helper functions.
- */
-extern struct request *elv_rb_former_request(struct request_queue *, struct request *);
-extern struct request *elv_rb_latter_request(struct request_queue *, struct request *);
-
-/*
- * rb support functions.
- */
-extern void elv_rb_add(struct rb_root *, struct request *);
-extern void elv_rb_del(struct rb_root *, struct request *);
-extern struct request *elv_rb_find(struct rb_root *, sector_t);
-
-/*
- * Insertion selection
- */
-#define ELEVATOR_INSERT_FRONT	1
-#define ELEVATOR_INSERT_BACK	2
-#define ELEVATOR_INSERT_SORT	3
-#define ELEVATOR_INSERT_REQUEUE	4
-#define ELEVATOR_INSERT_FLUSH	5
-#define ELEVATOR_INSERT_SORT_MERGE	6
-
-#define rq_end_sector(rq)	(blk_rq_pos(rq) + blk_rq_sectors(rq))
-#define rb_entry_rq(node)	rb_entry((node), struct request, rb_node)
-
-#define rq_entry_fifo(ptr)	list_entry((ptr), struct request, queuelist)
-#define rq_fifo_clear(rq)	list_del_init(&(rq)->queuelist)
-
-/*
- * Elevator features.
- */
-
-/* Supports zoned block devices sequential write constraint */
-#define ELEVATOR_F_ZBD_SEQ_WRITE	(1U << 0)
-/* Supports scheduling on multiple hardware queues */
-#define ELEVATOR_F_MQ_AWARE		(1U << 1)
-
-#endif /* CONFIG_BLOCK */
-#endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e7a633353fd2..31029a91f440 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -48,6 +48,7 @@
 struct backing_dev_info;
 struct bdi_writeback;
 struct bio;
+struct io_comp_batch;
 struct export_operations;
 struct fiemap_extent_info;
 struct hd_geometry;
@@ -334,11 +335,7 @@ struct kiocb {
 	int			ki_flags;
 	u16			ki_hint;
 	u16			ki_ioprio; /* See linux/ioprio.h */
-	union {
-		unsigned int		ki_cookie; /* for ->iopoll */
-		struct wait_page_queue	*ki_waitq; /* for async buffered IO */
-	};
-
+	struct wait_page_queue	*ki_waitq; /* for async buffered IO */
 	randomized_struct_fields_end
 };
 
@@ -2075,7 +2072,8 @@ struct file_operations {
 	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
-	int (*iopoll)(struct kiocb *kiocb, bool spin);
+	int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *,
+			unsigned int flags);
 	int (*iterate) (struct file *, struct dir_context *);
 	int (*iterate_shared) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 0f5315c2b5a3..13f313ab99e7 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -12,12 +12,10 @@
 
 #include <linux/types.h>
 #include <linux/kdev_t.h>
-#include <linux/rcupdate.h>
-#include <linux/slab.h>
-#include <linux/percpu-refcount.h>
 #include <linux/uuid.h>
 #include <linux/blk_types.h>
-#include <asm/local.h>
+#include <linux/device.h>
+#include <linux/xarray.h>
 
 extern const struct device_type disk_type;
 extern struct device_type part_type;
@@ -26,14 +24,6 @@ extern struct class block_class;
 #define DISK_MAX_PARTS			256
 #define DISK_NAME_LEN			32
 
-#include <linux/major.h>
-#include <linux/device.h>
-#include <linux/smp.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/workqueue.h>
-#include <linux/xarray.h>
-
 #define PARTITION_META_INFO_VOLNAMELTH	64
 /*
  * Enough for the string representation of any kind of UUID plus NULL.
@@ -223,6 +213,8 @@ static inline int add_disk(struct gendisk *disk)
 }
 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)
@@ -231,6 +223,11 @@ static inline int get_disk_ro(struct gendisk *disk)
 		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);
@@ -291,10 +288,6 @@ 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);
 
-/* 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_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);
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 24f8489583ca..63f4ea4dac9b 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -313,8 +313,8 @@ int iomap_writepages(struct address_space *mapping,
 struct iomap_dio_ops {
 	int (*end_io)(struct kiocb *iocb, ssize_t size, int error,
 		      unsigned flags);
-	blk_qc_t (*submit_io)(const struct iomap_iter *iter, struct bio *bio,
-			      loff_t file_offset);
+	void (*submit_io)(const struct iomap_iter *iter, struct bio *bio,
+		          loff_t file_offset);
 };
 
 /*
@@ -337,7 +337,6 @@ struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		unsigned int dio_flags);
 ssize_t iomap_dio_complete(struct iomap_dio *dio);
-int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
 
 #ifdef CONFIG_SWAP
 struct file;
diff --git a/include/linux/keyslot-manager.h b/include/linux/keyslot-manager.h
deleted file mode 100644
index a27605e2f826..000000000000
--- a/include/linux/keyslot-manager.h
+++ /dev/null
@@ -1,120 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright 2019 Google LLC
- */
-
-#ifndef __LINUX_KEYSLOT_MANAGER_H
-#define __LINUX_KEYSLOT_MANAGER_H
-
-#include <linux/bio.h>
-#include <linux/blk-crypto.h>
-
-struct blk_keyslot_manager;
-
-/**
- * struct blk_ksm_ll_ops - functions to manage keyslots in hardware
- * @keyslot_program:	Program the specified key into the specified slot in the
- *			inline encryption hardware.
- * @keyslot_evict:	Evict key from the specified keyslot in the hardware.
- *			The key is provided so that e.g. dm layers can evict
- *			keys from the devices that they map over.
- *			Returns 0 on success, -errno otherwise.
- *
- * This structure should be provided by storage device drivers when they set up
- * a keyslot manager - this structure holds the function ptrs that the keyslot
- * manager will use to manipulate keyslots in the hardware.
- */
-struct blk_ksm_ll_ops {
-	int (*keyslot_program)(struct blk_keyslot_manager *ksm,
-			       const struct blk_crypto_key *key,
-			       unsigned int slot);
-	int (*keyslot_evict)(struct blk_keyslot_manager *ksm,
-			     const struct blk_crypto_key *key,
-			     unsigned int slot);
-};
-
-struct blk_keyslot_manager {
-	/*
-	 * The struct blk_ksm_ll_ops that this keyslot manager will use
-	 * to perform operations like programming and evicting keys on the
-	 * device
-	 */
-	struct blk_ksm_ll_ops ksm_ll_ops;
-
-	/*
-	 * The maximum number of bytes supported for specifying the data unit
-	 * number.
-	 */
-	unsigned int max_dun_bytes_supported;
-
-	/*
-	 * Array of size BLK_ENCRYPTION_MODE_MAX of bitmasks that represents
-	 * whether a crypto mode and data unit size are supported. The i'th
-	 * bit of crypto_mode_supported[crypto_mode] is set iff a data unit
-	 * size of (1 << i) is supported. We only support data unit sizes
-	 * that are powers of 2.
-	 */
-	unsigned int crypto_modes_supported[BLK_ENCRYPTION_MODE_MAX];
-
-	/* Device for runtime power management (NULL if none) */
-	struct device *dev;
-
-	/* Here onwards are *private* fields for internal keyslot manager use */
-
-	unsigned int num_slots;
-
-	/* Protects programming and evicting keys from the device */
-	struct rw_semaphore lock;
-
-	/* List of idle slots, with least recently used slot at front */
-	wait_queue_head_t idle_slots_wait_queue;
-	struct list_head idle_slots;
-	spinlock_t idle_slots_lock;
-
-	/*
-	 * Hash table which maps struct *blk_crypto_key to keyslots, so that we
-	 * can find a key's keyslot in O(1) time rather than O(num_slots).
-	 * Protected by 'lock'.
-	 */
-	struct hlist_head *slot_hashtable;
-	unsigned int log_slot_ht_size;
-
-	/* Per-keyslot data */
-	struct blk_ksm_keyslot *slots;
-};
-
-int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots);
-
-int devm_blk_ksm_init(struct device *dev, struct blk_keyslot_manager *ksm,
-		      unsigned int num_slots);
-
-blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm,
-				      const struct blk_crypto_key *key,
-				      struct blk_ksm_keyslot **slot_ptr);
-
-unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot);
-
-void blk_ksm_put_slot(struct blk_ksm_keyslot *slot);
-
-bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm,
-				  const struct blk_crypto_config *cfg);
-
-int blk_ksm_evict_key(struct blk_keyslot_manager *ksm,
-		      const struct blk_crypto_key *key);
-
-void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm);
-
-void blk_ksm_destroy(struct blk_keyslot_manager *ksm);
-
-void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent,
-			     const struct blk_keyslot_manager *child);
-
-void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm);
-
-bool blk_ksm_is_superset(struct blk_keyslot_manager *ksm_superset,
-			 struct blk_keyslot_manager *ksm_subset);
-
-void blk_ksm_update_capabilities(struct blk_keyslot_manager *target_ksm,
-				 struct blk_keyslot_manager *reference_ksm);
-
-#endif /* __LINUX_KEYSLOT_MANAGER_H */
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 0c0c9a0fdf57..52eae8c45b8d 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -15,7 +15,7 @@
 #include <linux/mmc/card.h>
 #include <linux/mmc/pm.h>
 #include <linux/dma-direction.h>
-#include <linux/keyslot-manager.h>
+#include <linux/blk-crypto-profile.h>
 
 struct mmc_ios {
 	unsigned int	clock;			/* clock rate */
@@ -492,7 +492,7 @@ struct mmc_host {
 
 	/* Inline encryption support */
 #ifdef CONFIG_MMC_CRYPTO
-	struct blk_keyslot_manager ksm;
+	struct blk_crypto_profile crypto_profile;
 #endif
 
 	/* Host Software Queue support */
diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h
index d2558121d48c..6f7949b2fd8d 100644
--- a/include/linux/part_stat.h
+++ b/include/linux/part_stat.h
@@ -3,6 +3,7 @@
 #define _LINUX_PART_STAT_H
 
 #include <linux/genhd.h>
+#include <asm/local.h>
 
 struct disk_stats {
 	u64 nsecs[NR_STAT_GROUPS];
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index ae16a9856305..b31d3f3312ce 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -267,6 +267,28 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 }
 
 /**
+ * percpu_ref_tryget_live_rcu - same as percpu_ref_tryget_live() but the
+ * caller is responsible for taking RCU.
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+static inline bool percpu_ref_tryget_live_rcu(struct percpu_ref *ref)
+{
+	unsigned long __percpu *percpu_count;
+	bool ret = false;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	if (likely(__ref_is_percpu(ref, &percpu_count))) {
+		this_cpu_inc(*percpu_count);
+		ret = true;
+	} else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) {
+		ret = atomic_long_inc_not_zero(&ref->data->count);
+	}
+	return ret;
+}
+
+/**
  * percpu_ref_tryget_live - try to increment a live percpu refcount
  * @ref: percpu_ref to try-get
  *
@@ -283,20 +305,11 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
  */
 static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 {
-	unsigned long __percpu *percpu_count;
 	bool ret = false;
 
 	rcu_read_lock();
-
-	if (__ref_is_percpu(ref, &percpu_count)) {
-		this_cpu_inc(*percpu_count);
-		ret = true;
-	} else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) {
-		ret = atomic_long_inc_not_zero(&ref->data->count);
-	}
-
+	ret = percpu_ref_tryget_live_rcu(ref);
 	rcu_read_unlock();
-
 	return ret;
 }
 
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 2713e689ad66..4a6ff274335a 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -427,6 +427,19 @@ void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth);
 int __sbitmap_queue_get(struct sbitmap_queue *sbq);
 
 /**
+ * __sbitmap_queue_get_batch() - Try to allocate a batch of free bits
+ * @sbq: Bitmap queue to allocate from.
+ * @nr_tags: number of tags requested
+ * @offset: offset to add to returned bits
+ *
+ * Return: Mask of allocated tags, 0 if none are found. Each tag allocated is
+ * a bit in the mask returned, and the caller must add @offset to the value to
+ * get the absolute tag value.
+ */
+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, limiting the depth used from each word, with preemption
  * already disabled.
@@ -515,6 +528,17 @@ void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq,
 void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
 			 unsigned int cpu);
 
+/**
+ * sbitmap_queue_clear_batch() - Free a batch of allocated bits
+ * &struct sbitmap_queue.
+ * @sbq: Bitmap to free from.
+ * @offset: offset for each tag in array
+ * @tags: array of tags
+ * @nr_tags: number of tags in array
+ */
+void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset,
+				int *tags, int nr_tags);
+
 static inline int sbq_index_inc(int index)
 {
 	return (index + 1) & (SBQ_WAIT_QUEUES - 1);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c1a927ddec64..e0454e60fe8f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1160,10 +1160,8 @@ struct task_struct {
 	/* Stacked block device info: */
 	struct bio_list			*bio_list;
 
-#ifdef CONFIG_BLOCK
 	/* Stack plugging: */
 	struct blk_plug			*plug;
-#endif
 
 	/* VM state: */
 	struct reclaim_state		*reclaim_state;
diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h
index 96305a64a5a7..c635c2e014e3 100644
--- a/include/linux/t10-pi.h
+++ b/include/linux/t10-pi.h
@@ -3,7 +3,7 @@
 #define _LINUX_T10_PI_H
 
 #include <linux/types.h>
-#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 
 /*
  * A T10 PI-capable target device can be formatted with different
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 3571f383dfb6..3bfd487d1dd2 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -11,7 +11,6 @@
 #include <linux/flex_proportions.h>
 #include <linux/backing-dev-defs.h>
 #include <linux/blk_types.h>
-#include <linux/blk-cgroup.h>
 
 struct bio;
 
@@ -109,15 +108,12 @@ static inline int wbc_to_write_flags(struct writeback_control *wbc)
 	return flags;
 }
 
-static inline struct cgroup_subsys_state *
-wbc_blkcg_css(struct writeback_control *wbc)
-{
 #ifdef CONFIG_CGROUP_WRITEBACK
-	if (wbc->wb)
-		return wbc->wb->blkcg_css;
-#endif
-	return blkcg_root_css;
-}
+#define wbc_blkcg_css(wbc) \
+	((wbc)->wb ? (wbc)->wb->blkcg_css : blkcg_root_css)
+#else
+#define wbc_blkcg_css(wbc)		(blkcg_root_css)
+#endif /* CONFIG_CGROUP_WRITEBACK */
 
 /*
  * A wb_domain represents a domain that wb's (bdi_writeback's) belong to