Merge tag 'for-5.20/block-2022-07-29' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

- Improve the type checking of request flags (Bart)

- Ensure queue mapping for a single queues always picks the right queue
(Bart)

- Sanitize the io priority handling (Jan)

- rq-qos race fix (Jinke)

- Reserved tags handling improvements (John)

- Separate memory alignment from file/disk offset aligment for O_DIRECT
(Keith)

- Add new ublk driver, userspace block driver using io_uring for
communication with the userspace backend (Ming)

- Use try_cmpxchg() to cleanup the code in various spots (Uros)

- Finally remove bdevname() (Christoph)

- Clean up the zoned device handling (Christoph)

- Clean up independent access range support (Christoph)

- Clean up and improve block sysfs handling (Christoph)

- Clean up and improve teardown of block devices.

This turns the usual two step process into something that is simpler
to implement and handle in block drivers (Christoph)

- Clean up chunk size handling (Christoph)

- Misc cleanups and fixes (Bart, Bo, Dan, GuoYong, Jason, Keith, Liu,
Ming, Sebastian, Yang, Ying)

* tag 'for-5.20/block-2022-07-29' of git://git.kernel.dk/linux-block: (178 commits)
ublk_drv: fix double shift bug
ublk_drv: make sure that correct flags(features) returned to userspace
ublk_drv: fix error handling of ublk_add_dev
ublk_drv: fix lockdep warning
block: remove __blk_get_queue
block: call blk_mq_exit_queue from disk_release for never added disks
blk-mq: fix error handling in __blk_mq_alloc_disk
ublk: defer disk allocation
ublk: rewrite ublk_ctrl_get_queue_affinity to not rely on hctx->cpumask
ublk: fold __ublk_create_dev into ublk_ctrl_add_dev
ublk: cleanup ublk_ctrl_uring_cmd
ublk: simplify ublk_ch_open and ublk_ch_release
ublk: remove the empty open and release block device operations
ublk: remove UBLK_IO_F_PREFLUSH
ublk: add a MAINTAINERS entry
block: don't allow the same type rq_qos add more than once
mmc: fix disk/queue leak in case of adding disk failure
ublk_drv: fix an IS_ERR() vs NULL check
ublk: remove UBLK_IO_F_INTEGRITY
ublk_drv: remove unneeded semicolon
...

Documentation/ABI/stable/sysfs-block

···
 		for discards, and don't read this file.
 
 
+What:		/sys/block/<disk>/queue/dma_alignment
+Date:		May 2022
+Contact:	[e-mail]
+Description:
+		Reports the alignment that user space addresses must have to be
+		used for raw block device access with O_DIRECT and other driver
+		specific passthrough mechanisms.
+
+
 What:		/sys/block/<disk>/queue/fua
 Date:		May 2018
 Contact:	[e-mail]

Documentation/scsi/scsi_eh.rst

···
 1.2.2 Completing a scmd w/ timeout
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-The timeout handler is scsi_times_out().  When a timeout occurs, this
-function
+The timeout handler is scsi_timeout().  When a timeout occurs, this function
 
  1. invokes optional hostt->eh_timed_out() callback.  Return value can
     be one of

Documentation/scsi/scsi_mid_low_api.rst

···
     *      Notes: If 'no_async_abort' is defined this callback
     *  	will be invoked from scsi_eh thread. No other commands
     *	will then be queued on current host during eh.
-    *	Otherwise it will be called whenever scsi_times_out()
+    *	Otherwise it will be called whenever scsi_timeout()
     *      is called due to a command timeout.
     *
     *      Optionally defined in: LLD

MAINTAINERS

···
 F:	Documentation/filesystems/ubifs.rst
 F:	fs/ubifs/
 
+UBLK USERSPACE BLOCK DRIVER
+M:	Ming Lei <[e-mail]>
+L:	[e-mail]
+S:	Maintained
+F:	drivers/block/ublk_drv.c
+F:	include/uapi/linux/ublk_cmd.h
+
 UCLINUX (M68KNOMMU AND COLDFIRE)
 M:	Greg Ungerer <[e-mail]>
 L:	[e-mail]

arch/m68k/emu/nfblock.c

···
 	return 0;
 
 out_cleanup_disk:
-	blk_cleanup_disk(dev->disk);
+	put_disk(dev->disk);
 free_dev:
 	kfree(dev);
 out:
···
 	list_for_each_entry_safe(dev, next, &nfhd_list, list) {
 		list_del(&dev->list);
 		del_gendisk(dev->disk);
-		blk_cleanup_disk(dev->disk);
+		put_disk(dev->disk);
 		kfree(dev);
 	}
 	unregister_blkdev(major_num, "nfhd");

arch/um/drivers/ubd_kern.c

···
 	return 0;
 
 out_cleanup_disk:
-	blk_cleanup_disk(disk);
+	put_disk(disk);
 out_cleanup_tags:
 	blk_mq_free_tag_set(&ubd_dev->tag_set);
 out:
···
 	ubd_gendisk[n] = NULL;
 	if(disk != NULL){
 		del_gendisk(disk);
-		blk_cleanup_disk(disk);
+		put_disk(disk);
 	}
 
 	err = 0;
···
 	struct req_iterator iter;
 	int i = 0;
 	unsigned long byte_offset = io_req->offset;
-	int op = req_op(req);
+	enum req_op op = req_op(req);
 
 	if (op == REQ_OP_WRITE_ZEROES || op == REQ_OP_DISCARD) {
 		io_req->io_desc[0].buffer = NULL;
···
 	int segs = 0;
 	struct io_thread_req *io_req;
 	int ret;
-	int op = req_op(req);
+	enum req_op op = req_op(req);
 
 	if (op == REQ_OP_FLUSH)
 		segs = 0;

arch/xtensa/platforms/iss/simdisk.c

···
 	return 0;
 
 out_cleanup_disk:
-	blk_cleanup_disk(dev->gd);
+	put_disk(dev->gd);
 out:
 	return err;
 }
···
 	simdisk_detach(dev);
 	if (dev->gd) {
 		del_gendisk(dev->gd);
-		blk_cleanup_disk(dev->gd);
+		put_disk(dev->gd);
 	}
 	remove_proc_entry(tmp, procdir);
 }

block/Kconfig

···
 config BLK_CGROUP_IOCOST
 	bool "Enable support for cost model based cgroup IO controller"
 	depends on BLK_CGROUP
-	select BLK_RQ_IO_DATA_LEN
 	select BLK_RQ_ALLOC_TIME
 	help
 	Enabling this option enables the .weight interface for cost

block/bdev.c

···
 	while (inode->i_state & I_DIRTY) {
 		spin_unlock(&inode->i_lock);
 		ret = write_inode_now(inode, true);
-		if (ret) {
-			char name[BDEVNAME_SIZE];
-			pr_warn_ratelimited("VFS: Dirty inode writeback failed "
-					    "for block device %s (err=%d).\n",
-					    bdevname(bdev, name), ret);
-		}
+		if (ret)
+			pr_warn_ratelimited(
+	"VFS: Dirty inode writeback failed for block device %pg (err=%d).\n",
+				bdev, ret);
 		spin_lock(&inode->i_lock);
 	}
 	spin_unlock(&inode->i_lock);

block/bfq-cgroup.c

···
 }
 
 void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
-			      unsigned int op)
+			      blk_opf_t opf)
 {
-	blkg_rwstat_add(&bfqg->stats.queued, op, 1);
+	blkg_rwstat_add(&bfqg->stats.queued, opf, 1);
 	bfqg_stats_end_empty_time(&bfqg->stats);
 	if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue))
 		bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq));
 }
 
-void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op)
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, blk_opf_t opf)
 {
-	blkg_rwstat_add(&bfqg->stats.queued, op, -1);
+	blkg_rwstat_add(&bfqg->stats.queued, opf, -1);
 }
 
-void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op)
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, blk_opf_t opf)
 {
-	blkg_rwstat_add(&bfqg->stats.merged, op, 1);
+	blkg_rwstat_add(&bfqg->stats.merged, opf, 1);
 }
 
 void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
-				  u64 io_start_time_ns, unsigned int op)
+				  u64 io_start_time_ns, blk_opf_t opf)
 {
 	struct bfqg_stats *stats = &bfqg->stats;
 	u64 now = ktime_get_ns();
 
 	if (now > io_start_time_ns)
-		blkg_rwstat_add(&stats->service_time, op,
+		blkg_rwstat_add(&stats->service_time, opf,
 				now - io_start_time_ns);
 	if (io_start_time_ns > start_time_ns)
-		blkg_rwstat_add(&stats->wait_time, op,
+		blkg_rwstat_add(&stats->wait_time, opf,
 				io_start_time_ns - start_time_ns);
 }
 
 #else /* CONFIG_BFQ_CGROUP_DEBUG */
 
 void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
-			      unsigned int op) { }
-void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { }
-void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { }
+			      blk_opf_t opf) { }
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, blk_opf_t opf) { }
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, blk_opf_t opf) { }
 void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
-				  u64 io_start_time_ns, unsigned int op) { }
+				  u64 io_start_time_ns, blk_opf_t opf) { }
 void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
 void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
 void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
···
 }
 
 /**
- * __bfq_bic_change_cgroup - move @bic to @cgroup.
+ * __bfq_bic_change_cgroup - move @bic to @bfqg.
  * @bfqd: the queue descriptor.
  * @bic: the bic to move.
- * @blkcg: the blk-cgroup to move to.
+ * @bfqg: the group to move to.
  *
  * Move bic to blkcg, assuming that bfqd->lock is held; which makes
  * sure that the reference to cgroup is valid across the call (see
···
  * @bfqd: the device data structure with the root group.
  * @entity: the entity to move, if entity is a leaf; or the parent entity
  *	    of an active leaf entity to move, if entity is not a leaf.
+ * @ioprio_class: I/O priority class to reparent.
  */
 static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
 				     struct bfq_entity *entity,
···
  * @bfqd: the device data structure with the root group.
  * @bfqg: the group to move from.
  * @st: the service tree to start the search from.
+ * @ioprio_class: I/O priority class to reparent.
  */
 static void bfq_reparent_active_queues(struct bfq_data *bfqd,
 				       struct bfq_group *bfqg,
···
 {
 	return bfqq->bfqd->root_group;
 }
-
-void bfqg_and_blkg_get(struct bfq_group *bfqg) {}
 
 void bfqg_and_blkg_put(struct bfq_group *bfqg) {}
 

block/bfq-iosched.c

···
  * significantly affect service guarantees coming from the BFQ scheduling
  * algorithm.
  */
-static void bfq_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
+static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 {
 	struct bfq_data *bfqd = data->q->elevator->elevator_data;
 	struct bfq_io_cq *bic = bfq_bic_lookup(data->q);
-	struct bfq_queue *bfqq = bic ? bic_to_bfqq(bic, op_is_sync(op)) : NULL;
+	struct bfq_queue *bfqq = bic ? bic_to_bfqq(bic, op_is_sync(opf)) : NULL;
 	int depth;
 	unsigned limit = data->q->nr_requests;
 
 	/* Sync reads have full depth available */
-	if (op_is_sync(op) && !op_is_write(op)) {
+	if (op_is_sync(opf) && !op_is_write(opf)) {
 		depth = 0;
 	} else {
-		depth = bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(op)];
+		depth = bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(opf)];
 		limit = (limit * depth) >> bfqd->full_depth_shift;
 	}
 
···
 		depth = 1;
 
 	bfq_log(bfqd, "[%s] wr_busy %d sync %d depth %u",
-		__func__, bfqd->wr_busy_queues, op_is_sync(op), depth);
+		__func__, bfqd->wr_busy_queues, op_is_sync(opf), depth);
 	if (depth)
 		data->shallow_depth = depth;
 }
···
 static void bfq_update_insert_stats(struct request_queue *q,
 				    struct bfq_queue *bfqq,
 				    bool idle_timer_disabled,
-				    unsigned int cmd_flags)
+				    blk_opf_t cmd_flags)
 {
 	if (!bfqq)
 		return;
···
 static inline void bfq_update_insert_stats(struct request_queue *q,
 					   struct bfq_queue *bfqq,
 					   bool idle_timer_disabled,
-					   unsigned int cmd_flags) {}
+					   blk_opf_t cmd_flags) {}
 #endif /* CONFIG_BFQ_CGROUP_DEBUG */
 
 static struct bfq_queue *bfq_init_rq(struct request *rq);
···
 	struct bfq_data *bfqd = q->elevator->elevator_data;
 	struct bfq_queue *bfqq;
 	bool idle_timer_disabled = false;
-	unsigned int cmd_flags;
+	blk_opf_t cmd_flags;
 	LIST_HEAD(free);
 
 #ifdef CONFIG_BFQ_GROUP_IOSCHED

block/bfq-iosched.h

···
 
 void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq);
 void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
-			      unsigned int op);
-void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op);
-void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op);
+			      blk_opf_t opf);
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, blk_opf_t opf);
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, blk_opf_t opf);
 void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
-				  u64 io_start_time_ns, unsigned int op);
+				  u64 io_start_time_ns, blk_opf_t opf);
 void bfqg_stats_update_dequeue(struct bfq_group *bfqg);
 void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
 void bfqg_stats_update_idle_time(struct bfq_group *bfqg);

block/bfq-wf2q.c

···
 /**
  * __bfq_lookup_next_entity - return the first eligible entity in @st.
  * @st: the service tree.
+ * @in_service: whether or not there is an in-service entity for the sched_data
+ *	this active tree belongs to.
  *
  * If there is no in-service entity for the sched_data st belongs to,
  * then return the entity that will be set in service if:
···
 		if (entity)
 			break;
 	}
-
-	if (!entity)
-		return NULL;
 
 	return entity;
 }

block/bio.c

···
  * when IO has completed, or when the bio is released.
  */
 void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table,
-	      unsigned short max_vecs, unsigned int opf)
+	      unsigned short max_vecs, blk_opf_t opf)
 {
 	bio->bi_next = NULL;
 	bio->bi_bdev = bdev;
···
  *   preserved are the ones that are initialized by bio_alloc_bioset(). See
  *   comment in struct bio.
  */
-void bio_reset(struct bio *bio, struct block_device *bdev, unsigned int opf)
+void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf)
 {
 	bio_uninit(bio);
 	memset(bio, 0, BIO_RESET_BYTES);
···
 EXPORT_SYMBOL(bio_chain);
 
 struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
-		unsigned int nr_pages, unsigned int opf, gfp_t gfp)
+		unsigned int nr_pages, blk_opf_t opf, gfp_t gfp)
 {
 	struct bio *new = bio_alloc(bdev, nr_pages, opf, gfp);
 
···
 }
 
 static struct bio *bio_alloc_percpu_cache(struct block_device *bdev,
-		unsigned short nr_vecs, unsigned int opf, gfp_t gfp,
+		unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp,
 		struct bio_set *bs)
 {
 	struct bio_alloc_cache *cache;
···
  * Returns: Pointer to new bio on success, NULL on failure.
  */
 struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
-			     unsigned int opf, gfp_t gfp_mask,
+			     blk_opf_t opf, gfp_t gfp_mask,
 			     struct bio_set *bs)
 {
 	gfp_t saved_gfp = gfp_mask;
···
 	if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_ZONE_APPEND))
 		return 0;
 
-	if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
+	if (WARN_ON_ONCE(!bdev_is_zoned(bio->bi_bdev)))
 		return 0;
 
 	return bio_add_hw_page(q, bio, page, len, offset,
···
 		put_page(pages[i]);
 }
 
+static int bio_iov_add_page(struct bio *bio, struct page *page,
+		unsigned int len, unsigned int offset)
+{
+	bool same_page = false;
+
+	if (!__bio_try_merge_page(bio, page, len, offset, &same_page)) {
+		if (WARN_ON_ONCE(bio_full(bio, len)))
+			return -EINVAL;
+		__bio_add_page(bio, page, len, offset);
+		return 0;
+	}
+
+	if (same_page)
+		put_page(page);
+	return 0;
+}
+
+static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
+		unsigned int len, unsigned int offset)
+{
+	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+	bool same_page = false;
+
+	if (bio_add_hw_page(q, bio, page, len, offset,
+			queue_max_zone_append_sectors(q), &same_page) != len)
+		return -EINVAL;
+	if (same_page)
+		put_page(page);
+	return 0;
+}
+
 #define PAGE_PTRS_PER_BVEC     (sizeof(struct bio_vec) / sizeof(struct page *))
 
 /**
···
 	unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
 	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
 	struct page **pages = (struct page **)bv;
-	bool same_page = false;
 	ssize_t size, left;
 	unsigned len, i;
 	size_t offset;
-
-	/*
-	 * Move page array up in the allocated memory for the bio vecs as far as
-	 * possible so that we can start filling biovecs from the beginning
-	 * without overwriting the temporary page array.
-	*/
-	BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
-	pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
-
-	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
-	if (unlikely(size <= 0))
-		return size ? size : -EFAULT;
-
-	for (left = size, i = 0; left > 0; left -= len, i++) {
-		struct page *page = pages[i];
-
-		len = min_t(size_t, PAGE_SIZE - offset, left);
-
-		if (__bio_try_merge_page(bio, page, len, offset, &same_page)) {
-			if (same_page)
-				put_page(page);
-		} else {
-			if (WARN_ON_ONCE(bio_full(bio, len))) {
-				bio_put_pages(pages + i, left, offset);
-				return -EINVAL;
-			}
-			__bio_add_page(bio, page, len, offset);
-		}
-		offset = 0;
-	}
-
-	iov_iter_advance(iter, size);
-	return 0;
-}
-
-static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter)
-{
-	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
-	unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
-	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	unsigned int max_append_sectors = queue_max_zone_append_sectors(q);
-	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
-	struct page **pages = (struct page **)bv;
-	ssize_t size, left;
-	unsigned len, i;
-	size_t offset;
-	int ret = 0;
-
-	if (WARN_ON_ONCE(!max_append_sectors))
-		return 0;
 
 	/*
 	 * Move page array up in the allocated memory for the bio vecs as far as
···
 	BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
 	pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
 
+	/*
+	 * Each segment in the iov is required to be a block size multiple.
+	 * However, we may not be able to get the entire segment if it spans
+	 * more pages than bi_max_vecs allows, so we have to ALIGN_DOWN the
+	 * result to ensure the bio's total size is correct. The remainder of
+	 * the iov data will be picked up in the next bio iteration.
+	 */
 	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
+	if (size > 0)
+		size = ALIGN_DOWN(size, bdev_logical_block_size(bio->bi_bdev));
 	if (unlikely(size <= 0))
 		return size ? size : -EFAULT;
 
 	for (left = size, i = 0; left > 0; left -= len, i++) {
 		struct page *page = pages[i];
-		bool same_page = false;
+		int ret;
 
 		len = min_t(size_t, PAGE_SIZE - offset, left);
-		if (bio_add_hw_page(q, bio, page, len, offset,
-				max_append_sectors, &same_page) != len) {
+		if (bio_op(bio) == REQ_OP_ZONE_APPEND)
+			ret = bio_iov_add_zone_append_page(bio, page, len,
+					offset);
+		else
+			ret = bio_iov_add_page(bio, page, len, offset);
+
+		if (ret) {
 			bio_put_pages(pages + i, left, offset);
-			ret = -EINVAL;
-			break;
+			return ret;
 		}
-		if (same_page)
-			put_page(page);
 		offset = 0;
 	}
 
-	iov_iter_advance(iter, size - left);
-	return ret;
+	iov_iter_advance(iter, size);
+	return 0;
 }
 
 /**
···
 	}
 
 	do {
-		if (bio_op(bio) == REQ_OP_ZONE_APPEND)
-			ret = __bio_iov_append_get_pages(bio, iter);
-		else
-			ret = __bio_iov_iter_get_pages(bio, iter);
+		ret = __bio_iov_iter_get_pages(bio, iter);
 	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
 
 	/* don't account direct I/O as memory stall */

block/blk-cgroup-rwstat.h

···
  * caller is responsible for synchronizing calls to this function.
  */
 static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
-				   unsigned int op, uint64_t val)
+				   blk_opf_t opf, uint64_t val)
 {
 	struct percpu_counter *cnt;
 
-	if (op_is_discard(op))
+	if (op_is_discard(opf))
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD];
-	else if (op_is_write(op))
+	else if (op_is_write(opf))
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE];
 	else
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];
 
 	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
 
-	if (op_is_sync(op))
+	if (op_is_sync(opf))
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC];
 	else
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC];

block/blk-cgroup.c

···
 	}
 }
 
+static void blkcg_iostat_update(struct blkcg_gq *blkg, struct blkg_iostat *cur,
+				struct blkg_iostat *last)
+{
+	struct blkg_iostat delta;
+	unsigned long flags;
+
+	/* propagate percpu delta to global */
+	flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync);
+	blkg_iostat_set(&delta, cur);
+	blkg_iostat_sub(&delta, last);
+	blkg_iostat_add(&blkg->iostat.cur, &delta);
+	blkg_iostat_add(last, &delta);
+	u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags);
+}
+
 static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
···
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
 		struct blkcg_gq *parent = blkg->parent;
 		struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu);
-		struct blkg_iostat cur, delta;
-		unsigned long flags;
+		struct blkg_iostat cur;
 		unsigned int seq;
 
 		/* fetch the current per-cpu values */
···
 			blkg_iostat_set(&cur, &bisc->cur);
 		} while (u64_stats_fetch_retry(&bisc->sync, seq));
 
-		/* propagate percpu delta to global */
-		flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync);
-		blkg_iostat_set(&delta, &cur);
-		blkg_iostat_sub(&delta, &bisc->last);
-		blkg_iostat_add(&blkg->iostat.cur, &delta);
-		blkg_iostat_add(&bisc->last, &delta);
-		u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags);
+		blkcg_iostat_update(blkg, &cur, &bisc->last);
 
 		/* propagate global delta to parent (unless that's root) */
-		if (parent && parent->parent) {
-			flags = u64_stats_update_begin_irqsave(&parent->iostat.sync);
-			blkg_iostat_set(&delta, &blkg->iostat.cur);
-			blkg_iostat_sub(&delta, &blkg->iostat.last);
-			blkg_iostat_add(&parent->iostat.cur, &delta);
-			blkg_iostat_add(&blkg->iostat.last, &delta);
-			u64_stats_update_end_irqrestore(&parent->iostat.sync, flags);
-		}
+		if (parent && parent->parent)
+			blkcg_iostat_update(parent, &blkg->iostat.cur,
+					    &blkg->iostat.last);
 	}
 
 	rcu_read_unlock();
···
 	ret = blk_iolatency_init(q);
 	if (ret) {
 		blk_throtl_exit(q);
+		blk_ioprio_exit(q);
 		goto err_destroy_all;
 	}
 
···
 }
 EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);
 
+static void blkcg_free_all_cpd(struct blkcg_policy *pol)
+{
+	struct blkcg *blkcg;
+
+	list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
+		if (blkcg->cpd[pol->plid]) {
+			pol->cpd_free_fn(blkcg->cpd[pol->plid]);
+			blkcg->cpd[pol->plid] = NULL;
+		}
+	}
+}
+
 /**
  * blkcg_policy_register - register a blkcg policy
  * @pol: blkcg policy to register
···
 	return 0;
 
 err_free_cpds:
-	if (pol->cpd_free_fn) {
-		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
-			if (blkcg->cpd[pol->plid]) {
-				pol->cpd_free_fn(blkcg->cpd[pol->plid]);
-				blkcg->cpd[pol->plid] = NULL;
-			}
-		}
-	}
+	if (pol->cpd_free_fn)
+		blkcg_free_all_cpd(pol);
+
 	blkcg_policy[pol->plid] = NULL;
 err_unlock:
 	mutex_unlock(&blkcg_pol_mutex);
···
  */
 void blkcg_policy_unregister(struct blkcg_policy *pol)
 {
-	struct blkcg *blkcg;
-
 	mutex_lock(&blkcg_pol_register_mutex);
 
 	if (WARN_ON(blkcg_policy[pol->plid] != pol))
···
 	/* remove cpds and unregister */
 	mutex_lock(&blkcg_pol_mutex);
 
-	if (pol->cpd_free_fn) {
-		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
-			if (blkcg->cpd[pol->plid]) {
-				pol->cpd_free_fn(blkcg->cpd[pol->plid]);
-				blkcg->cpd[pol->plid] = NULL;
-			}
-		}
-	}
+	if (pol->cpd_free_fn)
+		blkcg_free_all_cpd(pol);
+
 	blkcg_policy[pol->plid] = NULL;
 
 	mutex_unlock(&blkcg_pol_mutex);
···
 	 * everybody is happy with their IO latencies.
 	 */
 	if (time_before64(old + NSEC_PER_SEC, now) &&
-	    atomic64_cmpxchg(&blkg->delay_start, old, now) == old) {
+	    atomic64_try_cmpxchg(&blkg->delay_start, &old, now)) {
 		u64 cur = atomic64_read(&blkg->delay_nsec);
 		u64 sub = min_t(u64, blkg->last_delay, now - old);
 		int cur_use = atomic_read(&blkg->use_delay);

block/blk-cgroup.h

···
 	 * then check to see if we were the last delay so we can drop the
 	 * congestion count on the cgroup.
 	 */
-	while (old) {
-		int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1);
-		if (cur == old)
-			break;
-		old = cur;
-	}
+	while (old && !atomic_try_cmpxchg(&blkg->use_delay, &old, old - 1))
+		;
 
 	if (old == 0)
 		return 0;
···
 	int old = atomic_read(&blkg->use_delay);
 
 	/* We only want 1 person setting the congestion count for this blkg. */
-	if (!old && atomic_cmpxchg(&blkg->use_delay, old, -1) == old)
+	if (!old && atomic_try_cmpxchg(&blkg->use_delay, &old, -1))
 		atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
 
 	atomic64_set(&blkg->delay_nsec, delay);
···
 	int old = atomic_read(&blkg->use_delay);
 
 	/* We only want 1 person clearing the congestion count for this blkg. */
-	if (old && atomic_cmpxchg(&blkg->use_delay, old, 0) == old)
+	if (old && atomic_try_cmpxchg(&blkg->use_delay, &old, 0))
 		atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
 }
 

block/blk-core.c

···
  * string format. Useful in the debugging and tracing bio or request. For
  * invalid REQ_OP_XXX it returns string "UNKNOWN".
  */
-inline const char *blk_op_str(unsigned int op)
+inline const char *blk_op_str(enum req_op op)
 {
 	const char *op_str = "UNKNOWN";
 
···
 }
 
 /**
- * blk_cleanup_queue - shutdown a request queue
- * @q: request queue to shutdown
- *
- * Mark @q DYING, drain all pending requests, mark @q DEAD, destroy and
- * put it.  All future requests will be failed immediately with -ENODEV.
- *
- * Context: can sleep
- */
-void blk_cleanup_queue(struct request_queue *q)
-{
-	/* cannot be called from atomic context */
-	might_sleep();
-
-	WARN_ON_ONCE(blk_queue_registered(q));
-
-	/* mark @q DYING, no new request or merges will be allowed afterwards */
-	blk_queue_flag_set(QUEUE_FLAG_DYING, q);
-	blk_queue_start_drain(q);
-
-	blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q);
-	blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
-
-	/*
-	 * Drain all requests queued before DYING marking. Set DEAD flag to
-	 * prevent that blk_mq_run_hw_queues() accesses the hardware queues
-	 * after draining finished.
-	 */
-	blk_freeze_queue(q);
-
-	blk_queue_flag_set(QUEUE_FLAG_DEAD, q);
-
-	blk_sync_queue(q);
-	if (queue_is_mq(q)) {
-		blk_mq_cancel_work_sync(q);
-		blk_mq_exit_queue(q);
-	}
-
-	/* @q is and will stay empty, shutdown and put */
-	blk_put_queue(q);
-}
-EXPORT_SYMBOL(blk_cleanup_queue);
-
-/**
  * blk_queue_enter() - try to increase q->q_usage_counter
  * @q: request queue pointer
  * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM
···
 
 	q->last_merge = NULL;
 
-	q->id = ida_simple_get(&blk_queue_ida, 0, 0, GFP_KERNEL);
+	q->id = ida_alloc(&blk_queue_ida, GFP_KERNEL);
 	if (q->id < 0)
 		goto fail_srcu;
 
···
 fail_split:
 	bioset_exit(&q->bio_split);
 fail_id:
-	ida_simple_remove(&blk_queue_ida, q->id);
+	ida_free(&blk_queue_ida, q->id);
 fail_srcu:
 	if (alloc_srcu)
 		cleanup_srcu_struct(q->srcu);
···
  */
 bool blk_get_queue(struct request_queue *q)
 {
-	if (likely(!blk_queue_dying(q))) {
-		__blk_get_queue(q);
-		return true;
-	}
-
-	return false;
+	if (unlikely(blk_queue_dying(q)))
+		return false;
+	kobject_get(&q->kobj);
+	return true;
 }
 EXPORT_SYMBOL(blk_get_queue);
 
···
 static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 						 struct bio *bio)
 {
-	sector_t pos = bio->bi_iter.bi_sector;
 	int nr_sectors = bio_sectors(bio);
 
 	/* Only applicable to zoned block devices */
-	if (!blk_queue_is_zoned(q))
+	if (!bdev_is_zoned(bio->bi_bdev))
 		return BLK_STS_NOTSUPP;
 
 	/* The bio sector must point to the start of a sequential zone */
-	if (pos & (blk_queue_zone_sectors(q) - 1) ||
-	    !blk_queue_zone_is_seq(q, pos))
+	if (bio->bi_iter.bi_sector & (bdev_zone_sectors(bio->bi_bdev) - 1) ||
+	    !bio_zone_is_seq(bio))
 		return BLK_STS_IOERR;
 
 	/*
···
 
 	might_sleep();
 
-	plug = blk_mq_plug(q, bio);
+	plug = blk_mq_plug(bio);
 	if (plug && plug->nowait)
 		bio->bi_opf |= REQ_NOWAIT;
 
···
 	case REQ_OP_ZONE_OPEN:
 	case REQ_OP_ZONE_CLOSE:
 	case REQ_OP_ZONE_FINISH:
-		if (!blk_queue_is_zoned(q))
+		if (!bdev_is_zoned(bio->bi_bdev))
 			goto not_supported;
 		break;
 	case REQ_OP_ZONE_RESET_ALL:
-		if (!blk_queue_is_zoned(q) || !blk_queue_zone_resetall(q))
+		if (!bdev_is_zoned(bio->bi_bdev) || !blk_queue_zone_resetall(q))
 			goto not_supported;
 		break;
 	case REQ_OP_WRITE_ZEROES:
···
 again:
 	stamp = READ_ONCE(part->bd_stamp);
 	if (unlikely(time_after(now, stamp))) {
-		if (likely(cmpxchg(&part->bd_stamp, stamp, now) == stamp))
+		if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now)))
 			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
 	}
 	if (part->bd_partno) {
···
 }
 
 unsigned long bdev_start_io_acct(struct block_device *bdev,
-				 unsigned int sectors, unsigned int op,
+				 unsigned int sectors, enum req_op op,
 				 unsigned long start_time)
 {
 	const int sgrp = op_stat_group(op);
···
 }
 EXPORT_SYMBOL_GPL(bio_start_io_acct);
 
-void bdev_end_io_acct(struct block_device *bdev, unsigned int op,
+void bdev_end_io_acct(struct block_device *bdev, enum req_op op,
 		      unsigned long start_time)
 {
 	const int sgrp = op_stat_group(op);
···
 
 int __init blk_dev_init(void)
 {
-	BUILD_BUG_ON(REQ_OP_LAST >= (1 << REQ_OP_BITS));
+	BUILD_BUG_ON((__force u32)REQ_OP_LAST >= (1 << REQ_OP_BITS));
 	BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 *
 			sizeof_field(struct request, cmd_flags));
 	BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 *

block/blk-flush.c

···
 };
 
 static void blk_kick_flush(struct request_queue *q,
-			   struct blk_flush_queue *fq, unsigned int flags);
+			   struct blk_flush_queue *fq, blk_opf_t flags);
 
 static inline struct blk_flush_queue *
 blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx)
···
 {
 	struct request_queue *q = rq->q;
 	struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx];
-	unsigned int cmd_flags;
+	blk_opf_t cmd_flags;
 
 	BUG_ON(rq->flush.seq & seq);
 	rq->flush.seq |= seq;
···
  *
  */
 static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
-			   unsigned int flags)
+			   blk_opf_t flags)
 {
 	struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx];
 	struct request *first_rq =

block/blk-ia-ranges.c

···
  * disk_register_independent_access_ranges - register with sysfs a set of
  *		independent access ranges
  * @disk:	Target disk
- * @new_iars:	New set of independent access ranges
  *
  * Register with sysfs a set of independent access ranges for @disk.
- * If @new_iars is not NULL, this set of ranges is registered and the old set
- * specified by q->ia_ranges is unregistered. Otherwise, q->ia_ranges is
- * registered if it is not already.
  */
-int disk_register_independent_access_ranges(struct gendisk *disk,
-				struct blk_independent_access_ranges *new_iars)
+int disk_register_independent_access_ranges(struct gendisk *disk)
 {
+	struct blk_independent_access_ranges *iars = disk->ia_ranges;
 	struct request_queue *q = disk->queue;
-	struct blk_independent_access_ranges *iars;
 	int i, ret;
 
 	lockdep_assert_held(&q->sysfs_dir_lock);
 	lockdep_assert_held(&q->sysfs_lock);
 
-	/* If a new range set is specified, unregister the old one */
-	if (new_iars) {
-		if (q->ia_ranges)
-			disk_unregister_independent_access_ranges(disk);
-		q->ia_ranges = new_iars;
-	}
-
-	iars = q->ia_ranges;
 	if (!iars)
 		return 0;
 
···
 	ret = kobject_init_and_add(&iars->kobj, &blk_ia_ranges_ktype,
 				   &q->kobj, "%s", "independent_access_ranges");
 	if (ret) {
-		q->ia_ranges = NULL;
+		disk->ia_ranges = NULL;
 		kobject_put(&iars->kobj);
 		return ret;
 	}
···
 void disk_unregister_independent_access_ranges(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
-	struct blk_independent_access_ranges *iars = q->ia_ranges;
+	struct blk_independent_access_ranges *iars = disk->ia_ranges;
 	int i;
 
 	lockdep_assert_held(&q->sysfs_dir_lock);
···
 		kfree(iars);
 	}
 
-	q->ia_ranges = NULL;
+	disk->ia_ranges = NULL;
 }
 
 static struct blk_independent_access_range *
···
 	sector_t capacity = get_capacity(disk);
 	sector_t sector = 0;
 	int i;
+
+	if (WARN_ON_ONCE(!iars->nr_ia_ranges))
+		return false;
 
 	/*
 	 * While sorting the ranges in increasing LBA order, check that the
···
 static bool disk_ia_ranges_changed(struct gendisk *disk,
 				   struct blk_independent_access_ranges *new)
 {
-	struct blk_independent_access_ranges *old = disk->queue->ia_ranges;
+	struct blk_independent_access_ranges *old = disk->ia_ranges;
 	int i;
 
 	if (!old)
···
 {
 	struct request_queue *q = disk->queue;
 
-	if (WARN_ON_ONCE(iars && !iars->nr_ia_ranges)) {
+	mutex_lock(&q->sysfs_dir_lock);
+	mutex_lock(&q->sysfs_lock);
+	if (iars && !disk_check_ia_ranges(disk, iars)) {
 		kfree(iars);
 		iars = NULL;
 	}
-
-	mutex_lock(&q->sysfs_dir_lock);
-	mutex_lock(&q->sysfs_lock);
-
-	if (iars) {
-		if (!disk_check_ia_ranges(disk, iars)) {
-			kfree(iars);
-			iars = NULL;
-			goto reg;
-		}
-
-		if (!disk_ia_ranges_changed(disk, iars)) {
-			kfree(iars);
-			goto unlock;
-		}
+	if (iars && !disk_ia_ranges_changed(disk, iars)) {
+		kfree(iars);
+		goto unlock;
 	}
 
 	/*
···
 	 * revalidation. If that is the case, we need to unregister the old
 	 * set of independent access ranges and register the new set. If the
 	 * queue is not registered, registration of the device request queue
-	 * will register the independent access ranges, so only swap in the
-	 * new set and free the old one.
+	 * will register the independent access ranges.
 	 */
-reg:
-	if (blk_queue_registered(q)) {
-		disk_register_independent_access_ranges(disk, iars);
-	} else {
-		swap(q->ia_ranges, iars);
-		kfree(iars);
-	}
-
+	disk_unregister_independent_access_ranges(disk);
+	disk->ia_ranges = iars;
+	if (blk_queue_registered(q))
+		disk_register_independent_access_ranges(disk);
 unlock:
 	mutex_unlock(&q->sysfs_lock);
 	mutex_unlock(&q->sysfs_dir_lock);

block/blk-ioc.c

···
 	INIT_HLIST_HEAD(&ioc->icq_list);
 	INIT_WORK(&ioc->release_work, ioc_release_fn);
 #endif
+	ioc->ioprio = IOPRIO_DEFAULT;
+
 	return ioc;
 }
 

block/blk-iocost.c

···
 	if (!ioc->enabled || !rq->alloc_time_ns || !rq->start_time_ns)
 		return;
 
-	switch (req_op(rq) & REQ_OP_MASK) {
+	switch (req_op(rq)) {
 	case REQ_OP_READ:
 		pidx = QOS_RLAT;
 		rw = READ;
···
 	 * called before policy activation completion, can't assume that the
 	 * target bio has an iocg associated and need to test for NULL iocg.
 	 */
-	rq_qos_add(q, rqos);
+	ret = rq_qos_add(q, rqos);
+	if (ret)
+		goto err_free_ioc;
+
 	ret = blkcg_activate_policy(q, &blkcg_policy_iocost);
-	if (ret) {
-		rq_qos_del(q, rqos);
-		free_percpu(ioc->pcpu_stat);
-		kfree(ioc);
-		return ret;
-	}
+	if (ret)
+		goto err_del_qos;
 	return 0;
+
+err_del_qos:
+	rq_qos_del(q, rqos);
+err_free_ioc:
+	free_percpu(ioc->pcpu_stat);
+	kfree(ioc);
+	return ret;
 }
 
 static struct blkcg_policy_data *ioc_cpd_alloc(gfp_t gfp)

block/blk-iolatency.c

···
 	unsigned int cur_cookie;
 	unsigned int our_cookie = atomic_read(&iolat->scale_cookie);
 	u64 scale_lat;
-	unsigned int old;
 	int direction = 0;
 
 	if (lat_to_blkg(iolat)->parent == NULL)
···
 	else
 		return;
 
-	old = atomic_cmpxchg(&iolat->scale_cookie, our_cookie, cur_cookie);
-
-	/* Somebody beat us to the punch, just bail. */
-	if (old != our_cookie)
+	if (!atomic_try_cmpxchg(&iolat->scale_cookie, &our_cookie, cur_cookie)) {
+		/* Somebody beat us to the punch, just bail. */
 		return;
+	}
 
 	if (direction < 0 && iolat->min_lat_nsec) {
 		u64 samples_thresh;
···
 			window_start = atomic64_read(&iolat->window_start);
 			if (now > window_start &&
 			    (now - window_start) >= iolat->cur_win_nsec) {
-				if (atomic64_cmpxchg(&iolat->window_start,
-					     window_start, now) == window_start)
+				if (atomic64_try_cmpxchg(&iolat->window_start,
+							 &window_start, now))
 					iolatency_check_latencies(iolat, now);
 			}
 		}
···
 	rqos->ops = &blkcg_iolatency_ops;
 	rqos->q = q;
 
-	rq_qos_add(q, rqos);
-
+	ret = rq_qos_add(q, rqos);
+	if (ret)
+		goto err_free;
 	ret = blkcg_activate_policy(q, &blkcg_policy_iolatency);
-	if (ret) {
-		rq_qos_del(q, rqos);
-		kfree(blkiolat);
-		return ret;
-	}
+	if (ret)
+		goto err_qos_del;
 
 	timer_setup(&blkiolat->timer, blkiolatency_timer_fn, 0);
 	INIT_WORK(&blkiolat->enable_work, blkiolatency_enable_work_fn);
 
 	return 0;
+
+err_qos_del:
+	rq_qos_del(q, rqos);
+err_free:
+	kfree(blkiolat);
+	return ret;
 }
 
 static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val)

block/blk-ioprio.c

···
 struct ioprio_blkcg {
 	struct blkcg_policy_data cpd;
 	enum prio_policy	 prio_policy;
-	bool			 prio_set;
 };
 
 static inline struct ioprio_blkg *pd_to_ioprio(struct blkg_policy_data *pd)
···
 	if (ret < 0)
 		return ret;
 	blkcg->prio_policy = ret;
-	blkcg->prio_set = true;
 	return nbytes;
 }
 
···
 	.pd_free_fn	= ioprio_free_pd,
 };
 
-struct blk_ioprio {
-	struct rq_qos rqos;
-};
-
-static void blkcg_ioprio_track(struct rq_qos *rqos, struct request *rq,
-			       struct bio *bio)
+void blkcg_set_ioprio(struct bio *bio)
 {
 	struct ioprio_blkcg *blkcg = ioprio_blkcg_from_bio(bio);
 	u16 prio;
 
-	if (!blkcg->prio_set)
+	if (!blkcg || blkcg->prio_policy == POLICY_NO_CHANGE)
 		return;
 
 	/*
 	 * Except for IOPRIO_CLASS_NONE, higher I/O priority numbers
 	 * correspond to a lower priority. Hence, the max_t() below selects
 	 * the lower priority of bi_ioprio and the cgroup I/O priority class.
-	 * If the cgroup policy has been set to POLICY_NO_CHANGE == 0, the
-	 * bio I/O priority is not modified. If the bio I/O priority equals
-	 * IOPRIO_CLASS_NONE, the cgroup I/O priority is assigned to the bio.
+	 * If the bio I/O priority equals IOPRIO_CLASS_NONE, the cgroup I/O
+	 * priority is assigned to the bio.
 	 */
 	prio = max_t(u16, bio->bi_ioprio,
 			IOPRIO_PRIO_VALUE(blkcg->prio_policy, 0));
···
 		bio->bi_ioprio = prio;
 }
 
-static void blkcg_ioprio_exit(struct rq_qos *rqos)
+void blk_ioprio_exit(struct request_queue *q)
 {
-	struct blk_ioprio *blkioprio_blkg =
-		container_of(rqos, typeof(*blkioprio_blkg), rqos);
-
-	blkcg_deactivate_policy(rqos->q, &ioprio_policy);
-	kfree(blkioprio_blkg);
+	blkcg_deactivate_policy(q, &ioprio_policy);
 }
-
-static struct rq_qos_ops blkcg_ioprio_ops = {
-	.track	= blkcg_ioprio_track,
-	.exit	= blkcg_ioprio_exit,
-};
 
 int blk_ioprio_init(struct request_queue *q)
 {
-	struct blk_ioprio *blkioprio_blkg;
-	struct rq_qos *rqos;
-	int ret;
-
-	blkioprio_blkg = kzalloc(sizeof(*blkioprio_blkg), GFP_KERNEL);
-	if (!blkioprio_blkg)
-		return -ENOMEM;
-
-	ret = blkcg_activate_policy(q, &ioprio_policy);
-	if (ret) {
-		kfree(blkioprio_blkg);
-		return ret;
-	}
-
-	rqos = &blkioprio_blkg->rqos;
-	rqos->id = RQ_QOS_IOPRIO;
-	rqos->ops = &blkcg_ioprio_ops;
-	rqos->q = q;
-
-	/*
-	 * Registering the rq-qos policy after activating the blk-cgroup
-	 * policy guarantees that ioprio_blkcg_from_bio(bio) != NULL in the
-	 * rq-qos callbacks.
-	 */
-	rq_qos_add(q, rqos);
-
-	return 0;
+	return blkcg_activate_policy(q, &ioprio_policy);
 }
 
 static int __init ioprio_init(void)

block/blk-ioprio.h

···
 #include <linux/kconfig.h>
 
 struct request_queue;
+struct bio;
 
 #ifdef CONFIG_BLK_CGROUP_IOPRIO
 int blk_ioprio_init(struct request_queue *q);
+void blk_ioprio_exit(struct request_queue *q);
+void blkcg_set_ioprio(struct bio *bio);
 #else
 static inline int blk_ioprio_init(struct request_queue *q)
 {
 	return 0;
+}
+static inline void blk_ioprio_exit(struct request_queue *q)
+{
+}
+static inline void blkcg_set_ioprio(struct bio *bio)
+{
 }
 #endif
 

block/blk-lib.c

···
 
 	/* In case the discard granularity isn't set by buggy device driver */
 	if (WARN_ON_ONCE(!bdev_discard_granularity(bdev))) {
-		char dev_name[BDEVNAME_SIZE];
-
-		bdevname(bdev, dev_name);
-		pr_err_ratelimited("%s: Error: discard_granularity is 0.\n", dev_name);
+		pr_err_ratelimited("%pg: Error: discard_granularity is 0.\n",
+				   bdev);
 		return -EOPNOTSUPP;
 	}
 

block/blk-merge.c

···
 static inline unsigned get_max_io_size(struct request_queue *q,
 				       struct bio *bio)
 {
-	unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector, 0);
-	unsigned max_sectors = sectors;
 	unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT;
 	unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT;
-	unsigned start_offset = bio->bi_iter.bi_sector & (pbs - 1);
+	unsigned max_sectors = queue_max_sectors(q), start, end;
 
-	max_sectors += start_offset;
-	max_sectors &= ~(pbs - 1);
-	if (max_sectors > start_offset)
-		return max_sectors - start_offset;
+	if (q->limits.chunk_sectors) {
+		max_sectors = min(max_sectors,
+			blk_chunk_sectors_left(bio->bi_iter.bi_sector,
+					       q->limits.chunk_sectors));
+	}
 
-	return sectors & ~(lbs - 1);
+	start = bio->bi_iter.bi_sector & (pbs - 1);
+	end = (start + max_sectors) & ~(pbs - 1);
+	if (end > start)
+		return end - start;
+	return max_sectors & ~(lbs - 1);
 }
 
 static inline unsigned get_max_segment_size(const struct request_queue *q,
···
  * @nsegs:    [in,out] Number of segments in the bio being built. Incremented
  *            by the number of segments from @bv that may be appended to that
  *            bio without exceeding @max_segs
- * @sectors:  [in,out] Number of sectors in the bio being built. Incremented
- *            by the number of sectors from @bv that may be appended to that
- *            bio without exceeding @max_sectors
+ * @bytes:    [in,out] Number of bytes in the bio being built. Incremented
+ *            by the number of bytes from @bv that may be appended to that
+ *            bio without exceeding @max_bytes
  * @max_segs: [in] upper bound for *@nsegs
- * @max_sectors: [in] upper bound for *@sectors
+ * @max_bytes: [in] upper bound for *@bytes
  *
  * When splitting a bio, it can happen that a bvec is encountered that is too
  * big to fit in a single segment and hence that it has to be split in the
···
  */
 static bool bvec_split_segs(const struct request_queue *q,
 			    const struct bio_vec *bv, unsigned *nsegs,
-			    unsigned *sectors, unsigned max_segs,
-			    unsigned max_sectors)
+			    unsigned *bytes, unsigned max_segs,
+			    unsigned max_bytes)
 {
-	unsigned max_len = (min(max_sectors, UINT_MAX >> 9) - *sectors) << 9;
+	unsigned max_len = min(max_bytes, UINT_MAX) - *bytes;
 	unsigned len = min(bv->bv_len, max_len);
 	unsigned total_len = 0;
 	unsigned seg_size = 0;
···
 			break;
 	}
 
-	*sectors += total_len >> 9;
+	*bytes += total_len;
 
 	/* tell the caller to split the bvec if it is too big to fit */
 	return len > 0 || bv->bv_len > max_len;
···
 {
 	struct bio_vec bv, bvprv, *bvprvp = NULL;
 	struct bvec_iter iter;
-	unsigned nsegs = 0, sectors = 0;
-	const unsigned max_sectors = get_max_io_size(q, bio);
+	unsigned nsegs = 0, bytes = 0;
+	const unsigned max_bytes = get_max_io_size(q, bio) << 9;
 	const unsigned max_segs = queue_max_segments(q);
 
 	bio_for_each_bvec(bv, bio, iter) {
···
 			goto split;
 
 		if (nsegs < max_segs &&
-		    sectors + (bv.bv_len >> 9) <= max_sectors &&
+		    bytes + bv.bv_len <= max_bytes &&
 		    bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
 			nsegs++;
-			sectors += bv.bv_len >> 9;
-		} else if (bvec_split_segs(q, &bv, &nsegs, &sectors, max_segs,
-					 max_sectors)) {
+			bytes += bv.bv_len;
+		} else if (bvec_split_segs(q, &bv, &nsegs, &bytes, max_segs,
+					   max_bytes)) {
 			goto split;
 		}
 
···
 	*segs = nsegs;
 
 	/*
+	 * Individual bvecs might not be logical block aligned. Round down the
+	 * split size so that each bio is properly block size aligned, even if
+	 * we do not use the full hardware limits.
+	 */
+	bytes = ALIGN_DOWN(bytes, queue_logical_block_size(q));
+
+	/*
 	 * Bio splitting may cause subtle trouble such as hang when doing sync
 	 * iopoll in direct IO routine. Given performance gain of iopoll for
 	 * big IO can be trival, disable iopoll when split needed.
 	 */
 	bio_clear_polled(bio);
-	return bio_split(bio, sectors, GFP_NOIO, bs);
+	return bio_split(bio, bytes >> SECTOR_SHIFT, GFP_NOIO, bs);
 }
 
 /**
···
 unsigned int blk_recalc_rq_segments(struct request *rq)
 {
 	unsigned int nr_phys_segs = 0;
-	unsigned int nr_sectors = 0;
+	unsigned int bytes = 0;
 	struct req_iterator iter;
 	struct bio_vec bv;
 
···
 		return 1;
 	case REQ_OP_WRITE_ZEROES:
 		return 0;
+	default:
+		break;
 	}
 
 	rq_for_each_bvec(bv, rq, iter)
-		bvec_split_segs(rq->q, &bv, &nr_phys_segs, &nr_sectors,
+		bvec_split_segs(rq->q, &bv, &nr_phys_segs, &bytes,
 				UINT_MAX, UINT_MAX);
 	return nr_phys_segs;
 }
···
 						  sector_t offset)
 {
 	struct request_queue *q = rq->q;
+	unsigned int max_sectors;
 
 	if (blk_rq_is_passthrough(rq))
 		return q->limits.max_hw_sectors;
 
+	max_sectors = blk_queue_get_max_sectors(q, req_op(rq));
 	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)));
+		return max_sectors;
+	return min(max_sectors,
+		   blk_chunk_sectors_left(offset, q->limits.chunk_sectors));
 }
 
 static inline int ll_new_hw_segment(struct request *req, struct bio *bio,
···
  */
 void blk_rq_set_mixed_merge(struct request *rq)
 {
-	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+	blk_opf_t ff = rq->cmd_flags & REQ_FAILFAST_MASK;
 	struct bio *bio;
 
 	if (rq->rq_flags & RQF_MIXED_MERGE)
···
 static enum bio_merge_status bio_attempt_back_merge(struct request *req,
 		struct bio *bio, unsigned int nr_segs)
 {
-	const int ff = bio->bi_opf & REQ_FAILFAST_MASK;
+	const blk_opf_t ff = bio->bi_opf & REQ_FAILFAST_MASK;
 
 	if (!ll_back_merge_fn(req, bio, nr_segs))
 		return BIO_MERGE_FAILED;
···
 static enum bio_merge_status bio_attempt_front_merge(struct request *req,
 		struct bio *bio, unsigned int nr_segs)
 {
-	const int ff = bio->bi_opf & REQ_FAILFAST_MASK;
+	const blk_opf_t ff = bio->bi_opf & REQ_FAILFAST_MASK;
 
 	if (!ll_front_merge_fn(req, bio, nr_segs))
 		return BIO_MERGE_FAILED;
···
 	struct blk_plug *plug;
 	struct request *rq;
 
-	plug = blk_mq_plug(q, bio);
+	plug = blk_mq_plug(bio);
 	if (!plug || rq_list_empty(plug->mq_list))
 		return false;
 

block/blk-mq-debugfs-zoned.c

···
 	struct request_queue *q = data;
 	unsigned int i;
 
-	if (!q->seq_zones_wlock)
+	if (!q->disk->seq_zones_wlock)
 		return 0;
 
-	for (i = 0; i < q->nr_zones; i++)
-		if (test_bit(i, q->seq_zones_wlock))
+	for (i = 0; i < q->disk->nr_zones; i++)
+		if (test_bit(i, q->disk->seq_zones_wlock))
 			seq_printf(m, "%u\n", i);
 
 	return 0;

block/blk-mq-debugfs.c

···
 	QUEUE_FLAG_NAME(NOXMERGES),
 	QUEUE_FLAG_NAME(ADD_RANDOM),
 	QUEUE_FLAG_NAME(SAME_FORCE),
-	QUEUE_FLAG_NAME(DEAD),
 	QUEUE_FLAG_NAME(INIT_DONE),
 	QUEUE_FLAG_NAME(STABLE_WRITES),
 	QUEUE_FLAG_NAME(POLL),
···
 	char opbuf[16] = { }, *op;
 
 	/*
-	 * The "state" attribute is removed after blk_cleanup_queue() has called
-	 * blk_mq_free_queue(). Return if QUEUE_FLAG_DEAD has been set to avoid
-	 * triggering a use-after-free.
+	 * The "state" attribute is removed when the queue is removed.  Don't
+	 * allow setting the state on a dying queue to avoid a use-after-free.
 	 */
-	if (blk_queue_dead(q))
+	if (blk_queue_dying(q))
 		return -ENOENT;
 
 	if (count >= sizeof(opbuf)) {
···
 int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
 {
 	const struct blk_mq_ops *const mq_ops = rq->q->mq_ops;
-	const unsigned int op = req_op(rq);
+	const enum req_op op = req_op(rq);
 	const char *op_str = blk_op_str(op);
 
 	seq_printf(m, "%p {.op=", rq);
···
 	else
 		seq_printf(m, "%s", op_str);
 	seq_puts(m, ", .cmd_flags=");
-	blk_flags_show(m, rq->cmd_flags & ~REQ_OP_MASK, cmd_flag_name,
-		       ARRAY_SIZE(cmd_flag_name));
+	blk_flags_show(m, (__force unsigned int)(rq->cmd_flags & ~REQ_OP_MASK),
+		       cmd_flag_name, ARRAY_SIZE(cmd_flag_name));
 	seq_puts(m, ", .rq_flags=");
 	blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name,
 		       ARRAY_SIZE(rqf_name));
···
  * e.g. due to a concurrent blk_mq_finish_request() call. Returns true to
  * keep iterating requests.
  */
-static bool hctx_show_busy_rq(struct request *rq, void *data, bool reserved)
+static bool hctx_show_busy_rq(struct request *rq, void *data)
 {
 	const struct show_busy_params *params = data;
 
···
 	struct blk_mq_ctx *ctx;
 	char name[20];
 	int i;
+
+	if (!q->debugfs_dir)
+		return;
 
 	snprintf(name, sizeof(name), "hctx%u", hctx->queue_num);
 	hctx->debugfs_dir = debugfs_create_dir(name, q->debugfs_dir);

block/blk-mq-sysfs.c

···
 	return ret;
 }
 
-void blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
-{
-	struct blk_mq_hw_ctx *hctx;
-	unsigned long i;
-
-	lockdep_assert_held(&q->sysfs_dir_lock);
-
-	queue_for_each_hw_ctx(q, hctx, i)
-		blk_mq_unregister_hctx(hctx);
-
-	kobject_uevent(q->mq_kobj, KOBJ_REMOVE);
-	kobject_del(q->mq_kobj);
-	kobject_put(&dev->kobj);
-
-	q->mq_sysfs_init_done = false;
-}
-
 void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)
 {
 	kobject_init(&hctx->kobj, &blk_mq_hw_ktype);
···
 	}
 }
 
-int __blk_mq_register_dev(struct device *dev, struct request_queue *q)
+int blk_mq_sysfs_register(struct gendisk *disk)
 {
+	struct request_queue *q = disk->queue;
 	struct blk_mq_hw_ctx *hctx;
 	unsigned long i, j;
 	int ret;
 
-	WARN_ON_ONCE(!q->kobj.parent);
 	lockdep_assert_held(&q->sysfs_dir_lock);
 
-	ret = kobject_add(q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
+	ret = kobject_add(q->mq_kobj, &disk_to_dev(disk)->kobj, "mq");
 	if (ret < 0)
 		goto out;
 
···
 
 	kobject_uevent(q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(q->mq_kobj);
-	kobject_put(&dev->kobj);
 	return ret;
 }
 
-void blk_mq_sysfs_unregister(struct request_queue *q)
+void blk_mq_sysfs_unregister(struct gendisk *disk)
+{
+	struct request_queue *q = disk->queue;
+	struct blk_mq_hw_ctx *hctx;
+	unsigned long i;
+
+	lockdep_assert_held(&q->sysfs_dir_lock);
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		blk_mq_unregister_hctx(hctx);
+
+	kobject_uevent(q->mq_kobj, KOBJ_REMOVE);
+	kobject_del(q->mq_kobj);
+
+	q->mq_sysfs_init_done = false;
+}
+
+void blk_mq_sysfs_unregister_hctxs(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	unsigned long i;
···
 	mutex_unlock(&q->sysfs_dir_lock);
 }
 
-int blk_mq_sysfs_register(struct request_queue *q)
+int blk_mq_sysfs_register_hctxs(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	unsigned long i;

block/blk-mq-tag.c

···
  * to get tag when first time, the other shared-tag users could reserve
  * budget for it.
  */
-bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
+void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
 	unsigned int users;
 
 	if (blk_mq_is_shared_tags(hctx->flags)) {
 		struct request_queue *q = hctx->queue;
 
-		if (test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) ||
-		    test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) {
-			return true;
-		}
+		if (test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags))
+			return;
+		set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags);
 	} else {
-		if (test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) ||
-		    test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) {
-			return true;
-		}
+		if (test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
+			return;
+		set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state);
 	}
 
 	users = atomic_inc_return(&hctx->tags->active_queues);
 
 	blk_mq_update_wake_batch(hctx->tags, users);
-
-	return true;
 }
 
 /*
···
 	struct blk_mq_hw_ctx *hctx = iter_data->hctx;
 	struct request_queue *q = iter_data->q;
 	struct blk_mq_tag_set *set = q->tag_set;
-	bool reserved = iter_data->reserved;
 	struct blk_mq_tags *tags;
 	struct request *rq;
 	bool ret = true;
···
 	else
 		tags = hctx->tags;
 
-	if (!reserved)
+	if (!iter_data->reserved)
 		bitnr += tags->nr_reserved_tags;
 	/*
 	 * We can hit rq == NULL here, because the tagging functions
···
 		return true;
 
 	if (rq->q == q && (!hctx || rq->mq_hctx == hctx))
-		ret = iter_data->fn(rq, iter_data->data, reserved);
+		ret = iter_data->fn(rq, iter_data->data);
 	blk_mq_put_rq_ref(rq);
 	return ret;
 }
···
 {
 	struct bt_tags_iter_data *iter_data = data;
 	struct blk_mq_tags *tags = iter_data->tags;
-	bool reserved = iter_data->flags & BT_TAG_ITER_RESERVED;
 	struct request *rq;
 	bool ret = true;
 	bool iter_static_rqs = !!(iter_data->flags & BT_TAG_ITER_STATIC_RQS);
 
-	if (!reserved)
+	if (!(iter_data->flags & BT_TAG_ITER_RESERVED))
 		bitnr += tags->nr_reserved_tags;
 
 	/*
···
 
 	if (!(iter_data->flags & BT_TAG_ITER_STARTED) ||
 	    blk_mq_request_started(rq))
-		ret = iter_data->fn(rq, iter_data->data, reserved);
+		ret = iter_data->fn(rq, iter_data->data);
 	if (!iter_static_rqs)
 		blk_mq_put_rq_ref(rq);
 	return ret;
···
 }
 EXPORT_SYMBOL(blk_mq_tagset_busy_iter);
 
-static bool blk_mq_tagset_count_completed_rqs(struct request *rq,
-		void *data, bool reserved)
+static bool blk_mq_tagset_count_completed_rqs(struct request *rq, void *data)
 {
 	unsigned *count = data;
 

block/blk-mq-tag.h

···
 	BLK_MQ_TAG_MAX		= BLK_MQ_NO_TAG - 1,
 };
 
-extern bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *);
+extern void __blk_mq_tag_busy(struct blk_mq_hw_ctx *);
 extern void __blk_mq_tag_idle(struct blk_mq_hw_ctx *);
 
-static inline bool blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
+static inline void blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
-	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
-		return false;
-
-	return __blk_mq_tag_busy(hctx);
+	if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
+		__blk_mq_tag_busy(hctx);
 }
 
 static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)

block/blk-mq.c

···
 #include "blk-stat.h"
 #include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
+#include "blk-ioprio.h"
 
 static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);
 
···
 	unsigned int inflight[2];
 };
 
-static bool blk_mq_check_inflight(struct request *rq, void *priv,
-				  bool reserved)
+static bool blk_mq_check_inflight(struct request *rq, void *priv)
 {
 	struct mq_inflight *mi = priv;
 
···
 	if (!(data->rq_flags & RQF_ELV))
 		blk_mq_tag_busy(data->hctx);
 
+	if (data->flags & BLK_MQ_REQ_RESERVED)
+		data->rq_flags |= RQF_RESV;
+
 	/*
 	 * Try batched alloc if we want more than 1 tag.
 	 */
···
 					alloc_time_ns);
 }
 
-struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
+struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf,
 		blk_mq_req_flags_t flags)
 {
 	struct blk_mq_alloc_data data = {
 		.q		= q,
 		.flags		= flags,
-		.cmd_flags	= op,
+		.cmd_flags	= opf,
 		.nr_tags	= 1,
 	};
 	struct request *rq;
···
 EXPORT_SYMBOL(blk_mq_alloc_request);
 
 struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
-	unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx)
+	blk_opf_t opf, blk_mq_req_flags_t flags, unsigned int hctx_idx)
 {
 	struct blk_mq_alloc_data data = {
 		.q		= q,
 		.flags		= flags,
-		.cmd_flags	= op,
+		.cmd_flags	= opf,
 		.nr_tags	= 1,
 	};
 	u64 alloc_time_ns = 0;
···
 		blk_mq_tag_busy(data.hctx);
 	else
 		data.rq_flags |= RQF_ELV;
+
+	if (flags & BLK_MQ_REQ_RESERVED)
+		data.rq_flags |= RQF_RESV;
 
 	ret = -EWOULDBLOCK;
 	tag = blk_mq_get_tag(&data);
···
 {
 	printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg,
 		rq->q->disk ? rq->q->disk->disk_name : "?",
-		(unsigned long long) rq->cmd_flags);
+		(__force unsigned long long) rq->cmd_flags);
 
 	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u\n",
 	       (unsigned long long)blk_rq_pos(rq),
···
 		"phys_seg %u prio class %u\n",
 		blk_status_to_str(status),
 		req->q->disk ? req->q->disk->disk_name : "?",
-		blk_rq_pos(req), req_op(req), blk_op_str(req_op(req)),
-		req->cmd_flags & ~REQ_OP_MASK,
+		blk_rq_pos(req), (__force u32)req_op(req),
+		blk_op_str(req_op(req)),
+		(__force u32)(req->cmd_flags & ~REQ_OP_MASK),
 		req->nr_phys_segments,
 		IOPRIO_PRIO_CLASS(req->ioprio));
 }
···
 }
 EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
 
-static bool blk_mq_rq_inflight(struct request *rq, void *priv,
-			       bool reserved)
+static bool blk_mq_rq_inflight(struct request *rq, void *priv)
 {
 	/*
 	 * If we find a request that isn't idle we know the queue is busy
···
 }
 EXPORT_SYMBOL_GPL(blk_mq_queue_inflight);
 
-static void blk_mq_rq_timed_out(struct request *req, bool reserved)
+static void blk_mq_rq_timed_out(struct request *req)
 {
 	req->rq_flags |= RQF_TIMED_OUT;
 	if (req->q->mq_ops->timeout) {
 		enum blk_eh_timer_return ret;
 
-		ret = req->q->mq_ops->timeout(req, reserved);
+		ret = req->q->mq_ops->timeout(req);
 		if (ret == BLK_EH_DONE)
 			return;
 		WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER);
···
 		__blk_mq_free_request(rq);
 }
 
-static bool blk_mq_check_expired(struct request *rq, void *priv, bool reserved)
+static bool blk_mq_check_expired(struct request *rq, void *priv)
 {
 	unsigned long *next = priv;
 
···
 	 * from blk_mq_check_expired().
 	 */
 	if (blk_mq_req_expired(rq, next))
-		blk_mq_rq_timed_out(rq, reserved);
+		blk_mq_rq_timed_out(rq);
 	return true;
 }
 
···
 		return;
 
 	if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
-		int cpu = get_cpu();
-		if (cpumask_test_cpu(cpu, hctx->cpumask)) {
+		if (cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
 			__blk_mq_run_hw_queue(hctx);
-			put_cpu();
 			return;
 		}
-
-		put_cpu();
 	}
 
 	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work,
···
 	 * just causes lock contention inside the scheduler and pointless cache
 	 * bouncing.
 	 */
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, 0, ctx);
+	struct blk_mq_hw_ctx *hctx = ctx->hctxs[HCTX_TYPE_DEFAULT];
 
 	if (!blk_mq_hctx_stopped(hctx))
 		return hctx;
···
 	return rq;
 }
 
+static void bio_set_ioprio(struct bio *bio)
+{
+	/* Nobody set ioprio so far? Initialize it based on task's nice value */
+	if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE)
+		bio->bi_ioprio = get_current_ioprio();
+	blkcg_set_ioprio(bio);
+}
+
 /**
  * blk_mq_submit_bio - Create and send a request to block device.
  * @bio: Bio pointer.
···
 void blk_mq_submit_bio(struct bio *bio)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	struct blk_plug *plug = blk_mq_plug(q, bio);
+	struct blk_plug *plug = blk_mq_plug(bio);
 	const int is_sync = op_is_sync(bio->bi_opf);
 	struct request *rq;
 	unsigned int nr_segs = 1;
···
 
 	if (!bio_integrity_prep(bio))
 		return;
+
+	bio_set_ioprio(bio);
 
 	rq = blk_mq_get_cached_request(q, plug, &bio, nr_segs);
 	if (!rq) {
···
 	bool has_rq;
 };
 
-static bool blk_mq_has_request(struct request *rq, void *data, bool reserved)
+static bool blk_mq_has_request(struct request *rq, void *data)
 {
 	struct rq_iter_data *iter_data = data;
 
···
 	q->queuedata = queuedata;
 	ret = blk_mq_init_allocated_queue(set, q);
 	if (ret) {
-		blk_cleanup_queue(q);
+		blk_put_queue(q);
 		return ERR_PTR(ret);
 	}
 	return q;
···
 	return blk_mq_init_queue_data(set, NULL);
 }
 EXPORT_SYMBOL(blk_mq_init_queue);
+
+/**
+ * blk_mq_destroy_queue - shutdown a request queue
+ * @q: request queue to shutdown
+ *
+ * This shuts down a request queue allocated by blk_mq_init_queue() and drops
+ * the initial reference.  All future requests will failed with -ENODEV.
+ *
+ * Context: can sleep
+ */
+void blk_mq_destroy_queue(struct request_queue *q)
+{
+	WARN_ON_ONCE(!queue_is_mq(q));
+	WARN_ON_ONCE(blk_queue_registered(q));
+
+	might_sleep();
+
+	blk_queue_flag_set(QUEUE_FLAG_DYING, q);
+	blk_queue_start_drain(q);
+	blk_freeze_queue(q);
+
+	blk_sync_queue(q);
+	blk_mq_cancel_work_sync(q);
+	blk_mq_exit_queue(q);
+
+	/* @q is and will stay empty, shutdown and put */
+	blk_put_queue(q);
+}
+EXPORT_SYMBOL(blk_mq_destroy_queue);
 
 struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata,
 		struct lock_class_key *lkclass)
···
 
 	disk = __alloc_disk_node(q, set->numa_node, lkclass);
 	if (!disk) {
-		blk_cleanup_queue(q);
+		blk_mq_destroy_queue(q);
 		return ERR_PTR(-ENOMEM);
 	}
+	set_bit(GD_OWNS_QUEUE, &disk->state);
 	return disk;
 }
 EXPORT_SYMBOL(__blk_mq_alloc_disk);
+
+struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q,
+		struct lock_class_key *lkclass)
+{
+	if (!blk_get_queue(q))
+		return NULL;
+	return __alloc_disk_node(q, NUMA_NO_NODE, lkclass);
+}
+EXPORT_SYMBOL(blk_mq_alloc_disk_for_queue);
 
 static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx(
 		struct blk_mq_tag_set *set, struct request_queue *q,
···
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_debugfs_unregister_hctxs(q);
-		blk_mq_sysfs_unregister(q);
+		blk_mq_sysfs_unregister_hctxs(q);
 	}
 
 	prev_nr_hw_queues = set->nr_hw_queues;
···
 
 reregister:
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
-		blk_mq_sysfs_register(q);
+		blk_mq_sysfs_register_hctxs(q);
 		blk_mq_debugfs_register_hctxs(q);
 	}
 

block/blk-mq.h

···
 	return xa_load(&q->hctx_table, q->tag_set->map[type].mq_map[cpu]);
 }
 
-static inline enum hctx_type blk_mq_get_hctx_type(unsigned int flags)
+static inline enum hctx_type blk_mq_get_hctx_type(blk_opf_t opf)
 {
 	enum hctx_type type = HCTX_TYPE_DEFAULT;
 
 	/*
 	 * The caller ensure that if REQ_POLLED, poll must be enabled.
 	 */
-	if (flags & REQ_POLLED)
+	if (opf & REQ_POLLED)
 		type = HCTX_TYPE_POLL;
-	else if ((flags & REQ_OP_MASK) == REQ_OP_READ)
+	else if ((opf & REQ_OP_MASK) == REQ_OP_READ)
 		type = HCTX_TYPE_READ;
 	return type;
 }
···
 /*
  * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue
  * @q: request queue
- * @flags: request command flags
+ * @opf: operation type (REQ_OP_*) and flags (e.g. REQ_POLLED).
  * @ctx: software queue cpu ctx
  */
 static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
-						     unsigned int flags,
+						     blk_opf_t opf,
 						     struct blk_mq_ctx *ctx)
 {
-	return ctx->hctxs[blk_mq_get_hctx_type(flags)];
+	return ctx->hctxs[blk_mq_get_hctx_type(opf)];
 }
 
 /*
···
  */
 extern void blk_mq_sysfs_init(struct request_queue *q);
 extern void blk_mq_sysfs_deinit(struct request_queue *q);
-extern int __blk_mq_register_dev(struct device *dev, struct request_queue *q);
-extern int blk_mq_sysfs_register(struct request_queue *q);
-extern void blk_mq_sysfs_unregister(struct request_queue *q);
+int blk_mq_sysfs_register(struct gendisk *disk);
+void blk_mq_sysfs_unregister(struct gendisk *disk);
+int blk_mq_sysfs_register_hctxs(struct request_queue *q);
+void blk_mq_sysfs_unregister_hctxs(struct request_queue *q);
 extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
 void blk_mq_free_plug_rqs(struct blk_plug *plug);
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
···
 	struct request_queue *q;
 	blk_mq_req_flags_t flags;
 	unsigned int shallow_depth;
-	unsigned int cmd_flags;
+	blk_opf_t cmd_flags;
 	req_flags_t rq_flags;
 
 	/* allocate multiple requests/tags in one go */
···
 
 /*
  * blk_mq_plug() - Get caller context plug
- * @q: request queue
  * @bio : the bio being submitted by the caller context
  *
  * Plugging, by design, may delay the insertion of BIOs into the elevator in
···
  * order. While this is not a problem with regular block devices, this ordering
  * change can cause write BIO failures with zoned block devices as these
  * require sequential write patterns to zones. Prevent this from happening by
- * ignoring the plug state of a BIO issuing context if the target request queue
- * is for a zoned block device and the BIO to plug is a write operation.
+ * ignoring the plug state of a BIO issuing context if it is for a zoned block
+ * device and the BIO to plug is a write operation.
  *
  * Return current->plug if the bio can be plugged and NULL otherwise
  */
-static inline struct blk_plug *blk_mq_plug(struct request_queue *q,
-					   struct bio *bio)
+static inline struct blk_plug *blk_mq_plug( struct bio *bio)
 {
+	/* Zoned block device write operation case: do not plug the BIO */
+	if (bdev_is_zoned(bio->bi_bdev) && op_is_write(bio_op(bio)))
+		return NULL;
+
 	/*
 	 * For regular block devices or read operations, use the context plug
 	 * which may be NULL if blk_start_plug() was not executed.
 	 */
-	if (!blk_queue_is_zoned(q) || !op_is_write(bio_op(bio)))
-		return current->plug;
-
-	/* Zoned block device write operation case: do not plug the BIO */
-	return NULL;
+	return current->plug;
 }
 
 /* Free all requests on the list */

block/blk-rq-qos.c

···
 {
 	unsigned int cur = atomic_read(v);
 
-	for (;;) {
-		unsigned int old;
-
+	do {
 		if (cur >= below)
 			return false;
-		old = atomic_cmpxchg(v, cur, cur + 1);
-		if (old == cur)
-			break;
-		cur = old;
-	}
+	} while (!atomic_try_cmpxchg(v, &cur, cur + 1));
 
 	return true;
 }

block/blk-rq-qos.h

···
 	init_waitqueue_head(&rq_wait->wait);
 }
 
-static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
+static inline int rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
 {
 	/*
 	 * No IO can be in-flight when adding rqos, so freeze queue, which
···
 	blk_mq_freeze_queue(q);
 
 	spin_lock_irq(&q->queue_lock);
+	if (rq_qos_id(q, rqos->id))
+		goto ebusy;
 	rqos->next = q->rq_qos;
 	q->rq_qos = rqos;
 	spin_unlock_irq(&q->queue_lock);
···
 		blk_mq_debugfs_register_rqos(rqos);
 		mutex_unlock(&q->debugfs_mutex);
 	}
+
+	return 0;
+ebusy:
+	spin_unlock_irq(&q->queue_lock);
+	blk_mq_unfreeze_queue(q);
+	return -EBUSY;
+
 }
 
 static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)

block/blk-settings.c

···
 }
 
 /**
- * blk_queue_set_zoned - configure a disk queue zoned model.
+ * disk_set_zoned - configure the zoned model for a disk
  * @disk:	the gendisk of the queue to configure
  * @model:	the zoned model to set
  *
- * Set the zoned model of the request queue of @disk according to @model.
+ * Set the zoned model of @disk to @model.
+ *
  * When @model is BLK_ZONED_HM (host managed), this should be called only
  * if zoned block device support is enabled (CONFIG_BLK_DEV_ZONED option).
  * If @model specifies BLK_ZONED_HA (host aware), the effective model used
  * depends on CONFIG_BLK_DEV_ZONED settings and on the existence of partitions
  * on the disk.
  */
-void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
+void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
 {
 	struct request_queue *q = disk->queue;
 
···
 		blk_queue_zone_write_granularity(q,
 						queue_logical_block_size(q));
 	} else {
-		blk_queue_clear_zone_settings(q);
+		disk_clear_zone_settings(disk);
 	}
 }
-EXPORT_SYMBOL_GPL(blk_queue_set_zoned);
+EXPORT_SYMBOL_GPL(disk_set_zoned);
 
 int bdev_alignment_offset(struct block_device *bdev)
 {

block/blk-sysfs.c

···
 	return queue_var_show(q->limits.virt_boundary_mask, page);
 }
 
+static ssize_t queue_dma_alignment_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_dma_alignment(q), page);
+}
+
 #define QUEUE_SYSFS_BIT_FNS(name, flag, neg)				\
 static ssize_t								\
 queue_##name##_show(struct request_queue *q, char *page)		\
···
 
 static ssize_t queue_nr_zones_show(struct request_queue *q, char *page)
 {
-	return queue_var_show(blk_queue_nr_zones(q), page);
+	return queue_var_show(disk_nr_zones(q->disk), page);
 }
 
 static ssize_t queue_max_open_zones_show(struct request_queue *q, char *page)
 {
-	return queue_var_show(queue_max_open_zones(q), page);
+	return queue_var_show(bdev_max_open_zones(q->disk->part0), page);
 }
 
 static ssize_t queue_max_active_zones_show(struct request_queue *q, char *page)
 {
-	return queue_var_show(queue_max_active_zones(q), page);
+	return queue_var_show(bdev_max_active_zones(q->disk->part0), page);
 }
 
 static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
···
 QUEUE_RW_ENTRY(queue_io_timeout, "io_timeout");
 QUEUE_RW_ENTRY(queue_wb_lat, "wbt_lat_usec");
 QUEUE_RO_ENTRY(queue_virt_boundary_mask, "virt_boundary_mask");
+QUEUE_RO_ENTRY(queue_dma_alignment, "dma_alignment");
 
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 QUEUE_RW_ENTRY(blk_throtl_sample_time, "throttle_sample_time");
···
 	&blk_throtl_sample_time_entry.attr,
 #endif
 	&queue_virt_boundary_mask_entry.attr,
+	&queue_dma_alignment_entry.attr,
 	NULL,
 };
 
···
  * decremented with blk_put_queue(). Once the refcount reaches 0 this function
  * is called.
  *
- * For drivers that have a request_queue on a gendisk and added with
- * __device_add_disk() the refcount to request_queue will reach 0 with
- * the last put_disk() called by the driver. For drivers which don't use
- * __device_add_disk() this happens with blk_cleanup_queue().
- *
  * Drivers exist which depend on the release of the request_queue to be
  * synchronous, it should not be deferred.
  *
···
 	blk_free_queue_stats(q->stats);
 	kfree(q->poll_stat);
 
-	blk_queue_free_zone_bitmaps(q);
-
 	if (queue_is_mq(q))
 		blk_mq_release(q);
 
···
 	if (blk_queue_has_srcu(q))
 		cleanup_srcu_struct(q->srcu);
 
-	ida_simple_remove(&blk_queue_ida, q->id);
+	ida_free(&blk_queue_ida, q->id);
 	call_rcu(&q->rcu_head, blk_free_queue_rcu);
 }
 
···
 	.store	= queue_attr_store,
 };
 
+static const struct attribute_group *blk_queue_attr_groups[] = {
+	&queue_attr_group,
+	NULL
+};
+
 struct kobj_type blk_queue_ktype = {
+	.default_groups = blk_queue_attr_groups,
 	.sysfs_ops	= &queue_sysfs_ops,
 	.release	= blk_release_queue,
 };
···
  */
 int blk_register_queue(struct gendisk *disk)
 {
-	int ret;
-	struct device *dev = disk_to_dev(disk);
 	struct request_queue *q = disk->queue;
-
-	ret = blk_trace_init_sysfs(dev);
-	if (ret)
-		return ret;
+	int ret;
 
 	mutex_lock(&q->sysfs_dir_lock);
 
-	ret = kobject_add(&q->kobj, kobject_get(&dev->kobj), "%s", "queue");
-	if (ret < 0) {
-		blk_trace_remove_sysfs(dev);
+	ret = kobject_add(&q->kobj, &disk_to_dev(disk)->kobj, "queue");
+	if (ret < 0)
 		goto unlock;
-	}
-
-	ret = sysfs_create_group(&q->kobj, &queue_attr_group);
-	if (ret) {
-		blk_trace_remove_sysfs(dev);
-		kobject_del(&q->kobj);
-		kobject_put(&dev->kobj);
-		goto unlock;
-	}
 
 	if (queue_is_mq(q))
-		__blk_mq_register_dev(dev, q);
+		blk_mq_sysfs_register(disk);
 	mutex_lock(&q->sysfs_lock);
 
 	mutex_lock(&q->debugfs_mutex);
···
 		blk_mq_debugfs_register(q);
 	mutex_unlock(&q->debugfs_mutex);
 
-	ret = disk_register_independent_access_ranges(disk, NULL);
+	ret = disk_register_independent_access_ranges(disk);
 	if (ret)
 		goto put_dev;
 
···
 	mutex_unlock(&q->sysfs_lock);
 	mutex_unlock(&q->sysfs_dir_lock);
 	kobject_del(&q->kobj);
-	blk_trace_remove_sysfs(dev);
-	kobject_put(&dev->kobj);
 
 	return ret;
 }
···
 	 * structures that can be modified through sysfs.
 	 */
 	if (queue_is_mq(q))
-		blk_mq_unregister_dev(disk_to_dev(disk), q);
+		blk_mq_sysfs_unregister(disk);
 	blk_crypto_sysfs_unregister(q);
-	blk_trace_remove_sysfs(disk_to_dev(disk));
 
 	mutex_lock(&q->sysfs_lock);
 	elv_unregister_queue(q);
···
 	q->sched_debugfs_dir = NULL;
 	q->rqos_debugfs_dir = NULL;
 	mutex_unlock(&q->debugfs_mutex);
-
-	kobject_put(&disk_to_dev(disk)->kobj);
 }

block/blk-throttle.c

···
 
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 static void throtl_track_latency(struct throtl_data *td, sector_t size,
-	int op, unsigned long time)
+				 enum req_op op, unsigned long time)
 {
+	const bool rw = op_is_write(op);
 	struct latency_bucket *latency;
 	int index;
 
···
 
 	index = request_bucket_index(size);
 
-	latency = get_cpu_ptr(td->latency_buckets[op]);
+	latency = get_cpu_ptr(td->latency_buckets[rw]);
 	latency[index].total_latency += time;
 	latency[index].samples++;
-	put_cpu_ptr(td->latency_buckets[op]);
+	put_cpu_ptr(td->latency_buckets[rw]);
 }
 
 void blk_throtl_stat_add(struct request *rq, u64 time_ns)

block/blk-wbt.c

···
 
 #define REQ_HIPRIO	(REQ_SYNC | REQ_META | REQ_PRIO)
 
-static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
+static inline unsigned int get_limit(struct rq_wb *rwb, blk_opf_t opf)
 {
 	unsigned int limit;
 
···
 	if (!rwb_enabled(rwb))
 		return UINT_MAX;
 
-	if ((rw & REQ_OP_MASK) == REQ_OP_DISCARD)
+	if ((opf & REQ_OP_MASK) == REQ_OP_DISCARD)
 		return rwb->wb_background;
 
 	/*
···
 	 * the idle limit, or go to normal if we haven't had competing
 	 * IO for a bit.
 	 */
-	if ((rw & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd())
+	if ((opf & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd())
 		limit = rwb->rq_depth.max_depth;
-	else if ((rw & REQ_BACKGROUND) || close_io(rwb)) {
+	else if ((opf & REQ_BACKGROUND) || close_io(rwb)) {
 		/*
 		 * If less than 100ms since we completed unrelated IO,
 		 * limit us to half the depth for background writeback.
···
 struct wbt_wait_data {
 	struct rq_wb *rwb;
 	enum wbt_flags wb_acct;
-	unsigned long rw;
+	blk_opf_t opf;
 };
 
 static bool wbt_inflight_cb(struct rq_wait *rqw, void *private_data)
 {
 	struct wbt_wait_data *data = private_data;
-	return rq_wait_inc_below(rqw, get_limit(data->rwb, data->rw));
+	return rq_wait_inc_below(rqw, get_limit(data->rwb, data->opf));
 }
 
 static void wbt_cleanup_cb(struct rq_wait *rqw, void *private_data)
···
  * the timer to kick off queuing again.
  */
 static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct,
-		       unsigned long rw)
+		       blk_opf_t opf)
 {
 	struct rq_wait *rqw = get_rq_wait(rwb, wb_acct);
 	struct wbt_wait_data data = {
 		.rwb = rwb,
 		.wb_acct = wb_acct,
-		.rw = rw,
+		.opf = opf,
 	};
 
 	rq_qos_wait(rqw, &data, wbt_inflight_cb, wbt_cleanup_cb);
···
 
 static int wbt_data_dir(const struct request *rq)
 {
-	const int op = req_op(rq);
+	const enum req_op op = req_op(rq);
 
 	if (op == REQ_OP_READ)
 		return READ;
···
 {
 	struct rq_wb *rwb;
 	int i;
+	int ret;
 
 	rwb = kzalloc(sizeof(*rwb), GFP_KERNEL);
 	if (!rwb)
···
 	/*
 	 * Assign rwb and add the stats callback.
 	 */
-	rq_qos_add(q, &rwb->rqos);
+	ret = rq_qos_add(q, &rwb->rqos);
+	if (ret)
+		goto err_free;
+
 	blk_stat_add_callback(q, rwb->cb);
 
 	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
···
 	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 
 	return 0;
+
+err_free:
+	blk_stat_free_callback(rwb->cb);
+	kfree(rwb);
+	return ret;
+
 }

block/blk-zoned.c

···
  */
 bool blk_req_needs_zone_write_lock(struct request *rq)
 {
-	if (!rq->q->seq_zones_wlock)
+	if (blk_rq_is_passthrough(rq))
 		return false;
 
-	if (blk_rq_is_passthrough(rq))
+	if (!rq->q->disk->seq_zones_wlock)
 		return false;
 
 	switch (req_op(rq)) {
···
 {
 	unsigned int zno = blk_rq_zone_no(rq);
 
-	if (test_and_set_bit(zno, rq->q->seq_zones_wlock))
+	if (test_and_set_bit(zno, rq->q->disk->seq_zones_wlock))
 		return false;
 
 	WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED);
···
 void __blk_req_zone_write_lock(struct request *rq)
 {
 	if (WARN_ON_ONCE(test_and_set_bit(blk_rq_zone_no(rq),
-					  rq->q->seq_zones_wlock)))
+					  rq->q->disk->seq_zones_wlock)))
 		return;
 
 	WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED);
···
 void __blk_req_zone_write_unlock(struct request *rq)
 {
 	rq->rq_flags &= ~RQF_ZONE_WRITE_LOCKED;
-	if (rq->q->seq_zones_wlock)
+	if (rq->q->disk->seq_zones_wlock)
 		WARN_ON_ONCE(!test_and_clear_bit(blk_rq_zone_no(rq),
-						 rq->q->seq_zones_wlock));
+						 rq->q->disk->seq_zones_wlock));
 }
 EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock);
 
 /**
- * blkdev_nr_zones - Get number of zones
- * @disk:	Target gendisk
+ * bdev_nr_zones - Get number of zones
+ * @bdev:	Target device
  *
  * Return the total number of zones of a zoned block device.  For a block
  * device without zone capabilities, the number of zones is always 0.
  */
-unsigned int blkdev_nr_zones(struct gendisk *disk)
+unsigned int bdev_nr_zones(struct block_device *bdev)
 {
-	sector_t zone_sectors = blk_queue_zone_sectors(disk->queue);
+	sector_t zone_sectors = bdev_zone_sectors(bdev);
 
-	if (!blk_queue_is_zoned(disk->queue))
+	if (!bdev_is_zoned(bdev))
 		return 0;
-	return (get_capacity(disk) + zone_sectors - 1) >> ilog2(zone_sectors);
+	return (bdev_nr_sectors(bdev) + zone_sectors - 1) >>
+		ilog2(zone_sectors);
 }
-EXPORT_SYMBOL_GPL(blkdev_nr_zones);
+EXPORT_SYMBOL_GPL(bdev_nr_zones);
 
 /**
  * blkdev_report_zones - Get zones information
···
 	struct gendisk *disk = bdev->bd_disk;
 	sector_t capacity = get_capacity(disk);
 
-	if (!blk_queue_is_zoned(bdev_get_queue(bdev)) ||
-	    WARN_ON_ONCE(!disk->fops->report_zones))
+	if (!bdev_is_zoned(bdev) || WARN_ON_ONCE(!disk->fops->report_zones))
 		return -EOPNOTSUPP;
 
 	if (!nr_zones || sector >= capacity)
···
 static int blkdev_zone_reset_all_emulated(struct block_device *bdev,
 					  gfp_t gfp_mask)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-	sector_t capacity = get_capacity(bdev->bd_disk);
-	sector_t zone_sectors = blk_queue_zone_sectors(q);
+	struct gendisk *disk = bdev->bd_disk;
+	sector_t capacity = bdev_nr_sectors(bdev);
+	sector_t zone_sectors = bdev_zone_sectors(bdev);
 	unsigned long *need_reset;
 	struct bio *bio = NULL;
 	sector_t sector = 0;
 	int ret;
 
-	need_reset = blk_alloc_zone_bitmap(q->node, q->nr_zones);
+	need_reset = blk_alloc_zone_bitmap(disk->queue->node, disk->nr_zones);
 	if (!need_reset)
 		return -ENOMEM;
 
-	ret = bdev->bd_disk->fops->report_zones(bdev->bd_disk, 0,
-				q->nr_zones, blk_zone_need_reset_cb,
-				need_reset);
+	ret = disk->fops->report_zones(disk, 0, disk->nr_zones,
+				       blk_zone_need_reset_cb, need_reset);
 	if (ret < 0)
 		goto out_free_need_reset;
 
 	ret = 0;
 	while (sector < capacity) {
-		if (!test_bit(blk_queue_zone_no(q, sector), need_reset)) {
+		if (!test_bit(disk_zone_no(disk, sector), need_reset)) {
 			sector += zone_sectors;
 			continue;
 		}
···
  *    The operation to execute on each zone can be a zone reset, open, close
  *    or finish request.
  */
-int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
-		     sector_t sector, sector_t nr_sectors,
-		     gfp_t gfp_mask)
+int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
+		     sector_t sector, sector_t nr_sectors, gfp_t gfp_mask)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
-	sector_t zone_sectors = blk_queue_zone_sectors(q);
-	sector_t capacity = get_capacity(bdev->bd_disk);
+	sector_t zone_sectors = bdev_zone_sectors(bdev);
+	sector_t capacity = bdev_nr_sectors(bdev);
 	sector_t end_sector = sector + nr_sectors;
 	struct bio *bio = NULL;
 	int ret = 0;
 
-	if (!blk_queue_is_zoned(q))
+	if (!bdev_is_zoned(bdev))
 		return -EOPNOTSUPP;
 
 	if (bdev_read_only(bdev))
···
 	if (!q)
 		return -ENXIO;
 
-	if (!blk_queue_is_zoned(q))
+	if (!bdev_is_zoned(bdev))
 		return -ENOTTY;
 
 	if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report)))
···
 	void __user *argp = (void __user *)arg;
 	struct request_queue *q;
 	struct blk_zone_range zrange;
-	enum req_opf op;
+	enum req_op op;
 	int ret;
 
 	if (!argp)
···
 	if (!q)
 		return -ENXIO;
 
-	if (!blk_queue_is_zoned(q))
+	if (!bdev_is_zoned(bdev))
 		return -ENOTTY;
 
 	if (!(mode & FMODE_WRITE))
···
 	return ret;
 }
 
-void blk_queue_free_zone_bitmaps(struct request_queue *q)
+void disk_free_zone_bitmaps(struct gendisk *disk)
 {
-	kfree(q->conv_zones_bitmap);
-	q->conv_zones_bitmap = NULL;
-	kfree(q->seq_zones_wlock);
-	q->seq_zones_wlock = NULL;
+	kfree(disk->conv_zones_bitmap);
+	disk->conv_zones_bitmap = NULL;
+	kfree(disk->seq_zones_wlock);
+	disk->seq_zones_wlock = NULL;
 }
 
 struct blk_revalidate_zone_args {
···
 	blk_mq_freeze_queue(q);
 	if (ret > 0) {
 		blk_queue_chunk_sectors(q, args.zone_sectors);
-		q->nr_zones = args.nr_zones;
-		swap(q->seq_zones_wlock, args.seq_zones_wlock);
-		swap(q->conv_zones_bitmap, args.conv_zones_bitmap);
+		disk->nr_zones = args.nr_zones;
+		swap(disk->seq_zones_wlock, args.seq_zones_wlock);
+		swap(disk->conv_zones_bitmap, args.conv_zones_bitmap);
 		if (update_driver_data)
 			update_driver_data(disk);
 		ret = 0;
 	} else {
 		pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
-		blk_queue_free_zone_bitmaps(q);
+		disk_free_zone_bitmaps(disk);
 	}
 	blk_mq_unfreeze_queue(q);
 
···
 }
 EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
 
-void blk_queue_clear_zone_settings(struct request_queue *q)
+void disk_clear_zone_settings(struct gendisk *disk)
 {
+	struct request_queue *q = disk->queue;
+
 	blk_mq_freeze_queue(q);
 
-	blk_queue_free_zone_bitmaps(q);
+	disk_free_zone_bitmaps(disk);
 	blk_queue_flag_clear(QUEUE_FLAG_ZONE_RESETALL, q);
 	q->required_elevator_features &= ~ELEVATOR_F_ZBD_SEQ_WRITE;
-	q->nr_zones = 0;
-	q->max_open_zones = 0;
-	q->max_active_zones = 0;
+	disk->nr_zones = 0;
+	disk->max_open_zones = 0;
+	disk->max_active_zones = 0;
 	q->limits.chunk_sectors = 0;
 	q->limits.zone_write_granularity = 0;
 	q->limits.max_zone_append_sectors = 0;

block/blk.h

···
 extern struct kobj_type blk_queue_ktype;
 extern struct ida blk_queue_ida;
 
-static inline void __blk_get_queue(struct request_queue *q)
-{
-	kobject_get(&q->kobj);
-}
-
 bool is_flush_rq(struct request *req);
 
 struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size,
···
 	    queue_max_discard_segments(req->q) > 1)
 		return true;
 	return false;
+}
+
+static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
+						     enum req_op op)
+{
+	if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE))
+		return min(q->limits.max_discard_sectors,
+			   UINT_MAX >> SECTOR_SHIFT);
+
+	if (unlikely(op == REQ_OP_WRITE_ZEROES))
+		return q->limits.max_write_zeroes_sectors;
+
+	return q->limits.max_sectors;
 }
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
···
 #endif
 
 #ifdef CONFIG_BLK_DEV_ZONED
-void blk_queue_free_zone_bitmaps(struct request_queue *q);
-void blk_queue_clear_zone_settings(struct request_queue *q);
+void disk_free_zone_bitmaps(struct gendisk *disk);
+void disk_clear_zone_settings(struct gendisk *disk);
 #else
-static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {}
-static inline void blk_queue_clear_zone_settings(struct request_queue *q) {}
+static inline void disk_free_zone_bitmaps(struct gendisk *disk) {}
+static inline void disk_clear_zone_settings(struct gendisk *disk) {}
 #endif
 
 int blk_alloc_ext_minor(void);
···
 int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start,
 		sector_t length);
 void blk_drop_partitions(struct gendisk *disk);
+
+struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
+		struct lock_class_key *lkclass);
 
 int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
···
 extern struct device_attribute dev_attr_events_async;
 extern struct device_attribute dev_attr_events_poll_msecs;
 
+extern struct attribute_group blk_trace_attr_group;
+
 long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);
 long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);
 
 extern const struct address_space_operations def_blk_aops;
 
-int disk_register_independent_access_ranges(struct gendisk *disk,
-				struct blk_independent_access_ranges *new_iars);
+int disk_register_independent_access_ranges(struct gendisk *disk);
 void disk_unregister_independent_access_ranges(struct gendisk *disk);
 
 #ifdef CONFIG_FAIL_MAKE_REQUEST

block/bounce.c

···
 	int rw = bio_data_dir(*bio_orig);
 	struct bio_vec *to, from;
 	struct bvec_iter iter;
-	unsigned i = 0;
+	unsigned i = 0, bytes = 0;
 	bool bounce = false;
-	int sectors = 0;
+	int sectors;
 
 	bio_for_each_segment(from, *bio_orig, iter) {
 		if (i++ < BIO_MAX_VECS)
-			sectors += from.bv_len >> 9;
+			bytes += from.bv_len;
 		if (PageHighMem(from.bv_page))
 			bounce = true;
 	}
 	if (!bounce)
 		return;
 
+	/*
+	 * Individual bvecs might not be logical block aligned. Round down
+	 * the split size so that each bio is properly block size aligned,
+	 * even if we do not use the full hardware limits.
+	 */
+	sectors = ALIGN_DOWN(bytes, queue_logical_block_size(q)) >>
+			SECTOR_SHIFT;
 	if (sectors < bio_sectors(*bio_orig)) {
 		bio = bio_split(*bio_orig, sectors, GFP_NOIO, &bounce_bio_split);
 		bio_chain(bio, *bio_orig);

block/bsg-lib.c

···
 			container_of(q->tag_set, struct bsg_set, tag_set);
 
 		bsg_unregister_queue(bset->bd);
-		blk_cleanup_queue(q);
+		blk_mq_destroy_queue(q);
 		blk_mq_free_tag_set(&bset->tag_set);
 		kfree(bset);
 	}
 }
 EXPORT_SYMBOL_GPL(bsg_remove_queue);
 
-static enum blk_eh_timer_return bsg_timeout(struct request *rq, bool reserved)
+static enum blk_eh_timer_return bsg_timeout(struct request *rq)
 {
 	struct bsg_set *bset =
 		container_of(rq->q->tag_set, struct bsg_set, tag_set);
···
 
 	return q;
 out_cleanup_queue:
-	blk_cleanup_queue(q);
+	blk_mq_destroy_queue(q);
 out_queue:
 	blk_mq_free_tag_set(set);
 out_tag_set:

block/elevator.h

···
 	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 (*limit_depth)(blk_opf_t, 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);

block/fops.c

···
 	return 0;
 }
 
-static unsigned int dio_bio_write_op(struct kiocb *iocb)
+static blk_opf_t dio_bio_write_op(struct kiocb *iocb)
 {
-	unsigned int op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
+	blk_opf_t opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
 
 	/* avoid the need for a I/O completion work item */
 	if (iocb->ki_flags & IOCB_DSYNC)
-		op |= REQ_FUA;
-	return op;
+		opf |= REQ_FUA;
+	return opf;
+}
+
+static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos,
+			      struct iov_iter *iter)
+{
+	return pos & (bdev_logical_block_size(bdev) - 1) ||
+		!bdev_iter_is_aligned(bdev, iter);
 }
 
 #define DIO_INLINE_BIO_VECS 4
···
 	struct bio bio;
 	ssize_t ret;
 
-	if ((pos | iov_iter_alignment(iter)) &
-	    (bdev_logical_block_size(bdev) - 1))
+	if (blkdev_dio_unaligned(bdev, pos, iter))
 		return -EINVAL;
 
 	if (nr_pages <= DIO_INLINE_BIO_VECS)
···
 	struct blkdev_dio *dio;
 	struct bio *bio;
 	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
-	unsigned int opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
+	blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
 	loff_t pos = iocb->ki_pos;
 	int ret = 0;
 
-	if ((pos | iov_iter_alignment(iter)) &
-	    (bdev_logical_block_size(bdev) - 1))
+	if (blkdev_dio_unaligned(bdev, pos, iter))
 		return -EINVAL;
 
 	if (iocb->ki_flags & IOCB_ALLOC_CACHE)
···
 {
 	struct block_device *bdev = iocb->ki_filp->private_data;
 	bool is_read = iov_iter_rw(iter) == READ;
-	unsigned int opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
+	blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb);
 	struct blkdev_dio *dio;
 	struct bio *bio;
 	loff_t pos = iocb->ki_pos;
 	int ret = 0;
 
-	if ((pos | iov_iter_alignment(iter)) &
-	    (bdev_logical_block_size(bdev) - 1))
+	if (blkdev_dio_unaligned(bdev, pos, iter))
 		return -EINVAL;
 
 	if (iocb->ki_flags & IOCB_ALLOC_CACHE)

block/genhd.c

···
 }
 EXPORT_SYMBOL_GPL(set_capacity_and_notify);
 
-/*
- * Format the device name of the indicated block device into the supplied buffer
- * and return a pointer to that same buffer for convenience.
- *
- * Note: do not use this in new code, use the %pg specifier to sprintf and
- * printk insted.
- */
-const char *bdevname(struct block_device *bdev, char *buf)
-{
-	struct gendisk *hd = bdev->bd_disk;
-	int partno = bdev->bd_partno;
-
-	if (!partno)
-		snprintf(buf, BDEVNAME_SIZE, "%s", hd->disk_name);
-	else if (isdigit(hd->disk_name[strlen(hd->disk_name)-1]))
-		snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, partno);
-	else
-		snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, partno);
-
-	return buf;
-}
-EXPORT_SYMBOL(bdevname);
-
 static void part_stat_read_all(struct block_device *part,
 		struct disk_stats *stat)
 {
···
 	 * Fail any new I/O.
 	 */
 	set_bit(GD_DEAD, &disk->state);
+	if (test_bit(GD_OWNS_QUEUE, &disk->state))
+		blk_queue_flag_set(QUEUE_FLAG_DYING, q);
 	set_capacity(disk, 0);
 
 	/*
···
 	blk_mq_unquiesce_queue(q);
 
 	/*
-	 * Allow using passthrough request again after the queue is torn down.
+	 * If the disk does not own the queue, allow using passthrough requests
+	 * again.  Else leave the queue frozen to fail all I/O.
 	 */
-	blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
-	__blk_mq_unfreeze_queue(q, true);
-
+	if (!test_bit(GD_OWNS_QUEUE, &disk->state)) {
+		blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
+		__blk_mq_unfreeze_queue(q, true);
+	} else {
+		if (queue_is_mq(q))
+			blk_mq_exit_queue(q);
+	}
 }
 EXPORT_SYMBOL(del_gendisk);
 
···
 
 static const struct attribute_group *disk_attr_groups[] = {
 	&disk_attr_group,
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+	&blk_trace_attr_group,
+#endif
 	NULL
 };
 
···
 	might_sleep();
 	WARN_ON_ONCE(disk_live(disk));
 
+	/*
+	 * To undo the all initialization from blk_mq_init_allocated_queue in
+	 * case of a probe failure where add_disk is never called we have to
+	 * call blk_mq_exit_queue here. We can't do this for the more common
+	 * teardown case (yet) as the tagset can be gone by the time the disk
+	 * is released once it was added.
+	 */
+	if (queue_is_mq(disk->queue) &&
+	    test_bit(GD_OWNS_QUEUE, &disk->state) &&
+	    !test_bit(GD_ADDED, &disk->state))
+		blk_mq_exit_queue(disk->queue);
+
 	blkcg_exit_queue(disk->queue);
 
 	disk_release_events(disk);
 	kfree(disk->random);
+	disk_free_zone_bitmaps(disk);
 	xa_destroy(&disk->part_tbl);
 
 	disk->queue->disk = NULL;
···
 {
 	struct gendisk *disk;
 
-	if (!blk_get_queue(q))
-		return NULL;
-
 	disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id);
 	if (!disk)
 		goto out_put_queue;
···
 	blk_put_queue(q);
 	return NULL;
 }
-EXPORT_SYMBOL(__alloc_disk_node);
 
 struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass)
 {
···
 
 	disk = __alloc_disk_node(q, node, lkclass);
 	if (!disk) {
-		blk_cleanup_queue(q);
+		blk_put_queue(q);
 		return NULL;
 	}
+	set_bit(GD_OWNS_QUEUE, &disk->state);
 	return disk;
 }
 EXPORT_SYMBOL(__blk_alloc_disk);
···
  * This decrements the refcount for the struct gendisk. When this reaches 0
  * we'll have disk_release() called.
  *
+ * Note: for blk-mq disk put_disk must be called before freeing the tag_set
+ * when handling probe errors (that is before add_disk() is called).
+ *
  * Context: Any context, but the last reference must not be dropped from
  *          atomic context.
  */
···
 		put_device(disk_to_dev(disk));
 }
 EXPORT_SYMBOL(put_disk);
-
-/**
- * blk_cleanup_disk - shutdown a gendisk allocated by blk_alloc_disk
- * @disk: gendisk to shutdown
- *
- * Mark the queue hanging off @disk DYING, drain all pending requests, then mark
- * the queue DEAD, destroy and put it and the gendisk structure.
- *
- * Context: can sleep
- */
-void blk_cleanup_disk(struct gendisk *disk)
-{
-	blk_cleanup_queue(disk->queue);
-	put_disk(disk);
-}
-EXPORT_SYMBOL(blk_cleanup_disk);
 
 static void set_disk_ro_uevent(struct gendisk *gd, int ro)
 {

block/ioctl.c

···
 	case BLKGETZONESZ:
 		return put_uint(argp, bdev_zone_sectors(bdev));
 	case BLKGETNRZONES:
-		return put_uint(argp, blkdev_nr_zones(bdev->bd_disk));
+		return put_uint(argp, bdev_nr_zones(bdev));
 	case BLKROGET:
 		return put_int(argp, bdev_read_only(bdev) != 0);
 	case BLKSSZGET: /* get block device logical block size */

block/ioprio.c

···
 	return ret;
 }
 
+/*
+ * If the task has set an I/O priority, use that. Otherwise, return
+ * the default I/O priority.
+ *
+ * Expected to be called for current task or with task_lock() held to keep
+ * io_context stable.
+ */
+int __get_task_ioprio(struct task_struct *p)
+{
+	struct io_context *ioc = p->io_context;
+	int prio;
+
+	if (p != current)
+		lockdep_assert_held(&p->alloc_lock);
+	if (ioc)
+		prio = ioc->ioprio;
+	else
+		prio = IOPRIO_DEFAULT;
+
+	if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE)
+		prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
+					 task_nice_ioprio(p));
+	return prio;
+}
+EXPORT_SYMBOL_GPL(__get_task_ioprio);
+
 static int get_task_ioprio(struct task_struct *p)
 {
 	int ret;
···
 	ret = security_task_getioprio(p);
 	if (ret)
 		goto out;
-	ret = IOPRIO_DEFAULT;
 	task_lock(p);
-	if (p->io_context)
-		ret = p->io_context->ioprio;
+	ret = __get_task_ioprio(p);
 	task_unlock(p);
 out:
 	return ret;
 }
 
-int ioprio_best(unsigned short aprio, unsigned short bprio)
+/*
+ * Return raw IO priority value as set by userspace. We use this for
+ * ioprio_get(pid, IOPRIO_WHO_PROCESS) so that we keep historical behavior and
+ * also so that userspace can distinguish unset IO priority (which just gets
+ * overriden based on task's nice value) from IO priority set to some value.
+ */
+static int get_task_raw_ioprio(struct task_struct *p)
 {
-	if (!ioprio_valid(aprio))
-		aprio = IOPRIO_DEFAULT;
-	if (!ioprio_valid(bprio))
-		bprio = IOPRIO_DEFAULT;
+	int ret;
 
+	ret = security_task_getioprio(p);
+	if (ret)
+		goto out;
+	task_lock(p);
+	if (p->io_context)
+		ret = p->io_context->ioprio;
+	else
+		ret = IOPRIO_DEFAULT;
+	task_unlock(p);
+out:
+	return ret;
+}
+
+static int ioprio_best(unsigned short aprio, unsigned short bprio)
+{
 	return min(aprio, bprio);
 }
 
···
 			else
 				p = find_task_by_vpid(who);
 			if (p)
-				ret = get_task_ioprio(p);
+				ret = get_task_raw_ioprio(p);
 			break;
 		case IOPRIO_WHO_PGRP:
 			if (!who)

block/kyber-iosched.c

···
 static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags,
 			     void *key);
 
-static unsigned int kyber_sched_domain(unsigned int op)
+static unsigned int kyber_sched_domain(blk_opf_t opf)
 {
-	switch (op & REQ_OP_MASK) {
+	switch (opf & REQ_OP_MASK) {
 	case REQ_OP_READ:
 		return KYBER_READ;
 	case REQ_OP_WRITE:
···
 	}
 }
 
-static void kyber_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
+static void kyber_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 {
 	/*
 	 * We use the scheduler tags as per-hardware queue queueing tokens.
 	 * Async requests can be limited at this stage.
 	 */
-	if (!op_is_sync(op)) {
+	if (!op_is_sync(opf)) {
 		struct kyber_queue_data *kqd = data->q->elevator->elevator_data;
 
 		data->shallow_depth = kqd->async_depth;

block/mq-deadline.c

···
  * Called by __blk_mq_alloc_request(). The shallow_depth value set by this
  * function is used by __blk_mq_get_tag().
  */
-static void dd_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
+static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 {
 	struct deadline_data *dd = data->q->elevator->elevator_data;
 
 	/* Do not throttle synchronous reads. */
-	if (op_is_sync(op) && !op_is_write(op))
+	if (op_is_sync(opf) && !op_is_write(opf))
 		return;
 
 	/*

block/partitions/core.c

···
 #include <linux/slab.h>
 #include <linux/ctype.h>
 #include <linux/vmalloc.h>
-#include <linux/blktrace_api.h>
 #include <linux/raid/detect.h>
 #include "check.h"
 
···
 	case BLK_ZONED_HA:
 		pr_info("%s: disabling host aware zoned block device support due to partitions\n",
 			disk->disk_name);
-		blk_queue_set_zoned(disk, BLK_ZONED_NONE);
+		disk_set_zoned(disk, BLK_ZONED_NONE);
 		break;
 	case BLK_ZONED_NONE:
 		break;

drivers/block/Kconfig

···
 
 	  If unsure, say N.
 
+config BLK_DEV_UBLK
+	tristate "Userspace block driver (Experimental)"
+	select IO_URING
+	help
+	  io_uring based userspace block driver. Together with ublk server, ublk
+	  has been working well, but interface with userspace or command data
+	  definition isn't finalized yet, and might change according to future
+	  requirement, so mark is as experimental now.
+
 source "drivers/block/rnbd/Kconfig"
 
 endif # BLK_DEV

drivers/block/Makefile

···
 
 obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk/
 
+obj-$(CONFIG_BLK_DEV_UBLK)			+= ublk_drv.o
+
 swim_mod-y	:= swim.o swim_asm.o

drivers/block/amiflop.c

···
 	unit[drive].gendisk[system] = disk;
 	err = add_disk(disk);
 	if (err)
-		blk_cleanup_disk(disk);
+		put_disk(disk);
 	return err;
 }
 

drivers/block/aoe/aoeblk.c

···
 	return;
 
 out_disk_cleanup:
-	blk_cleanup_disk(gd);
+	put_disk(gd);
 err_tagset:
 	blk_mq_free_tag_set(set);
 err_mempool:

drivers/block/aoe/aoedev.c

···
 	if (d->gd) {
 		aoedisk_rm_debugfs(d);
 		del_gendisk(d->gd);
-		blk_cleanup_disk(d->gd);
+		put_disk(d->gd);
 		blk_mq_free_tag_set(&d->tag_set);
 	}
 	t = d->targets;

drivers/block/ataflop.c

···
 	return;
 
 cleanup_disk:
-	blk_cleanup_disk(unit[drive].disk[type]);
+	put_disk(unit[drive].disk[type]);
 	unit[drive].disk[type] = NULL;
 }
 
···
 			if (!unit[i].disk[type])
 				continue;
 			del_gendisk(unit[i].disk[type]);
-			blk_cleanup_queue(unit[i].disk[type]->queue);
 			put_disk(unit[i].disk[type]);
 		}
 		blk_mq_free_tag_set(&unit[i].tag_set);
···
 			continue;
 		if (fs->registered[type])
 			del_gendisk(fs->disk[type]);
-		blk_cleanup_disk(fs->disk[type]);
+		put_disk(fs->disk[type]);
 	}
 	blk_mq_free_tag_set(&fs->tag_set);
 }

drivers/block/brd.c

···
  * Process a single bvec of a bio.
  */
 static int brd_do_bvec(struct brd_device *brd, struct page *page,
-			unsigned int len, unsigned int off, unsigned int op,
+			unsigned int len, unsigned int off, enum req_op op,
 			sector_t sector)
 {
 	void *mem;
···
 }
 
 static int brd_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, unsigned int op)
+		       struct page *page, enum req_op op)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	int err;
···
 	return 0;
 
 out_cleanup_disk:
-	blk_cleanup_disk(disk);
+	put_disk(disk);
 out_free_dev:
 	list_del(&brd->brd_list);
 	kfree(brd);
···
 
 	list_for_each_entry_safe(brd, next, &brd_devices, brd_list) {
 		del_gendisk(brd->brd_disk);
-		blk_cleanup_disk(brd->brd_disk);
+		put_disk(brd->brd_disk);
 		brd_free_pages(brd);
 		list_del(&brd->brd_list);
 		kfree(brd);

drivers/block/drbd/drbd_actlog.c

···
 
 static int _drbd_md_sync_page_io(struct drbd_device *device,
 				 struct drbd_backing_dev *bdev,
-				 sector_t sector, int op)
+				 sector_t sector, enum req_op op)
 {
 	struct bio *bio;
 	/* we do all our meta data IO in aligned 4k blocks. */
 	const int size = 4096;
-	int err, op_flags = 0;
+	int err;
+	blk_opf_t op_flags = 0;
 
 	device->md_io.done = 0;
 	device->md_io.error = -ENODEV;
···
 }
 
 int drbd_md_sync_page_io(struct drbd_device *device, struct drbd_backing_dev *bdev,
-			 sector_t sector, int op)
+			 sector_t sector, enum req_op op)
 {
 	int err;
 	D_ASSERT(device, atomic_read(&device->md_io.in_use) == 1);
···
 		write_al_updates = rcu_dereference(device->ldev->disk_conf)->al_updates;
 		rcu_read_unlock();
 		if (write_al_updates) {
-			if (drbd_md_sync_page_io(device, device->ldev, sector, WRITE)) {
+			if (drbd_md_sync_page_io(device, device->ldev, sector, REQ_OP_WRITE)) {
 				err = -EIO;
 				drbd_chk_io_error(device, 1, DRBD_META_IO_ERROR);
 			} else {

drivers/block/drbd/drbd_bitmap.c

···
 static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_hold(local)
 {
 	struct drbd_device *device = ctx->device;
-	unsigned int op = (ctx->flags & BM_AIO_READ) ? REQ_OP_READ : REQ_OP_WRITE;
+	enum req_op op = ctx->flags & BM_AIO_READ ? REQ_OP_READ : REQ_OP_WRITE;
 	struct bio *bio = bio_alloc_bioset(device->ldev->md_bdev, 1, op,
 					   GFP_NOIO, &drbd_md_io_bio_set);
 	struct drbd_bitmap *b = device->bitmap;

drivers/block/drbd/drbd_int.h

···
 extern void *drbd_md_get_buffer(struct drbd_device *device, const char *intent);
 extern void drbd_md_put_buffer(struct drbd_device *device);
 extern int drbd_md_sync_page_io(struct drbd_device *device,
-		struct drbd_backing_dev *bdev, sector_t sector, int op);
+		struct drbd_backing_dev *bdev, sector_t sector, enum req_op op);
 extern void drbd_ov_out_of_sync_found(struct drbd_device *, sector_t, int);
 extern void wait_until_done_or_force_detached(struct drbd_device *device,
 		struct drbd_backing_dev *bdev, unsigned int *done);
···
 extern bool drbd_rs_should_slow_down(struct drbd_device *device, sector_t sector,
 		bool throttle_if_app_is_waiting);
 extern int drbd_submit_peer_request(struct drbd_device *,
-				    struct drbd_peer_request *, const unsigned,
-				    const unsigned, const int);
+				    struct drbd_peer_request *, blk_opf_t, int);
 extern int drbd_free_peer_reqs(struct drbd_device *, struct list_head *);
 extern struct drbd_peer_request *drbd_alloc_peer_req(struct drbd_peer_device *, u64,
 						     sector_t, unsigned int,

drivers/block/drbd/drbd_main.c

···
 	if (device->bitmap) /* should no longer be there. */
 		drbd_bm_cleanup(device);
 	__free_page(device->md_io.page);
-	blk_cleanup_disk(device->vdisk);
+	put_disk(device->vdisk);
 	kfree(device->rs_plan_s);
 
 	/* not for_each_connection(connection, resource):
···
 out_no_bitmap:
 	__free_page(device->md_io.page);
 out_no_io_page:
-	blk_cleanup_disk(disk);
+	put_disk(disk);
 out_no_disk:
 	kref_put(&resource->kref, drbd_destroy_resource);
 	kfree(device);

drivers/block/drbd/drbd_receiver.c

···
 /* TODO allocate from our own bio_set. */
 int drbd_submit_peer_request(struct drbd_device *device,
 			     struct drbd_peer_request *peer_req,
-			     const unsigned op, const unsigned op_flags,
-			     const int fault_type)
+			     const blk_opf_t opf, const int fault_type)
 {
 	struct bio *bios = NULL;
 	struct bio *bio;
···
 	 * generated bio, but a bio allocated on behalf of the peer.
 	 */
 next_bio:
-	bio = bio_alloc(device->ldev->backing_bdev, nr_pages, op | op_flags,
-			GFP_NOIO);
+	bio = bio_alloc(device->ldev->backing_bdev, nr_pages, opf, GFP_NOIO);
 	/* > peer_req->i.sector, unless this is the first bio */
 	bio->bi_iter.bi_sector = sector;
 	bio->bi_private = peer_req;
···
 	spin_unlock_irq(&device->resource->req_lock);
 
 	atomic_add(pi->size >> 9, &device->rs_sect_ev);
-	if (drbd_submit_peer_request(device, peer_req, REQ_OP_WRITE, 0,
+	if (drbd_submit_peer_request(device, peer_req, REQ_OP_WRITE,
 				     DRBD_FAULT_RS_WR) == 0)
 		return 0;
 
···
 /* see also bio_flags_to_wire()
  * DRBD_REQ_*, because we need to semantically map the flags to data packet
  * flags and back. We may replicate to other kernel versions. */
-static unsigned long wire_flags_to_bio_flags(u32 dpf)
+static blk_opf_t wire_flags_to_bio_flags(u32 dpf)
 {
 	return  (dpf & DP_RW_SYNC ? REQ_SYNC : 0) |
 		(dpf & DP_FUA ? REQ_FUA : 0) |
 		(dpf & DP_FLUSH ? REQ_PREFLUSH : 0);
 }
 
-static unsigned long wire_flags_to_bio_op(u32 dpf)
+static enum req_op wire_flags_to_bio_op(u32 dpf)
 {
 	if (dpf & DP_ZEROES)
 		return REQ_OP_WRITE_ZEROES;
···
 	struct drbd_peer_request *peer_req;
 	struct p_data *p = pi->data;
 	u32 peer_seq = be32_to_cpu(p->seq_num);
-	int op, op_flags;
+	enum req_op op;
+	blk_opf_t op_flags;
 	u32 dp_flags;
 	int err, tp;
 
···
 		peer_req->flags |= EE_CALL_AL_COMPLETE_IO;
 	}
 
-	err = drbd_submit_peer_request(device, peer_req, op, op_flags,
+	err = drbd_submit_peer_request(device, peer_req, op | op_flags,
 				       DRBD_FAULT_DT_WR);
 	if (!err)
 		return 0;
···
 submit:
 	update_receiver_timing_details(connection, drbd_submit_peer_request);
 	inc_unacked(device);
-	if (drbd_submit_peer_request(device, peer_req, REQ_OP_READ, 0,
+	if (drbd_submit_peer_request(device, peer_req, REQ_OP_READ,
 				     fault_type) == 0)
 		return 0;
 
···
 
 	if (get_ldev(device)) {
 		struct drbd_peer_request *peer_req;
-		const int op = REQ_OP_WRITE_ZEROES;
+		const enum req_op op = REQ_OP_WRITE_ZEROES;
 
 		peer_req = drbd_alloc_peer_req(peer_device, ID_SYNCER, sector,
 					       size, 0, GFP_NOIO);
···
 		spin_unlock_irq(&device->resource->req_lock);
 
 		atomic_add(pi->size >> 9, &device->rs_sect_ev);
-		err = drbd_submit_peer_request(device, peer_req, op, 0, DRBD_FAULT_RS_WR);
+		err = drbd_submit_peer_request(device, peer_req, op,
+					       DRBD_FAULT_RS_WR);
 
 		if (err) {
 			spin_lock_irq(&device->resource->req_lock);

drivers/block/drbd/drbd_req.c

···
 
 static void drbd_report_io_error(struct drbd_device *device, struct drbd_request *req)
 {
-        char b[BDEVNAME_SIZE];
-
 	if (!__ratelimit(&drbd_ratelimit_state))
 		return;
 
-	drbd_warn(device, "local %s IO error sector %llu+%u on %s\n",
+	drbd_warn(device, "local %s IO error sector %llu+%u on %pg\n",
 			(req->rq_state & RQ_WRITE) ? "WRITE" : "READ",
 			(unsigned long long)req->i.sector,
 			req->i.size >> 9,
-			bdevname(device->ldev->backing_bdev, b));
+			device->ldev->backing_bdev);
 }
 
 /* Helper for HANDED_OVER_TO_NETWORK.

drivers/block/drbd/drbd_worker.c

···
 	spin_unlock_irq(&device->resource->req_lock);
 
 	atomic_add(size >> 9, &device->rs_sect_ev);
-	if (drbd_submit_peer_request(device, peer_req, REQ_OP_READ, 0,
+	if (drbd_submit_peer_request(device, peer_req, REQ_OP_READ,
 				     DRBD_FAULT_RS_RD) == 0)
 		return 0;
 

drivers/block/floppy.c

···
 	if (WARN(atomic_read(&usage_count) == 0,
 		 "warning: usage count=0, current_req=%p sect=%ld flags=%llx\n",
 		 current_req, (long)blk_rq_pos(current_req),
-		 (unsigned long long) current_req->cmd_flags))
+		 (__force unsigned long long) current_req->cmd_flags))
 		return BLK_STS_IOERR;
 
 	if (test_and_set_bit(0, &fdc_busy)) {
···
 	return;
 
 cleanup_disk:
-	blk_cleanup_disk(disks[drive][type]);
+	put_disk(disks[drive][type]);
 	disks[drive][type] = NULL;
 	mutex_unlock(&floppy_probe_lock);
 }
···
 		if (!disks[drive][0])
 			break;
 		del_timer_sync(&motor_off_timer[drive]);
-		blk_cleanup_disk(disks[drive][0]);
+		put_disk(disks[drive][0]);
 		blk_mq_free_tag_set(&tag_sets[drive]);
 	}
 	return err;
···
 		}
 		for (i = 0; i < ARRAY_SIZE(floppy_type); i++) {
 			if (disks[drive][i])
-				blk_cleanup_disk(disks[drive][i]);
+				put_disk(disks[drive][i]);
 		}
 		blk_mq_free_tag_set(&tag_sets[drive]);
 	}

drivers/block/loop.c

···
 	return i;
 
 out_cleanup_disk:
-	blk_cleanup_disk(disk);
+	put_disk(disk);
 out_cleanup_tags:
 	blk_mq_free_tag_set(&lo->tag_set);
 out_free_idr:
···
 {
 	/* Make this loop device unreachable from pathname. */
 	del_gendisk(lo->lo_disk);
-	blk_cleanup_queue(lo->lo_disk->queue);
 	blk_mq_free_tag_set(&lo->tag_set);
 
 	mutex_lock(&loop_ctl_mutex);

drivers/block/mtip32xx/mtip32xx.c

···
 /* Device instance number, incremented each time a device is probed. */
 static int instance;
 
-static LIST_HEAD(online_list);
-static LIST_HEAD(removing_list);
-static DEFINE_SPINLOCK(dev_lock);
-
 /*
  * Global variable used to hold the major block device number
  * allocated in mtip_init().
  */
 static int mtip_major;
 static struct dentry *dfs_parent;
-static struct dentry *dfs_device_status;
 
 static u32 cpu_use[NR_CPUS];
 
···
 	pci_read_config_word(dd->pdev, 0x00, &vendor_id);
 	if (vendor_id == 0xFFFF) {
 		dd->sr = true;
-		if (dd->queue)
-			blk_queue_flag_set(QUEUE_FLAG_DEAD, dd->queue);
-		else
-			dev_warn(&dd->pdev->dev,
-				"%s: dd->queue is NULL\n", __func__);
+		if (dd->disk)
+			blk_mark_disk_dead(dd->disk);
 		return true; /* device removed */
 	}
 
···
 	NULL,
 };
 
-/* debugsfs entries */
-
-static ssize_t show_device_status(struct device_driver *drv, char *buf)
-{
-	int size = 0;
-	struct driver_data *dd, *tmp;
-	unsigned long flags;
-	char id_buf[42];
-	u16 status = 0;
-
-	spin_lock_irqsave(&dev_lock, flags);
-	size += sprintf(&buf[size], "Devices Present:\n");
-	list_for_each_entry_safe(dd, tmp, &online_list, online_list) {
-		if (dd->pdev) {
-			if (dd->port &&
-			    dd->port->identify &&
-			    dd->port->identify_valid) {
-				strlcpy(id_buf,
-					(char *) (dd->port->identify + 10), 21);
-				status = *(dd->port->identify + 141);
-			} else {
-				memset(id_buf, 0, 42);
-				status = 0;
-			}
-
-			if (dd->port &&
-			    test_bit(MTIP_PF_REBUILD_BIT, &dd->port->flags)) {
-				size += sprintf(&buf[size],
-					" device %s %s (ftl rebuild %d %%)\n",
-					dev_name(&dd->pdev->dev),
-					id_buf,
-					status);
-			} else {
-				size += sprintf(&buf[size],
-					" device %s %s\n",
-					dev_name(&dd->pdev->dev),
-					id_buf);
-			}
-		}
-	}
-
-	size += sprintf(&buf[size], "Devices Being Removed:\n");
-	list_for_each_entry_safe(dd, tmp, &removing_list, remove_list) {
-		if (dd->pdev) {
-			if (dd->port &&
-			    dd->port->identify &&
-			    dd->port->identify_valid) {
-				strlcpy(id_buf,
-					(char *) (dd->port->identify+10), 21);
-				status = *(dd->port->identify + 141);
-			} else {
-				memset(id_buf, 0, 42);
-				status = 0;
-			}
-
-			if (dd->port &&
-			    test_bit(MTIP_PF_REBUILD_BIT, &dd->port->flags)) {
-				size += sprintf(&buf[size],
-					" device %s %s (ftl rebuild %d %%)\n",
-					dev_name(&dd->pdev->dev),
-					id_buf,
-					status);
-			} else {
-				size += sprintf(&buf[size],
-					" device %s %s\n",
-					dev_name(&dd->pdev->dev),
-					id_buf);
-			}
-		}
-	}
-	spin_unlock_irqrestore(&dev_lock, flags);
-
-	return size;
-}
-
-static ssize_t mtip_hw_read_device_status(struct file *f, char __user *ubuf,
-						size_t len, loff_t *offset)
-{
-	int size = *offset;
-	char *buf;
-	int rv = 0;
-
-	if (!len || *offset)
-		return 0;
-
-	buf = kzalloc(MTIP_DFS_MAX_BUF_SIZE, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	size += show_device_status(NULL, buf);
-
-	*offset = size <= len ? size : len;
-	size = copy_to_user(ubuf, buf, *offset);
-	if (size)
-		rv = -EFAULT;
-
-	kfree(buf);
-	return rv ? rv : *offset;
-}
-
 static ssize_t mtip_hw_read_registers(struct file *f, char __user *ubuf,
 				  size_t len, loff_t *offset)
 {
···
 	kfree(buf);
 	return rv ? rv : *offset;
 }
-
-static const struct file_operations mtip_device_status_fops = {
-	.owner  = THIS_MODULE,
-	.open   = simple_open,
-	.read   = mtip_hw_read_device_status,
-	.llseek = no_llseek,
-};
 
 static const struct file_operations mtip_regs_fops = {
 	.owner  = THIS_MODULE,
···
 	blk_mq_end_request(rq, cmd->status);
 }
 
-static bool mtip_abort_cmd(struct request *req, void *data, bool reserved)
+static bool mtip_abort_cmd(struct request *req, void *data)
 {
 	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
 	struct driver_data *dd = data;
···
 	return true;
 }
 
-static bool mtip_queue_cmd(struct request *req, void *data, bool reserved)
+static bool mtip_queue_cmd(struct request *req, void *data)
 {
 	struct driver_data *dd = data;
 
···
 	return 0;
 }
 
-static int mtip_block_open(struct block_device *dev, fmode_t mode)
+static void mtip_block_free_disk(struct gendisk *disk)
 {
-	struct driver_data *dd;
+	struct driver_data *dd = disk->private_data;
 
-	if (dev && dev->bd_disk) {
-		dd = (struct driver_data *) dev->bd_disk->private_data;
-
-		if (dd) {
-			if (test_bit(MTIP_DDF_REMOVAL_BIT,
-							&dd->dd_flag)) {
-				return -ENODEV;
-			}
-			return 0;
-		}
-	}
-	return -ENODEV;
-}
-
-static void mtip_block_release(struct gendisk *disk, fmode_t mode)
-{
+	ida_free(&rssd_index_ida, dd->index);
+	kfree(dd);
 }
 
 /*
···
  * layer.
  */
 static const struct block_device_operations mtip_block_ops = {
-	.open		= mtip_block_open,
-	.release	= mtip_block_release,
 	.ioctl		= mtip_block_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= mtip_block_compat_ioctl,
 #endif
 	.getgeo		= mtip_block_getgeo,
+	.free_disk	= mtip_block_free_disk,
 	.owner		= THIS_MODULE
 };
 
···
 	return 0;
 }
 
-static enum blk_eh_timer_return mtip_cmd_timeout(struct request *req,
-								bool reserved)
+static enum blk_eh_timer_return mtip_cmd_timeout(struct request *req)
 {
 	struct driver_data *dd = req->q->queuedata;
 
-	if (reserved) {
+	if (blk_mq_is_reserved_rq(req)) {
 		struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
 
 		cmd->status = BLK_STS_TIMEOUT;
···
 disk_index_error:
 	ida_free(&rssd_index_ida, index);
 ida_get_error:
-	blk_cleanup_disk(dd->disk);
+	put_disk(dd->disk);
 block_queue_alloc_init_error:
 	blk_mq_free_tag_set(&dd->tags);
 block_queue_alloc_tag_error:
 	mtip_hw_exit(dd); /* De-initialize the protocol layer. */
 protocol_init_error:
 	return rv;
-}
-
-static bool mtip_no_dev_cleanup(struct request *rq, void *data, bool reserv)
-{
-	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
-
-	cmd->status = BLK_STS_IOERR;
-	blk_mq_complete_request(rq);
-	return true;
-}
-
-/*
- * Block layer deinitialization function.
- *
- * Called by the PCI layer as each P320 device is removed.
- *
- * @dd Pointer to the driver data structure.
- *
- * return value
- *	0
- */
-static int mtip_block_remove(struct driver_data *dd)
-{
-	mtip_hw_debugfs_exit(dd);
-
-	if (dd->mtip_svc_handler) {
-		set_bit(MTIP_PF_SVC_THD_STOP_BIT, &dd->port->flags);
-		wake_up_interruptible(&dd->port->svc_wait);
-		kthread_stop(dd->mtip_svc_handler);
-	}
-
-	if (!dd->sr) {
-		/*
-		 * Explicitly wait here for IOs to quiesce,
-		 * as mtip_standby_drive usually won't wait for IOs.
-		 */
-		if (!mtip_quiesce_io(dd->port, MTIP_QUIESCE_IO_TIMEOUT_MS))
-			mtip_standby_drive(dd);
-	}
-	else
-		dev_info(&dd->pdev->dev, "device %s surprise removal\n",
-						dd->disk->disk_name);
-
-	blk_freeze_queue_start(dd->queue);
-	blk_mq_quiesce_queue(dd->queue);
-	blk_mq_tagset_busy_iter(&dd->tags, mtip_no_dev_cleanup, dd);
-	blk_mq_unquiesce_queue(dd->queue);
-
-	if (dd->disk) {
-		if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag))
-			del_gendisk(dd->disk);
-		if (dd->disk->queue) {
-			blk_cleanup_queue(dd->queue);
-			blk_mq_free_tag_set(&dd->tags);
-			dd->queue = NULL;
-		}
-		put_disk(dd->disk);
-	}
-	dd->disk  = NULL;
-
-	ida_free(&rssd_index_ida, dd->index);
-
-	/* De-initialize the protocol layer. */
-	mtip_hw_exit(dd);
-
-	return 0;
 }
 
 /*
···
 {
 	mtip_hw_shutdown(dd);
 
-	/* Delete our gendisk structure, and cleanup the blk queue. */
-	if (dd->disk) {
-		dev_info(&dd->pdev->dev,
-			"Shutting down %s ...\n", dd->disk->disk_name);
+	dev_info(&dd->pdev->dev,
+		"Shutting down %s ...\n", dd->disk->disk_name);
 
-		if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag))
-			del_gendisk(dd->disk);
-		if (dd->disk->queue) {
-			blk_cleanup_queue(dd->queue);
-			blk_mq_free_tag_set(&dd->tags);
-		}
-		put_disk(dd->disk);
-		dd->disk  = NULL;
-		dd->queue = NULL;
-	}
+	if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag))
+		del_gendisk(dd->disk);
 
-	ida_free(&rssd_index_ida, dd->index);
+	blk_mq_free_tag_set(&dd->tags);
+	put_disk(dd->disk);
 	return 0;
 }
 
···
 	const struct cpumask *node_mask;
 	int cpu, i = 0, j = 0;
 	int my_node = NUMA_NO_NODE;
-	unsigned long flags;
 
 	/* Allocate memory for this devices private data. */
 	my_node = pcibus_to_node(pdev->bus);
···
 	dd->instance	= instance;
 	dd->pdev	= pdev;
 	dd->numa_node	= my_node;
-
-	INIT_LIST_HEAD(&dd->online_list);
-	INIT_LIST_HEAD(&dd->remove_list);
 
 	memset(dd->workq_name, 0, 32);
 	snprintf(dd->workq_name, 31, "mtipq%d", dd->instance);
···
 	else
 		rv = 0; /* device in rebuild state, return 0 from probe */
 
-	/* Add to online list even if in ftl rebuild */
-	spin_lock_irqsave(&dev_lock, flags);
-	list_add(&dd->online_list, &online_list);
-	spin_unlock_irqrestore(&dev_lock, flags);
-
 	goto done;
 
 block_initialize_err:
···
 static void mtip_pci_remove(struct pci_dev *pdev)
 {
 	struct driver_data *dd = pci_get_drvdata(pdev);
-	unsigned long flags, to;
-
-	set_bit(MTIP_DDF_REMOVAL_BIT, &dd->dd_flag);
-
-	spin_lock_irqsave(&dev_lock, flags);
-	list_del_init(&dd->online_list);
-	list_add(&dd->remove_list, &removing_list);
-	spin_unlock_irqrestore(&dev_lock, flags);
+	unsigned long to;
 
 	mtip_check_surprise_removal(dd);
 	synchronize_irq(dd->pdev->irq);
···
 			"Completion workers still active!\n");
 	}
 
-	blk_mark_disk_dead(dd->disk);
 	set_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag);
 
-	/* Clean up the block layer. */
-	mtip_block_remove(dd);
+	if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag))
+		del_gendisk(dd->disk);
+
+	mtip_hw_debugfs_exit(dd);
+
+	if (dd->mtip_svc_handler) {
+		set_bit(MTIP_PF_SVC_THD_STOP_BIT, &dd->port->flags);
+		wake_up_interruptible(&dd->port->svc_wait);
+		kthread_stop(dd->mtip_svc_handler);
+	}
+
+	if (!dd->sr) {
+		/*
+		 * Explicitly wait here for IOs to quiesce,
+		 * as mtip_standby_drive usually won't wait for IOs.
+		 */
+		if (!mtip_quiesce_io(dd->port, MTIP_QUIESCE_IO_TIMEOUT_MS))
+			mtip_standby_drive(dd);
+	}
+	else
+		dev_info(&dd->pdev->dev, "device %s surprise removal\n",
+						dd->disk->disk_name);
+
+	blk_mq_free_tag_set(&dd->tags);
+
+	/* De-initialize the protocol layer. */
+	mtip_hw_exit(dd);
 
 	if (dd->isr_workq) {
 		destroy_workqueue(dd->isr_workq);
···
 
 	pci_disable_msi(pdev);
 
-	spin_lock_irqsave(&dev_lock, flags);
-	list_del_init(&dd->remove_list);
-	spin_unlock_irqrestore(&dev_lock, flags);
-
-	kfree(dd);
-
 	pcim_iounmap_regions(pdev, 1 << MTIP_ABAR);
 	pci_set_drvdata(pdev, NULL);
+
+	put_disk(dd->disk);
 }
 
 /*
···
 	if (IS_ERR_OR_NULL(dfs_parent)) {
 		pr_warn("Error creating debugfs parent\n");
 		dfs_parent = NULL;
-	}
-	if (dfs_parent) {
-		dfs_device_status = debugfs_create_file("device_status",
-					0444, dfs_parent, NULL,
-					&mtip_device_status_fops);
-		if (IS_ERR_OR_NULL(dfs_device_status)) {
-			pr_err("Error creating device_status node\n");
-			dfs_device_status = NULL;
-		}
 	}
 
 	/* Register our PCI operations. */

drivers/block/mtip32xx/mtip32xx.h

···
 	MTIP_DDF_RESUME_BIT         = 6,
 	MTIP_DDF_INIT_DONE_BIT      = 7,
 	MTIP_DDF_REBUILD_FAILED_BIT = 8,
-	MTIP_DDF_REMOVAL_BIT	    = 9,
 
 	MTIP_DDF_STOP_IO      = ((1 << MTIP_DDF_REMOVE_PENDING_BIT) |
 				(1 << MTIP_DDF_SEC_LOCK_BIT) |
···
 	struct mtip_work work[MTIP_MAX_SLOT_GROUPS];
 
 	int isr_binding;
-
-	struct list_head online_list; /* linkage for online list */
-
-	struct list_head remove_list; /* linkage for removing list */
 
 	int unal_qdepth; /* qdepth of unaligned IO queue */
 };

drivers/block/n64cart.c

···
 	return 0;
 
 out_cleanup_disk:
-	blk_cleanup_disk(disk);
+	put_disk(disk);
 out:
 	return err;
 }

drivers/block/nbd.c

···
 	struct gendisk *disk = nbd->disk;
 
 	del_gendisk(disk);
-	blk_cleanup_disk(disk);
+	put_disk(disk);
 	blk_mq_free_tag_set(&nbd->tag_set);
 
 	/*
···
 	}
 }
 
-static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
-						 bool reserved)
+static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
 	struct nbd_device *nbd = cmd->nbd;
···
 	kfree(args);
 }
 
-static bool nbd_clear_req(struct request *req, void *data, bool reserved)
+static bool nbd_clear_req(struct request *req, void *data)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
 
···
 out_free_work:
 	destroy_workqueue(nbd->recv_workq);
 out_err_disk:
-	blk_cleanup_disk(disk);
+	put_disk(disk);
 out_free_idr:
 	mutex_lock(&nbd_index_mutex);
 	idr_remove(&nbd_index_idr, index);

drivers/block/null_blk/main.c

···
 }
 
 static inline blk_status_t null_handle_memory_backed(struct nullb_cmd *cmd,
-						     enum req_opf op,
+						     enum req_op op,
 						     sector_t sector,
 						     sector_t nr_sectors)
 {
···
 	}
 }
 
-blk_status_t null_process_cmd(struct nullb_cmd *cmd,
-			      enum req_opf op, sector_t sector,
-			      unsigned int nr_sectors)
+blk_status_t null_process_cmd(struct nullb_cmd *cmd, enum req_op op,
+			      sector_t sector, unsigned int nr_sectors)
 {
 	struct nullb_device *dev = cmd->nq->dev;
 	blk_status_t ret;
···
 }
 
 static blk_status_t null_handle_cmd(struct nullb_cmd *cmd, sector_t sector,
-				    sector_t nr_sectors, enum req_opf op)
+				    sector_t nr_sectors, enum req_op op)
 {
 	struct nullb_device *dev = cmd->nq->dev;
 	struct nullb *nullb = dev->nullb;
···
 	return nr;
 }
 
-static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res)
+static enum blk_eh_timer_return null_timeout_rq(struct request *rq)
 {
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
···
 		null_restart_queue_async(nullb);
 	}
 
-	blk_cleanup_disk(nullb->disk);
+	put_disk(nullb->disk);
 	if (dev->queue_mode == NULL_Q_MQ &&
 	    nullb->tag_set == &nullb->__tag_set)
 		blk_mq_free_tag_set(nullb->tag_set);
···
 out_cleanup_zone:
 	null_free_zoned_dev(dev);
 out_cleanup_disk:
-	blk_cleanup_disk(nullb->disk);
+	put_disk(nullb->disk);
 out_cleanup_tags:
 	if (dev->queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set)
 		blk_mq_free_tag_set(nullb->tag_set);

drivers/block/null_blk/null_blk.h

···
 
 blk_status_t null_handle_discard(struct nullb_device *dev, sector_t sector,
 				 sector_t nr_sectors);
-blk_status_t null_process_cmd(struct nullb_cmd *cmd,
-			      enum req_opf op, sector_t sector,
-			      unsigned int nr_sectors);
+blk_status_t null_process_cmd(struct nullb_cmd *cmd, enum req_op op,
+			      sector_t sector, unsigned int nr_sectors);
 
 #ifdef CONFIG_BLK_DEV_ZONED
 int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q);
···
 void null_free_zoned_dev(struct nullb_device *dev);
 int null_report_zones(struct gendisk *disk, sector_t sector,
 		      unsigned int nr_zones, report_zones_cb cb, void *data);
-blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd,
-				    enum req_opf op, sector_t sector,
-				    sector_t nr_sectors);
+blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_op op,
+				    sector_t sector, sector_t nr_sectors);
 size_t null_zone_valid_read_len(struct nullb *nullb,
 				sector_t sector, unsigned int len);
 #else
···
 }
 static inline void null_free_zoned_dev(struct nullb_device *dev) {}
 static inline blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd,
-			enum req_opf op, sector_t sector, sector_t nr_sectors)
+			enum req_op op, sector_t sector, sector_t nr_sectors)
 {
 	return BLK_STS_NOTSUPP;
 }

drivers/block/null_blk/trace.h

···
 	    TP_ARGS(cmd, zone_no, zone_cond),
 	    TP_STRUCT__entry(
 		__array(char, disk, DISK_NAME_LEN)
-		__field(enum req_opf, op)
+		__field(enum req_op, op)
 		__field(unsigned int, zone_no)
 		__field(unsigned int, zone_cond)
 	    ),

drivers/block/null_blk/zoned.c

···
 	struct nullb_device *dev = nullb->dev;
 	struct request_queue *q = nullb->q;
 
-	blk_queue_set_zoned(nullb->disk, BLK_ZONED_HM);
+	disk_set_zoned(nullb->disk, BLK_ZONED_HM);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
 
···
 			return ret;
 	} else {
 		blk_queue_chunk_sectors(q, dev->zone_size_sects);
-		q->nr_zones = blkdev_nr_zones(nullb->disk);
+		nullb->disk->nr_zones = bdev_nr_zones(nullb->disk->part0);
 	}
 
 	blk_queue_max_zone_append_sectors(q, dev->zone_size_sects);
-	blk_queue_max_open_zones(q, dev->zone_max_open);
-	blk_queue_max_active_zones(q, dev->zone_max_active);
+	disk_set_max_open_zones(nullb->disk, dev->zone_max_open);
+	disk_set_max_active_zones(nullb->disk, dev->zone_max_active);
 
 	return 0;
 }
···
 	return BLK_STS_OK;
 }
 
-static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
+static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_op op,
 				   sector_t sector)
 {
 	struct nullb_device *dev = cmd->nq->dev;
···
 	return ret;
 }
 
-blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_opf op,
+blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_op op,
 				    sector_t sector, sector_t nr_sectors)
 {
 	struct nullb_device *dev;

drivers/block/paride/pcd.c

···
 out_pi_release:
 	pi_release(cd->pi);
 out_free_disk:
-	blk_cleanup_disk(cd->disk);
+	put_disk(cd->disk);
 out_free_tag_set:
 	blk_mq_free_tag_set(&cd->tag_set);
 	return ret;
···
 		unregister_cdrom(&cd->info);
 		del_gendisk(cd->disk);
 		pi_release(cd->pi);
-		blk_cleanup_disk(cd->disk);
+		put_disk(cd->disk);
 
 		blk_mq_free_tag_set(&cd->tag_set);
 	}

drivers/block/paride/pd.c

···
 			return do_pd_read_start();
 		else
 			return do_pd_write_start();
+	default:
+		break;
 	}
 	return Fail;
 }
···
 		goto cleanup_disk;
 	return 0;
 cleanup_disk:
-	blk_cleanup_disk(disk->gd);
+	put_disk(disk->gd);
 put_disk:
 	put_disk(p);
 	disk->gd = NULL;
···
 		if (p) {
 			disk->gd = NULL;
 			del_gendisk(p);
-			blk_cleanup_disk(p);
+			put_disk(p);
 			blk_mq_free_tag_set(&disk->tag_set);
 			pi_release(disk->pi);
 		}

drivers/block/paride/pf.c

···
 out_pi_release:
 	pi_release(pf->pi);
 out_free_disk:
-	blk_cleanup_disk(pf->disk);
+	put_disk(pf->disk);
 out_free_tag_set:
 	blk_mq_free_tag_set(&pf->tag_set);
 	return ret;
···
 		if (!pf->present)
 			continue;
 		del_gendisk(pf->disk);
-		blk_cleanup_disk(pf->disk);
+		put_disk(pf->disk);
 		blk_mq_free_tag_set(&pf->tag_set);
 		pi_release(pf->pi);
 	}

drivers/block/pktcdvd.c

···
 {
 	struct pktcdvd_device *pd = m->private;
 	char *msg;
-	char bdev_buf[BDEVNAME_SIZE];
 	int states[PACKET_NUM_STATES];
 
-	seq_printf(m, "Writer %s mapped to %s:\n", pd->name,
-		   bdevname(pd->bdev, bdev_buf));
+	seq_printf(m, "Writer %s mapped to %pg:\n", pd->name, pd->bdev);
 
 	seq_printf(m, "\nSettings:\n");
 	seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2);
···
 static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 {
 	int i;
-	char b[BDEVNAME_SIZE];
 	struct block_device *bdev;
 	struct scsi_device *sdev;
 
···
 		if (!pd2)
 			continue;
 		if (pd2->bdev->bd_dev == dev) {
-			pkt_err(pd, "%s already setup\n",
-				bdevname(pd2->bdev, b));
+			pkt_err(pd, "%pg already setup\n", pd2->bdev);
 			return -EBUSY;
 		}
 		if (pd2->pkt_dev == dev) {
···
 	}
 
 	proc_create_single_data(pd->name, 0, pkt_proc, pkt_seq_show, pd);
-	pkt_dbg(1, pd, "writer mapped to %s\n", bdevname(bdev, b));
+	pkt_dbg(1, pd, "writer mapped to %pg\n", bdev);
 	return 0;
 
 out_mem:
···
 	return 0;
 
 out_mem2:
-	blk_cleanup_disk(disk);
+	put_disk(disk);
 out_mem:
 	mempool_exit(&pd->rb_pool);
 	kfree(pd);
···
 	pkt_dbg(1, pd, "writer unmapped\n");
 
 	del_gendisk(pd->disk);
-	blk_cleanup_disk(pd->disk);
+	put_disk(pd->disk);
 
 	mempool_exit(&pd->rb_pool);
 	kfree(pd);

drivers/block/ps3disk.c

···
 
 	return 0;
 fail_cleanup_disk:
-	blk_cleanup_disk(gendisk);
+	put_disk(gendisk);
 fail_free_tag_set:
 	blk_mq_free_tag_set(&priv->tag_set);
 fail_teardown:
···
 		    &ps3disk_mask);
 	mutex_unlock(&ps3disk_mask_mutex);
 	del_gendisk(priv->gendisk);
-	blk_cleanup_disk(priv->gendisk);
+	put_disk(priv->gendisk);
 	blk_mq_free_tag_set(&priv->tag_set);
 	dev_notice(&dev->sbd.core, "Synchronizing disk cache\n");
 	ps3disk_sync_cache(dev);

drivers/block/ps3vram.c

···
 	return 0;
 
 out_cleanup_disk:
-	blk_cleanup_disk(gendisk);
+	put_disk(gendisk);
 out_cache_cleanup:
 	remove_proc_entry(DEVICE_NAME, NULL);
 	ps3vram_cache_cleanup(dev);
···
 	struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
 
 	del_gendisk(priv->gendisk);
-	blk_cleanup_disk(priv->gendisk);
+	put_disk(priv->gendisk);
 	remove_proc_entry(DEVICE_NAME, NULL);
 	ps3vram_cache_cleanup(dev);
 	iounmap(priv->reports);

drivers/block/rbd.c

···
 
 static void rbd_free_disk(struct rbd_device *rbd_dev)
 {
-	blk_cleanup_disk(rbd_dev->disk);
+	put_disk(rbd_dev->disk);
 	blk_mq_free_tag_set(&rbd_dev->tag_set);
 	rbd_dev->disk = NULL;
 }

drivers/block/rnbd/rnbd-clt.c

···
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, dev->queue);
 	err = add_disk(dev->gd);
 	if (err)
-		blk_cleanup_disk(dev->gd);
+		put_disk(dev->gd);
 
 	return err;
 }
···
 static void destroy_gen_disk(struct rnbd_clt_dev *dev)
 {
 	del_gendisk(dev->gd);
-	blk_cleanup_disk(dev->gd);
+	put_disk(dev->gd);
 }
 
 static void destroy_sysfs(struct rnbd_clt_dev *dev,
···
 		list_for_each_entry_safe(dev, tn, &sess->devs_list, list) {
 			/*
 			 * Here unmap happens in parallel for only one reason:
-			 * blk_cleanup_queue() takes around half a second, so
+			 * del_gendisk() takes around half a second, so
 			 * on huge amount of devices the whole module unload
 			 * procedure takes minutes.
 			 */

drivers/block/rnbd/rnbd-proto.h

···
 	return true;
 }
 
-static inline u32 rnbd_to_bio_flags(u32 rnbd_opf)
+static inline blk_opf_t rnbd_to_bio_flags(u32 rnbd_opf)
 {
-	u32 bio_opf;
+	blk_opf_t bio_opf;
 
 	switch (rnbd_op(rnbd_opf)) {
 	case RNBD_OP_READ:
···
 		break;
 	default:
 		WARN(1, "Unknown request type %d (flags %llu)\n",
-		     req_op(rq), (unsigned long long)rq->cmd_flags);
+		     (__force u32)req_op(rq),
+		     (__force unsigned long long)rq->cmd_flags);
 		rnbd_opf = 0;
 	}
 

drivers/block/rnbd/rnbd-srv-dev.c

···
 		goto err;
 
 	dev->blk_open_flags = flags;
-	bdevname(dev->bdev, dev->name);
 
 	return dev;
 

drivers/block/rnbd/rnbd-srv-dev.h

···
 struct rnbd_dev {
 	struct block_device	*bdev;
 	fmode_t			blk_open_flags;
-	char			name[BDEVNAME_SIZE];
 };
 
 /**

drivers/block/rnbd/rnbd-srv-sysfs.c

···
 };
 
 int rnbd_srv_create_dev_sysfs(struct rnbd_srv_dev *dev,
-			       struct block_device *bdev,
-			       const char *dev_name)
+			       struct block_device *bdev)
 {
 	struct kobject *bdev_kobj;
 	int ret;
 
 	ret = kobject_init_and_add(&dev->dev_kobj, &dev_ktype,
-				   rnbd_devs_kobj, dev_name);
+				   rnbd_devs_kobj, "%pg", bdev);
 	if (ret) {
 		kobject_put(&dev->dev_kobj);
 		return ret;

drivers/block/rnbd/rnbd-srv.c

···
 	return sess_dev;
 }
 
-static struct rnbd_srv_dev *rnbd_srv_init_srv_dev(const char *id)
+static struct rnbd_srv_dev *rnbd_srv_init_srv_dev(struct block_device *bdev)
 {
 	struct rnbd_srv_dev *dev;
 
···
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	strscpy(dev->id, id, sizeof(dev->id));
+	snprintf(dev->id, sizeof(dev->id), "%pg", bdev);
 	kref_init(&dev->kref);
 	INIT_LIST_HEAD(&dev->sess_dev_list);
 	mutex_init(&dev->lock);
···
 	int ret;
 	struct rnbd_srv_dev *new_dev, *dev;
 
-	new_dev = rnbd_srv_init_srv_dev(rnbd_dev->name);
+	new_dev = rnbd_srv_init_srv_dev(rnbd_dev->bdev);
 	if (IS_ERR(new_dev))
 		return new_dev;
 
···
 	 */
 	mutex_lock(&srv_dev->lock);
 	if (!srv_dev->dev_kobj.state_in_sysfs) {
-		ret = rnbd_srv_create_dev_sysfs(srv_dev, rnbd_dev->bdev,
-						 rnbd_dev->name);
+		ret = rnbd_srv_create_dev_sysfs(srv_dev, rnbd_dev->bdev);
 		if (ret) {
 			mutex_unlock(&srv_dev->lock);
 			rnbd_srv_err(srv_sess_dev,

drivers/block/rnbd/rnbd-srv.h

···
 /* rnbd-srv-sysfs.c */
 
 int rnbd_srv_create_dev_sysfs(struct rnbd_srv_dev *dev,
-			      struct block_device *bdev,
-			      const char *dir_name);
+			      struct block_device *bdev);
 void rnbd_srv_destroy_dev_sysfs(struct rnbd_srv_dev *dev);
 int rnbd_srv_create_dev_session_sysfs(struct rnbd_srv_sess_dev *sess_dev);
 void rnbd_srv_destroy_dev_session_sysfs(struct rnbd_srv_sess_dev *sess_dev);

drivers/block/sunvdc.c

···
 	return 0;
 
 out_cleanup_disk:
-	blk_cleanup_disk(g);
+	put_disk(g);
 out_free_tag:
 	blk_mq_free_tag_set(&port->tag_set);
 	return err;
···
 		del_timer_sync(&port->vio.timer);
 
 		del_gendisk(port->disk);
-		blk_cleanup_disk(port->disk);
+		put_disk(port->disk);
 		blk_mq_free_tag_set(&port->tag_set);
 
 		vdc_free_tx_ring(port);

drivers/block/swim.c

···
 	if (fs->registered)
 		del_gendisk(fs->disk);
 
-	blk_cleanup_disk(disk);
+	put_disk(disk);
 	blk_mq_free_tag_set(&fs->tag_set);
 }
 

drivers/block/swim3.c

···
 	return 0;
 
 out_cleanup_disk:
-	blk_cleanup_disk(disk);
+	put_disk(disk);
 out_free_tag_set:
 	blk_mq_free_tag_set(&fs->tag_set);
 out_unregister:

drivers/block/sx8.c

···
 
 	if (host->state > HST_DEV_ACTIVATE)
 		del_gendisk(disk);
-	blk_cleanup_disk(disk);
+	put_disk(disk);
 }
 
 static int carm_init_shm(struct carm_host *host)
···
 		clear_bit(0, &carm_major_alloc);
 	else if (host->major == 161)
 		clear_bit(1, &carm_major_alloc);
-	blk_cleanup_queue(host->oob_q);
+	blk_mq_destroy_queue(host->oob_q);
 	blk_mq_free_tag_set(&host->tag_set);
 err_out_dma_free:
 	dma_free_coherent(&pdev->dev, CARM_SHM_SIZE, host->shm, host->shm_dma);
···
 		clear_bit(0, &carm_major_alloc);
 	else if (host->major == 161)
 		clear_bit(1, &carm_major_alloc);
-	blk_cleanup_queue(host->oob_q);
+	blk_mq_destroy_queue(host->oob_q);
 	blk_mq_free_tag_set(&host->tag_set);
 	dma_free_coherent(&pdev->dev, CARM_SHM_SIZE, host->shm, host->shm_dma);
 	iounmap(host->mmio);

drivers/block/ublk_drv.c

···
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Userspace block device - block device which IO is handled from userspace
+ *
+ * Take full use of io_uring passthrough command for communicating with
+ * ublk userspace daemon(ublksrvd) for handling basic IO request.
+ *
+ * Copyright 2022 Ming Lei <[e-mail]>
+ *
+ * (part of code stolen from loop.c)
+ */
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/errno.h>
+#include <linux/major.h>
+#include <linux/wait.h>
+#include <linux/blkdev.h>
+#include <linux/init.h>
+#include <linux/swap.h>
+#include <linux/slab.h>
+#include <linux/compat.h>
+#include <linux/mutex.h>
+#include <linux/writeback.h>
+#include <linux/completion.h>
+#include <linux/highmem.h>
+#include <linux/sysfs.h>
+#include <linux/miscdevice.h>
+#include <linux/falloc.h>
+#include <linux/uio.h>
+#include <linux/ioprio.h>
+#include <linux/sched/mm.h>
+#include <linux/uaccess.h>
+#include <linux/cdev.h>
+#include <linux/io_uring.h>
+#include <linux/blk-mq.h>
+#include <linux/delay.h>
+#include <linux/mm.h>
+#include <asm/page.h>
+#include <linux/task_work.h>
+#include <uapi/linux/ublk_cmd.h>
+
+#define UBLK_MINORS		(1U << MINORBITS)
+
+/* All UBLK_F_* have to be included into UBLK_F_ALL */
+#define UBLK_F_ALL (UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_URING_CMD_COMP_IN_TASK)
+
+struct ublk_rq_data {
+	struct callback_head work;
+};
+
+struct ublk_uring_cmd_pdu {
+	struct request *req;
+};
+
+/*
+ * io command is active: sqe cmd is received, and its cqe isn't done
+ *
+ * If the flag is set, the io command is owned by ublk driver, and waited
+ * for incoming blk-mq request from the ublk block device.
+ *
+ * If the flag is cleared, the io command will be completed, and owned by
+ * ublk server.
+ */
+#define UBLK_IO_FLAG_ACTIVE	0x01
+
+/*
+ * IO command is completed via cqe, and it is being handled by ublksrv, and
+ * not committed yet
+ *
+ * Basically exclusively with UBLK_IO_FLAG_ACTIVE, so can be served for
+ * cross verification
+ */
+#define UBLK_IO_FLAG_OWNED_BY_SRV 0x02
+
+/*
+ * IO command is aborted, so this flag is set in case of
+ * !UBLK_IO_FLAG_ACTIVE.
+ *
+ * After this flag is observed, any pending or new incoming request
+ * associated with this io command will be failed immediately
+ */
+#define UBLK_IO_FLAG_ABORTED 0x04
+
+struct ublk_io {
+	/* userspace buffer address from io cmd */
+	__u64	addr;
+	unsigned int flags;
+	int res;
+
+	struct io_uring_cmd *cmd;
+};
+
+struct ublk_queue {
+	int q_id;
+	int q_depth;
+
+	unsigned long flags;
+	struct task_struct	*ubq_daemon;
+	char *io_cmd_buf;
+
+	unsigned long io_addr;	/* mapped vm address */
+	unsigned int max_io_sz;
+	bool abort_work_pending;
+	unsigned short nr_io_ready;	/* how many ios setup */
+	struct ublk_device *dev;
+	struct ublk_io ios[0];
+};
+
+#define UBLK_DAEMON_MONITOR_PERIOD	(5 * HZ)
+
+struct ublk_device {
+	struct gendisk		*ub_disk;
+
+	char	*__queues;
+
+	unsigned short  queue_size;
+	unsigned short  bs_shift;
+	struct ublksrv_ctrl_dev_info	dev_info;
+
+	struct blk_mq_tag_set	tag_set;
+
+	struct cdev		cdev;
+	struct device		cdev_dev;
+
+#define UB_STATE_OPEN		0
+#define UB_STATE_USED		1
+	unsigned long		state;
+	int			ub_number;
+
+	struct mutex		mutex;
+
+	spinlock_t		mm_lock;
+	struct mm_struct	*mm;
+
+	struct completion	completion;
+	unsigned int		nr_queues_ready;
+	atomic_t		nr_aborted_queues;
+
+	/*
+	 * Our ubq->daemon may be killed without any notification, so
+	 * monitor each queue's daemon periodically
+	 */
+	struct delayed_work	monitor_work;
+	struct work_struct	stop_work;
+};
+
+static dev_t ublk_chr_devt;
+static struct class *ublk_chr_class;
+
+static DEFINE_IDR(ublk_index_idr);
+static DEFINE_SPINLOCK(ublk_idr_lock);
+static wait_queue_head_t ublk_idr_wq;	/* wait until one idr is freed */
+
+static DEFINE_MUTEX(ublk_ctl_mutex);
+
+static struct miscdevice ublk_misc;
+
+static inline bool ublk_can_use_task_work(const struct ublk_queue *ubq)
+{
+	if (IS_BUILTIN(CONFIG_BLK_DEV_UBLK) &&
+			!(ubq->flags & UBLK_F_URING_CMD_COMP_IN_TASK))
+		return true;
+	return false;
+}
+
+static struct ublk_device *ublk_get_device(struct ublk_device *ub)
+{
+	if (kobject_get_unless_zero(&ub->cdev_dev.kobj))
+		return ub;
+	return NULL;
+}
+
+static void ublk_put_device(struct ublk_device *ub)
+{
+	put_device(&ub->cdev_dev);
+}
+
+static inline struct ublk_queue *ublk_get_queue(struct ublk_device *dev,
+		int qid)
+{
+       return (struct ublk_queue *)&(dev->__queues[qid * dev->queue_size]);
+}
+
+static inline bool ublk_rq_has_data(const struct request *rq)
+{
+	return rq->bio && bio_has_data(rq->bio);
+}
+
+static inline struct ublksrv_io_desc *ublk_get_iod(struct ublk_queue *ubq,
+		int tag)
+{
+	return (struct ublksrv_io_desc *)
+		&(ubq->io_cmd_buf[tag * sizeof(struct ublksrv_io_desc)]);
+}
+
+static inline char *ublk_queue_cmd_buf(struct ublk_device *ub, int q_id)
+{
+	return ublk_get_queue(ub, q_id)->io_cmd_buf;
+}
+
+static inline int ublk_queue_cmd_buf_size(struct ublk_device *ub, int q_id)
+{
+	struct ublk_queue *ubq = ublk_get_queue(ub, q_id);
+
+	return round_up(ubq->q_depth * sizeof(struct ublksrv_io_desc),
+			PAGE_SIZE);
+}
+
+static void ublk_free_disk(struct gendisk *disk)
+{
+	struct ublk_device *ub = disk->private_data;
+
+	clear_bit(UB_STATE_USED, &ub->state);
+	put_device(&ub->cdev_dev);
+}
+
+static const struct block_device_operations ub_fops = {
+	.owner =	THIS_MODULE,
+	.free_disk =	ublk_free_disk,
+};
+
+#define UBLK_MAX_PIN_PAGES	32
+
+struct ublk_map_data {
+	const struct ublk_queue *ubq;
+	const struct request *rq;
+	const struct ublk_io *io;
+	unsigned max_bytes;
+};
+
+struct ublk_io_iter {
+	struct page *pages[UBLK_MAX_PIN_PAGES];
+	unsigned pg_off;	/* offset in the 1st page in pages */
+	int nr_pages;		/* how many page pointers in pages */
+	struct bio *bio;
+	struct bvec_iter iter;
+};
+
+static inline unsigned ublk_copy_io_pages(struct ublk_io_iter *data,
+		unsigned max_bytes, bool to_vm)
+{
+	const unsigned total = min_t(unsigned, max_bytes,
+			PAGE_SIZE - data->pg_off +
+			((data->nr_pages - 1) << PAGE_SHIFT));
+	unsigned done = 0;
+	unsigned pg_idx = 0;
+
+	while (done < total) {
+		struct bio_vec bv = bio_iter_iovec(data->bio, data->iter);
+		const unsigned int bytes = min3(bv.bv_len, total - done,
+				(unsigned)(PAGE_SIZE - data->pg_off));
+		void *bv_buf = bvec_kmap_local(&bv);
+		void *pg_buf = kmap_local_page(data->pages[pg_idx]);
+
+		if (to_vm)
+			memcpy(pg_buf + data->pg_off, bv_buf, bytes);
+		else
+			memcpy(bv_buf, pg_buf + data->pg_off, bytes);
+
+		kunmap_local(pg_buf);
+		kunmap_local(bv_buf);
+
+		/* advance page array */
+		data->pg_off += bytes;
+		if (data->pg_off == PAGE_SIZE) {
+			pg_idx += 1;
+			data->pg_off = 0;
+		}
+
+		done += bytes;
+
+		/* advance bio */
+		bio_advance_iter_single(data->bio, &data->iter, bytes);
+		if (!data->iter.bi_size) {
+			data->bio = data->bio->bi_next;
+			if (data->bio == NULL)
+				break;
+			data->iter = data->bio->bi_iter;
+		}
+	}
+
+	return done;
+}
+
+static inline int ublk_copy_user_pages(struct ublk_map_data *data,
+		bool to_vm)
+{
+	const unsigned int gup_flags = to_vm ? FOLL_WRITE : 0;
+	const unsigned long start_vm = data->io->addr;
+	unsigned int done = 0;
+	struct ublk_io_iter iter = {
+		.pg_off	= start_vm & (PAGE_SIZE - 1),
+		.bio	= data->rq->bio,
+		.iter	= data->rq->bio->bi_iter,
+	};
+	const unsigned int nr_pages = round_up(data->max_bytes +
+			(start_vm & (PAGE_SIZE - 1)), PAGE_SIZE) >> PAGE_SHIFT;
+
+	while (done < nr_pages) {
+		const unsigned to_pin = min_t(unsigned, UBLK_MAX_PIN_PAGES,
+				nr_pages - done);
+		unsigned i, len;
+
+		iter.nr_pages = get_user_pages_fast(start_vm +
+				(done << PAGE_SHIFT), to_pin, gup_flags,
+				iter.pages);
+		if (iter.nr_pages <= 0)
+			return done == 0 ? iter.nr_pages : done;
+		len = ublk_copy_io_pages(&iter, data->max_bytes, to_vm);
+		for (i = 0; i < iter.nr_pages; i++) {
+			if (to_vm)
+				set_page_dirty(iter.pages[i]);
+			put_page(iter.pages[i]);
+		}
+		data->max_bytes -= len;
+		done += iter.nr_pages;
+	}
+
+	return done;
+}
+
+static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req,
+		struct ublk_io *io)
+{
+	const unsigned int rq_bytes = blk_rq_bytes(req);
+	/*
+	 * no zero copy, we delay copy WRITE request data into ublksrv
+	 * context and the big benefit is that pinning pages in current
+	 * context is pretty fast, see ublk_pin_user_pages
+	 */
+	if (req_op(req) != REQ_OP_WRITE && req_op(req) != REQ_OP_FLUSH)
+		return rq_bytes;
+
+	if (ublk_rq_has_data(req)) {
+		struct ublk_map_data data = {
+			.ubq	=	ubq,
+			.rq	=	req,
+			.io	=	io,
+			.max_bytes =	rq_bytes,
+		};
+
+		ublk_copy_user_pages(&data, true);
+
+		return rq_bytes - data.max_bytes;
+	}
+	return rq_bytes;
+}
+
+static int ublk_unmap_io(const struct ublk_queue *ubq,
+		const struct request *req,
+		struct ublk_io *io)
+{
+	const unsigned int rq_bytes = blk_rq_bytes(req);
+
+	if (req_op(req) == REQ_OP_READ && ublk_rq_has_data(req)) {
+		struct ublk_map_data data = {
+			.ubq	=	ubq,
+			.rq	=	req,
+			.io	=	io,
+			.max_bytes =	io->res,
+		};
+
+		WARN_ON_ONCE(io->res > rq_bytes);
+
+		ublk_copy_user_pages(&data, false);
+
+		return io->res - data.max_bytes;
+	}
+	return rq_bytes;
+}
+
+static inline unsigned int ublk_req_build_flags(struct request *req)
+{
+	unsigned flags = 0;
+
+	if (req->cmd_flags & REQ_FAILFAST_DEV)
+		flags |= UBLK_IO_F_FAILFAST_DEV;
+
+	if (req->cmd_flags & REQ_FAILFAST_TRANSPORT)
+		flags |= UBLK_IO_F_FAILFAST_TRANSPORT;
+
+	if (req->cmd_flags & REQ_FAILFAST_DRIVER)
+		flags |= UBLK_IO_F_FAILFAST_DRIVER;
+
+	if (req->cmd_flags & REQ_META)
+		flags |= UBLK_IO_F_META;
+
+	if (req->cmd_flags & REQ_FUA)
+		flags |= UBLK_IO_F_FUA;
+
+	if (req->cmd_flags & REQ_NOUNMAP)
+		flags |= UBLK_IO_F_NOUNMAP;
+
+	if (req->cmd_flags & REQ_SWAP)
+		flags |= UBLK_IO_F_SWAP;
+
+	return flags;
+}
+
+static blk_status_t ublk_setup_iod(struct ublk_queue *ubq, struct request *req)
+{
+	struct ublksrv_io_desc *iod = ublk_get_iod(ubq, req->tag);
+	struct ublk_io *io = &ubq->ios[req->tag];
+	u32 ublk_op;
+
+	switch (req_op(req)) {
+	case REQ_OP_READ:
+		ublk_op = UBLK_IO_OP_READ;
+		break;
+	case REQ_OP_WRITE:
+		ublk_op = UBLK_IO_OP_WRITE;
+		break;
+	case REQ_OP_FLUSH:
+		ublk_op = UBLK_IO_OP_FLUSH;
+		break;
+	case REQ_OP_DISCARD:
+		ublk_op = UBLK_IO_OP_DISCARD;
+		break;
+	case REQ_OP_WRITE_ZEROES:
+		ublk_op = UBLK_IO_OP_WRITE_ZEROES;
+		break;
+	default:
+		return BLK_STS_IOERR;
+	}
+
+	/* need to translate since kernel may change */
+	iod->op_flags = ublk_op | ublk_req_build_flags(req);
+	iod->nr_sectors = blk_rq_sectors(req);
+	iod->start_sector = blk_rq_pos(req);
+	iod->addr = io->addr;
+
+	return BLK_STS_OK;
+}
+
+static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu(
+		struct io_uring_cmd *ioucmd)
+{
+	return (struct ublk_uring_cmd_pdu *)&ioucmd->pdu;
+}
+
+static bool ubq_daemon_is_dying(struct ublk_queue *ubq)
+{
+	return ubq->ubq_daemon->flags & PF_EXITING;
+}
+
+/* todo: handle partial completion */
+static void ublk_complete_rq(struct request *req)
+{
+	struct ublk_queue *ubq = req->mq_hctx->driver_data;
+	struct ublk_io *io = &ubq->ios[req->tag];
+	unsigned int unmapped_bytes;
+
+	/* failed read IO if nothing is read */
+	if (!io->res && req_op(req) == REQ_OP_READ)
+		io->res = -EIO;
+
+	if (io->res < 0) {
+		blk_mq_end_request(req, errno_to_blk_status(io->res));
+		return;
+	}
+
+	/*
+	 * FLUSH or DISCARD usually won't return bytes returned, so end them
+	 * directly.
+	 *
+	 * Both the two needn't unmap.
+	 */
+	if (req_op(req) != REQ_OP_READ && req_op(req) != REQ_OP_WRITE) {
+		blk_mq_end_request(req, BLK_STS_OK);
+		return;
+	}
+
+	/* for READ request, writing data in iod->addr to rq buffers */
+	unmapped_bytes = ublk_unmap_io(ubq, req, io);
+
+	/*
+	 * Extremely impossible since we got data filled in just before
+	 *
+	 * Re-read simply for this unlikely case.
+	 */
+	if (unlikely(unmapped_bytes < io->res))
+		io->res = unmapped_bytes;
+
+	if (blk_update_request(req, BLK_STS_OK, io->res))
+		blk_mq_requeue_request(req, true);
+	else
+		__blk_mq_end_request(req, BLK_STS_OK);
+}
+
+/*
+ * __ublk_fail_req() may be called from abort context or ->ubq_daemon
+ * context during exiting, so lock is required.
+ *
+ * Also aborting may not be started yet, keep in mind that one failed
+ * request may be issued by block layer again.
+ */
+static void __ublk_fail_req(struct ublk_io *io, struct request *req)
+{
+	WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);
+
+	if (!(io->flags & UBLK_IO_FLAG_ABORTED)) {
+		io->flags |= UBLK_IO_FLAG_ABORTED;
+		blk_mq_end_request(req, BLK_STS_IOERR);
+	}
+}
+
+#define UBLK_REQUEUE_DELAY_MS	3
+
+static inline void __ublk_rq_task_work(struct request *req)
+{
+	struct ublk_queue *ubq = req->mq_hctx->driver_data;
+	struct ublk_device *ub = ubq->dev;
+	int tag = req->tag;
+	struct ublk_io *io = &ubq->ios[tag];
+	bool task_exiting = current != ubq->ubq_daemon ||
+		(current->flags & PF_EXITING);
+	unsigned int mapped_bytes;
+
+	pr_devel("%s: complete: op %d, qid %d tag %d io_flags %x addr %llx\n",
+			__func__, io->cmd->cmd_op, ubq->q_id, req->tag, io->flags,
+			ublk_get_iod(ubq, req->tag)->addr);
+
+	if (unlikely(task_exiting)) {
+		blk_mq_end_request(req, BLK_STS_IOERR);
+		mod_delayed_work(system_wq, &ub->monitor_work, 0);
+		return;
+	}
+
+	mapped_bytes = ublk_map_io(ubq, req, io);
+
+	/* partially mapped, update io descriptor */
+	if (unlikely(mapped_bytes != blk_rq_bytes(req))) {
+		/*
+		 * Nothing mapped, retry until we succeed.
+		 *
+		 * We may never succeed in mapping any bytes here because
+		 * of OOM. TODO: reserve one buffer with single page pinned
+		 * for providing forward progress guarantee.
+		 */
+		if (unlikely(!mapped_bytes)) {
+			blk_mq_requeue_request(req, false);
+			blk_mq_delay_kick_requeue_list(req->q,
+					UBLK_REQUEUE_DELAY_MS);
+			return;
+		}
+
+		ublk_get_iod(ubq, req->tag)->nr_sectors =
+			mapped_bytes >> 9;
+	}
+
+	/* mark this cmd owned by ublksrv */
+	io->flags |= UBLK_IO_FLAG_OWNED_BY_SRV;
+
+	/*
+	 * clear ACTIVE since we are done with this sqe/cmd slot
+	 * We can only accept io cmd in case of being not active.
+	 */
+	io->flags &= ~UBLK_IO_FLAG_ACTIVE;
+
+	/* tell ublksrv one io request is coming */
+	io_uring_cmd_done(io->cmd, UBLK_IO_RES_OK, 0);
+}
+
+static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd)
+{
+	struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
+
+	__ublk_rq_task_work(pdu->req);
+}
+
+static void ublk_rq_task_work_fn(struct callback_head *work)
+{
+	struct ublk_rq_data *data = container_of(work,
+			struct ublk_rq_data, work);
+	struct request *req = blk_mq_rq_from_pdu(data);
+
+	__ublk_rq_task_work(req);
+}
+
+static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
+		const struct blk_mq_queue_data *bd)
+{
+	struct ublk_queue *ubq = hctx->driver_data;
+	struct request *rq = bd->rq;
+	blk_status_t res;
+
+	/* fill iod to slot in io cmd buffer */
+	res = ublk_setup_iod(ubq, rq);
+	if (unlikely(res != BLK_STS_OK))
+		return BLK_STS_IOERR;
+
+	blk_mq_start_request(bd->rq);
+
+	if (unlikely(ubq_daemon_is_dying(ubq))) {
+ fail:
+		mod_delayed_work(system_wq, &ubq->dev->monitor_work, 0);
+		return BLK_STS_IOERR;
+	}
+
+	if (ublk_can_use_task_work(ubq)) {
+		struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq);
+		enum task_work_notify_mode notify_mode = bd->last ?
+			TWA_SIGNAL_NO_IPI : TWA_NONE;
+
+		if (task_work_add(ubq->ubq_daemon, &data->work, notify_mode))
+			goto fail;
+	} else {
+		struct io_uring_cmd *cmd = ubq->ios[rq->tag].cmd;
+		struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
+
+		pdu->req = rq;
+		io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb);
+	}
+
+	return BLK_STS_OK;
+}
+
+static void ublk_commit_rqs(struct blk_mq_hw_ctx *hctx)
+{
+	struct ublk_queue *ubq = hctx->driver_data;
+
+	if (ublk_can_use_task_work(ubq))
+		__set_notify_signal(ubq->ubq_daemon);
+}
+
+static int ublk_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data,
+		unsigned int hctx_idx)
+{
+	struct ublk_device *ub = driver_data;
+	struct ublk_queue *ubq = ublk_get_queue(ub, hctx->queue_num);
+
+	hctx->driver_data = ubq;
+	return 0;
+}
+
+static int ublk_init_rq(struct blk_mq_tag_set *set, struct request *req,
+		unsigned int hctx_idx, unsigned int numa_node)
+{
+	struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
+
+	init_task_work(&data->work, ublk_rq_task_work_fn);
+	return 0;
+}
+
+static const struct blk_mq_ops ublk_mq_ops = {
+	.queue_rq       = ublk_queue_rq,
+	.commit_rqs     = ublk_commit_rqs,
+	.init_hctx	= ublk_init_hctx,
+	.init_request   = ublk_init_rq,
+};
+
+static int ublk_ch_open(struct inode *inode, struct file *filp)
+{
+	struct ublk_device *ub = container_of(inode->i_cdev,
+			struct ublk_device, cdev);
+
+	if (test_and_set_bit(UB_STATE_OPEN, &ub->state))
+		return -EBUSY;
+	filp->private_data = ub;
+	return 0;
+}
+
+static int ublk_ch_release(struct inode *inode, struct file *filp)
+{
+	struct ublk_device *ub = filp->private_data;
+
+	clear_bit(UB_STATE_OPEN, &ub->state);
+	return 0;
+}
+
+/* map pre-allocated per-queue cmd buffer to ublksrv daemon */
+static int ublk_ch_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct ublk_device *ub = filp->private_data;
+	size_t sz = vma->vm_end - vma->vm_start;
+	unsigned max_sz = UBLK_MAX_QUEUE_DEPTH * sizeof(struct ublksrv_io_desc);
+	unsigned long pfn, end, phys_off = vma->vm_pgoff << PAGE_SHIFT;
+	int q_id, ret = 0;
+
+	spin_lock(&ub->mm_lock);
+	if (!ub->mm)
+		ub->mm = current->mm;
+	if (current->mm != ub->mm)
+		ret = -EINVAL;
+	spin_unlock(&ub->mm_lock);
+
+	if (ret)
+		return ret;
+
+	if (vma->vm_flags & VM_WRITE)
+		return -EPERM;
+
+	end = UBLKSRV_CMD_BUF_OFFSET + ub->dev_info.nr_hw_queues * max_sz;
+	if (phys_off < UBLKSRV_CMD_BUF_OFFSET || phys_off >= end)
+		return -EINVAL;
+
+	q_id = (phys_off - UBLKSRV_CMD_BUF_OFFSET) / max_sz;
+	pr_devel("%s: qid %d, pid %d, addr %lx pg_off %lx sz %lu\n",
+			__func__, q_id, current->pid, vma->vm_start,
+			phys_off, (unsigned long)sz);
+
+	if (sz != ublk_queue_cmd_buf_size(ub, q_id))
+		return -EINVAL;
+
+	pfn = virt_to_phys(ublk_queue_cmd_buf(ub, q_id)) >> PAGE_SHIFT;
+	return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot);
+}
+
+static void ublk_commit_completion(struct ublk_device *ub,
+		struct ublksrv_io_cmd *ub_cmd)
+{
+	u32 qid = ub_cmd->q_id, tag = ub_cmd->tag;
+	struct ublk_queue *ubq = ublk_get_queue(ub, qid);
+	struct ublk_io *io = &ubq->ios[tag];
+	struct request *req;
+
+	/* now this cmd slot is owned by nbd driver */
+	io->flags &= ~UBLK_IO_FLAG_OWNED_BY_SRV;
+	io->res = ub_cmd->result;
+
+	/* find the io request and complete */
+	req = blk_mq_tag_to_rq(ub->tag_set.tags[qid], tag);
+
+	if (req && likely(!blk_should_fake_timeout(req->q)))
+		ublk_complete_rq(req);
+}
+
+/*
+ * When ->ubq_daemon is exiting, either new request is ended immediately,
+ * or any queued io command is drained, so it is safe to abort queue
+ * lockless
+ */
+static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq)
+{
+	int i;
+
+	if (!ublk_get_device(ub))
+		return;
+
+	for (i = 0; i < ubq->q_depth; i++) {
+		struct ublk_io *io = &ubq->ios[i];
+
+		if (!(io->flags & UBLK_IO_FLAG_ACTIVE)) {
+			struct request *rq;
+
+			/*
+			 * Either we fail the request or ublk_rq_task_work_fn
+			 * will do it
+			 */
+			rq = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], i);
+			if (rq)
+				__ublk_fail_req(io, rq);
+		}
+	}
+	ublk_put_device(ub);
+}
+
+static void ublk_daemon_monitor_work(struct work_struct *work)
+{
+	struct ublk_device *ub =
+		container_of(work, struct ublk_device, monitor_work.work);
+	int i;
+
+	for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
+		struct ublk_queue *ubq = ublk_get_queue(ub, i);
+
+		if (ubq_daemon_is_dying(ubq)) {
+			schedule_work(&ub->stop_work);
+
+			/* abort queue is for making forward progress */
+			ublk_abort_queue(ub, ubq);
+		}
+	}
+
+	/*
+	 * We can't schedule monitor work after ublk_remove() is started.
+	 *
+	 * No need ub->mutex, monitor work are canceled after state is marked
+	 * as DEAD, so DEAD state is observed reliably.
+	 */
+	if (ub->dev_info.state != UBLK_S_DEV_DEAD)
+		schedule_delayed_work(&ub->monitor_work,
+				UBLK_DAEMON_MONITOR_PERIOD);
+}
+
+static void ublk_cancel_queue(struct ublk_queue *ubq)
+{
+	int i;
+
+	for (i = 0; i < ubq->q_depth; i++) {
+		struct ublk_io *io = &ubq->ios[i];
+
+		if (io->flags & UBLK_IO_FLAG_ACTIVE)
+			io_uring_cmd_done(io->cmd, UBLK_IO_RES_ABORT, 0);
+	}
+}
+
+/* Cancel all pending commands, must be called after del_gendisk() returns */
+static void ublk_cancel_dev(struct ublk_device *ub)
+{
+	int i;
+
+	for (i = 0; i < ub->dev_info.nr_hw_queues; i++)
+		ublk_cancel_queue(ublk_get_queue(ub, i));
+}
+
+static void ublk_stop_dev(struct ublk_device *ub)
+{
+	mutex_lock(&ub->mutex);
+	if (ub->dev_info.state != UBLK_S_DEV_LIVE)
+		goto unlock;
+
+	del_gendisk(ub->ub_disk);
+	ub->dev_info.state = UBLK_S_DEV_DEAD;
+	ub->dev_info.ublksrv_pid = -1;
+	ublk_cancel_dev(ub);
+	put_disk(ub->ub_disk);
+	ub->ub_disk = NULL;
+ unlock:
+	mutex_unlock(&ub->mutex);
+	cancel_delayed_work_sync(&ub->monitor_work);
+}
+
+static inline bool ublk_queue_ready(struct ublk_queue *ubq)
+{
+	return ubq->nr_io_ready == ubq->q_depth;
+}
+
+/* device can only be started after all IOs are ready */
+static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq)
+{
+	mutex_lock(&ub->mutex);
+	ubq->nr_io_ready++;
+	if (ublk_queue_ready(ubq)) {
+		ubq->ubq_daemon = current;
+		get_task_struct(ubq->ubq_daemon);
+		ub->nr_queues_ready++;
+	}
+	if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues)
+		complete_all(&ub->completion);
+	mutex_unlock(&ub->mutex);
+}
+
+static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
+{
+	struct ublksrv_io_cmd *ub_cmd = (struct ublksrv_io_cmd *)cmd->cmd;
+	struct ublk_device *ub = cmd->file->private_data;
+	struct ublk_queue *ubq;
+	struct ublk_io *io;
+	u32 cmd_op = cmd->cmd_op;
+	unsigned tag = ub_cmd->tag;
+	int ret = -EINVAL;
+
+	pr_devel("%s: received: cmd op %d queue %d tag %d result %d\n",
+			__func__, cmd->cmd_op, ub_cmd->q_id, tag,
+			ub_cmd->result);
+
+	if (!(issue_flags & IO_URING_F_SQE128))
+		goto out;
+
+	if (ub_cmd->q_id >= ub->dev_info.nr_hw_queues)
+		goto out;
+
+	ubq = ublk_get_queue(ub, ub_cmd->q_id);
+	if (!ubq || ub_cmd->q_id != ubq->q_id)
+		goto out;
+
+	if (ubq->ubq_daemon && ubq->ubq_daemon != current)
+		goto out;
+
+	if (tag >= ubq->q_depth)
+		goto out;
+
+	io = &ubq->ios[tag];
+
+	/* there is pending io cmd, something must be wrong */
+	if (io->flags & UBLK_IO_FLAG_ACTIVE) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	switch (cmd_op) {
+	case UBLK_IO_FETCH_REQ:
+		/* UBLK_IO_FETCH_REQ is only allowed before queue is setup */
+		if (ublk_queue_ready(ubq)) {
+			ret = -EBUSY;
+			goto out;
+		}
+		/*
+		 * The io is being handled by server, so COMMIT_RQ is expected
+		 * instead of FETCH_REQ
+		 */
+		if (io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)
+			goto out;
+		/* FETCH_RQ has to provide IO buffer */
+		if (!ub_cmd->addr)
+			goto out;
+		io->cmd = cmd;
+		io->flags |= UBLK_IO_FLAG_ACTIVE;
+		io->addr = ub_cmd->addr;
+
+		ublk_mark_io_ready(ub, ubq);
+		break;
+	case UBLK_IO_COMMIT_AND_FETCH_REQ:
+		/* FETCH_RQ has to provide IO buffer */
+		if (!ub_cmd->addr)
+			goto out;
+		if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
+			goto out;
+		io->addr = ub_cmd->addr;
+		io->flags |= UBLK_IO_FLAG_ACTIVE;
+		io->cmd = cmd;
+		ublk_commit_completion(ub, ub_cmd);
+		break;
+	default:
+		goto out;
+	}
+	return -EIOCBQUEUED;
+
+ out:
+	io_uring_cmd_done(cmd, ret, 0);
+	pr_devel("%s: complete: cmd op %d, tag %d ret %x io_flags %x\n",
+			__func__, cmd_op, tag, ret, io->flags);
+	return -EIOCBQUEUED;
+}
+
+static const struct file_operations ublk_ch_fops = {
+	.owner = THIS_MODULE,
+	.open = ublk_ch_open,
+	.release = ublk_ch_release,
+	.llseek = no_llseek,
+	.uring_cmd = ublk_ch_uring_cmd,
+	.mmap = ublk_ch_mmap,
+};
+
+static void ublk_deinit_queue(struct ublk_device *ub, int q_id)
+{
+	int size = ublk_queue_cmd_buf_size(ub, q_id);
+	struct ublk_queue *ubq = ublk_get_queue(ub, q_id);
+
+	if (ubq->ubq_daemon)
+		put_task_struct(ubq->ubq_daemon);
+	if (ubq->io_cmd_buf)
+		free_pages((unsigned long)ubq->io_cmd_buf, get_order(size));
+}
+
+static int ublk_init_queue(struct ublk_device *ub, int q_id)
+{
+	struct ublk_queue *ubq = ublk_get_queue(ub, q_id);
+	gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO;
+	void *ptr;
+	int size;
+
+	ubq->flags = ub->dev_info.flags;
+	ubq->q_id = q_id;
+	ubq->q_depth = ub->dev_info.queue_depth;
+	size = ublk_queue_cmd_buf_size(ub, q_id);
+
+	ptr = (void *) __get_free_pages(gfp_flags, get_order(size));
+	if (!ptr)
+		return -ENOMEM;
+
+	ubq->io_cmd_buf = ptr;
+	ubq->dev = ub;
+	return 0;
+}
+
+static void ublk_deinit_queues(struct ublk_device *ub)
+{
+	int nr_queues = ub->dev_info.nr_hw_queues;
+	int i;
+
+	if (!ub->__queues)
+		return;
+
+	for (i = 0; i < nr_queues; i++)
+		ublk_deinit_queue(ub, i);
+	kfree(ub->__queues);
+}
+
+static int ublk_init_queues(struct ublk_device *ub)
+{
+	int nr_queues = ub->dev_info.nr_hw_queues;
+	int depth = ub->dev_info.queue_depth;
+	int ubq_size = sizeof(struct ublk_queue) + depth * sizeof(struct ublk_io);
+	int i, ret = -ENOMEM;
+
+	ub->queue_size = ubq_size;
+	ub->__queues = kcalloc(nr_queues, ubq_size, GFP_KERNEL);
+	if (!ub->__queues)
+		return ret;
+
+	for (i = 0; i < nr_queues; i++) {
+		if (ublk_init_queue(ub, i))
+			goto fail;
+	}
+
+	init_completion(&ub->completion);
+	return 0;
+
+ fail:
+	ublk_deinit_queues(ub);
+	return ret;
+}
+
+static int ublk_alloc_dev_number(struct ublk_device *ub, int idx)
+{
+	int i = idx;
+	int err;
+
+	spin_lock(&ublk_idr_lock);
+	/* allocate id, if @id >= 0, we're requesting that specific id */
+	if (i >= 0) {
+		err = idr_alloc(&ublk_index_idr, ub, i, i + 1, GFP_NOWAIT);
+		if (err == -ENOSPC)
+			err = -EEXIST;
+	} else {
+		err = idr_alloc(&ublk_index_idr, ub, 0, 0, GFP_NOWAIT);
+	}
+	spin_unlock(&ublk_idr_lock);
+
+	if (err >= 0)
+		ub->ub_number = err;
+
+	return err;
+}
+
+static void ublk_free_dev_number(struct ublk_device *ub)
+{
+	spin_lock(&ublk_idr_lock);
+	idr_remove(&ublk_index_idr, ub->ub_number);
+	wake_up_all(&ublk_idr_wq);
+	spin_unlock(&ublk_idr_lock);
+}
+
+static void ublk_cdev_rel(struct device *dev)
+{
+	struct ublk_device *ub = container_of(dev, struct ublk_device, cdev_dev);
+
+	blk_mq_free_tag_set(&ub->tag_set);
+	ublk_deinit_queues(ub);
+	ublk_free_dev_number(ub);
+	mutex_destroy(&ub->mutex);
+	kfree(ub);
+}
+
+static int ublk_add_chdev(struct ublk_device *ub)
+{
+	struct device *dev = &ub->cdev_dev;
+	int minor = ub->ub_number;
+	int ret;
+
+	dev->parent = ublk_misc.this_device;
+	dev->devt = MKDEV(MAJOR(ublk_chr_devt), minor);
+	dev->class = ublk_chr_class;
+	dev->release = ublk_cdev_rel;
+	device_initialize(dev);
+
+	ret = dev_set_name(dev, "ublkc%d", minor);
+	if (ret)
+		goto fail;
+
+	cdev_init(&ub->cdev, &ublk_ch_fops);
+	ret = cdev_device_add(&ub->cdev, dev);
+	if (ret)
+		goto fail;
+	return 0;
+ fail:
+	put_device(dev);
+	return ret;
+}
+
+static void ublk_stop_work_fn(struct work_struct *work)
+{
+	struct ublk_device *ub =
+		container_of(work, struct ublk_device, stop_work);
+
+	ublk_stop_dev(ub);
+}
+
+/* align maximum I/O size to PAGE_SIZE */
+static void ublk_align_max_io_size(struct ublk_device *ub)
+{
+	unsigned int max_rq_bytes = ub->dev_info.rq_max_blocks << ub->bs_shift;
+
+	ub->dev_info.rq_max_blocks =
+		round_down(max_rq_bytes, PAGE_SIZE) >> ub->bs_shift;
+}
+
+static int ublk_add_tag_set(struct ublk_device *ub)
+{
+	ub->tag_set.ops = &ublk_mq_ops;
+	ub->tag_set.nr_hw_queues = ub->dev_info.nr_hw_queues;
+	ub->tag_set.queue_depth = ub->dev_info.queue_depth;
+	ub->tag_set.numa_node = NUMA_NO_NODE;
+	ub->tag_set.cmd_size = sizeof(struct ublk_rq_data);
+	ub->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	ub->tag_set.driver_data = ub;
+	return blk_mq_alloc_tag_set(&ub->tag_set);
+}
+
+static void ublk_remove(struct ublk_device *ub)
+{
+	ublk_stop_dev(ub);
+	cancel_work_sync(&ub->stop_work);
+	cdev_device_del(&ub->cdev, &ub->cdev_dev);
+	put_device(&ub->cdev_dev);
+}
+
+static struct ublk_device *ublk_get_device_from_id(int idx)
+{
+	struct ublk_device *ub = NULL;
+
+	if (idx < 0)
+		return NULL;
+
+	spin_lock(&ublk_idr_lock);
+	ub = idr_find(&ublk_index_idr, idx);
+	if (ub)
+		ub = ublk_get_device(ub);
+	spin_unlock(&ublk_idr_lock);
+
+	return ub;
+}
+
+static int ublk_ctrl_start_dev(struct io_uring_cmd *cmd)
+{
+	struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
+	int ublksrv_pid = (int)header->data[0];
+	unsigned long dev_blocks = header->data[1];
+	struct ublk_device *ub;
+	struct gendisk *disk;
+	int ret = -EINVAL;
+
+	if (ublksrv_pid <= 0)
+		return -EINVAL;
+
+	ub = ublk_get_device_from_id(header->dev_id);
+	if (!ub)
+		return -EINVAL;
+
+	wait_for_completion_interruptible(&ub->completion);
+
+	schedule_delayed_work(&ub->monitor_work, UBLK_DAEMON_MONITOR_PERIOD);
+
+	mutex_lock(&ub->mutex);
+	if (ub->dev_info.state == UBLK_S_DEV_LIVE ||
+	    test_bit(UB_STATE_USED, &ub->state)) {
+		ret = -EEXIST;
+		goto out_unlock;
+	}
+
+	/* We may get disk size updated */
+	if (dev_blocks)
+		ub->dev_info.dev_blocks = dev_blocks;
+
+	disk = blk_mq_alloc_disk(&ub->tag_set, ub);
+	if (IS_ERR(disk)) {
+		ret = PTR_ERR(disk);
+		goto out_unlock;
+	}
+	sprintf(disk->disk_name, "ublkb%d", ub->ub_number);
+	disk->fops = &ub_fops;
+	disk->private_data = ub;
+
+	blk_queue_logical_block_size(disk->queue, ub->dev_info.block_size);
+	blk_queue_physical_block_size(disk->queue, ub->dev_info.block_size);
+	blk_queue_io_min(disk->queue, ub->dev_info.block_size);
+	blk_queue_max_hw_sectors(disk->queue,
+		ub->dev_info.rq_max_blocks << (ub->bs_shift - 9));
+	disk->queue->limits.discard_granularity = PAGE_SIZE;
+	blk_queue_max_discard_sectors(disk->queue, UINT_MAX >> 9);
+	blk_queue_max_write_zeroes_sectors(disk->queue, UINT_MAX >> 9);
+
+	set_capacity(disk, ub->dev_info.dev_blocks << (ub->bs_shift - 9));
+
+	ub->dev_info.ublksrv_pid = ublksrv_pid;
+	ub->ub_disk = disk;
+	get_device(&ub->cdev_dev);
+	ret = add_disk(disk);
+	if (ret) {
+		put_disk(disk);
+		goto out_unlock;
+	}
+	set_bit(UB_STATE_USED, &ub->state);
+	ub->dev_info.state = UBLK_S_DEV_LIVE;
+out_unlock:
+	mutex_unlock(&ub->mutex);
+	ublk_put_device(ub);
+	return ret;
+}
+
+static int ublk_ctrl_get_queue_affinity(struct io_uring_cmd *cmd)
+{
+	struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
+	void __user *argp = (void __user *)(unsigned long)header->addr;
+	struct ublk_device *ub;
+	cpumask_var_t cpumask;
+	unsigned long queue;
+	unsigned int retlen;
+	unsigned int i;
+	int ret = -EINVAL;
+	
+	if (header->len * BITS_PER_BYTE < nr_cpu_ids)
+		return -EINVAL;
+	if (header->len & (sizeof(unsigned long)-1))
+		return -EINVAL;
+	if (!header->addr)
+		return -EINVAL;
+
+	ub = ublk_get_device_from_id(header->dev_id);
+	if (!ub)
+		return -EINVAL;
+
+	queue = header->data[0];
+	if (queue >= ub->dev_info.nr_hw_queues)
+		goto out_put_device;
+
+	ret = -ENOMEM;
+	if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL))
+		goto out_put_device;
+
+	for_each_possible_cpu(i) {
+		if (ub->tag_set.map[HCTX_TYPE_DEFAULT].mq_map[i] == queue)
+			cpumask_set_cpu(i, cpumask);
+	}
+
+	ret = -EFAULT;
+	retlen = min_t(unsigned short, header->len, cpumask_size());
+	if (copy_to_user(argp, cpumask, retlen))
+		goto out_free_cpumask;
+	if (retlen != header->len &&
+	    clear_user(argp + retlen, header->len - retlen))
+		goto out_free_cpumask;
+
+	ret = 0;
+out_free_cpumask:
+	free_cpumask_var(cpumask);
+out_put_device:
+	ublk_put_device(ub);
+	return ret;
+}
+
+static inline void ublk_dump_dev_info(struct ublksrv_ctrl_dev_info *info)
+{
+	pr_devel("%s: dev id %d flags %llx\n", __func__,
+			info->dev_id, info->flags);
+	pr_devel("\t nr_hw_queues %d queue_depth %d block size %d dev_capacity %lld\n",
+			info->nr_hw_queues, info->queue_depth,
+			info->block_size, info->dev_blocks);
+}
+
+static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
+{
+	struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
+	void __user *argp = (void __user *)(unsigned long)header->addr;
+	struct ublksrv_ctrl_dev_info info;
+	struct ublk_device *ub;
+	int ret = -EINVAL;
+
+	if (header->len < sizeof(info) || !header->addr)
+		return -EINVAL;
+	if (header->queue_id != (u16)-1) {
+		pr_warn("%s: queue_id is wrong %x\n",
+			__func__, header->queue_id);
+		return -EINVAL;
+	}
+	if (copy_from_user(&info, argp, sizeof(info)))
+		return -EFAULT;
+	ublk_dump_dev_info(&info);
+	if (header->dev_id != info.dev_id) {
+		pr_warn("%s: dev id not match %u %u\n",
+			__func__, header->dev_id, info.dev_id);
+		return -EINVAL;
+	}
+
+	ret = mutex_lock_killable(&ublk_ctl_mutex);
+	if (ret)
+		return ret;
+
+	ret = -ENOMEM;
+	ub = kzalloc(sizeof(*ub), GFP_KERNEL);
+	if (!ub)
+		goto out_unlock;
+	mutex_init(&ub->mutex);
+	spin_lock_init(&ub->mm_lock);
+	INIT_WORK(&ub->stop_work, ublk_stop_work_fn);
+	INIT_DELAYED_WORK(&ub->monitor_work, ublk_daemon_monitor_work);
+
+	ret = ublk_alloc_dev_number(ub, header->dev_id);
+	if (ret < 0)
+		goto out_free_ub;
+
+	memcpy(&ub->dev_info, &info, sizeof(info));
+
+	/* update device id */
+	ub->dev_info.dev_id = ub->ub_number;
+
+	/*
+	 * 64bit flags will be copied back to userspace as feature
+	 * negotiation result, so have to clear flags which driver
+	 * doesn't support yet, then userspace can get correct flags
+	 * (features) to handle.
+	 */
+	ub->dev_info.flags &= UBLK_F_ALL;
+
+	/* We are not ready to support zero copy */
+	ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY;
+
+	ub->bs_shift = ilog2(ub->dev_info.block_size);
+	ub->dev_info.nr_hw_queues = min_t(unsigned int,
+			ub->dev_info.nr_hw_queues, nr_cpu_ids);
+	ublk_align_max_io_size(ub);
+
+	ret = ublk_init_queues(ub);
+	if (ret)
+		goto out_free_dev_number;
+
+	ret = ublk_add_tag_set(ub);
+	if (ret)
+		goto out_deinit_queues;
+
+	ret = -EFAULT;
+	if (copy_to_user(argp, &ub->dev_info, sizeof(info)))
+		goto out_free_tag_set;
+
+	/*
+	 * Add the char dev so that ublksrv daemon can be setup.
+	 * ublk_add_chdev() will cleanup everything if it fails.
+	 */
+	ret = ublk_add_chdev(ub);
+	goto out_unlock;
+
+out_free_tag_set:
+	blk_mq_free_tag_set(&ub->tag_set);
+out_deinit_queues:
+	ublk_deinit_queues(ub);
+out_free_dev_number:
+	ublk_free_dev_number(ub);
+out_free_ub:
+	mutex_destroy(&ub->mutex);
+	kfree(ub);
+out_unlock:
+	mutex_unlock(&ublk_ctl_mutex);
+	return ret;
+}
+
+static inline bool ublk_idr_freed(int id)
+{
+	void *ptr;
+
+	spin_lock(&ublk_idr_lock);
+	ptr = idr_find(&ublk_index_idr, id);
+	spin_unlock(&ublk_idr_lock);
+
+	return ptr == NULL;
+}
+
+static int ublk_ctrl_del_dev(int idx)
+{
+	struct ublk_device *ub;
+	int ret;
+
+	ret = mutex_lock_killable(&ublk_ctl_mutex);
+	if (ret)
+		return ret;
+
+	ub = ublk_get_device_from_id(idx);
+	if (ub) {
+		ublk_remove(ub);
+		ublk_put_device(ub);
+		ret = 0;
+	} else {
+		ret = -ENODEV;
+	}
+
+	/*
+	 * Wait until the idr is removed, then it can be reused after
+	 * DEL_DEV command is returned.
+	 */
+	if (!ret)
+		wait_event(ublk_idr_wq, ublk_idr_freed(idx));
+	mutex_unlock(&ublk_ctl_mutex);
+
+	return ret;
+}
+
+static inline void ublk_ctrl_cmd_dump(struct io_uring_cmd *cmd)
+{
+	struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
+
+	pr_devel("%s: cmd_op %x, dev id %d qid %d data %llx buf %llx len %u\n",
+			__func__, cmd->cmd_op, header->dev_id, header->queue_id,
+			header->data[0], header->addr, header->len);
+}
+
+static int ublk_ctrl_stop_dev(struct io_uring_cmd *cmd)
+{
+	struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
+	struct ublk_device *ub;
+
+	ub = ublk_get_device_from_id(header->dev_id);
+	if (!ub)
+		return -EINVAL;
+
+	ublk_stop_dev(ub);
+	cancel_work_sync(&ub->stop_work);
+
+	ublk_put_device(ub);
+	return 0;
+}
+
+static int ublk_ctrl_get_dev_info(struct io_uring_cmd *cmd)
+{
+	struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
+	void __user *argp = (void __user *)(unsigned long)header->addr;
+	struct ublk_device *ub;
+	int ret = 0;
+
+	if (header->len < sizeof(struct ublksrv_ctrl_dev_info) || !header->addr)
+		return -EINVAL;
+
+	ub = ublk_get_device_from_id(header->dev_id);
+	if (!ub)
+		return -EINVAL;
+
+	if (copy_to_user(argp, &ub->dev_info, sizeof(ub->dev_info)))
+		ret = -EFAULT;
+	ublk_put_device(ub);
+
+	return ret;
+}
+
+static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
+		unsigned int issue_flags)
+{
+	struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
+	int ret = -EINVAL;
+
+	ublk_ctrl_cmd_dump(cmd);
+
+	if (!(issue_flags & IO_URING_F_SQE128))
+		goto out;
+
+	ret = -EPERM;
+	if (!capable(CAP_SYS_ADMIN))
+		goto out;
+
+	ret = -ENODEV;
+	switch (cmd->cmd_op) {
+	case UBLK_CMD_START_DEV:
+		ret = ublk_ctrl_start_dev(cmd);
+		break;
+	case UBLK_CMD_STOP_DEV:
+		ret = ublk_ctrl_stop_dev(cmd);
+		break;
+	case UBLK_CMD_GET_DEV_INFO:
+		ret = ublk_ctrl_get_dev_info(cmd);
+		break;
+	case UBLK_CMD_ADD_DEV:
+		ret = ublk_ctrl_add_dev(cmd);
+		break;
+	case UBLK_CMD_DEL_DEV:
+		ret = ublk_ctrl_del_dev(header->dev_id);
+		break;
+	case UBLK_CMD_GET_QUEUE_AFFINITY:
+		ret = ublk_ctrl_get_queue_affinity(cmd);
+		break;
+	default:
+		break;
+	}
+ out:
+	io_uring_cmd_done(cmd, ret, 0);
+	pr_devel("%s: cmd done ret %d cmd_op %x, dev id %d qid %d\n",
+			__func__, ret, cmd->cmd_op, header->dev_id, header->queue_id);
+	return -EIOCBQUEUED;
+}
+
+static const struct file_operations ublk_ctl_fops = {
+	.open		= nonseekable_open,
+	.uring_cmd      = ublk_ctrl_uring_cmd,
+	.owner		= THIS_MODULE,
+	.llseek		= noop_llseek,
+};
+
+static struct miscdevice ublk_misc = {
+	.minor		= MISC_DYNAMIC_MINOR,
+	.name		= "ublk-control",
+	.fops		= &ublk_ctl_fops,
+};
+
+static int __init ublk_init(void)
+{
+	int ret;
+
+	init_waitqueue_head(&ublk_idr_wq);
+
+	ret = misc_register(&ublk_misc);
+	if (ret)
+		return ret;
+
+	ret = alloc_chrdev_region(&ublk_chr_devt, 0, UBLK_MINORS, "ublk-char");
+	if (ret)
+		goto unregister_mis;
+
+	ublk_chr_class = class_create(THIS_MODULE, "ublk-char");
+	if (IS_ERR(ublk_chr_class)) {
+		ret = PTR_ERR(ublk_chr_class);
+		goto free_chrdev_region;
+	}
+	return 0;
+
+free_chrdev_region:
+	unregister_chrdev_region(ublk_chr_devt, UBLK_MINORS);
+unregister_mis:
+	misc_deregister(&ublk_misc);
+	return ret;
+}
+
+static void __exit ublk_exit(void)
+{
+	struct ublk_device *ub;
+	int id;
+
+	class_destroy(ublk_chr_class);
+
+	misc_deregister(&ublk_misc);
+
+	idr_for_each_entry(&ublk_index_idr, ub, id)
+		ublk_remove(ub);
+
+	idr_destroy(&ublk_index_idr);
+	unregister_chrdev_region(ublk_chr_devt, UBLK_MINORS);
+}
+
+module_init(ublk_init);
+module_exit(ublk_exit);
+
+MODULE_AUTHOR("Ming Lei <[e-mail]>");
+MODULE_LICENSE("GPL");

drivers/block/virtio_blk.c

···
 	return 0;
 
 out_cleanup_disk:
-	blk_cleanup_disk(vblk->disk);
+	put_disk(vblk->disk);
 out_free_tags:
 	blk_mq_free_tag_set(&vblk->tag_set);
 out_free_vq:
···
 	flush_work(&vblk->config_work);
 
 	del_gendisk(vblk->disk);
-	blk_cleanup_queue(vblk->disk->queue);
 	blk_mq_free_tag_set(&vblk->tag_set);
 
 	mutex_lock(&vblk->vdev_mutex);

drivers/block/xen-blkback/blkback.c

···
  * Routines for managing virtual block devices (vbds).
  */
 static int xen_vbd_translate(struct phys_req *req, struct xen_blkif *blkif,
-			     int operation)
+			     enum req_op operation)
 {
 	struct xen_vbd *vbd = &blkif->vbd;
 	int rc = -EACCES;
···
 	struct bio *bio = NULL;
 	struct bio **biolist = pending_req->biolist;
 	int i, nbio = 0;
-	int operation;
-	int operation_flags = 0;
+	enum req_op operation;
+	blk_opf_t operation_flags = 0;
 	struct blk_plug plug;
 	bool drain = false;
 	struct grant_page **pages = pending_req->segments;

drivers/block/xen-blkfront.c

···
 
 	err = device_add_disk(&info->xbdev->dev, info->gd, NULL);
 	if (err) {
-		blk_cleanup_disk(info->gd);
+		put_disk(info->gd);
 		blk_mq_free_tag_set(&info->tag_set);
 		info->rq = NULL;
 		goto fail;
···
 	blkif_free(info, 0);
 	if (info->gd) {
 		xlbd_release_minors(info->gd->first_minor, info->gd->minors);
-		blk_cleanup_disk(info->gd);
+		put_disk(info->gd);
 		blk_mq_free_tag_set(&info->tag_set);
 	}
 

drivers/block/z2ram.c

···
 	z2ram_gendisk[minor] = disk;
 	err = add_disk(disk);
 	if (err)
-		blk_cleanup_disk(disk);
+		put_disk(disk);
 	return err;
 }
 
···
 
 	for (i = 0; i < Z2MINOR_COUNT; i++) {
 		del_gendisk(z2ram_gendisk[i]);
-		blk_cleanup_queue(z2ram_gendisk[i]->queue);
 		put_disk(z2ram_gendisk[i]);
 	}
 	blk_mq_free_tag_set(&tag_set);

drivers/block/zram/zram_drv.c

···
  * Returns 1 if IO request was successfully submitted.
  */
 static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
-			int offset, unsigned int op, struct bio *bio)
+			int offset, enum req_op op, struct bio *bio)
 {
 	int ret;
 
···
 }
 
 static int zram_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, unsigned int op)
+		       struct page *page, enum req_op op)
 {
 	int offset, ret;
 	u32 index;
···
 	return device_id;
 
 out_cleanup_disk:
-	blk_cleanup_disk(zram->disk);
+	put_disk(zram->disk);
 out_free_idr:
 	idr_remove(&zram_index_idr, device_id);
 out_free_dev:
···
 	 */
 	zram_reset_device(zram);
 
-	blk_cleanup_disk(zram->disk);
+	put_disk(zram->disk);
 	kfree(zram);
 	return 0;
 }

drivers/cdrom/gdrom.c

···
 	free_irq(HW_EVENT_GDROM_DMA, &gd);
 	free_irq(HW_EVENT_GDROM_CMD, &gd);
 probe_fail_cleanup_disk:
-	blk_cleanup_disk(gd.disk);
+	put_disk(gd.disk);
 probe_fail_free_tag_set:
 	blk_mq_free_tag_set(&gd.tag_set);
 probe_fail_free_cd_info:
···
 
 static int remove_gdrom(struct platform_device *devptr)
 {
-	blk_cleanup_queue(gd.gdrom_rq);
 	blk_mq_free_tag_set(&gd.tag_set);
 	free_irq(HW_EVENT_GDROM_CMD, &gd);
 	free_irq(HW_EVENT_GDROM_DMA, &gd);

drivers/infiniband/ulp/srp/ib_srp.c

···
 	int scsi_result;
 };
 
-static bool srp_terminate_cmd(struct scsi_cmnd *scmnd, void *context_ptr,
-			      bool reserved)
+static bool srp_terminate_cmd(struct scsi_cmnd *scmnd, void *context_ptr)
 {
 	struct srp_terminate_context *context = context_ptr;
 	struct srp_target_port *target = context->srp_target;

drivers/md/bcache/super.c

···
 	up(&c->uuid_write_mutex);
 }
 
-static void uuid_io(struct cache_set *c, int op, unsigned long op_flags,
-		    struct bkey *k, struct closure *parent)
+static void uuid_io(struct cache_set *c, blk_opf_t opf, struct bkey *k,
+		    struct closure *parent)
 {
 	struct closure *cl = &c->uuid_write;
 	struct uuid_entry *u;
···
 	for (i = 0; i < KEY_PTRS(k); i++) {
 		struct bio *bio = bch_bbio_alloc(c);
 
-		bio->bi_opf = REQ_SYNC | REQ_META | op_flags;
+		bio->bi_opf = opf | REQ_SYNC | REQ_META;
 		bio->bi_iter.bi_size = KEY_SIZE(k) << 9;
 
 		bio->bi_end_io	= uuid_endio;
 		bio->bi_private = cl;
-		bio_set_op_attrs(bio, op, REQ_SYNC|REQ_META|op_flags);
 		bch_bio_map(bio, c->uuids);
 
 		bch_submit_bbio(bio, c, k, i);
 
-		if (op != REQ_OP_WRITE)
+		if ((opf & REQ_OP_MASK) != REQ_OP_WRITE)
 			break;
 	}
 
 	bch_extent_to_text(buf, sizeof(buf), k);
-	pr_debug("%s UUIDs at %s\n", op == REQ_OP_WRITE ? "wrote" : "read", buf);
+	pr_debug("%s UUIDs at %s\n", (opf & REQ_OP_MASK) == REQ_OP_WRITE ?
+		 "wrote" : "read", buf);
 
 	for (u = c->uuids; u < c->uuids + c->nr_uuids; u++)
 		if (!bch_is_zero(u->uuid, 16))
···
 		return "bad uuid pointer";
 
 	bkey_copy(&c->uuid_bucket, k);
-	uuid_io(c, REQ_OP_READ, 0, k, cl);
+	uuid_io(c, REQ_OP_READ, k, cl);
 
 	if (j->version < BCACHE_JSET_VERSION_UUIDv1) {
 		struct uuid_entry_v0	*u0 = (void *) c->uuids;
···
 
 	size =  meta_bucket_pages(&ca->sb) * PAGE_SECTORS;
 	SET_KEY_SIZE(&k.key, size);
-	uuid_io(c, REQ_OP_WRITE, 0, &k.key, &cl);
+	uuid_io(c, REQ_OP_WRITE, &k.key, &cl);
 	closure_sync(&cl);
 
 	/* Only one bucket used for uuid write */
···
 	closure_put(&ca->prio);
 }
 
-static void prio_io(struct cache *ca, uint64_t bucket, int op,
-		    unsigned long op_flags)
+static void prio_io(struct cache *ca, uint64_t bucket, blk_opf_t opf)
 {
 	struct closure *cl = &ca->prio;
 	struct bio *bio = bch_bbio_alloc(ca->set);
···
 
 	bio->bi_end_io	= prio_endio;
 	bio->bi_private = ca;
-	bio_set_op_attrs(bio, op, REQ_SYNC|REQ_META|op_flags);
+	bio->bi_opf = opf | REQ_SYNC | REQ_META;
 	bch_bio_map(bio, ca->disk_buckets);
 
 	closure_bio_submit(ca->set, bio, &ca->prio);
···
 		BUG_ON(bucket == -1);
 
 		mutex_unlock(&ca->set->bucket_lock);
-		prio_io(ca, bucket, REQ_OP_WRITE, 0);
+		prio_io(ca, bucket, REQ_OP_WRITE);
 		mutex_lock(&ca->set->bucket_lock);
 
 		ca->prio_buckets[i] = bucket;
···
 			ca->prio_last_buckets[bucket_nr] = bucket;
 			bucket_nr++;
 
-			prio_io(ca, bucket, REQ_OP_READ, 0);
+			prio_io(ca, bucket, REQ_OP_READ);
 
 			if (p->csum !=
 			    bch_crc64(&p->magic, meta_bucket_bytes(&ca->sb) - 8)) {
···
 	if (disk) {
 		ida_simple_remove(&bcache_device_idx,
 				  first_minor_to_idx(disk->first_minor));
-		blk_cleanup_disk(disk);
+		put_disk(disk);
 	}
 
 	bioset_exit(&d->bio_split);

drivers/md/dm-bufio.c

···
 	b->end_io(b, unlikely(error != 0) ? BLK_STS_IOERR : 0);
 }
 
-static void use_dmio(struct dm_buffer *b, int rw, sector_t sector,
+static void use_dmio(struct dm_buffer *b, enum req_op op, sector_t sector,
 		     unsigned n_sectors, unsigned offset)
 {
 	int r;
 	struct dm_io_request io_req = {
-		.bi_op = rw,
-		.bi_op_flags = 0,
+		.bi_opf = op,
 		.notify.fn = dmio_complete,
 		.notify.context = b,
 		.client = b->c->dm_io,
···
 	b->end_io(b, status);
 }
 
-static void use_bio(struct dm_buffer *b, int rw, sector_t sector,
+static void use_bio(struct dm_buffer *b, enum req_op op, sector_t sector,
 		    unsigned n_sectors, unsigned offset)
 {
 	struct bio *bio;
···
 	bio = bio_kmalloc(vec_size, GFP_NOWAIT | __GFP_NORETRY | __GFP_NOWARN);
 	if (!bio) {
 dmio:
-		use_dmio(b, rw, sector, n_sectors, offset);
+		use_dmio(b, op, sector, n_sectors, offset);
 		return;
 	}
-	bio_init(bio, b->c->bdev, bio->bi_inline_vecs, vec_size, rw);
+	bio_init(bio, b->c->bdev, bio->bi_inline_vecs, vec_size, op);
 	bio->bi_iter.bi_sector = sector;
 	bio->bi_end_io = bio_complete;
 	bio->bi_private = b;
···
 	return sector;
 }
 
-static void submit_io(struct dm_buffer *b, int rw, void (*end_io)(struct dm_buffer *, blk_status_t))
+static void submit_io(struct dm_buffer *b, enum req_op op,
+		      void (*end_io)(struct dm_buffer *, blk_status_t))
 {
 	unsigned n_sectors;
 	sector_t sector;
···
 
 	sector = block_to_sector(b->c, b->block);
 
-	if (rw != REQ_OP_WRITE) {
+	if (op != REQ_OP_WRITE) {
 		n_sectors = b->c->block_size >> SECTOR_SHIFT;
 		offset = 0;
 	} else {
···
 	}
 
 	if (b->data_mode != DATA_MODE_VMALLOC)
-		use_bio(b, rw, sector, n_sectors, offset);
+		use_bio(b, op, sector, n_sectors, offset);
 	else
-		use_dmio(b, rw, sector, n_sectors, offset);
+		use_dmio(b, op, sector, n_sectors, offset);
 }
 
 /*----------------------------------------------------------------
···
 int dm_bufio_issue_flush(struct dm_bufio_client *c)
 {
 	struct dm_io_request io_req = {
-		.bi_op = REQ_OP_WRITE,
-		.bi_op_flags = REQ_PREFLUSH | REQ_SYNC,
+		.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC,
 		.mem.type = DM_IO_KMEM,
 		.mem.ptr.addr = NULL,
 		.client = c->dm_io,
···
 int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t count)
 {
 	struct dm_io_request io_req = {
-		.bi_op = REQ_OP_DISCARD,
-		.bi_op_flags = REQ_SYNC,
+		.bi_opf = REQ_OP_DISCARD | REQ_SYNC,
 		.mem.type = DM_IO_KMEM,
 		.mem.ptr.addr = NULL,
 		.client = c->dm_io,

drivers/md/dm-ebs-target.c

···
  *
  * copy blocks between bufio blocks and bio vector's (partial/overlapping) pages.
  */
-static int __ebs_rw_bvec(struct ebs_c *ec, int rw, struct bio_vec *bv, struct bvec_iter *iter)
+static int __ebs_rw_bvec(struct ebs_c *ec, enum req_op op, struct bio_vec *bv,
+			 struct bvec_iter *iter)
 {
 	int r = 0;
 	unsigned char *ba, *pa;
···
 		cur_len = min(dm_bufio_get_block_size(ec->bufio) - buf_off, bv_len);
 
 		/* Avoid reading for writes in case bio vector's page overwrites block completely. */
-		if (rw == READ || buf_off || bv_len < dm_bufio_get_block_size(ec->bufio))
+		if (op == REQ_OP_READ || buf_off || bv_len < dm_bufio_get_block_size(ec->bufio))
 			ba = dm_bufio_read(ec->bufio, block, &b);
 		else
 			ba = dm_bufio_new(ec->bufio, block, &b);
···
 		} else {
 			/* Copy data to/from bio to buffer if read/new was successful above. */
 			ba += buf_off;
-			if (rw == READ) {
+			if (op == REQ_OP_READ) {
 				memcpy(pa, ba, cur_len);
 				flush_dcache_page(bv->bv_page);
 			} else {
···
 }
 
 /* READ/WRITE: iterate bio vector's copying between (partial) pages and bufio blocks. */
-static int __ebs_rw_bio(struct ebs_c *ec, int rw, struct bio *bio)
+static int __ebs_rw_bio(struct ebs_c *ec, enum req_op op, struct bio *bio)
 {
 	int r = 0, rr;
 	struct bio_vec bv;
 	struct bvec_iter iter;
 
 	bio_for_each_bvec(bv, bio, iter) {
-		rr = __ebs_rw_bvec(ec, rw, &bv, &iter);
+		rr = __ebs_rw_bvec(ec, op, &bv, &iter);
 		if (rr)
 			r = rr;
 	}
···
 	bio_list_for_each(bio, &bios) {
 		r = -EIO;
 		if (bio_op(bio) == REQ_OP_READ)
-			r = __ebs_rw_bio(ec, READ, bio);
+			r = __ebs_rw_bio(ec, REQ_OP_READ, bio);
 		else if (bio_op(bio) == REQ_OP_WRITE) {
 			write = true;
-			r = __ebs_rw_bio(ec, WRITE, bio);
+			r = __ebs_rw_bio(ec, REQ_OP_WRITE, bio);
 		} else if (bio_op(bio) == REQ_OP_DISCARD) {
 			__ebs_forget_bio(ec, bio);
 			r = __ebs_discard_bio(ec, bio);

drivers/md/dm-flakey.c

···
 	unsigned corrupt_bio_byte;
 	unsigned corrupt_bio_rw;
 	unsigned corrupt_bio_value;
-	unsigned corrupt_bio_flags;
+	blk_opf_t corrupt_bio_flags;
 };
 
 enum feature_flag_bits {
···
 			/*
 			 * Only corrupt bios with these flags set.
 			 */
-			r = dm_read_arg(_args + 3, as, &fc->corrupt_bio_flags, &ti->error);
+			BUILD_BUG_ON(sizeof(fc->corrupt_bio_flags) !=
+				     sizeof(unsigned int));
+			r = dm_read_arg(_args + 3, as,
+				(__force unsigned *)&fc->corrupt_bio_flags,
+				&ti->error);
 			if (r)
 				return r;
 			argc--;

drivers/md/dm-integrity.c

···
 	struct work_struct work;
 
 	struct dm_integrity_c *ic;
-	enum req_opf op;
+	enum req_op op;
 	bool fua;
 
 	struct dm_integrity_range range;
···
 	return 0;
 }
 
-static int sync_rw_sb(struct dm_integrity_c *ic, int op, int op_flags)
+static int sync_rw_sb(struct dm_integrity_c *ic, blk_opf_t opf)
 {
 	struct dm_io_request io_req;
 	struct dm_io_region io_loc;
+	const enum req_op op = opf & REQ_OP_MASK;
 	int r;
 
-	io_req.bi_op = op;
-	io_req.bi_op_flags = op_flags;
+	io_req.bi_opf = opf;
 	io_req.mem.type = DM_IO_KMEM;
 	io_req.mem.ptr.addr = ic->sb;
 	io_req.notify.fn = NULL;
···
 	complete_journal_op(comp);
 }
 
-static void rw_journal_sectors(struct dm_integrity_c *ic, int op, int op_flags,
-			       unsigned sector, unsigned n_sectors, struct journal_completion *comp)
+static void rw_journal_sectors(struct dm_integrity_c *ic, blk_opf_t opf,
+			       unsigned sector, unsigned n_sectors,
+			       struct journal_completion *comp)
 {
 	struct dm_io_request io_req;
 	struct dm_io_region io_loc;
···
 	pl_index = sector >> (PAGE_SHIFT - SECTOR_SHIFT);
 	pl_offset = (sector << SECTOR_SHIFT) & (PAGE_SIZE - 1);
 
-	io_req.bi_op = op;
-	io_req.bi_op_flags = op_flags;
+	io_req.bi_opf = opf;
 	io_req.mem.type = DM_IO_PAGE_LIST;
 	if (ic->journal_io)
 		io_req.mem.ptr.pl = &ic->journal_io[pl_index];
···
 
 	r = dm_io(&io_req, 1, &io_loc, NULL);
 	if (unlikely(r)) {
-		dm_integrity_io_error(ic, op == REQ_OP_READ ? "reading journal" : "writing journal", r);
+		dm_integrity_io_error(ic, (opf & REQ_OP_MASK) == REQ_OP_READ ?
+				      "reading journal" : "writing journal", r);
 		if (comp) {
 			WARN_ONCE(1, "asynchronous dm_io failed: %d", r);
 			complete_journal_io(-1UL, comp);
···
 	}
 }
 
-static void rw_journal(struct dm_integrity_c *ic, int op, int op_flags, unsigned section,
-		       unsigned n_sections, struct journal_completion *comp)
+static void rw_journal(struct dm_integrity_c *ic, blk_opf_t opf,
+		       unsigned section, unsigned n_sections,
+		       struct journal_completion *comp)
 {
 	unsigned sector, n_sectors;
 
 	sector = section * ic->journal_section_sectors;
 	n_sectors = n_sections * ic->journal_section_sectors;
 
-	rw_journal_sectors(ic, op, op_flags, sector, n_sectors, comp);
+	rw_journal_sectors(ic, opf, sector, n_sectors, comp);
 }
 
 static void write_journal(struct dm_integrity_c *ic, unsigned commit_start, unsigned commit_sections)
···
 			for (i = 0; i < commit_sections; i++)
 				rw_section_mac(ic, commit_start + i, true);
 		}
-		rw_journal(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC, commit_start,
+		rw_journal(ic, REQ_OP_WRITE | REQ_FUA | REQ_SYNC, commit_start,
 			   commit_sections, &io_comp);
 	} else {
 		unsigned to_end;
···
 			crypt_comp_1.in_flight = (atomic_t)ATOMIC_INIT(0);
 			encrypt_journal(ic, true, commit_start, to_end, &crypt_comp_1);
 			if (try_wait_for_completion(&crypt_comp_1.comp)) {
-				rw_journal(ic, REQ_OP_WRITE, REQ_FUA, commit_start, to_end, &io_comp);
+				rw_journal(ic, REQ_OP_WRITE | REQ_FUA,
+					   commit_start, to_end, &io_comp);
 				reinit_completion(&crypt_comp_1.comp);
 				crypt_comp_1.in_flight = (atomic_t)ATOMIC_INIT(0);
 				encrypt_journal(ic, true, 0, commit_sections - to_end, &crypt_comp_1);
···
 				crypt_comp_2.in_flight = (atomic_t)ATOMIC_INIT(0);
 				encrypt_journal(ic, true, 0, commit_sections - to_end, &crypt_comp_2);
 				wait_for_completion_io(&crypt_comp_1.comp);
-				rw_journal(ic, REQ_OP_WRITE, REQ_FUA, commit_start, to_end, &io_comp);
+				rw_journal(ic, REQ_OP_WRITE | REQ_FUA, commit_start, to_end, &io_comp);
 				wait_for_completion_io(&crypt_comp_2.comp);
 			}
 		} else {
 			for (i = 0; i < to_end; i++)
 				rw_section_mac(ic, commit_start + i, true);
-			rw_journal(ic, REQ_OP_WRITE, REQ_FUA, commit_start, to_end, &io_comp);
+			rw_journal(ic, REQ_OP_WRITE | REQ_FUA, commit_start, to_end, &io_comp);
 			for (i = 0; i < commit_sections - to_end; i++)
 				rw_section_mac(ic, i, true);
 		}
-		rw_journal(ic, REQ_OP_WRITE, REQ_FUA, 0, commit_sections - to_end, &io_comp);
+		rw_journal(ic, REQ_OP_WRITE | REQ_FUA, 0, commit_sections - to_end, &io_comp);
 	}
 
 	wait_for_completion_io(&io_comp.comp);
···
 	pl_index = sector >> (PAGE_SHIFT - SECTOR_SHIFT);
 	pl_offset = (sector << SECTOR_SHIFT) & (PAGE_SIZE - 1);
 
-	io_req.bi_op = REQ_OP_WRITE;
-	io_req.bi_op_flags = 0;
+	io_req.bi_opf = REQ_OP_WRITE;
 	io_req.mem.type = DM_IO_PAGE_LIST;
 	io_req.mem.ptr.pl = &ic->journal[pl_index];
 	io_req.mem.offset = pl_offset;
···
 	if (!ic->meta_dev)
 		flush_data = false;
 	if (flush_data) {
-		fr.io_req.bi_op = REQ_OP_WRITE,
-		fr.io_req.bi_op_flags = REQ_PREFLUSH | REQ_SYNC,
+		fr.io_req.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC,
 		fr.io_req.mem.type = DM_IO_KMEM,
 		fr.io_req.mem.ptr.addr = NULL,
 		fr.io_req.notify.fn = flush_notify,
···
 	if (dm_integrity_failed(ic))
 		return;
 
-	r = sync_rw_sb(ic, REQ_OP_WRITE, 0);
+	r = sync_rw_sb(ic, REQ_OP_WRITE);
 	if (unlikely(r))
 		dm_integrity_io_error(ic, "writing superblock", r);
 }
···
 	if (unlikely(dm_integrity_failed(ic)))
 		goto err;
 
-	io_req.bi_op = REQ_OP_READ;
-	io_req.bi_op_flags = 0;
+	io_req.bi_opf = REQ_OP_READ;
 	io_req.mem.type = DM_IO_VMA;
 	io_req.mem.ptr.addr = ic->recalc_buffer;
 	io_req.notify.fn = NULL;
···
 	if (bio_list_empty(&waiting))
 		return;
 
-	rw_journal_sectors(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC,
+	rw_journal_sectors(ic, REQ_OP_WRITE | REQ_FUA | REQ_SYNC,
 			   bbs->idx * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT),
 			   BITMAP_BLOCK_SIZE >> SECTOR_SHIFT, NULL);
 
···
 	block_bitmap_op(ic, ic->journal, 0, limit, BITMAP_OP_CLEAR);
 	block_bitmap_op(ic, ic->may_write_bitmap, 0, limit, BITMAP_OP_CLEAR);
 
-	rw_journal_sectors(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC, 0,
+	rw_journal_sectors(ic, REQ_OP_WRITE | REQ_FUA | REQ_SYNC, 0,
 			   ic->n_bitmap_blocks * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT), NULL);
 
 	spin_lock_irq(&ic->endio_wait.lock);
···
 
 	if (!ic->just_formatted) {
 		DEBUG_print("reading journal\n");
-		rw_journal(ic, REQ_OP_READ, 0, 0, ic->journal_sections, NULL);
+		rw_journal(ic, REQ_OP_READ, 0, ic->journal_sections, NULL);
 		if (ic->journal_io)
 			DEBUG_bytes(lowmem_page_address(ic->journal_io[0].page), 64, "read journal");
 		if (ic->journal_io) {
···
 		/* set to 0 to test bitmap replay code */
 		init_journal(ic, 0, ic->journal_sections, 0);
 		ic->sb->flags &= ~cpu_to_le32(SB_FLAG_DIRTY_BITMAP);
-		r = sync_rw_sb(ic, REQ_OP_WRITE, REQ_FUA);
+		r = sync_rw_sb(ic, REQ_OP_WRITE | REQ_FUA);
 		if (unlikely(r))
 			dm_integrity_io_error(ic, "writing superblock", r);
 #endif
···
 		if (ic->provided_data_sectors > old_provided_data_sectors &&
 		    ic->mode == 'B' &&
 		    ic->sb->log2_blocks_per_bitmap_bit == ic->log2_blocks_per_bitmap_bit) {
-			rw_journal_sectors(ic, REQ_OP_READ, 0, 0,
+			rw_journal_sectors(ic, REQ_OP_READ, 0,
 					   ic->n_bitmap_blocks * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT), NULL);
 			block_bitmap_op(ic, ic->journal, old_provided_data_sectors,
 					ic->provided_data_sectors - old_provided_data_sectors, BITMAP_OP_SET);
-			rw_journal_sectors(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC, 0,
+			rw_journal_sectors(ic, REQ_OP_WRITE | REQ_FUA | REQ_SYNC, 0,
 					   ic->n_bitmap_blocks * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT), NULL);
 		}
 
 		ic->sb->provided_data_sectors = cpu_to_le64(ic->provided_data_sectors);
-		r = sync_rw_sb(ic, REQ_OP_WRITE, REQ_FUA);
+		r = sync_rw_sb(ic, REQ_OP_WRITE | REQ_FUA);
 		if (unlikely(r))
 			dm_integrity_io_error(ic, "writing superblock", r);
 	}
 
 	if (ic->sb->flags & cpu_to_le32(SB_FLAG_DIRTY_BITMAP)) {
 		DEBUG_print("resume dirty_bitmap\n");
-		rw_journal_sectors(ic, REQ_OP_READ, 0, 0,
+		rw_journal_sectors(ic, REQ_OP_READ, 0,
 				   ic->n_bitmap_blocks * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT), NULL);
 		if (ic->mode == 'B') {
 			if (ic->sb->log2_blocks_per_bitmap_bit == ic->log2_blocks_per_bitmap_bit &&
···
 				block_bitmap_op(ic, ic->recalc_bitmap, 0, ic->provided_data_sectors, BITMAP_OP_SET);
 				block_bitmap_op(ic, ic->may_write_bitmap, 0, ic->provided_data_sectors, BITMAP_OP_SET);
 				block_bitmap_op(ic, ic->journal, 0, ic->provided_data_sectors, BITMAP_OP_SET);
-				rw_journal_sectors(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC, 0,
+				rw_journal_sectors(ic, REQ_OP_WRITE | REQ_FUA | REQ_SYNC, 0,
 						   ic->n_bitmap_blocks * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT), NULL);
 				ic->sb->flags |= cpu_to_le32(SB_FLAG_RECALCULATING);
 				ic->sb->recalc_sector = cpu_to_le64(0);
···
 			replay_journal(ic);
 			ic->sb->flags &= ~cpu_to_le32(SB_FLAG_DIRTY_BITMAP);
 		}
-		r = sync_rw_sb(ic, REQ_OP_WRITE, REQ_FUA);
+		r = sync_rw_sb(ic, REQ_OP_WRITE | REQ_FUA);
 		if (unlikely(r))
 			dm_integrity_io_error(ic, "writing superblock", r);
 	} else {
···
 		if (ic->mode == 'B') {
 			ic->sb->flags |= cpu_to_le32(SB_FLAG_DIRTY_BITMAP);
 			ic->sb->log2_blocks_per_bitmap_bit = ic->log2_blocks_per_bitmap_bit;
-			r = sync_rw_sb(ic, REQ_OP_WRITE, REQ_FUA);
+			r = sync_rw_sb(ic, REQ_OP_WRITE | REQ_FUA);
 			if (unlikely(r))
 				dm_integrity_io_error(ic, "writing superblock", r);
 
···
 				block_bitmap_op(ic, ic->may_write_bitmap, le64_to_cpu(ic->sb->recalc_sector),
 						ic->provided_data_sectors - le64_to_cpu(ic->sb->recalc_sector), BITMAP_OP_SET);
 			}
-			rw_journal_sectors(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC, 0,
+			rw_journal_sectors(ic, REQ_OP_WRITE | REQ_FUA | REQ_SYNC, 0,
 					   ic->n_bitmap_blocks * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT), NULL);
 		}
 	}
···
 		goto bad;
 	}
 
-	r = sync_rw_sb(ic, REQ_OP_READ, 0);
+	r = sync_rw_sb(ic, REQ_OP_READ);
 	if (r) {
 		ti->error = "Error reading superblock";
 		goto bad;
···
 			ti->error = "Error initializing journal";
 			goto bad;
 		}
-		r = sync_rw_sb(ic, REQ_OP_WRITE, REQ_FUA);
+		r = sync_rw_sb(ic, REQ_OP_WRITE | REQ_FUA);
 		if (r) {
 			ti->error = "Error initializing superblock";
 			goto bad;

drivers/md/dm-io.c

···
 /*-----------------------------------------------------------------
  * IO routines that accept a list of pages.
  *---------------------------------------------------------------*/
-static void do_region(int op, int op_flags, unsigned region,
+static void do_region(const blk_opf_t opf, unsigned region,
 		      struct dm_io_region *where, struct dpages *dp,
 		      struct io *io)
 {
···
 	struct request_queue *q = bdev_get_queue(where->bdev);
 	sector_t num_sectors;
 	unsigned int special_cmd_max_sectors;
+	const enum req_op op = opf & REQ_OP_MASK;
 
 	/*
 	 * Reject unsupported discard and write same requests.
···
 						(PAGE_SIZE >> SECTOR_SHIFT)));
 		}
 
-		bio = bio_alloc_bioset(where->bdev, num_bvecs, op | op_flags,
-				       GFP_NOIO, &io->client->bios);
+		bio = bio_alloc_bioset(where->bdev, num_bvecs, opf, GFP_NOIO,
+				       &io->client->bios);
 		bio->bi_iter.bi_sector = where->sector + (where->count - remaining);
 		bio->bi_end_io = endio;
 		store_io_and_region_in_bio(bio, io, region);
···
 	} while (remaining);
 }
 
-static void dispatch_io(int op, int op_flags, unsigned int num_regions,
+static void dispatch_io(blk_opf_t opf, unsigned int num_regions,
 			struct dm_io_region *where, struct dpages *dp,
 			struct io *io, int sync)
 {
···
 	BUG_ON(num_regions > DM_IO_MAX_REGIONS);
 
 	if (sync)
-		op_flags |= REQ_SYNC;
+		opf |= REQ_SYNC;
 
 	/*
 	 * For multiple regions we need to be careful to rewind
···
 	 */
 	for (i = 0; i < num_regions; i++) {
 		*dp = old_pages;
-		if (where[i].count || (op_flags & REQ_PREFLUSH))
-			do_region(op, op_flags, i, where + i, dp, io);
+		if (where[i].count || (opf & REQ_PREFLUSH))
+			do_region(opf, i, where + i, dp, io);
 	}
 
 	/*
···
 }
 
 static int sync_io(struct dm_io_client *client, unsigned int num_regions,
-		   struct dm_io_region *where, int op, int op_flags,
-		   struct dpages *dp, unsigned long *error_bits)
+		   struct dm_io_region *where, blk_opf_t opf, struct dpages *dp,
+		   unsigned long *error_bits)
 {
 	struct io *io;
 	struct sync_io sio;
 
-	if (num_regions > 1 && !op_is_write(op)) {
+	if (num_regions > 1 && !op_is_write(opf)) {
 		WARN_ON(1);
 		return -EIO;
 	}
···
 	io->vma_invalidate_address = dp->vma_invalidate_address;
 	io->vma_invalidate_size = dp->vma_invalidate_size;
 
-	dispatch_io(op, op_flags, num_regions, where, dp, io, 1);
+	dispatch_io(opf, num_regions, where, dp, io, 1);
 
 	wait_for_completion_io(&sio.wait);
 
···
 }
 
 static int async_io(struct dm_io_client *client, unsigned int num_regions,
-		    struct dm_io_region *where, int op, int op_flags,
+		    struct dm_io_region *where, blk_opf_t opf,
 		    struct dpages *dp, io_notify_fn fn, void *context)
 {
 	struct io *io;
 
-	if (num_regions > 1 && !op_is_write(op)) {
+	if (num_regions > 1 && !op_is_write(opf)) {
 		WARN_ON(1);
 		fn(1, context);
 		return -EIO;
···
 	io->vma_invalidate_address = dp->vma_invalidate_address;
 	io->vma_invalidate_size = dp->vma_invalidate_size;
 
-	dispatch_io(op, op_flags, num_regions, where, dp, io, 0);
+	dispatch_io(opf, num_regions, where, dp, io, 0);
 	return 0;
 }
 
···
 
 	case DM_IO_VMA:
 		flush_kernel_vmap_range(io_req->mem.ptr.vma, size);
-		if (io_req->bi_op == REQ_OP_READ) {
+		if ((io_req->bi_opf & REQ_OP_MASK) == REQ_OP_READ) {
 			dp->vma_invalidate_address = io_req->mem.ptr.vma;
 			dp->vma_invalidate_size = size;
 		}
···
 
 	if (!io_req->notify.fn)
 		return sync_io(io_req->client, num_regions, where,
-			       io_req->bi_op, io_req->bi_op_flags, &dp,
-			       sync_error_bits);
+			       io_req->bi_opf, &dp, sync_error_bits);
 
-	return async_io(io_req->client, num_regions, where, io_req->bi_op,
-			io_req->bi_op_flags, &dp, io_req->notify.fn,
+	return async_io(io_req->client, num_regions, where,
+			io_req->bi_opf, &dp, io_req->notify.fn,
 			io_req->notify.context);
 }
 EXPORT_SYMBOL(dm_io);

drivers/md/dm-kcopyd.c

···
 	unsigned long write_err;
 
 	/*
-	 * Either READ or WRITE
+	 * REQ_OP_READ, REQ_OP_WRITE or REQ_OP_WRITE_ZEROES.
 	 */
-	int rw;
+	enum req_op op;
 	struct dm_io_region source;
 
 	/*
···
 	 * constraint and sequential writes that are at the right position.
 	 */
 	list_for_each_entry(job, jobs, list) {
-		if (job->rw == READ || !(job->flags & BIT(DM_KCOPYD_WRITE_SEQ))) {
+		if (job->op == REQ_OP_READ ||
+		    !(job->flags & BIT(DM_KCOPYD_WRITE_SEQ))) {
 			list_del(&job->list);
 			return job;
 		}
···
 	io_job_finish(kc->throttle);
 
 	if (error) {
-		if (op_is_write(job->rw))
+		if (op_is_write(job->op))
 			job->write_err |= error;
 		else
 			job->read_err = 1;
···
 		}
 	}
 
-	if (op_is_write(job->rw))
+	if (op_is_write(job->op))
 		push(&kc->complete_jobs, job);
 
 	else {
-		job->rw = WRITE;
+		job->op = REQ_OP_WRITE;
 		push(&kc->io_jobs, job);
 	}
 
···
 {
 	int r;
 	struct dm_io_request io_req = {
-		.bi_op = job->rw,
-		.bi_op_flags = 0,
+		.bi_opf = job->op,
 		.mem.type = DM_IO_PAGE_LIST,
 		.mem.ptr.pl = job->pages,
 		.mem.offset = 0,
···
 
 	io_job_start(job->kc->throttle);
 
-	if (job->rw == READ)
+	if (job->op == REQ_OP_READ)
 		r = dm_io(&io_req, 1, &job->source, NULL);
 	else
 		r = dm_io(&io_req, job->num_dests, job->dests, NULL);
···
 
 		if (r < 0) {
 			/* error this rogue job */
-			if (op_is_write(job->rw))
+			if (op_is_write(job->op))
 				job->write_err = (unsigned long) -1L;
 			else
 				job->read_err = 1;
···
 	if (from) {
 		job->source = *from;
 		job->pages = NULL;
-		job->rw = READ;
+		job->op = REQ_OP_READ;
 	} else {
 		memset(&job->source, 0, sizeof job->source);
 		job->source.count = job->dests[0].count;
···
 		/*
 		 * Use WRITE ZEROES to optimize zeroing if all dests support it.
 		 */
-		job->rw = REQ_OP_WRITE_ZEROES;
+		job->op = REQ_OP_WRITE_ZEROES;
 		for (i = 0; i < job->num_dests; i++)
 			if (!bdev_write_zeroes_sectors(job->dests[i].bdev)) {
-				job->rw = WRITE;
+				job->op = REQ_OP_WRITE;
 				break;
 			}
 	}

drivers/md/dm-log.c

···
 	core->nr_regions = le64_to_cpu(disk->nr_regions);
 }
 
-static int rw_header(struct log_c *lc, int op)
+static int rw_header(struct log_c *lc, enum req_op op)
 {
-	lc->io_req.bi_op = op;
-	lc->io_req.bi_op_flags = 0;
+	lc->io_req.bi_opf = op;
 
 	return dm_io(&lc->io_req, 1, &lc->header_location, NULL);
 }
···
 		.count = 0,
 	};
 
-	lc->io_req.bi_op = REQ_OP_WRITE;
-	lc->io_req.bi_op_flags = REQ_PREFLUSH;
+	lc->io_req.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
 
 	return dm_io(&lc->io_req, 1, &null_location, NULL);
 }

drivers/md/dm-raid.c

···
 
 	rdev->sb_loaded = 0;
 
-	if (!sync_page_io(rdev, 0, size, rdev->sb_page, REQ_OP_READ, 0, true)) {
+	if (!sync_page_io(rdev, 0, size, rdev->sb_page, REQ_OP_READ, true)) {
 		DMERR("Failed to read superblock of device at position %d",
 		      rdev->raid_disk);
 		md_error(rdev->mddev, rdev);

drivers/md/dm-raid1.c

···
 	struct dm_io_region io[MAX_NR_MIRRORS];
 	struct mirror *m;
 	struct dm_io_request io_req = {
-		.bi_op = REQ_OP_WRITE,
-		.bi_op_flags = REQ_PREFLUSH | REQ_SYNC,
+		.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC,
 		.mem.type = DM_IO_KMEM,
 		.mem.ptr.addr = NULL,
 		.client = ms->io_client,
···
 {
 	struct dm_io_region io;
 	struct dm_io_request io_req = {
-		.bi_op = REQ_OP_READ,
-		.bi_op_flags = 0,
+		.bi_opf = REQ_OP_READ,
 		.mem.type = DM_IO_BIO,
 		.mem.ptr.bio = bio,
 		.notify.fn = read_callback,
···
 	unsigned int i;
 	struct dm_io_region io[MAX_NR_MIRRORS], *dest = io;
 	struct mirror *m;
+	blk_opf_t op_flags = bio->bi_opf & (REQ_FUA | REQ_PREFLUSH);
 	struct dm_io_request io_req = {
-		.bi_op = REQ_OP_WRITE,
-		.bi_op_flags = bio->bi_opf & (REQ_FUA | REQ_PREFLUSH),
+		.bi_opf = REQ_OP_WRITE | op_flags,
 		.mem.type = DM_IO_BIO,
 		.mem.ptr.bio = bio,
 		.notify.fn = write_callback,
···
 	};
 
 	if (bio_op(bio) == REQ_OP_DISCARD) {
-		io_req.bi_op = REQ_OP_DISCARD;
+		io_req.bi_opf = REQ_OP_DISCARD | op_flags;
 		io_req.mem.type = DM_IO_KMEM;
 		io_req.mem.ptr.addr = NULL;
 	}

drivers/md/dm-snap-persistent.c

···
 /*
  * Read or write a chunk aligned and sized block of data from a device.
  */
-static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int op,
-		    int op_flags, int metadata)
+static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, blk_opf_t opf,
+		    int metadata)
 {
 	struct dm_io_region where = {
 		.bdev = dm_snap_cow(ps->store->snap)->bdev,
···
 		.count = ps->store->chunk_size,
 	};
 	struct dm_io_request io_req = {
-		.bi_op = op,
-		.bi_op_flags = op_flags,
+		.bi_opf = opf,
 		.mem.type = DM_IO_VMA,
 		.mem.ptr.vma = area,
 		.client = ps->io_client,
···
  * Read or write a metadata area.  Remembering to skip the first
  * chunk which holds the header.
  */
-static int area_io(struct pstore *ps, int op, int op_flags)
+static int area_io(struct pstore *ps, blk_opf_t opf)
 {
 	chunk_t chunk = area_location(ps, ps->current_area);
 
-	return chunk_io(ps, ps->area, chunk, op, op_flags, 0);
+	return chunk_io(ps, ps->area, chunk, opf, 0);
 }
 
 static void zero_memory_area(struct pstore *ps)
···
 static int zero_disk_area(struct pstore *ps, chunk_t area)
 {
 	return chunk_io(ps, ps->zero_area, area_location(ps, area),
-			REQ_OP_WRITE, 0, 0);
+			REQ_OP_WRITE, 0);
 }
 
 static int read_header(struct pstore *ps, int *new_snapshot)
···
 	if (r)
 		return r;
 
-	r = chunk_io(ps, ps->header_area, 0, REQ_OP_READ, 0, 1);
+	r = chunk_io(ps, ps->header_area, 0, REQ_OP_READ, 1);
 	if (r)
 		goto bad;
 
···
 	dh->version = cpu_to_le32(ps->version);
 	dh->chunk_size = cpu_to_le32(ps->store->chunk_size);
 
-	return chunk_io(ps, ps->header_area, 0, REQ_OP_WRITE, 0, 1);
+	return chunk_io(ps, ps->header_area, 0, REQ_OP_WRITE, 1);
 }
 
 /*
···
 	/*
 	 * Commit exceptions to disk.
 	 */
-	if (ps->valid && area_io(ps, REQ_OP_WRITE,
-				 REQ_PREFLUSH | REQ_FUA | REQ_SYNC))
+	if (ps->valid && area_io(ps, REQ_OP_WRITE | REQ_PREFLUSH | REQ_FUA |
+				 REQ_SYNC))
 		ps->valid = 0;
 
 	/*
···
 			return 0;
 
 		ps->current_area--;
-		r = area_io(ps, REQ_OP_READ, 0);
+		r = area_io(ps, REQ_OP_READ);
 		if (r < 0)
 			return r;
 		ps->current_committed = ps->exceptions_per_area;
···
 	for (i = 0; i < nr_merged; i++)
 		clear_exception(ps, ps->current_committed - 1 - i);
 
-	r = area_io(ps, REQ_OP_WRITE, REQ_PREFLUSH | REQ_FUA);
+	r = area_io(ps, REQ_OP_WRITE | REQ_PREFLUSH | REQ_FUA);
 	if (r < 0)
 		return r;
 

drivers/md/dm-table.c

···
 static int device_not_matches_zone_sectors(struct dm_target *ti, struct dm_dev *dev,
 					   sector_t start, sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
 	unsigned int *zone_sectors = data;
 
-	if (!blk_queue_is_zoned(q))
+	if (!bdev_is_zoned(dev->bdev))
 		return 0;
-
-	return blk_queue_zone_sectors(q) != *zone_sectors;
+	return bdev_zone_sectors(dev->bdev) != *zone_sectors;
 }
 
 /*

drivers/md/dm-writecache.c

···
 
 		region.sector += wc->start_sector;
 		atomic_inc(&endio.count);
-		req.bi_op = REQ_OP_WRITE;
-		req.bi_op_flags = REQ_SYNC;
+		req.bi_opf = REQ_OP_WRITE | REQ_SYNC;
 		req.mem.type = DM_IO_VMA;
 		req.mem.ptr.vma = (char *)wc->memory_map + (size_t)i * BITMAP_GRANULARITY;
 		req.client = wc->dm_io;
···
 
 	region.sector += wc->start_sector;
 
-	req.bi_op = REQ_OP_WRITE;
-	req.bi_op_flags = REQ_SYNC | REQ_FUA;
+	req.bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_FUA;
 	req.mem.type = DM_IO_VMA;
 	req.mem.ptr.vma = (char *)wc->memory_map;
 	req.client = wc->dm_io;
···
 	region.bdev = dev->bdev;
 	region.sector = 0;
 	region.count = 0;
-	req.bi_op = REQ_OP_WRITE;
-	req.bi_op_flags = REQ_PREFLUSH;
+	req.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
 	req.mem.type = DM_IO_KMEM;
 	req.mem.ptr.addr = NULL;
 	req.client = wc->dm_io;
···
 	region.bdev = wc->ssd_dev->bdev;
 	region.sector = wc->start_sector;
 	region.count = n_sectors;
-	req.bi_op = REQ_OP_READ;
-	req.bi_op_flags = REQ_SYNC;
+	req.bi_opf = REQ_OP_READ | REQ_SYNC;
 	req.mem.type = DM_IO_VMA;
 	req.mem.ptr.vma = (char *)wc->memory_map;
 	req.client = wc->dm_io;

drivers/md/dm-zone.c

···
 
 void dm_cleanup_zoned_dev(struct mapped_device *md)
 {
-	struct request_queue *q = md->queue;
-
-	if (q) {
-		kfree(q->conv_zones_bitmap);
-		q->conv_zones_bitmap = NULL;
-		kfree(q->seq_zones_wlock);
-		q->seq_zones_wlock = NULL;
+	if (md->disk) {
+		kfree(md->disk->conv_zones_bitmap);
+		md->disk->conv_zones_bitmap = NULL;
+		kfree(md->disk->seq_zones_wlock);
+		md->disk->seq_zones_wlock = NULL;
 	}
 
 	kvfree(md->zwp_offset);
···
 				 void *data)
 {
 	struct mapped_device *md = data;
-	struct request_queue *q = md->queue;
+	struct gendisk *disk = md->disk;
 
 	switch (zone->type) {
 	case BLK_ZONE_TYPE_CONVENTIONAL:
-		if (!q->conv_zones_bitmap) {
-			q->conv_zones_bitmap =
-				kcalloc(BITS_TO_LONGS(q->nr_zones),
+		if (!disk->conv_zones_bitmap) {
+			disk->conv_zones_bitmap =
+				kcalloc(BITS_TO_LONGS(disk->nr_zones),
 					sizeof(unsigned long), GFP_NOIO);
-			if (!q->conv_zones_bitmap)
+			if (!disk->conv_zones_bitmap)
 				return -ENOMEM;
 		}
-		set_bit(idx, q->conv_zones_bitmap);
+		set_bit(idx, disk->conv_zones_bitmap);
 		break;
 	case BLK_ZONE_TYPE_SEQWRITE_REQ:
 	case BLK_ZONE_TYPE_SEQWRITE_PREF:
-		if (!q->seq_zones_wlock) {
-			q->seq_zones_wlock =
-				kcalloc(BITS_TO_LONGS(q->nr_zones),
+		if (!disk->seq_zones_wlock) {
+			disk->seq_zones_wlock =
+				kcalloc(BITS_TO_LONGS(disk->nr_zones),
 					sizeof(unsigned long), GFP_NOIO);
-			if (!q->seq_zones_wlock)
+			if (!disk->seq_zones_wlock)
 				return -ENOMEM;
 		}
 		if (!md->zwp_offset) {
 			md->zwp_offset =
-				kvcalloc(q->nr_zones, sizeof(unsigned int),
+				kvcalloc(disk->nr_zones, sizeof(unsigned int),
 					 GFP_KERNEL);
 			if (!md->zwp_offset)
 				return -ENOMEM;
···
  */
 static int dm_revalidate_zones(struct mapped_device *md, struct dm_table *t)
 {
-	struct request_queue *q = md->queue;
+	struct gendisk *disk = md->disk;
 	unsigned int noio_flag;
 	int ret;
 
···
 	 * Check if something changed. If yes, cleanup the current resources
 	 * and reallocate everything.
 	 */
-	if (!q->nr_zones || q->nr_zones != md->nr_zones)
+	if (!disk->nr_zones || disk->nr_zones != md->nr_zones)
 		dm_cleanup_zoned_dev(md);
 	if (md->nr_zones)
 		return 0;
···
 	 * operations in this context are done as if GFP_NOIO was specified.
 	 */
 	noio_flag = memalloc_noio_save();
-	ret = dm_blk_do_report_zones(md, t, 0, q->nr_zones,
+	ret = dm_blk_do_report_zones(md, t, 0, disk->nr_zones,
 				     dm_zone_revalidate_cb, md);
 	memalloc_noio_restore(noio_flag);
 	if (ret < 0)
 		goto err;
-	if (ret != q->nr_zones) {
+	if (ret != disk->nr_zones) {
 		ret = -EIO;
 		goto err;
 	}
 
-	md->nr_zones = q->nr_zones;
+	md->nr_zones = disk->nr_zones;
 
 	return 0;
 
···
 					  struct dm_dev *dev, sector_t start,
 					  sector_t len, void *data)
 {
-	return !blk_queue_is_zoned(bdev_get_queue(dev->bdev));
+	return !bdev_is_zoned(dev->bdev);
 }
 
 static bool dm_table_supports_zone_append(struct dm_table *t)
···
 	 * correct value to be exposed in sysfs queue/nr_zones.
 	 */
 	WARN_ON_ONCE(queue_is_mq(q));
-	q->nr_zones = blkdev_nr_zones(md->disk);
+	md->disk->nr_zones = bdev_nr_zones(md->disk->part0);
 
 	/* Check if zone append is natively supported */
 	if (dm_table_supports_zone_append(t)) {
···
 static int dm_update_zone_wp_offset(struct mapped_device *md, unsigned int zno,
 				    unsigned int *wp_ofst)
 {
-	sector_t sector = zno * blk_queue_zone_sectors(md->queue);
+	sector_t sector = zno * bdev_zone_sectors(md->disk->part0);
 	unsigned int noio_flag;
 	struct dm_table *t;
 	int srcu_idx, ret;
···
 }
 
 struct orig_bio_details {
-	unsigned int op;
+	enum req_op op;
 	unsigned int nr_sectors;
 };
 
···
 static bool dm_zone_map_bio_begin(struct mapped_device *md,
 				  unsigned int zno, struct bio *clone)
 {
-	sector_t zsectors = blk_queue_zone_sectors(md->queue);
+	sector_t zsectors = bdev_zone_sectors(md->disk->part0);
 	unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]);
 
 	/*
···
 		return BLK_STS_OK;
 	case REQ_OP_ZONE_FINISH:
 		WRITE_ONCE(md->zwp_offset[zno],
-			   blk_queue_zone_sectors(md->queue));
+			   bdev_zone_sectors(md->disk->part0));
 		return BLK_STS_OK;
 	case REQ_OP_WRITE_ZEROES:
 	case REQ_OP_WRITE:
···
 	}
 }
 
-static inline void dm_zone_lock(struct request_queue *q,
-				unsigned int zno, struct bio *clone)
+static inline void dm_zone_lock(struct gendisk *disk, unsigned int zno,
+				struct bio *clone)
 {
 	if (WARN_ON_ONCE(bio_flagged(clone, BIO_ZONE_WRITE_LOCKED)))
 		return;
 
-	wait_on_bit_lock_io(q->seq_zones_wlock, zno, TASK_UNINTERRUPTIBLE);
+	wait_on_bit_lock_io(disk->seq_zones_wlock, zno, TASK_UNINTERRUPTIBLE);
 	bio_set_flag(clone, BIO_ZONE_WRITE_LOCKED);
 }
 
-static inline void dm_zone_unlock(struct request_queue *q,
-				  unsigned int zno, struct bio *clone)
+static inline void dm_zone_unlock(struct gendisk *disk, unsigned int zno,
+				  struct bio *clone)
 {
 	if (!bio_flagged(clone, BIO_ZONE_WRITE_LOCKED))
 		return;
 
-	WARN_ON_ONCE(!test_bit(zno, q->seq_zones_wlock));
-	clear_bit_unlock(zno, q->seq_zones_wlock);
+	WARN_ON_ONCE(!test_bit(zno, disk->seq_zones_wlock));
+	clear_bit_unlock(zno, disk->seq_zones_wlock);
 	smp_mb__after_atomic();
-	wake_up_bit(q->seq_zones_wlock, zno);
+	wake_up_bit(disk->seq_zones_wlock, zno);
 
 	bio_clear_flag(clone, BIO_ZONE_WRITE_LOCKED);
 }
···
 	struct dm_io *io = tio->io;
 	struct dm_target *ti = tio->ti;
 	struct mapped_device *md = io->md;
-	struct request_queue *q = md->queue;
 	struct bio *clone = &tio->clone;
 	struct orig_bio_details orig_bio_details;
 	unsigned int zno;
···
 
 	/* Lock the target zone */
 	zno = bio_zone_no(clone);
-	dm_zone_lock(q, zno, clone);
+	dm_zone_lock(md->disk, zno, clone);
 
 	orig_bio_details.nr_sectors = bio_sectors(clone);
 	orig_bio_details.op = bio_op(clone);
···
 	 * both valid, and if the bio is a zone append, remap it to a write.
 	 */
 	if (!dm_zone_map_bio_begin(md, zno, clone)) {
-		dm_zone_unlock(q, zno, clone);
+		dm_zone_unlock(md->disk, zno, clone);
 		return DM_MAPIO_KILL;
 	}
 
···
 		sts = dm_zone_map_bio_end(md, zno, &orig_bio_details,
 					  *tio->len_ptr);
 		if (sts != BLK_STS_OK)
-			dm_zone_unlock(q, zno, clone);
+			dm_zone_unlock(md->disk, zno, clone);
 		break;
 	case DM_MAPIO_REQUEUE:
 	case DM_MAPIO_KILL:
 	default:
-		dm_zone_unlock(q, zno, clone);
+		dm_zone_unlock(md->disk, zno, clone);
 		sts = BLK_STS_IOERR;
 		break;
 	}
···
 void dm_zone_endio(struct dm_io *io, struct bio *clone)
 {
 	struct mapped_device *md = io->md;
-	struct request_queue *q = md->queue;
+	struct gendisk *disk = md->disk;
 	struct bio *orig_bio = io->orig_bio;
 	unsigned int zwp_offset;
 	unsigned int zno;
···
 		 */
 		if (clone->bi_status == BLK_STS_OK &&
 		    bio_op(clone) == REQ_OP_ZONE_APPEND) {
-			sector_t mask = (sector_t)blk_queue_zone_sectors(q) - 1;
+			sector_t mask =
+				(sector_t)bdev_zone_sectors(disk->part0) - 1;
 
 			orig_bio->bi_iter.bi_sector +=
 				clone->bi_iter.bi_sector & mask;
···
 				zwp_offset - bio_sectors(orig_bio);
 	}
 
-	dm_zone_unlock(q, zno, clone);
+	dm_zone_unlock(disk, zno, clone);
 }

drivers/md/dm-zoned-metadata.c

···
 /*
  * Read/write a metadata block.
  */
-static int dmz_rdwr_block(struct dmz_dev *dev, int op,
+static int dmz_rdwr_block(struct dmz_dev *dev, enum req_op op,
 			  sector_t block, struct page *page)
 {
 	struct bio *bio;
···
  * allocated and used to map the chunk.
  * The zone returned will be set to the active state.
  */
-struct dm_zone *dmz_get_chunk_mapping(struct dmz_metadata *zmd, unsigned int chunk, int op)
+struct dm_zone *dmz_get_chunk_mapping(struct dmz_metadata *zmd,
+				      unsigned int chunk, enum req_op op)
 {
 	struct dmz_mblock *dmap_mblk = zmd->map_mblk[chunk >> DMZ_MAP_ENTRIES_SHIFT];
 	struct dmz_map *dmap = (struct dmz_map *) dmap_mblk->data;

drivers/md/dm-zoned-target.c

···
 static int dmz_fixup_devices(struct dm_target *ti)
 {
 	struct dmz_target *dmz = ti->private;
-	struct dmz_dev *reg_dev, *zoned_dev;
-	struct request_queue *q;
+	struct dmz_dev *reg_dev = NULL;
 	sector_t zone_nr_sectors = 0;
 	int i;
 
···
 			return -EINVAL;
 		}
 		for (i = 1; i < dmz->nr_ddevs; i++) {
-			zoned_dev = &dmz->dev[i];
+			struct dmz_dev *zoned_dev = &dmz->dev[i];
+			struct block_device *bdev = zoned_dev->bdev;
+
 			if (zoned_dev->flags & DMZ_BDEV_REGULAR) {
 				ti->error = "Secondary disk is not a zoned device";
 				return -EINVAL;
 			}
-			q = bdev_get_queue(zoned_dev->bdev);
 			if (zone_nr_sectors &&
-			    zone_nr_sectors != blk_queue_zone_sectors(q)) {
+			    zone_nr_sectors != bdev_zone_sectors(bdev)) {
 				ti->error = "Zone nr sectors mismatch";
 				return -EINVAL;
 			}
-			zone_nr_sectors = blk_queue_zone_sectors(q);
+			zone_nr_sectors = bdev_zone_sectors(bdev);
 			zoned_dev->zone_nr_sectors = zone_nr_sectors;
-			zoned_dev->nr_zones =
-				blkdev_nr_zones(zoned_dev->bdev->bd_disk);
+			zoned_dev->nr_zones = bdev_nr_zones(bdev);
 		}
 	} else {
-		reg_dev = NULL;
-		zoned_dev = &dmz->dev[0];
+		struct dmz_dev *zoned_dev = &dmz->dev[0];
+		struct block_device *bdev = zoned_dev->bdev;
+
 		if (zoned_dev->flags & DMZ_BDEV_REGULAR) {
 			ti->error = "Disk is not a zoned device";
 			return -EINVAL;
 		}
-		q = bdev_get_queue(zoned_dev->bdev);
-		zoned_dev->zone_nr_sectors = blk_queue_zone_sectors(q);
-		zoned_dev->nr_zones = blkdev_nr_zones(zoned_dev->bdev->bd_disk);
+		zoned_dev->zone_nr_sectors = bdev_zone_sectors(bdev);
+		zoned_dev->nr_zones = bdev_nr_zones(bdev);
 	}
 
 	if (reg_dev) {

drivers/md/dm-zoned.h

···
 					 unsigned int dev_idx, bool idle);
 
 struct dm_zone *dmz_get_chunk_mapping(struct dmz_metadata *zmd,
-				      unsigned int chunk, int op);
+				      unsigned int chunk, enum req_op op);
 void dmz_put_chunk_mapping(struct dmz_metadata *zmd, struct dm_zone *zone);
 struct dm_zone *dmz_get_chunk_buffer(struct dmz_metadata *zmd,
 				     struct dm_zone *dzone);

drivers/md/dm.c

···
 }
 
 static inline struct dm_table *dm_get_live_table_bio(struct mapped_device *md,
-						     int *srcu_idx, unsigned bio_opf)
+					int *srcu_idx, blk_opf_t bio_opf)
 {
 	if (bio_opf & REQ_NOWAIT)
 		return dm_get_live_table_fast(md);
···
 }
 
 static inline void dm_put_live_table_bio(struct mapped_device *md, int srcu_idx,
-					 unsigned bio_opf)
+					 blk_opf_t bio_opf)
 {
 	if (bio_opf & REQ_NOWAIT)
 		dm_put_live_table_fast(md);
···
 	}
 
 	if (static_branch_unlikely(&zoned_enabled) &&
-	    unlikely(blk_queue_is_zoned(bdev_get_queue(bio->bi_bdev))))
+	    unlikely(bdev_is_zoned(bio->bi_bdev)))
 		dm_zone_endio(io, bio);
 
 	if (endio) {
···
 {
 	sector_t target_offset = dm_target_offset(ti, sector);
 	sector_t len = max_io_len_target_boundary(ti, target_offset);
-	sector_t max_len;
 
 	/*
 	 * Does the target need to split IO even further?
 	 * - varied (per target) IO splitting is a tenet of DM; this
 	 *   explains why stacked chunk_sectors based splitting via
-	 *   blk_max_size_offset() isn't possible here. So pass in
-	 *   ti->max_io_len to override stacked chunk_sectors.
+	 *   blk_queue_split() isn't possible here.
 	 */
-	if (ti->max_io_len) {
-		max_len = blk_max_size_offset(ti->table->md->queue,
-					      target_offset, ti->max_io_len);
-		if (len > max_len)
-			len = max_len;
-	}
-
-	return len;
+	if (!ti->max_io_len)
+		return len;
+	return min_t(sector_t, len,
+		min(queue_max_sectors(ti->table->md->queue),
+		    blk_chunk_sectors_left(target_offset, ti->max_io_len)));
 }
 
 int dm_set_target_max_io_len(struct dm_target *ti, sector_t len)
···
 
 static bool is_abnormal_io(struct bio *bio)
 {
-	unsigned int op = bio_op(bio);
+	enum req_op op = bio_op(bio);
 
 	if (op != REQ_OP_READ && op != REQ_OP_WRITE && op != REQ_OP_FLUSH) {
 		switch (op) {
···
 		break;
 	case REQ_OP_WRITE_ZEROES:
 		num_bios = ti->num_write_zeroes_bios;
+		break;
+	default:
 		break;
 	}
 
···
 	 * Only support bio polling for normal IO, and the target io is
 	 * exactly inside the dm_io instance (verified in dm_poll_dm_io)
 	 */
-	ci->submit_as_polled = ci->bio->bi_opf & REQ_POLLED;
+	ci->submit_as_polled = !!(ci->bio->bi_opf & REQ_POLLED);
 
 	len = min_t(sector_t, max_io_len(ti, ci->sector), ci->sector_count);
 	setup_split_accounting(ci, len);
···
 	struct mapped_device *md = bio->bi_bdev->bd_disk->private_data;
 	int srcu_idx;
 	struct dm_table *map;
-	unsigned bio_opf = bio->bi_opf;
+	blk_opf_t bio_opf = bio->bi_opf;
 
 	map = dm_get_live_table_bio(md, &srcu_idx, bio_opf);
 
···
 			del_gendisk(md->disk);
 		}
 		dm_queue_destroy_crypto_profile(md->queue);
-		blk_cleanup_disk(md->disk);
+		put_disk(md->disk);
 	}
 
 	if (md->pending_io) {

drivers/md/md-bitmap.c

···
 
 		if (sync_page_io(rdev, target,
 				 roundup(size, bdev_logical_block_size(rdev->bdev)),
-				 page, REQ_OP_READ, 0, true)) {
+				 page, REQ_OP_READ, true)) {
 			page->index = index;
 			return 0;
 		}
···
 			atomic_inc(&bitmap->pending_writes);
 			set_buffer_locked(bh);
 			set_buffer_mapped(bh);
-			submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
+			submit_bh(REQ_OP_WRITE | REQ_SYNC, bh);
 			bh = bh->b_this_page;
 		}
 
···
 			atomic_inc(&bitmap->pending_writes);
 			set_buffer_locked(bh);
 			set_buffer_mapped(bh);
-			submit_bh(REQ_OP_READ, 0, bh);
+			submit_bh(REQ_OP_READ, bh);
 		}
 		blk_cur++;
 		bh = bh->b_this_page;

drivers/md/md.c

···
 }
 
 int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
-		 struct page *page, int op, int op_flags, bool metadata_op)
+		 struct page *page, blk_opf_t opf, bool metadata_op)
 {
 	struct bio bio;
 	struct bio_vec bvec;
 
 	if (metadata_op && rdev->meta_bdev)
-		bio_init(&bio, rdev->meta_bdev, &bvec, 1, op | op_flags);
+		bio_init(&bio, rdev->meta_bdev, &bvec, 1, opf);
 	else
-		bio_init(&bio, rdev->bdev, &bvec, 1, op | op_flags);
+		bio_init(&bio, rdev->bdev, &bvec, 1, opf);
 
 	if (metadata_op)
 		bio.bi_iter.bi_sector = sector + rdev->sb_start;
···
 	if (rdev->sb_loaded)
 		return 0;
 
-	if (!sync_page_io(rdev, 0, size, rdev->sb_page, REQ_OP_READ, 0, true))
+	if (!sync_page_io(rdev, 0, size, rdev->sb_page, REQ_OP_READ, true))
 		goto fail;
 	rdev->sb_loaded = 1;
 	return 0;
···
 			return -EINVAL;
 		bb_sector = (long long)offset;
 		if (!sync_page_io(rdev, bb_sector, sectors << 9,
-				  rdev->bb_page, REQ_OP_READ, 0, true))
+				  rdev->bb_page, REQ_OP_READ, true))
 			return -EIO;
 		bbp = (__le64 *)page_address(rdev->bb_page);
 		rdev->badblocks.shift = sb->bblog_shift;
···
 			mdname(mddev), mddev->max_disks);
 		return -EBUSY;
 	}
-	bdevname(rdev->bdev,b);
+	snprintf(b, sizeof(b), "%pg", rdev->bdev);
 	strreplace(b, '/', '!');
 
 	rdev->mddev = mddev;
···
 
 	if (mddev->gendisk) {
 		del_gendisk(mddev->gendisk);
-		blk_cleanup_disk(mddev->gendisk);
+		put_disk(mddev->gendisk);
 	}
 	percpu_ref_exit(&mddev->writes_pending);
 
···
 out_del_gendisk:
 	del_gendisk(disk);
 out_cleanup_disk:
-	blk_cleanup_disk(disk);
+	put_disk(disk);
 out_unlock_disks_mutex:
 	mutex_unlock(&disks_mutex);
 	mddev_put(mddev);

drivers/md/md.h

···
 			   sector_t sector, int size, struct page *page);
 extern int md_super_wait(struct mddev *mddev);
 extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
-			struct page *page, int op, int op_flags,
-			bool metadata_op);
+		struct page *page, blk_opf_t opf, bool metadata_op);
 extern void md_do_sync(struct md_thread *thread);
 extern void md_new_event(void);
 extern void md_allow_write(struct mddev *mddev);

drivers/md/raid1.c

···
 	struct raid1_info *mirror;
 	struct bio *read_bio;
 	struct bitmap *bitmap = mddev->bitmap;
-	const int op = bio_op(bio);
-	const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
+	const enum req_op op = bio_op(bio);
+	const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
 	int max_sectors;
 	int rdisk;
 	bool r1bio_existed = !!r1_bio;
···
 		rcu_read_lock();
 		rdev = rcu_dereference(conf->mirrors[r1_bio->read_disk].rdev);
 		if (rdev)
-			bdevname(rdev->bdev, b);
+			snprintf(b, sizeof(b), "%pg", rdev->bdev);
 		else
 			strcpy(b, "???");
 		rcu_read_unlock();
···
 }
 
 static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector,
-			    int sectors, struct page *page, int rw)
+			   int sectors, struct page *page, int rw)
 {
-	if (sync_page_io(rdev, sector, sectors << 9, page, rw, 0, false))
+	if (sync_page_io(rdev, sector, sectors << 9, page, rw, false))
 		/* success */
 		return 1;
 	if (rw == WRITE) {
···
 				rdev = conf->mirrors[d].rdev;
 				if (sync_page_io(rdev, sect, s<<9,
 						 pages[idx],
-						 REQ_OP_READ, 0, false)) {
+						 REQ_OP_READ, false)) {
 					success = 1;
 					break;
 				}
···
 				atomic_inc(&rdev->nr_pending);
 				rcu_read_unlock();
 				if (sync_page_io(rdev, sect, s<<9,
-					 conf->tmppage, REQ_OP_READ, 0, false))
+					 conf->tmppage, REQ_OP_READ, false))
 					success = 1;
 				rdev_dec_pending(rdev, mddev);
 				if (success)

drivers/md/raid10.c

···
 {
 	struct r10conf *conf = mddev->private;
 	struct bio *read_bio;
-	const int op = bio_op(bio);
-	const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
+	const enum req_op op = bio_op(bio);
+	const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
 	int max_sectors;
 	struct md_rdev *rdev;
 	char b[BDEVNAME_SIZE];
···
 		disk = r10_bio->devs[slot].devnum;
 		err_rdev = rcu_dereference(conf->mirrors[disk].rdev);
 		if (err_rdev)
-			bdevname(err_rdev->bdev, b);
+			snprintf(b, sizeof(b), "%pg", err_rdev->bdev);
 		else {
 			strcpy(b, "???");
 			/* This never gets dereferenced */
···
 				  struct bio *bio, bool replacement,
 				  int n_copy)
 {
-	const int op = bio_op(bio);
-	const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
-	const unsigned long do_fua = (bio->bi_opf & REQ_FUA);
+	const enum req_op op = bio_op(bio);
+	const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
+	const blk_opf_t do_fua = bio->bi_opf & REQ_FUA;
 	unsigned long flags;
 	struct blk_plug_cb *cb;
 	struct raid1_plug_cb *plug = NULL;
···
 				  addr,
 				  s << 9,
 				  pages[idx],
-				  REQ_OP_READ, 0, false);
+				  REQ_OP_READ, false);
 		if (ok) {
 			rdev = conf->mirrors[dw].rdev;
 			addr = r10_bio->devs[1].addr + sect;
···
 					  addr,
 					  s << 9,
 					  pages[idx],
-					  REQ_OP_WRITE, 0, false);
+					  REQ_OP_WRITE, false);
 			if (!ok) {
 				set_bit(WriteErrorSeen, &rdev->flags);
 				if (!test_and_set_bit(WantReplacement,
···
 	if (is_badblock(rdev, sector, sectors, &first_bad, &bad_sectors)
 	    && (rw == READ || test_bit(WriteErrorSeen, &rdev->flags)))
 		return -1;
-	if (sync_page_io(rdev, sector, sectors << 9, page, rw, 0, false))
+	if (sync_page_io(rdev, sector, sectors << 9, page, rw, false))
 		/* success */
 		return 1;
 	if (rw == WRITE) {
···
 						       sect,
 						       s<<9,
 						       conf->tmppage,
-						       REQ_OP_READ, 0, false);
+						       REQ_OP_READ, false);
 				rdev_dec_pending(rdev, mddev);
 				rcu_read_lock();
 				if (success)
···
 					       addr,
 					       s << 9,
 					       pages[idx],
-					       REQ_OP_READ, 0, false);
+					       REQ_OP_READ, false);
 			rdev_dec_pending(rdev, mddev);
 			rcu_read_lock();
 			if (success)

drivers/md/raid5-cache.c

···
 	mb = page_address(page);
 	mb->checksum = cpu_to_le32(crc32c_le(log->uuid_checksum,
 					     mb, PAGE_SIZE));
-	if (!sync_page_io(log->rdev, pos, PAGE_SIZE, page, REQ_OP_WRITE,
+	if (!sync_page_io(log->rdev, pos, PAGE_SIZE, page, REQ_OP_WRITE |
 			  REQ_SYNC | REQ_FUA, false)) {
 		__free_page(page);
 		return -EIO;
···
 			atomic_inc(&rdev->nr_pending);
 			rcu_read_unlock();
 			sync_page_io(rdev, sh->sector, PAGE_SIZE,
-				     sh->dev[disk_index].page, REQ_OP_WRITE, 0,
+				     sh->dev[disk_index].page, REQ_OP_WRITE,
 				     false);
 			rdev_dec_pending(rdev, rdev->mddev);
 			rcu_read_lock();
···
 			atomic_inc(&rrdev->nr_pending);
 			rcu_read_unlock();
 			sync_page_io(rrdev, sh->sector, PAGE_SIZE,
-				     sh->dev[disk_index].page, REQ_OP_WRITE, 0,
+				     sh->dev[disk_index].page, REQ_OP_WRITE,
 				     false);
 			rdev_dec_pending(rrdev, rrdev->mddev);
 			rcu_read_lock();
···
 						  PAGE_SIZE));
 				kunmap_atomic(addr);
 				sync_page_io(log->rdev, write_pos, PAGE_SIZE,
-					     dev->page, REQ_OP_WRITE, 0, false);
+					     dev->page, REQ_OP_WRITE, false);
 				write_pos = r5l_ring_add(log, write_pos,
 							 BLOCK_SECTORS);
 				offset += sizeof(__le32) +
···
 		mb->checksum = cpu_to_le32(crc32c_le(log->uuid_checksum,
 						     mb, PAGE_SIZE));
 		sync_page_io(log->rdev, ctx->pos, PAGE_SIZE, page,
-			     REQ_OP_WRITE, REQ_SYNC | REQ_FUA, false);
+			     REQ_OP_WRITE | REQ_SYNC | REQ_FUA, false);
 		sh->log_start = ctx->pos;
 		list_add_tail(&sh->r5c, &log->stripe_in_journal_list);
 		atomic_inc(&log->stripe_in_journal_count);
···
 	if (!page)
 		return -ENOMEM;
 
-	if (!sync_page_io(rdev, cp, PAGE_SIZE, page, REQ_OP_READ, 0, false)) {
+	if (!sync_page_io(rdev, cp, PAGE_SIZE, page, REQ_OP_READ, false)) {
 		ret = -EIO;
 		goto ioerr;
 	}

drivers/md/raid5-ppl.c

···
 				 __func__, indent, "", rdev->bdev,
 				 (unsigned long long)sector);
 			if (!sync_page_io(rdev, sector, block_size, page2,
-					REQ_OP_READ, 0, false)) {
+					REQ_OP_READ, false)) {
 				md_error(mddev, rdev);
 				pr_debug("%s:%*s read failed!\n", __func__,
 					 indent, "");
···
 				 (unsigned long long)(ppl_sector + i));
 			if (!sync_page_io(log->rdev,
 					ppl_sector - log->rdev->data_offset + i,
-					block_size, page2, REQ_OP_READ, 0,
+					block_size, page2, REQ_OP_READ,
 					false)) {
 				pr_debug("%s:%*s read failed!\n", __func__,
 					 indent, "");
···
 			 (unsigned long long)parity_sector,
 			 parity_rdev->bdev);
 		if (!sync_page_io(parity_rdev, parity_sector, block_size,
-				page1, REQ_OP_WRITE, 0, false)) {
+				  page1, REQ_OP_WRITE, false)) {
 			pr_debug("%s:%*s parity write error!\n", __func__,
 				 indent, "");
 			md_error(mddev, parity_rdev);
···
 			int s = pp_size > PAGE_SIZE ? PAGE_SIZE : pp_size;
 
 			if (!sync_page_io(rdev, sector - rdev->data_offset,
-					s, page, REQ_OP_READ, 0, false)) {
+					s, page, REQ_OP_READ, false)) {
 				md_error(mddev, rdev);
 				ret = -EIO;
 				goto out;
···
 
 	if (!sync_page_io(rdev, rdev->ppl.sector - rdev->data_offset,
 			  PPL_HEADER_SIZE, page, REQ_OP_WRITE | REQ_SYNC |
-			  REQ_FUA, 0, false)) {
+			  REQ_FUA, false)) {
 		md_error(rdev->mddev, rdev);
 		ret = -EIO;
 	}
···
 		if (!sync_page_io(rdev,
 				  rdev->ppl.sector - rdev->data_offset +
 				  pplhdr_offset, PAGE_SIZE, page, REQ_OP_READ,
-				  0, false)) {
+				  false)) {
 			md_error(mddev, rdev);
 			ret = -EIO;
 			/* if not able to read - don't recover any PPL */

drivers/md/raid5.c

···
 	should_defer = conf->batch_bio_dispatch && conf->group_cnt;
 
 	for (i = disks; i--; ) {
-		int op, op_flags = 0;
+		enum req_op op;
+		blk_opf_t op_flags = 0;
 		int replace_only = 0;
 		struct bio *bi, *rbi;
 		struct md_rdev *rdev, *rrdev = NULL;

drivers/memstick/core/ms_block.c

···
 	return 0;
 
 out_cleanup_disk:
-	blk_cleanup_disk(msb->disk);
+	put_disk(msb->disk);
 out_free_tag_set:
 	blk_mq_free_tag_set(&msb->tag_set);
 out_release_id:
···
 
 	/* Remove the disk */
 	del_gendisk(msb->disk);
-	blk_cleanup_queue(msb->queue);
 	blk_mq_free_tag_set(&msb->tag_set);
 	msb->queue = NULL;
 

drivers/memstick/core/mspro_block.c

···
 	return 0;
 
 out_cleanup_disk:
-	blk_cleanup_disk(msb->disk);
+	put_disk(msb->disk);
 out_free_tag_set:
 	blk_mq_free_tag_set(&msb->tag_set);
 out_release_id:
···
 	del_gendisk(msb->disk);
 	dev_dbg(&card->dev, "mspro block remove\n");
 
-	blk_cleanup_queue(msb->queue);
 	blk_mq_free_tag_set(&msb->tag_set);
 	msb->queue = NULL;
 

drivers/mmc/core/block.c

···
 		dev_set_drvdata(&card->dev, md);
 	ret = device_add_disk(md->parent, md->disk, mmc_disk_attr_groups);
 	if (ret)
-		goto err_cleanup_queue;
+		goto err_put_disk;
 	return md;
 
- err_cleanup_queue:
-	blk_cleanup_queue(md->disk->queue);
+ err_put_disk:
+	put_disk(md->disk);
 	blk_mq_free_tag_set(&md->queue.tag_set);
  err_kfree:
 	kfree(md);

drivers/mmc/core/queue.c

···
 	}
 }
 
-static enum blk_eh_timer_return mmc_mq_timed_out(struct request *req,
-						 bool reserved)
+static enum blk_eh_timer_return mmc_mq_timed_out(struct request *req)
 {
 	struct request_queue *q = req->q;
 	struct mmc_queue *mq = q->queuedata;
···
 	if (blk_queue_quiesced(q))
 		blk_mq_unquiesce_queue(q);
 
-	blk_cleanup_queue(q);
 	blk_mq_free_tag_set(&mq->tag_set);
 
 	/*

drivers/mtd/mtd_blkdevs.c

···
 	struct mtd_blktrans_dev *dev =
 		container_of(kref, struct mtd_blktrans_dev, ref);
 
-	blk_cleanup_disk(dev->disk);
+	put_disk(dev->disk);
 	blk_mq_free_tag_set(dev->tag_set);
 	kfree(dev->tag_set);
 	list_del(&dev->list);
···
 	return 0;
 
 out_cleanup_disk:
-	blk_cleanup_disk(new->disk);
+	put_disk(new->disk);
 out_free_tag_set:
 	blk_mq_free_tag_set(new->tag_set);
 out_kfree_tag_set:

drivers/mtd/ubi/block.c

···
 out_remove_minor:
 	idr_remove(&ubiblock_minor_idr, gd->first_minor);
 out_cleanup_disk:
-	blk_cleanup_disk(dev->gd);
+	put_disk(dev->gd);
 out_free_tags:
 	blk_mq_free_tag_set(&dev->tag_set);
 out_free_dev:
···
 	destroy_workqueue(dev->wq);
 	/* Finally destroy the blk queue */
 	dev_info(disk_to_dev(dev->gd), "released");
-	blk_cleanup_disk(dev->gd);
+	put_disk(dev->gd);
 	blk_mq_free_tag_set(&dev->tag_set);
 	idr_remove(&ubiblock_minor_idr, dev->gd->first_minor);
 }

drivers/nvdimm/btt.c

···
 
 static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
 			struct page *page, unsigned int len, unsigned int off,
-			unsigned int op, sector_t sector)
+			enum req_op op, sector_t sector)
 {
 	int ret;
 
···
 }
 
 static int btt_rw_page(struct block_device *bdev, sector_t sector,
-		struct page *page, unsigned int op)
+		struct page *page, enum req_op op)
 {
 	struct btt *btt = bdev->bd_disk->private_data;
 	int rc;
···
 	return 0;
 
 out_cleanup_disk:
-	blk_cleanup_disk(btt->btt_disk);
+	put_disk(btt->btt_disk);
 	return rc;
 }
 
 static void btt_blk_cleanup(struct btt *btt)
 {
 	del_gendisk(btt->btt_disk);
-	blk_cleanup_disk(btt->btt_disk);
+	put_disk(btt->btt_disk);
 }
 
 /**

drivers/nvdimm/pmem.c

···
 }
 
 static int pmem_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, unsigned int op)
+		       struct page *page, enum req_op op)
 {
 	struct pmem_device *pmem = bdev->bd_disk->private_data;
 	blk_status_t rc;
···
 	put_dax(pmem->dax_dev);
 	del_gendisk(pmem->disk);
 
-	blk_cleanup_disk(pmem->disk);
+	put_disk(pmem->disk);
 }
 
 static int pmem_attach_disk(struct device *dev,
···
 	kill_dax(pmem->dax_dev);
 	put_dax(pmem->dax_dev);
 out:
-	blk_cleanup_disk(pmem->disk);
+	put_disk(pmem->disk);
 	return rc;
 }
 

drivers/nvme/host/apple.c

···
 	}
 }
 
-static enum blk_eh_timer_return apple_nvme_timeout(struct request *req,
-						   bool reserved)
+static enum blk_eh_timer_return apple_nvme_timeout(struct request *req)
 {
 	struct apple_nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct apple_nvme_queue *q = iod->q;
···
 
 	if (!blk_get_queue(anv->ctrl.admin_q)) {
 		nvme_start_admin_queue(&anv->ctrl);
-		blk_cleanup_queue(anv->ctrl.admin_q);
+		blk_mq_destroy_queue(anv->ctrl.admin_q);
 		anv->ctrl.admin_q = NULL;
 		ret = -ENODEV;
 		goto put_dev;

drivers/nvme/host/core.c

···
 }
 EXPORT_SYMBOL_GPL(nvme_host_path_error);
 
-bool nvme_cancel_request(struct request *req, void *data, bool reserved)
+bool nvme_cancel_request(struct request *req, void *data)
 {
 	dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
 				"Cancelling I/O %d", req->tag);
···
 	mutex_unlock(&ctrl->subsys->lock);
 	nvme_put_ns_head(ns->head);
  out_cleanup_disk:
-	blk_cleanup_disk(disk);
+	put_disk(disk);
  out_free_ns:
 	kfree(ns);
  out_free_id:
···
 	if (!nvme_ns_head_multipath(ns->head))
 		nvme_cdev_del(&ns->cdev, &ns->cdev_device);
 	del_gendisk(ns->disk);
-	blk_cleanup_queue(ns->queue);
 
 	down_write(&ns->ctrl->namespaces_rwsem);
 	list_del_init(&ns->list);

drivers/nvme/host/fc.c

···
 	unsigned long flags;
 
 	if (ctrl->ctrl.tagset) {
-		blk_cleanup_queue(ctrl->ctrl.connect_q);
+		blk_mq_destroy_queue(ctrl->ctrl.connect_q);
 		blk_mq_free_tag_set(&ctrl->tag_set);
 	}
 
···
 	spin_unlock_irqrestore(&ctrl->rport->lock, flags);
 
 	nvme_start_admin_queue(&ctrl->ctrl);
-	blk_cleanup_queue(ctrl->ctrl.admin_q);
-	blk_cleanup_queue(ctrl->ctrl.fabrics_q);
+	blk_mq_destroy_queue(ctrl->ctrl.admin_q);
+	blk_mq_destroy_queue(ctrl->ctrl.fabrics_q);
 	blk_mq_free_tag_set(&ctrl->admin_tag_set);
 
 	kfree(ctrl->queues);
···
  * status. The done path will return the io request back to the block
  * layer with an error status.
  */
-static bool
-nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
+static bool nvme_fc_terminate_exchange(struct request *req, void *data)
 {
 	struct nvme_ctrl *nctrl = data;
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
···
 	nvme_reset_ctrl(&ctrl->ctrl);
 }
 
-static enum blk_eh_timer_return
-nvme_fc_timeout(struct request *rq, bool reserved)
+static enum blk_eh_timer_return nvme_fc_timeout(struct request *rq)
 {
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
 	struct nvme_fc_ctrl *ctrl = op->ctrl;
···
 out_delete_hw_queues:
 	nvme_fc_delete_hw_io_queues(ctrl);
 out_cleanup_blk_queue:
-	blk_cleanup_queue(ctrl->ctrl.connect_q);
+	blk_mq_destroy_queue(ctrl->ctrl.connect_q);
 out_free_tag_set:
 	blk_mq_free_tag_set(&ctrl->tag_set);
 	nvme_fc_free_io_queues(ctrl);
···
 	return ERR_PTR(-EIO);
 
 out_cleanup_admin_q:
-	blk_cleanup_queue(ctrl->ctrl.admin_q);
+	blk_mq_destroy_queue(ctrl->ctrl.admin_q);
 out_cleanup_fabrics_q:
-	blk_cleanup_queue(ctrl->ctrl.fabrics_q);
+	blk_mq_destroy_queue(ctrl->ctrl.fabrics_q);
 out_free_admin_tag_set:
 	blk_mq_free_tag_set(&ctrl->admin_tag_set);
 out_free_queues:

drivers/nvme/host/ioctl.c

···
 		struct nvme_command *cmd, void __user *ubuffer,
 		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
 		u32 meta_seed, void **metap, unsigned timeout, bool vec,
-		unsigned int rq_flags, blk_mq_req_flags_t blk_flags)
+		blk_opf_t rq_flags, blk_mq_req_flags_t blk_flags)
 {
 	bool write = nvme_is_write(cmd);
 	struct nvme_ns *ns = q->queuedata;
···
 	struct nvme_uring_data d;
 	struct nvme_command c;
 	struct request *req;
-	unsigned int rq_flags = 0;
+	blk_opf_t rq_flags = 0;
 	blk_mq_req_flags_t blk_flags = 0;
 	void *meta = NULL;
 

drivers/nvme/host/multipath.c

···
 				   ns->head->disk->queue);
 #ifdef CONFIG_BLK_DEV_ZONED
 	if (blk_queue_is_zoned(ns->queue) && ns->head->disk)
-		ns->head->disk->queue->nr_zones = ns->queue->nr_zones;
+		ns->head->disk->nr_zones = ns->disk->nr_zones;
 #endif
 }
 
···
 	/* make sure all pending bios are cleaned up */
 	kblockd_schedule_work(&head->requeue_work);
 	flush_work(&head->requeue_work);
-	blk_cleanup_disk(head->disk);
+	put_disk(head->disk);
 }
 
 void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl)

drivers/nvme/host/nvme.h

···
 }
 
 blk_status_t nvme_host_path_error(struct request *req);
-bool nvme_cancel_request(struct request *req, void *data, bool reserved);
+bool nvme_cancel_request(struct request *req, void *data);
 void nvme_cancel_tagset(struct nvme_ctrl *ctrl);
 void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl);
 bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
···
 int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
 void nvme_start_freeze(struct nvme_ctrl *ctrl);
 
-static inline unsigned int nvme_req_op(struct nvme_command *cmd)
+static inline enum req_op nvme_req_op(struct nvme_command *cmd)
 {
 	return nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN;
 }

drivers/nvme/host/pci.c

···
 		 "Try \"nvme_core.default_ps_max_latency_us=0 pcie_aspm=off\" and report a bug\n");
 }
 
-static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
+static enum blk_eh_timer_return nvme_timeout(struct request *req)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct nvme_queue *nvmeq = iod->nvmeq;
···
 		 * queue to flush these to completion.
 		 */
 		nvme_start_admin_queue(&dev->ctrl);
-		blk_cleanup_queue(dev->ctrl.admin_q);
+		blk_mq_destroy_queue(dev->ctrl.admin_q);
 		blk_mq_free_tag_set(&dev->admin_tagset);
 	}
 }

drivers/nvme/host/rdma.c

···
 		bool remove)
 {
 	if (remove) {
-		blk_cleanup_queue(ctrl->ctrl.admin_q);
-		blk_cleanup_queue(ctrl->ctrl.fabrics_q);
+		blk_mq_destroy_queue(ctrl->ctrl.admin_q);
+		blk_mq_destroy_queue(ctrl->ctrl.fabrics_q);
 		blk_mq_free_tag_set(ctrl->ctrl.admin_tagset);
 	}
 	if (ctrl->async_event_sqe.data) {
···
 	nvme_cancel_admin_tagset(&ctrl->ctrl);
 out_cleanup_queue:
 	if (new)
-		blk_cleanup_queue(ctrl->ctrl.admin_q);
+		blk_mq_destroy_queue(ctrl->ctrl.admin_q);
 out_cleanup_fabrics_q:
 	if (new)
-		blk_cleanup_queue(ctrl->ctrl.fabrics_q);
+		blk_mq_destroy_queue(ctrl->ctrl.fabrics_q);
 out_free_tagset:
 	if (new)
 		blk_mq_free_tag_set(ctrl->ctrl.admin_tagset);
···
 		bool remove)
 {
 	if (remove) {
-		blk_cleanup_queue(ctrl->ctrl.connect_q);
+		blk_mq_destroy_queue(ctrl->ctrl.connect_q);
 		blk_mq_free_tag_set(ctrl->ctrl.tagset);
 	}
 	nvme_rdma_free_io_queues(ctrl);
···
 out_cleanup_connect_q:
 	nvme_cancel_tagset(&ctrl->ctrl);
 	if (new)
-		blk_cleanup_queue(ctrl->ctrl.connect_q);
+		blk_mq_destroy_queue(ctrl->ctrl.connect_q);
 out_free_tag_set:
 	if (new)
 		blk_mq_free_tag_set(ctrl->ctrl.tagset);
···
 	nvmf_complete_timed_out_request(rq);
 }
 
-static enum blk_eh_timer_return
-nvme_rdma_timeout(struct request *rq, bool reserved)
+static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq)
 {
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_rdma_queue *queue = req->queue;

drivers/nvme/host/tcp.c

···
 {
 	nvme_tcp_stop_io_queues(ctrl);
 	if (remove) {
-		blk_cleanup_queue(ctrl->connect_q);
+		blk_mq_destroy_queue(ctrl->connect_q);
 		blk_mq_free_tag_set(ctrl->tagset);
 	}
 	nvme_tcp_free_io_queues(ctrl);
···
 out_cleanup_connect_q:
 	nvme_cancel_tagset(ctrl);
 	if (new)
-		blk_cleanup_queue(ctrl->connect_q);
+		blk_mq_destroy_queue(ctrl->connect_q);
 out_free_tag_set:
 	if (new)
 		blk_mq_free_tag_set(ctrl->tagset);
···
 {
 	nvme_tcp_stop_queue(ctrl, 0);
 	if (remove) {
-		blk_cleanup_queue(ctrl->admin_q);
-		blk_cleanup_queue(ctrl->fabrics_q);
+		blk_mq_destroy_queue(ctrl->admin_q);
+		blk_mq_destroy_queue(ctrl->fabrics_q);
 		blk_mq_free_tag_set(ctrl->admin_tagset);
 	}
 	nvme_tcp_free_admin_queue(ctrl);
···
 	nvme_cancel_admin_tagset(ctrl);
 out_cleanup_queue:
 	if (new)
-		blk_cleanup_queue(ctrl->admin_q);
+		blk_mq_destroy_queue(ctrl->admin_q);
 out_cleanup_fabrics_q:
 	if (new)
-		blk_cleanup_queue(ctrl->fabrics_q);
+		blk_mq_destroy_queue(ctrl->fabrics_q);
 out_free_tagset:
 	if (new)
 		blk_mq_free_tag_set(ctrl->admin_tagset);
···
 	nvmf_complete_timed_out_request(rq);
 }
 
-static enum blk_eh_timer_return
-nvme_tcp_timeout(struct request *rq, bool reserved)
+static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq)
 {
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;

drivers/nvme/host/zns.c

···
 		goto free_data;
 	}
 
-	blk_queue_set_zoned(ns->disk, BLK_ZONED_HM);
+	disk_set_zoned(ns->disk, BLK_ZONED_HM);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
-	blk_queue_max_open_zones(q, le32_to_cpu(id->mor) + 1);
-	blk_queue_max_active_zones(q, le32_to_cpu(id->mar) + 1);
+	disk_set_max_open_zones(ns->disk, le32_to_cpu(id->mor) + 1);
+	disk_set_max_active_zones(ns->disk, le32_to_cpu(id->mar) + 1);
 free_data:
 	kfree(id);
 	return status;

drivers/nvme/target/io-cmd-bdev.c

···
 	struct scatterlist *sg;
 	struct blk_plug plug;
 	sector_t sector;
-	int op, i, rc;
+	blk_opf_t opf;
+	int i, rc;
 	struct sg_mapping_iter prot_miter;
 	unsigned int iter_flags;
 	unsigned int total_len = nvmet_rw_data_len(req) + req->metadata_len;
···
 	}
 
 	if (req->cmd->rw.opcode == nvme_cmd_write) {
-		op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
+		opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
 		if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
-			op |= REQ_FUA;
+			opf |= REQ_FUA;
 		iter_flags = SG_MITER_TO_SG;
 	} else {
-		op = REQ_OP_READ;
+		opf = REQ_OP_READ;
 		iter_flags = SG_MITER_FROM_SG;
 	}
 
 	if (is_pci_p2pdma_page(sg_page(req->sg)))
-		op |= REQ_NOMERGE;
+		opf |= REQ_NOMERGE;
 
 	sector = nvmet_lba_to_sect(req->ns, req->cmd->rw.slba);
 
 	if (nvmet_use_inline_bvec(req)) {
 		bio = &req->b.inline_bio;
 		bio_init(bio, req->ns->bdev, req->inline_bvec,
-			 ARRAY_SIZE(req->inline_bvec), op);
+			 ARRAY_SIZE(req->inline_bvec), opf);
 	} else {
-		bio = bio_alloc(req->ns->bdev, bio_max_segs(sg_cnt), op,
+		bio = bio_alloc(req->ns->bdev, bio_max_segs(sg_cnt), opf,
 				GFP_KERNEL);
 	}
 	bio->bi_iter.bi_sector = sector;
···
 			}
 
 			bio = bio_alloc(req->ns->bdev, bio_max_segs(sg_cnt),
-					op, GFP_KERNEL);
+					opf, GFP_KERNEL);
 			bio->bi_iter.bi_sector = sector;
 
 			bio_chain(bio, prev);

drivers/nvme/target/loop.c

···
 	if (!test_and_clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags))
 		return;
 	nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
-	blk_cleanup_queue(ctrl->ctrl.admin_q);
-	blk_cleanup_queue(ctrl->ctrl.fabrics_q);
+	blk_mq_destroy_queue(ctrl->ctrl.admin_q);
+	blk_mq_destroy_queue(ctrl->ctrl.fabrics_q);
 	blk_mq_free_tag_set(&ctrl->admin_tag_set);
 }
 
···
 	mutex_unlock(&nvme_loop_ctrl_mutex);
 
 	if (nctrl->tagset) {
-		blk_cleanup_queue(ctrl->ctrl.connect_q);
+		blk_mq_destroy_queue(ctrl->ctrl.connect_q);
 		blk_mq_free_tag_set(&ctrl->tag_set);
 	}
 	kfree(ctrl->queues);
···
 
 out_cleanup_queue:
 	clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags);
-	blk_cleanup_queue(ctrl->ctrl.admin_q);
+	blk_mq_destroy_queue(ctrl->ctrl.admin_q);
 out_cleanup_fabrics_q:
-	blk_cleanup_queue(ctrl->ctrl.fabrics_q);
+	blk_mq_destroy_queue(ctrl->ctrl.fabrics_q);
 out_free_tagset:
 	blk_mq_free_tag_set(&ctrl->admin_tag_set);
 out_free_sq:
···
 	return 0;
 
 out_cleanup_connect_q:
-	blk_cleanup_queue(ctrl->ctrl.connect_q);
+	blk_mq_destroy_queue(ctrl->ctrl.connect_q);
 out_free_tagset:
 	blk_mq_free_tag_set(&ctrl->tag_set);
 out_destroy_queues:

drivers/nvme/target/zns.c

···
 	 * zones, reject the device. Otherwise, use report zones to detect if
 	 * the device has conventional zones.
 	 */
-	if (ns->bdev->bd_disk->queue->conv_zones_bitmap)
+	if (ns->bdev->bd_disk->conv_zones_bitmap)
 		return false;
 
-	ret = blkdev_report_zones(ns->bdev, 0, blkdev_nr_zones(bd_disk),
+	ret = blkdev_report_zones(ns->bdev, 0, bdev_nr_zones(ns->bdev),
 				  validate_conv_zones_cb, NULL);
 	if (ret < 0)
 		return false;
···
 {
 	unsigned int sect = nvmet_lba_to_sect(req->ns, req->cmd->zmr.slba);
 
-	return blkdev_nr_zones(req->ns->bdev->bd_disk) -
+	return bdev_nr_zones(req->ns->bdev) -
 		(sect >> ilog2(bdev_zone_sectors(req->ns->bdev)));
 }
 
···
 	queue_work(zbd_wq, &req->z.zmgmt_work);
 }
 
-static inline enum req_opf zsa_req_op(u8 zsa)
+static inline enum req_op zsa_req_op(u8 zsa)
 {
 	switch (zsa) {
 	case NVME_ZONE_OPEN:
···
 static u16 nvmet_bdev_zone_mgmt_emulate_all(struct nvmet_req *req)
 {
 	struct block_device *bdev = req->ns->bdev;
-	unsigned int nr_zones = blkdev_nr_zones(bdev->bd_disk);
+	unsigned int nr_zones = bdev_nr_zones(bdev);
 	struct request_queue *q = bdev_get_queue(bdev);
 	struct bio *bio = NULL;
 	sector_t sector = 0;
···
 		ret = 0;
 	}
 
-	while (sector < get_capacity(bdev->bd_disk)) {
-		if (test_bit(blk_queue_zone_no(q, sector), d.zbitmap)) {
+	while (sector < bdev_nr_sectors(bdev)) {
+		if (test_bit(disk_zone_no(bdev->bd_disk, sector), d.zbitmap)) {
 			bio = blk_next_bio(bio, bdev, 0,
 				zsa_req_op(req->cmd->zms.zsa) | REQ_SYNC,
 				GFP_KERNEL);
···
 			/* This may take a while, so be nice to others */
 			cond_resched();
 		}
-		sector += blk_queue_zone_sectors(q);
+		sector += bdev_zone_sectors(bdev);
 	}
 
 	if (bio) {
···
 {
 	struct nvmet_req *req = container_of(w, struct nvmet_req, z.zmgmt_work);
 	sector_t sect = nvmet_lba_to_sect(req->ns, req->cmd->zms.slba);
-	enum req_opf op = zsa_req_op(req->cmd->zms.zsa);
+	enum req_op op = zsa_req_op(req->cmd->zms.zsa);
 	struct block_device *bdev = req->ns->bdev;
 	sector_t zone_sectors = bdev_zone_sectors(bdev);
 	u16 status = NVME_SC_SUCCESS;
···
 void nvmet_bdev_execute_zone_append(struct nvmet_req *req)
 {
 	sector_t sect = nvmet_lba_to_sect(req->ns, req->cmd->rw.slba);
-	const unsigned int op = REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE;
+	const blk_opf_t opf = REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE;
 	u16 status = NVME_SC_SUCCESS;
 	unsigned int total_len = 0;
 	struct scatterlist *sg;
···
 	if (nvmet_use_inline_bvec(req)) {
 		bio = &req->z.inline_bio;
 		bio_init(bio, req->ns->bdev, req->inline_bvec,
-			 ARRAY_SIZE(req->inline_bvec), op);
+			 ARRAY_SIZE(req->inline_bvec), opf);
 	} else {
-		bio = bio_alloc(req->ns->bdev, req->sg_cnt, op, GFP_KERNEL);
+		bio = bio_alloc(req->ns->bdev, req->sg_cnt, opf, GFP_KERNEL);
 	}
 
 	bio->bi_end_io = nvmet_bdev_zone_append_bio_done;

drivers/s390/block/dasd.c

···
  * BLK_EH_DONE if the request is handled or terminated
  *		      by the driver.
  */
-enum blk_eh_timer_return dasd_times_out(struct request *req, bool reserved)
+enum blk_eh_timer_return dasd_times_out(struct request *req)
 {
 	struct dasd_block *block = req->q->queuedata;
 	struct dasd_device *device;
···
 static void dasd_free_queue(struct dasd_block *block)
 {
 	if (block->request_queue) {
-		blk_cleanup_queue(block->request_queue);
+		blk_mq_destroy_queue(block->request_queue);
 		blk_mq_free_tag_set(&block->tag_set);
 		block->request_queue = NULL;
 	}

drivers/s390/block/dasd_genhd.c

···
 	if (base->devindex >= DASD_PER_MAJOR)
 		return -EBUSY;
 
-	gdp = __alloc_disk_node(block->request_queue, NUMA_NO_NODE,
-				&dasd_bio_compl_lkclass);
+	gdp = blk_mq_alloc_disk_for_queue(block->request_queue,
+					  &dasd_bio_compl_lkclass);
 	if (!gdp)
 		return -ENOMEM;
 

drivers/s390/block/dasd_int.h

···
 struct dasd_block *dasd_alloc_block(void);
 void dasd_free_block(struct dasd_block *);
 
-enum blk_eh_timer_return dasd_times_out(struct request *req, bool reserved);
+enum blk_eh_timer_return dasd_times_out(struct request *req);
 
 void dasd_enable_device(struct dasd_device *);
 void dasd_set_target_state(struct dasd_device *, int);

drivers/s390/block/dcssblk.c

···
 	kill_dax(dev_info->dax_dev);
 	put_dax(dev_info->dax_dev);
 	del_gendisk(dev_info->gd);
-	blk_cleanup_disk(dev_info->gd);
+	put_disk(dev_info->gd);
 	up_write(&dcssblk_devices_sem);
 
 	if (device_remove_file_self(dev, attr)) {
···
 	put_dax(dev_info->dax_dev);
 put_dev:
 	list_del(&dev_info->lh);
-	blk_cleanup_disk(dev_info->gd);
+	put_disk(dev_info->gd);
 	list_for_each_entry(seg_info, &dev_info->seg_list, lh) {
 		segment_unload(seg_info->segment_name);
 	}
···
 dev_list_del:
 	list_del(&dev_info->lh);
 release_gd:
-	blk_cleanup_disk(dev_info->gd);
+	put_disk(dev_info->gd);
 	up_write(&dcssblk_devices_sem);
 seg_list_del:
 	if (dev_info == NULL)
···
 	kill_dax(dev_info->dax_dev);
 	put_dax(dev_info->dax_dev);
 	del_gendisk(dev_info->gd);
-	blk_cleanup_disk(dev_info->gd);
+	put_disk(dev_info->gd);
 
 	/* unload all related segments */
 	list_for_each_entry(entry, &dev_info->seg_list, lh)

drivers/s390/block/scm_blk.c

···
 	return 0;
 
 out_cleanup_disk:
-	blk_cleanup_disk(bdev->gendisk);
+	put_disk(bdev->gendisk);
 out_tag:
 	blk_mq_free_tag_set(&bdev->tag_set);
 out:
···
 void scm_blk_dev_cleanup(struct scm_blk_dev *bdev)
 {
 	del_gendisk(bdev->gendisk);
-	blk_cleanup_disk(bdev->gendisk);
+	put_disk(bdev->gendisk);
 	blk_mq_free_tag_set(&bdev->tag_set);
 }
 

drivers/scsi/aacraid/comminit.c

···
 	q->entries = qsize;
 }
 
-static bool wait_for_io_iter(struct scsi_cmnd *cmd, void *data, bool rsvd)
+static bool wait_for_io_iter(struct scsi_cmnd *cmd, void *data)
 {
 	int *active = data;
 

drivers/scsi/aacraid/linit.c

···
 	int krlcnt;
 };
 
-static bool fib_count_iter(struct scsi_cmnd *scmnd, void *data, bool reserved)
+static bool fib_count_iter(struct scsi_cmnd *scmnd, void *data)
 {
 	struct fib_count_data *fib_count = data;
 

drivers/scsi/device_handler/scsi_dh_alua.c

···
 		       int bufflen, struct scsi_sense_hdr *sshdr, int flags)
 {
 	u8 cdb[MAX_COMMAND_SIZE];
-	int req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+	blk_opf_t req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
 		REQ_FAILFAST_DRIVER;
 
 	/* Prepare the command. */
···
 	u8 cdb[MAX_COMMAND_SIZE];
 	unsigned char stpg_data[8];
 	int stpg_len = 8;
-	int req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+	blk_opf_t req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
 		REQ_FAILFAST_DRIVER;
 
 	/* Prepare the data buffer */

drivers/scsi/device_handler/scsi_dh_emc.c

···
 	unsigned char cdb[MAX_COMMAND_SIZE];
 	int err, res = SCSI_DH_OK, len;
 	struct scsi_sense_hdr sshdr;
-	u64 req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+	blk_opf_t req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
 		REQ_FAILFAST_DRIVER;
 
 	if (csdev->flags & CLARIION_SHORT_TRESPASS) {

drivers/scsi/device_handler/scsi_dh_hp_sw.c

···
 	unsigned char cmd[6] = { TEST_UNIT_READY };
 	struct scsi_sense_hdr sshdr;
 	int ret = SCSI_DH_OK, res;
-	u64 req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+	blk_opf_t req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
 		REQ_FAILFAST_DRIVER;
 
 retry:
···
 	struct scsi_device *sdev = h->sdev;
 	int res, rc = SCSI_DH_OK;
 	int retry_cnt = HP_SW_RETRIES;
-	u64 req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+	blk_opf_t req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
 		REQ_FAILFAST_DRIVER;
 
 retry:

drivers/scsi/device_handler/scsi_dh_rdac.c

···
 	unsigned char cdb[MAX_COMMAND_SIZE];
 	struct scsi_sense_hdr sshdr;
 	unsigned int data_size;
-	u64 req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+	blk_opf_t req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
 		REQ_FAILFAST_DRIVER;
 
 	spin_lock(&ctlr->ms_lock);

drivers/scsi/fnic/fnic_scsi.c

···
 	return wq_work_done;
 }
 
-static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data,
-				 bool reserved)
+static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data)
 {
 	const int tag = scsi_cmd_to_rq(sc)->tag;
 	struct fnic *fnic = data;
···
 	int term_cnt;
 };
 
-static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data,
-				     bool reserved)
+static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data)
 {
 	struct fnic_rport_abort_io_iter_data *iter_data = data;
 	struct fnic *fnic = iter_data->fnic;
···
 	int ret;
 };
 
-static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc,
-				     void *data, bool reserved)
+static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data)
 {
 	struct fnic_pending_aborts_iter_data *iter_data = data;
 	struct fnic *fnic = iter_data->fnic;
···
 	enum fnic_ioreq_state old_ioreq_state;
 
 	if (sc == iter_data->lr_sc || sc->device != lun_dev)
-		return true;
-	if (reserved)
 		return true;
 
 	io_lock = fnic_io_lock_tag(fnic, abt_tag);
···
 
 }
 
-static bool fnic_abts_pending_iter(struct scsi_cmnd *sc, void *data,
-				   bool reserved)
+static bool fnic_abts_pending_iter(struct scsi_cmnd *sc, void *data)
 {
 	struct fnic_pending_aborts_iter_data *iter_data = data;
 	struct fnic *fnic = iter_data->fnic;

drivers/scsi/hosts.c

···
 }
 EXPORT_SYMBOL(scsi_host_get);
 
-static bool scsi_host_check_in_flight(struct request *rq, void *data,
-				      bool reserved)
+static bool scsi_host_check_in_flight(struct request *rq, void *data)
 {
 	int *count = data;
 	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
···
 }
 EXPORT_SYMBOL_GPL(scsi_flush_work);
 
-static bool complete_all_cmds_iter(struct request *rq, void *data, bool rsvd)
+static bool complete_all_cmds_iter(struct request *rq, void *data)
 {
 	struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(rq);
 	enum scsi_host_status status = *(enum scsi_host_status *)data;
···
 EXPORT_SYMBOL_GPL(scsi_host_complete_all_commands);
 
 struct scsi_host_busy_iter_data {
-	bool (*fn)(struct scsi_cmnd *, void *, bool);
+	bool (*fn)(struct scsi_cmnd *, void *);
 	void *priv;
 };
 
-static bool __scsi_host_busy_iter_fn(struct request *req, void *priv,
-				   bool reserved)
+static bool __scsi_host_busy_iter_fn(struct request *req, void *priv)
 {
 	struct scsi_host_busy_iter_data *iter_data = priv;
 	struct scsi_cmnd *sc = blk_mq_rq_to_pdu(req);
 
-	return iter_data->fn(sc, iter_data->priv, reserved);
+	return iter_data->fn(sc, iter_data->priv);
 }
 
 /**
···
  * ithas to be provided by the caller
  **/
 void scsi_host_busy_iter(struct Scsi_Host *shost,
-			 bool (*fn)(struct scsi_cmnd *, void *, bool),
+			 bool (*fn)(struct scsi_cmnd *, void *),
 			 void *priv)
 {
 	struct scsi_host_busy_iter_data iter_data = {

drivers/scsi/mpi3mr/mpi3mr_os.c

···
  * mpi3mr_print_scmd - print individual SCSI command
  * @rq: Block request
  * @data: Adapter instance reference
- * @reserved: N/A. Currently not used
  *
  * Print the SCSI command details if it is in LLD scope.
  *
  * Return: true always.
  */
-static bool mpi3mr_print_scmd(struct request *rq,
-	void *data, bool reserved)
+static bool mpi3mr_print_scmd(struct request *rq, void *data)
 {
 	struct mpi3mr_ioc *mrioc = (struct mpi3mr_ioc *)data;
 	struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(rq);
···
  * mpi3mr_flush_scmd - Flush individual SCSI command
  * @rq: Block request
  * @data: Adapter instance reference
- * @reserved: N/A. Currently not used
  *
  * Return the SCSI command to the upper layers if it is in LLD
  * scope.
···
  * Return: true always.
  */
 
-static bool mpi3mr_flush_scmd(struct request *rq,
-	void *data, bool reserved)
+static bool mpi3mr_flush_scmd(struct request *rq, void *data)
 {
 	struct mpi3mr_ioc *mrioc = (struct mpi3mr_ioc *)data;
 	struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(rq);
···
  * mpi3mr_count_dev_pending - Count commands pending for a lun
  * @rq: Block request
  * @data: SCSI device reference
- * @reserved: Unused
  *
  * This is an iterator function called for each SCSI command in
  * a host and if the command is pending in the LLD for the
···
  * Return: true always.
  */
 
-static bool mpi3mr_count_dev_pending(struct request *rq,
-	void *data, bool reserved)
+static bool mpi3mr_count_dev_pending(struct request *rq, void *data)
 {
 	struct scsi_device *sdev = (struct scsi_device *)data;
 	struct mpi3mr_sdev_priv_data *sdev_priv_data = sdev->hostdata;
···
  * mpi3mr_count_tgt_pending - Count commands pending for target
  * @rq: Block request
  * @data: SCSI target reference
- * @reserved: Unused
  *
  * This is an iterator function called for each SCSI command in
  * a host and if the command is pending in the LLD for the
···
  * Return: true always.
  */
 
-static bool mpi3mr_count_tgt_pending(struct request *rq,
-	void *data, bool reserved)
+static bool mpi3mr_count_tgt_pending(struct request *rq, void *data)
 {
 	struct scsi_target *starget = (struct scsi_target *)data;
 	struct mpi3mr_stgt_priv_data *stgt_priv_data = starget->hostdata;

drivers/scsi/scsi_error.c

···
  *
  * Note: this function must be called only for a command that has timed out.
  * Because the block layer marks a request as complete before it calls
- * scsi_times_out(), a .scsi_done() call from the LLD for a command that has
+ * scsi_timeout(), a .scsi_done() call from the LLD for a command that has
  * timed out do not have any effect. Hence it is safe to call
  * scsi_finish_command() from this function.
  */
···
 }
 
 /**
- * scsi_times_out - Timeout function for normal scsi commands.
+ * scsi_timeout - Timeout function for normal scsi commands.
  * @req:	request that is timing out.
  *
  * Notes:
···
  *     normal completion function determines that the timer has already
  *     fired, then it mustn't do anything.
  */
-enum blk_eh_timer_return scsi_times_out(struct request *req)
+enum blk_eh_timer_return scsi_timeout(struct request *req)
 {
 	struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req);
 	enum blk_eh_timer_return rtn = BLK_EH_DONE;
···
  * scsi_noretry_cmd - determine if command should be failed fast
  * @scmd:	SCSI cmd to examine.
  */
-int scsi_noretry_cmd(struct scsi_cmnd *scmd)
+bool scsi_noretry_cmd(struct scsi_cmnd *scmd)
 {
 	struct request *req = scsi_cmd_to_rq(scmd);
 
···
 	case DID_TIME_OUT:
 		goto check_type;
 	case DID_BUS_BUSY:
-		return req->cmd_flags & REQ_FAILFAST_TRANSPORT;
+		return !!(req->cmd_flags & REQ_FAILFAST_TRANSPORT);
 	case DID_PARITY:
-		return req->cmd_flags & REQ_FAILFAST_DEV;
+		return !!(req->cmd_flags & REQ_FAILFAST_DEV);
 	case DID_ERROR:
 		if (get_status_byte(scmd) == SAM_STAT_RESERVATION_CONFLICT)
-			return 0;
+			return false;
 		fallthrough;
 	case DID_SOFT_ERROR:
-		return req->cmd_flags & REQ_FAILFAST_DRIVER;
+		return !!(req->cmd_flags & REQ_FAILFAST_DRIVER);
 	}
 
 	if (!scsi_status_is_check_condition(scmd->result))
-		return 0;
+		return false;
 
 check_type:
 	/*
···
 	 * the check condition was retryable.
 	 */
 	if (req->cmd_flags & REQ_FAILFAST_DEV || blk_rq_is_passthrough(req))
-		return 1;
+		return true;
 
-	return 0;
+	return false;
 }
 
 /**

drivers/scsi/scsi_lib.c

···
 	 * Requeue this command.  It will go before all other commands
 	 * that are already in the queue. Schedule requeue work under
 	 * lock such that the kblockd_schedule_work() call happens
-	 * before blk_cleanup_queue() finishes.
+	 * before blk_mq_destroy_queue() finishes.
 	 */
 	cmd->result = 0;
 
···
 int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		 int data_direction, void *buffer, unsigned bufflen,
 		 unsigned char *sense, struct scsi_sense_hdr *sshdr,
-		 int timeout, int retries, u64 flags, req_flags_t rq_flags,
-		 int *resid)
+		 int timeout, int retries, blk_opf_t flags,
+		 req_flags_t rq_flags, int *resid)
 {
 	struct request *req;
 	struct scsi_cmnd *scmd;
···
 		 * it and the queue.  Mitigate by taking a reference to the
 		 * queue and never touching the sdev again after we drop the
 		 * host lock.  Note: if __scsi_remove_device() invokes
-		 * blk_cleanup_queue() before the queue is run from this
+		 * blk_mq_destroy_queue() before the queue is run from this
 		 * function then blk_run_queue() will return immediately since
-		 * blk_cleanup_queue() marks the queue with QUEUE_FLAG_DYING.
+		 * blk_mq_destroy_queue() marks the queue with QUEUE_FLAG_DYING.
 		 */
 		slq = sdev->request_queue;
 		if (!blk_get_queue(slq))
···
  */
 static unsigned int scsi_rq_err_bytes(const struct request *rq)
 {
-	unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+	blk_opf_t ff = rq->cmd_flags & REQ_FAILFAST_MASK;
 	unsigned int bytes = 0;
 	struct bio *bio;
 
···
 	cmd->retries = 0;
 }
 
-struct request *scsi_alloc_request(struct request_queue *q,
-		unsigned int op, blk_mq_req_flags_t flags)
+struct request *scsi_alloc_request(struct request_queue *q, blk_opf_t opf,
+				   blk_mq_req_flags_t flags)
 {
 	struct request *rq;
 
-	rq = blk_mq_alloc_request(q, op, flags);
+	rq = blk_mq_alloc_request(q, opf, flags);
 	if (!IS_ERR(rq))
 		scsi_initialize_rq(rq);
 	return rq;
···
 		break;
 	}
 	return ret;
-}
-
-static enum blk_eh_timer_return scsi_timeout(struct request *req,
-		bool reserved)
-{
-	if (reserved)
-		return BLK_EH_RESET_TIMER;
-	return scsi_times_out(req);
 }
 
 static int scsi_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,

drivers/scsi/scsi_priv.h

···
 
 /* scsi_error.c */
 extern void scmd_eh_abort_handler(struct work_struct *work);
-extern enum blk_eh_timer_return scsi_times_out(struct request *req);
+extern enum blk_eh_timer_return scsi_timeout(struct request *req);
 extern int scsi_error_handler(void *host);
 extern enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *cmd);
 extern void scsi_eh_wakeup(struct Scsi_Host *shost);
···
 			struct list_head *done_q);
 int scsi_eh_get_sense(struct list_head *work_q,
 		      struct list_head *done_q);
-int scsi_noretry_cmd(struct scsi_cmnd *scmd);
+bool scsi_noretry_cmd(struct scsi_cmnd *scmd);
 void scsi_eh_done(struct scsi_cmnd *scmd);
 
 /* scsi_lib.c */

drivers/scsi/scsi_sysfs.c

···
 	scsi_device_set_state(sdev, SDEV_DEL);
 	mutex_unlock(&sdev->state_mutex);
 
-	blk_cleanup_queue(sdev->request_queue);
+	blk_mq_destroy_queue(sdev->request_queue);
 	cancel_work_sync(&sdev->requeue_work);
 
 	if (sdev->host->hostt->slave_destroy)

drivers/scsi/sd.c

···
 
 	if (sdkp->device->type == TYPE_ZBC) {
 		/* Host-managed */
-		blk_queue_set_zoned(sdkp->disk, BLK_ZONED_HM);
+		disk_set_zoned(sdkp->disk, BLK_ZONED_HM);
 	} else {
 		sdkp->zoned = zoned;
 		if (sdkp->zoned == 1) {
 			/* Host-aware */
-			blk_queue_set_zoned(sdkp->disk, BLK_ZONED_HA);
+			disk_set_zoned(sdkp->disk, BLK_ZONED_HA);
 		} else {
 			/* Regular disk or drive managed disk */
-			blk_queue_set_zoned(sdkp->disk, BLK_ZONED_NONE);
+			disk_set_zoned(sdkp->disk, BLK_ZONED_NONE);
 		}
 	}
 
···
 	if (!sdkp)
 		goto out;
 
-	gd = __alloc_disk_node(sdp->request_queue, NUMA_NO_NODE,
-			       &sd_bio_compl_lkclass);
+	gd = blk_mq_alloc_disk_for_queue(sdp->request_queue,
+					 &sd_bio_compl_lkclass);
 	if (!gd)
 		goto out_free;
 

drivers/scsi/sd_zbc.c

···
 	struct request *rq = scsi_cmd_to_rq(cmd);
 	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
 	unsigned int zno = blk_rq_zone_no(rq);
-	enum req_opf op = req_op(rq);
+	enum req_op op = req_op(rq);
 	unsigned long flags;
 
 	/*
···
 
 	if (sdkp->zone_info.zone_blocks == zone_blocks &&
 	    sdkp->zone_info.nr_zones == nr_zones &&
-	    disk->queue->nr_zones == nr_zones)
+	    disk->nr_zones == nr_zones)
 		goto unlock;
 
 	flags = memalloc_noio_save();
···
 		/*
 		 * This can happen for a host aware disk with partitions.
 		 * The block device zone model was already cleared by
-		 * blk_queue_set_zoned(). Only free the scsi disk zone
+		 * disk_set_zoned(). Only free the scsi disk zone
 		 * information and exit early.
 		 */
 		sd_zbc_free_zone_info(sdkp);
···
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
 	if (sdkp->zones_max_open == U32_MAX)
-		blk_queue_max_open_zones(q, 0);
+		disk_set_max_open_zones(disk, 0);
 	else
-		blk_queue_max_open_zones(q, sdkp->zones_max_open);
-	blk_queue_max_active_zones(q, 0);
+		disk_set_max_open_zones(disk, sdkp->zones_max_open);
+	disk_set_max_active_zones(disk, 0);
 	nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks);
 
 	/*

drivers/scsi/sr.c

···
 	if (!cd)
 		goto fail;
 
-	disk = __alloc_disk_node(sdev->request_queue, NUMA_NO_NODE,
-				 &sr_bio_compl_lkclass);
+	disk = blk_mq_alloc_disk_for_queue(sdev->request_queue,
+					   &sr_bio_compl_lkclass);
 	if (!disk)
 		goto fail_free;
 	mutex_init(&cd->lock);

drivers/target/target_core_iblock.c

···
 }
 
 static struct bio *iblock_get_bio(struct se_cmd *cmd, sector_t lba, u32 sg_num,
-				  unsigned int opf)
+				  blk_opf_t opf)
 {
 	struct iblock_dev *ib_dev = IBLOCK_DEV(cmd->se_dev);
 	struct bio *bio;
···
 	struct bio_list list;
 	struct scatterlist *sg;
 	u32 sg_num = sgl_nents;
-	unsigned int opf;
+	blk_opf_t opf;
 	unsigned bio_cnt;
 	int i, rc;
 	struct sg_mapping_iter prot_miter;

drivers/ufs/core/ufshcd.c

···
 	ufs_bsg_remove(hba);
 	ufshpb_remove(hba);
 	ufs_sysfs_remove_nodes(hba->dev);
-	blk_cleanup_queue(hba->tmf_queue);
+	blk_mq_destroy_queue(hba->tmf_queue);
 	blk_mq_free_tag_set(&hba->tmf_tag_set);
 	scsi_remove_host(hba->host);
 	/* disable interrupts */
···
 	return 0;
 
 free_tmf_queue:
-	blk_cleanup_queue(hba->tmf_queue);
+	blk_mq_destroy_queue(hba->tmf_queue);
 free_tmf_tag_set:
 	blk_mq_free_tag_set(&hba->tmf_tag_set);
 out_remove_scsi_host:

drivers/ufs/core/ufshpb.c

···
 	return 0;
 }
 
-static struct ufshpb_req *ufshpb_get_req(struct ufshpb_lu *hpb,
-					 int rgn_idx, enum req_opf dir,
-					 bool atomic)
+static struct ufshpb_req *ufshpb_get_req(struct ufshpb_lu *hpb, int rgn_idx,
+					 enum req_op op, bool atomic)
 {
 	struct ufshpb_req *rq;
 	struct request *req;
···
 		return NULL;
 
 retry:
-	req = blk_mq_alloc_request(hpb->sdev_ufs_lu->request_queue, dir,
+	req = blk_mq_alloc_request(hpb->sdev_ufs_lu->request_queue, op,
 			      BLK_MQ_REQ_NOWAIT);
 
 	if (!atomic && (PTR_ERR(req) == -EWOULDBLOCK) && (--retries > 0)) {

fs/btrfs/check-integrity.c

···
 	struct btrfsic_block *next_in_same_bio;
 	void *orig_bio_private;
 	bio_end_io_t *orig_bio_end_io;
-	int submit_bio_bh_rw;
+	blk_opf_t submit_bio_bh_rw;
 	u64 flush_gen; /* only valid if !never_written */
 };
 
···
 					  u64 dev_bytenr, char **mapped_datav,
 					  unsigned int num_pages,
 					  struct bio *bio, int *bio_is_patched,
-					  int submit_bio_bh_rw)
+					  blk_opf_t submit_bio_bh_rw)
 {
 	int is_metadata;
 	struct btrfsic_block *block;

fs/btrfs/compression.c

···
 
 
 static struct bio *alloc_compressed_bio(struct compressed_bio *cb, u64 disk_bytenr,
-					unsigned int opf, bio_end_io_t endio_func,
+					blk_opf_t opf, bio_end_io_t endio_func,
 					u64 *next_stripe_start)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(cb->inode->i_sb);
···
 				 unsigned int compressed_len,
 				 struct page **compressed_pages,
 				 unsigned int nr_pages,
-				 unsigned int write_flags,
+				 blk_opf_t write_flags,
 				 struct cgroup_subsys_state *blkcg_css,
 				 bool writeback)
 {
···
 	blk_status_t ret;
 	int skip_sum = inode->flags & BTRFS_INODE_NODATASUM;
 	const bool use_append = btrfs_use_zone_append(inode, disk_start);
-	const unsigned int bio_op = use_append ? REQ_OP_ZONE_APPEND : REQ_OP_WRITE;
+	const enum req_op bio_op = use_append ? REQ_OP_ZONE_APPEND : REQ_OP_WRITE;
 
 	ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
 	       IS_ALIGNED(len, fs_info->sectorsize));

fs/btrfs/compression.h

···
 				  unsigned int compressed_len,
 				  struct page **compressed_pages,
 				  unsigned int nr_pages,
-				  unsigned int write_flags,
+				  blk_opf_t write_flags,
 				  struct cgroup_subsys_state *blkcg_css,
 				  bool writeback);
 void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,

fs/btrfs/extent_io.c

···
 static int alloc_new_bio(struct btrfs_inode *inode,
 			 struct btrfs_bio_ctrl *bio_ctrl,
 			 struct writeback_control *wbc,
-			 unsigned int opf,
+			 blk_opf_t opf,
 			 bio_end_io_t end_io_func,
 			 u64 disk_bytenr, u32 offset, u64 file_offset,
 			 enum btrfs_compression_type compress_type)
···
  * @prev_bio_flags:  flags of previous bio to see if we can merge the current one
  * @compress_type:   compress type for current bio
  */
-static int submit_extent_page(unsigned int opf,
+static int submit_extent_page(blk_opf_t opf,
 			      struct writeback_control *wbc,
 			      struct btrfs_bio_ctrl *bio_ctrl,
 			      struct page *page, u64 disk_bytenr,
···
  */
 static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 		      struct btrfs_bio_ctrl *bio_ctrl,
-		      unsigned int read_flags, u64 *prev_em_start)
+		      blk_opf_t read_flags, u64 *prev_em_start)
 {
 	struct inode *inode = page->mapping->host;
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
···
 	int saved_ret = 0;
 	int ret = 0;
 	int nr = 0;
-	u32 opf = REQ_OP_WRITE;
-	const unsigned int write_flags = wbc_to_write_flags(wbc);
+	enum req_op op = REQ_OP_WRITE;
+	const blk_opf_t write_flags = wbc_to_write_flags(wbc);
 	bool has_error = false;
 	bool compressed;
 
···
 		iosize = min(min(em_end, end + 1), dirty_range_end) - cur;
 
 		if (btrfs_use_zone_append(inode, em->block_start))
-			opf = REQ_OP_ZONE_APPEND;
+			op = REQ_OP_ZONE_APPEND;
 
 		free_extent_map(em);
 		em = NULL;
···
 		 */
 		btrfs_page_clear_dirty(fs_info, page, cur, iosize);
 
-		ret = submit_extent_page(opf | write_flags, wbc,
+		ret = submit_extent_page(op | write_flags, wbc,
 					 &epd->bio_ctrl, page,
 					 disk_bytenr, iosize,
 					 cur - page_offset(page),
···
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
 	struct page *page = eb->pages[0];
-	unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META;
+	blk_opf_t write_flags = wbc_to_write_flags(wbc) | REQ_META;
 	bool no_dirty_ebs = false;
 	int ret;
 
···
 {
 	u64 disk_bytenr = eb->start;
 	int i, num_pages;
-	unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META;
+	blk_opf_t write_flags = wbc_to_write_flags(wbc) | REQ_META;
 	int ret = 0;
 
 	prepare_eb_write(eb);

fs/btrfs/inode.c

···
 	struct page *locked_page;
 	u64 start;
 	u64 end;
-	unsigned int write_flags;
+	blk_opf_t write_flags;
 	struct list_head extents;
 	struct cgroup_subsys_state *blkcg_css;
 	struct btrfs_work work;
···
 	int i;
 	bool should_compress;
 	unsigned nofs_flag;
-	const unsigned int write_flags = wbc_to_write_flags(wbc);
+	const blk_opf_t write_flags = wbc_to_write_flags(wbc);
 
 	unlock_extent(&inode->io_tree, start, end);
 

fs/btrfs/raid56.c

···
 			      unsigned int stripe_nr,
 			      unsigned int sector_nr,
 			      unsigned long bio_max_len,
-			      unsigned int opf)
+			      enum req_op op)
 {
 	const u32 sectorsize = rbio->bioc->fs_info->sectorsize;
 	struct bio *last = bio_list->tail;
···
 
 	/* put a new bio on the list */
 	bio = bio_alloc(stripe->dev->bdev, max(bio_max_len >> PAGE_SHIFT, 1UL),
-			opf, GFP_NOFS);
+			op, GFP_NOFS);
 	bio->bi_iter.bi_sector = disk_start >> 9;
 	bio->bi_private = rbio;
 

fs/buffer.c

···
 #include "internal.h"
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
-static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
+static int submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
 			 struct writeback_control *wbc);
 
 #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
···
 	struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize);
 	if (bh) {
 		if (buffer_dirty(bh))
-			ll_rw_block(REQ_OP_WRITE, 0, 1, &bh);
+			ll_rw_block(REQ_OP_WRITE, 1, &bh);
 		put_bh(bh);
 	}
 }
···
 	} else {
 		get_bh(bh);
 		bh->b_end_io = end_buffer_read_sync;
-		submit_bh(REQ_OP_READ, 0, bh);
+		submit_bh(REQ_OP_READ, bh);
 		wait_on_buffer(bh);
 		if (buffer_uptodate(bh))
 			return bh;
···
 {
 	struct buffer_head *bh = __getblk(bdev, block, size);
 	if (likely(bh)) {
-		ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh);
+		ll_rw_block(REQ_OP_READ | REQ_RAHEAD, 1, &bh);
 		brelse(bh);
 	}
 }
···
 {
 	struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp);
 	if (likely(bh)) {
-		ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh);
+		ll_rw_block(REQ_OP_READ | REQ_RAHEAD, 1, &bh);
 		brelse(bh);
 	}
 }
···
 	struct buffer_head *bh, *head;
 	unsigned int blocksize, bbits;
 	int nr_underway = 0;
-	int write_flags = wbc_to_write_flags(wbc);
+	blk_opf_t write_flags = wbc_to_write_flags(wbc);
 
 	head = create_page_buffers(page, inode,
 					(1 << BH_Dirty)|(1 << BH_Uptodate));
···
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, wbc);
+			submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, wbc);
 			nr_underway++;
 		}
 		bh = next;
···
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
 			clear_buffer_dirty(bh);
-			submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, wbc);
+			submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, wbc);
 			nr_underway++;
 		}
 		bh = next;
···
 		if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
 		    !buffer_unwritten(bh) &&
 		     (block_start < from || block_end > to)) {
-			ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+			ll_rw_block(REQ_OP_READ, 1, &bh);
 			*wait_bh++=bh;
 		}
 	}
···
 		if (buffer_uptodate(bh))
 			end_buffer_async_read(bh, 1);
 		else
-			submit_bh(REQ_OP_READ, 0, bh);
+			submit_bh(REQ_OP_READ, bh);
 	}
 	return 0;
 }
···
 		if (block_start < from || block_end > to) {
 			lock_buffer(bh);
 			bh->b_end_io = end_buffer_read_nobh;
-			submit_bh(REQ_OP_READ, 0, bh);
+			submit_bh(REQ_OP_READ, bh);
 			nr_reads++;
 		}
 	}
···
 
 	if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) {
 		err = -EIO;
-		ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+		ll_rw_block(REQ_OP_READ, 1, &bh);
 		wait_on_buffer(bh);
 		/* Uhhuh. Read error. Complain and punt. */
 		if (!buffer_uptodate(bh))
···
 	bio_put(bio);
 }
 
-static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
+static int submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
 			 struct writeback_control *wbc)
 {
+	const enum req_op op = opf & REQ_OP_MASK;
 	struct bio *bio;
 
 	BUG_ON(!buffer_locked(bh));
···
 		clear_buffer_write_io_error(bh);
 
 	if (buffer_meta(bh))
-		op_flags |= REQ_META;
+		opf |= REQ_META;
 	if (buffer_prio(bh))
-		op_flags |= REQ_PRIO;
+		opf |= REQ_PRIO;
 
-	bio = bio_alloc(bh->b_bdev, 1, op | op_flags, GFP_NOIO);
+	bio = bio_alloc(bh->b_bdev, 1, opf, GFP_NOIO);
 
 	fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);
 
···
 	return 0;
 }
 
-int submit_bh(int op, int op_flags, struct buffer_head *bh)
+int submit_bh(blk_opf_t opf, struct buffer_head *bh)
 {
-	return submit_bh_wbc(op, op_flags, bh, NULL);
+	return submit_bh_wbc(opf, bh, NULL);
 }
 EXPORT_SYMBOL(submit_bh);
 
 /**
  * ll_rw_block: low-level access to block devices (DEPRECATED)
- * @op: whether to %READ or %WRITE
- * @op_flags: req_flag_bits
+ * @opf: block layer request operation and flags.
  * @nr: number of &struct buffer_heads in the array
  * @bhs: array of pointers to &struct buffer_head
  *
  * ll_rw_block() takes an array of pointers to &struct buffer_heads, and
  * requests an I/O operation on them, either a %REQ_OP_READ or a %REQ_OP_WRITE.
- * @op_flags contains flags modifying the detailed I/O behavior, most notably
+ * @opf contains flags modifying the detailed I/O behavior, most notably
  * %REQ_RAHEAD.
  *
  * This function drops any buffer that it cannot get a lock on (with the
···
  * All of the buffers must be for the same device, and must also be a
  * multiple of the current approved size for the device.
  */
-void ll_rw_block(int op, int op_flags,  int nr, struct buffer_head *bhs[])
+void ll_rw_block(const blk_opf_t opf, int nr, struct buffer_head *bhs[])
 {
+	const enum req_op op = opf & REQ_OP_MASK;
 	int i;
 
 	for (i = 0; i < nr; i++) {
···
 
 		if (!trylock_buffer(bh))
 			continue;
-		if (op == WRITE) {
+		if (op == REQ_OP_WRITE) {
 			if (test_clear_buffer_dirty(bh)) {
 				bh->b_end_io = end_buffer_write_sync;
 				get_bh(bh);
-				submit_bh(op, op_flags, bh);
+				submit_bh(opf, bh);
 				continue;
 			}
 		} else {
 			if (!buffer_uptodate(bh)) {
 				bh->b_end_io = end_buffer_read_sync;
 				get_bh(bh);
-				submit_bh(op, op_flags, bh);
+				submit_bh(opf, bh);
 				continue;
 			}
 		}
···
 }
 EXPORT_SYMBOL(ll_rw_block);
 
-void write_dirty_buffer(struct buffer_head *bh, int op_flags)
+void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags)
 {
 	lock_buffer(bh);
 	if (!test_clear_buffer_dirty(bh)) {
···
 	}
 	bh->b_end_io = end_buffer_write_sync;
 	get_bh(bh);
-	submit_bh(REQ_OP_WRITE, op_flags, bh);
+	submit_bh(REQ_OP_WRITE | op_flags, bh);
 }
 EXPORT_SYMBOL(write_dirty_buffer);
 
···
  * and then start new I/O and then wait upon it.  The caller must have a ref on
  * the buffer_head.
  */
-int __sync_dirty_buffer(struct buffer_head *bh, int op_flags)
+int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags)
 {
 	int ret = 0;
 
···
 
 		get_bh(bh);
 		bh->b_end_io = end_buffer_write_sync;
-		ret = submit_bh(REQ_OP_WRITE, op_flags, bh);
+		ret = submit_bh(REQ_OP_WRITE | op_flags, bh);
 		wait_on_buffer(bh);
 		if (!ret && !buffer_uptodate(bh))
 			ret = -EIO;
···
 
 	get_bh(bh);
 	bh->b_end_io = end_buffer_read_sync;
-	submit_bh(REQ_OP_READ, 0, bh);
+	submit_bh(REQ_OP_READ, bh);
 	wait_on_buffer(bh);
 	if (buffer_uptodate(bh))
 		return 0;

fs/direct-io.c

···
 /* dio_state communicated between submission path and end_io */
 struct dio {
 	int flags;			/* doesn't change */
-	int op;
-	int op_flags;
+	blk_opf_t opf;			/* request operation type and flags */
 	struct gendisk *bio_disk;
 	struct inode *inode;
 	loff_t i_size;			/* i_size when submitted */
···
  */
 static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
 {
+	const enum req_op dio_op = dio->opf & REQ_OP_MASK;
 	ssize_t ret;
 
 	ret = iov_iter_get_pages(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES,
 				&sdio->from);
 
-	if (ret < 0 && sdio->blocks_available && (dio->op == REQ_OP_WRITE)) {
+	if (ret < 0 && sdio->blocks_available && dio_op == REQ_OP_WRITE) {
 		struct page *page = ZERO_PAGE(0);
 		/*
 		 * A memory fault, but the filesystem has some outstanding
···
  */
 static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
 {
+	const enum req_op dio_op = dio->opf & REQ_OP_MASK;
 	loff_t offset = dio->iocb->ki_pos;
 	ssize_t transferred = 0;
 	int err;
···
 		transferred = dio->result;
 
 		/* Check for short read case */
-		if ((dio->op == REQ_OP_READ) &&
+		if (dio_op == REQ_OP_READ &&
 		    ((offset + transferred) > dio->i_size))
 			transferred = dio->i_size - offset;
 		/* ignore EFAULT if some IO has been done */
···
 	 * zeros from unwritten extents.
 	 */
 	if (flags & DIO_COMPLETE_INVALIDATE &&
-	    ret > 0 && dio->op == REQ_OP_WRITE &&
+	    ret > 0 && dio_op == REQ_OP_WRITE &&
 	    dio->inode->i_mapping->nrpages) {
 		err = invalidate_inode_pages2_range(dio->inode->i_mapping,
 					offset >> PAGE_SHIFT,
···
 		 */
 		dio->iocb->ki_pos += transferred;
 
-		if (ret > 0 && dio->op == REQ_OP_WRITE)
+		if (ret > 0 && dio_op == REQ_OP_WRITE)
 			ret = generic_write_sync(dio->iocb, ret);
 		dio->iocb->ki_complete(dio->iocb, ret);
 	}
···
 static void dio_bio_end_aio(struct bio *bio)
 {
 	struct dio *dio = bio->bi_private;
+	const enum req_op dio_op = dio->opf & REQ_OP_MASK;
 	unsigned long remaining;
 	unsigned long flags;
 	bool defer_completion = false;
···
 		 */
 		if (dio->result)
 			defer_completion = dio->defer_completion ||
-					   (dio->op == REQ_OP_WRITE &&
+					   (dio_op == REQ_OP_WRITE &&
 					    dio->inode->i_mapping->nrpages);
 		if (defer_completion) {
 			INIT_WORK(&dio->complete_work, dio_aio_complete_work);
···
 	 * bio_alloc() is guaranteed to return a bio when allowed to sleep and
 	 * we request a valid number of vectors.
 	 */
-	bio = bio_alloc(bdev, nr_vecs, dio->op | dio->op_flags, GFP_KERNEL);
+	bio = bio_alloc(bdev, nr_vecs, dio->opf, GFP_KERNEL);
 	bio->bi_iter.bi_sector = first_sector;
 	if (dio->is_async)
 		bio->bi_end_io = dio_bio_end_aio;
···
  */
 static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
 {
+	const enum req_op dio_op = dio->opf & REQ_OP_MASK;
 	struct bio *bio = sdio->bio;
 	unsigned long flags;
 
···
 	dio->refcount++;
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
 
-	if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty)
+	if (dio->is_async && dio_op == REQ_OP_READ && dio->should_dirty)
 		bio_set_pages_dirty(bio);
 
 	dio->bio_disk = bio->bi_bdev->bd_disk;
···
 static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio)
 {
 	blk_status_t err = bio->bi_status;
-	bool should_dirty = dio->op == REQ_OP_READ && dio->should_dirty;
+	const enum req_op dio_op = dio->opf & REQ_OP_MASK;
+	bool should_dirty = dio_op == REQ_OP_READ && dio->should_dirty;
 
 	if (err) {
 		if (err == BLK_STS_AGAIN && (bio->bi_opf & REQ_NOWAIT))
···
 static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
 			   struct buffer_head *map_bh)
 {
+	const enum req_op dio_op = dio->opf & REQ_OP_MASK;
 	int ret;
 	sector_t fs_startblk;	/* Into file, in filesystem-sized blocks */
 	sector_t fs_endblk;	/* Into file, in filesystem-sized blocks */
···
 		 * which may decide to handle it or also return an unmapped
 		 * buffer head.
 		 */
-		create = dio->op == REQ_OP_WRITE;
+		create = dio_op == REQ_OP_WRITE;
 		if (dio->flags & DIO_SKIP_HOLES) {
 			i_size = i_size_read(dio->inode);
 			if (i_size && fs_startblk <= (i_size - 1) >> i_blkbits)
···
 		    unsigned offset, unsigned len, sector_t blocknr,
 		    struct buffer_head *map_bh)
 {
+	const enum req_op dio_op = dio->opf & REQ_OP_MASK;
 	int ret = 0;
 	int boundary = sdio->boundary;	/* dio_send_cur_page may clear it */
 
-	if (dio->op == REQ_OP_WRITE) {
+	if (dio_op == REQ_OP_WRITE) {
 		/*
 		 * Read accounting is performed in submit_bio()
 		 */
···
 static int do_direct_IO(struct dio *dio, struct dio_submit *sdio,
 			struct buffer_head *map_bh)
 {
+	const enum req_op dio_op = dio->opf & REQ_OP_MASK;
 	const unsigned blkbits = sdio->blkbits;
 	const unsigned i_blkbits = blkbits + sdio->blkfactor;
 	int ret = 0;
···
 				loff_t i_size_aligned;
 
 				/* AKPM: eargh, -ENOTBLK is a hack */
-				if (dio->op == REQ_OP_WRITE) {
+				if (dio_op == REQ_OP_WRITE) {
 					put_page(page);
 					return -ENOTBLK;
 				}
···
 
 	dio->inode = inode;
 	if (iov_iter_rw(iter) == WRITE) {
-		dio->op = REQ_OP_WRITE;
-		dio->op_flags = REQ_SYNC | REQ_IDLE;
+		dio->opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
 		if (iocb->ki_flags & IOCB_NOWAIT)
-			dio->op_flags |= REQ_NOWAIT;
+			dio->opf |= REQ_NOWAIT;
 	} else {
-		dio->op = REQ_OP_READ;
+		dio->opf = REQ_OP_READ;
 	}
 
 	/*

fs/ext4/ext4.h

···
 
 /* super.c */
 extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
-					 sector_t block, int op_flags);
+					 sector_t block, blk_opf_t op_flags);
 extern struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
 						   sector_t block);
-extern void ext4_read_bh_nowait(struct buffer_head *bh, int op_flags,
+extern void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
 				bh_end_io_t *end_io);
-extern int ext4_read_bh(struct buffer_head *bh, int op_flags,
+extern int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
 			bh_end_io_t *end_io);
-extern int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait);
+extern int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait);
 extern void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block);
 extern int ext4_seq_options_show(struct seq_file *seq, void *offset);
 extern int ext4_calculate_overhead(struct super_block *sb);

fs/ext4/fast_commit.c

···
 
 static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail)
 {
-	int write_flags = REQ_SYNC;
+	blk_opf_t write_flags = REQ_SYNC;
 	struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh;
 
 	/* Add REQ_FUA | REQ_PREFLUSH only its tail */
···
 	set_buffer_dirty(bh);
 	set_buffer_uptodate(bh);
 	bh->b_end_io = ext4_end_buffer_io_sync;
-	submit_bh(REQ_OP_WRITE, write_flags, bh);
+	submit_bh(REQ_OP_WRITE | write_flags, bh);
 	EXT4_SB(sb)->s_fc_bh = NULL;
 }
 

fs/ext4/mmp.c

···
 	lock_buffer(bh);
 	bh->b_end_io = end_buffer_write_sync;
 	get_bh(bh);
-	submit_bh(REQ_OP_WRITE, REQ_SYNC | REQ_META | REQ_PRIO, bh);
+	submit_bh(REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO, bh);
 	wait_on_buffer(bh);
 	sb_end_write(sb);
 	if (unlikely(!buffer_uptodate(bh)))
···
 	mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval,
 				 EXT4_MMP_MIN_CHECK_INTERVAL);
 	mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
-	BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE);
-	bdevname(bh->b_bdev, mmp->mmp_bdevname);
 
 	memcpy(mmp->mmp_nodename, init_utsname()->nodename,
 	       sizeof(mmp->mmp_nodename));
···
 
 	EXT4_SB(sb)->s_mmp_bh = bh;
 
+	BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE);
+	snprintf(mmp->mmp_bdevname, sizeof(mmp->mmp_bdevname),
+		 "%pg", bh->b_bdev);
+
 	/*
 	 * Start a kernel thread to update the MMP block periodically.
 	 */
 	EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, sb, "kmmpd-%.*s",
 					     (int)sizeof(mmp->mmp_bdevname),
-					     bdevname(bh->b_bdev,
-						      mmp->mmp_bdevname));
+					     mmp->mmp_bdevname);
 	if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {
 		EXT4_SB(sb)->s_mmp_tsk = NULL;
 		ext4_warning(sb, "Unable to create kmmpd thread for %s.",

fs/ext4/super.c

···
 #define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)
 
 
-static inline void __ext4_read_bh(struct buffer_head *bh, int op_flags,
+static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
 				  bh_end_io_t *end_io)
 {
 	/*
···
 
 	bh->b_end_io = end_io ? end_io : end_buffer_read_sync;
 	get_bh(bh);
-	submit_bh(REQ_OP_READ, op_flags, bh);
+	submit_bh(REQ_OP_READ | op_flags, bh);
 }
 
-void ext4_read_bh_nowait(struct buffer_head *bh, int op_flags,
+void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
 			 bh_end_io_t *end_io)
 {
 	BUG_ON(!buffer_locked(bh));
···
 	__ext4_read_bh(bh, op_flags, end_io);
 }
 
-int ext4_read_bh(struct buffer_head *bh, int op_flags, bh_end_io_t *end_io)
+int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io)
 {
 	BUG_ON(!buffer_locked(bh));
 
···
 	return -EIO;
 }
 
-int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait)
+int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait)
 {
 	if (trylock_buffer(bh)) {
 		if (wait)
···
  * return.
  */
 static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb,
-					       sector_t block, int op_flags,
-					       gfp_t gfp)
+					       sector_t block,
+					       blk_opf_t op_flags, gfp_t gfp)
 {
 	struct buffer_head *bh;
 	int ret;
···
 }
 
 struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block,
-				   int op_flags)
+				   blk_opf_t op_flags)
 {
 	return __ext4_sb_bread_gfp(sb, block, op_flags, __GFP_MOVABLE);
 }
···
 	/* Clear potential dirty bit if it was journalled update */
 	clear_buffer_dirty(sbh);
 	sbh->b_end_io = end_buffer_write_sync;
-	submit_bh(REQ_OP_WRITE,
-		  REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0), sbh);
+	submit_bh(REQ_OP_WRITE | REQ_SYNC |
+		  (test_opt(sb, BARRIER) ? REQ_FUA : 0), sbh);
 	wait_on_buffer(sbh);
 	if (buffer_write_io_error(sbh)) {
 		ext4_msg(sb, KERN_ERR, "I/O error while writing "

fs/f2fs/data.c

···
 	return 0;
 }
 
-static unsigned int f2fs_io_flags(struct f2fs_io_info *fio)
+static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio)
 {
 	unsigned int temp_mask = (1 << NR_TEMP_TYPE) - 1;
 	unsigned int fua_flag, meta_flag, io_flag;
-	unsigned int op_flags = 0;
+	blk_opf_t op_flags = 0;
 
 	if (fio->op != REQ_OP_WRITE)
 		return 0;
···
 }
 
 static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
-				      unsigned nr_pages, unsigned op_flag,
+				      unsigned nr_pages, blk_opf_t op_flag,
 				      pgoff_t first_idx, bool for_write)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
···
 
 /* This can handle encryption stuffs */
 static int f2fs_submit_page_read(struct inode *inode, struct page *page,
-				 block_t blkaddr, int op_flags, bool for_write)
+				 block_t blkaddr, blk_opf_t op_flags,
+				 bool for_write)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct bio *bio;
···
 }
 
 struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
-						int op_flags, bool for_write)
+				     blk_opf_t op_flags, bool for_write)
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct dnode_of_data dn;

fs/f2fs/f2fs.h

···
 	nid_t ino;		/* inode number */
 	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
 	enum temp_type temp;	/* contains HOT/WARM/COLD */
-	int op;			/* contains REQ_OP_ */
-	int op_flags;		/* req_flag_bits */
+	enum req_op op;		/* contains REQ_OP_ */
+	blk_opf_t op_flags;	/* req_flag_bits */
 	block_t new_blkaddr;	/* new block address to be written */
 	block_t old_blkaddr;	/* old block address before Cow */
 	struct page *page;	/* page to be written */
···
 int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
 int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
 struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
-			int op_flags, bool for_write);
+			blk_opf_t op_flags, bool for_write);
 struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index);
 struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
 			bool for_write);

fs/f2fs/node.c

···
  * 0: f2fs_put_page(page, 0)
  * LOCKED_PAGE or error: f2fs_put_page(page, 1)
  */
-static int read_node_page(struct page *page, int op_flags)
+static int read_node_page(struct page *page, blk_opf_t op_flags)
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 	struct node_info ni;

fs/f2fs/segment.c

···
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
 	struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ?
 					&(dcc->fstrim_list) : &(dcc->wait_list);
-	int flag = dpolicy->sync ? REQ_SYNC : 0;
+	blk_opf_t flag = dpolicy->sync ? REQ_SYNC : 0;
 	block_t lstart, start, len, total_len;
 	int err = 0;
 

fs/gfs2/bmap.c

···
 		if (trylock_buffer(rabh)) {
 			if (!buffer_uptodate(rabh)) {
 				rabh->b_end_io = end_buffer_read_sync;
-				submit_bh(REQ_OP_READ,
-					  REQ_RAHEAD | REQ_META | REQ_PRIO,
-					  rabh);
+				submit_bh(REQ_OP_READ | REQ_RAHEAD | REQ_META |
+					  REQ_PRIO, rabh);
 				continue;
 			}
 			unlock_buffer(rabh);

fs/gfs2/dir.c

···
 				continue;
 			}
 			bh->b_end_io = end_buffer_read_sync;
-			submit_bh(REQ_OP_READ,
-				  REQ_RAHEAD | REQ_META | REQ_PRIO,
-				  bh);
+			submit_bh(REQ_OP_READ | REQ_RAHEAD | REQ_META |
+				  REQ_PRIO, bh);
 			continue;
 		}
 		brelse(bh);

fs/gfs2/log.c

···
 
 void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
 			   u64 seq, u32 tail, u32 lblock, u32 flags,
-			   int op_flags)
+			   blk_opf_t op_flags)
 {
 	struct gfs2_log_header *lh;
 	u32 hash, crc;
···
 
 static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
 {
-	int op_flags = REQ_PREFLUSH | REQ_FUA | REQ_META | REQ_SYNC;
+	blk_opf_t op_flags = REQ_PREFLUSH | REQ_FUA | REQ_META | REQ_SYNC;
 	enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
 
 	gfs2_assert_withdraw(sdp, (state != SFS_FROZEN));

fs/gfs2/log.h

···
 			     unsigned int *extra_revokes);
 extern void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
 				  u64 seq, u32 tail, u32 lblock, u32 flags,
-				  int op_flags);
+				  blk_opf_t op_flags);
 extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
 			   u32 type);
 extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);

fs/gfs2/lops.c

···
  * there is no pending bio, then this is a no-op.
  */
 
-void gfs2_log_submit_bio(struct bio **biop, int opf)
+void gfs2_log_submit_bio(struct bio **biop, blk_opf_t opf)
 {
 	struct bio *bio = *biop;
 	if (bio) {
···
  */
 
 static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno,
-				    struct bio **biop, int op,
+				    struct bio **biop, enum req_op op,
 				    bio_end_io_t *end_io, bool flush)
 {
 	struct bio *bio = *biop;

fs/gfs2/lops.h

···
 extern void gfs2_log_write(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
 			   struct page *page, unsigned size, unsigned offset,
 			   u64 blkno);
-extern void gfs2_log_submit_bio(struct bio **biop, int opf);
+extern void gfs2_log_submit_bio(struct bio **biop, blk_opf_t opf);
 extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
 extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
 			   struct gfs2_log_header_host *head, bool keep_cache);

fs/gfs2/meta_io.c

···
 {
 	struct buffer_head *bh, *head;
 	int nr_underway = 0;
-	int write_flags = REQ_META | REQ_PRIO | wbc_to_write_flags(wbc);
+	blk_opf_t write_flags = REQ_META | REQ_PRIO | wbc_to_write_flags(wbc);
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(!page_has_buffers(page));
···
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh(REQ_OP_WRITE, write_flags, bh);
+			submit_bh(REQ_OP_WRITE | write_flags, bh);
 			nr_underway++;
 		}
 		bh = next;
···
  * Submit several consecutive buffer head I/O requests as a single bio I/O
  * request.  (See submit_bh_wbc.)
  */
-static void gfs2_submit_bhs(int op, int op_flags, struct buffer_head *bhs[],
-			    int num)
+static void gfs2_submit_bhs(blk_opf_t opf, struct buffer_head *bhs[], int num)
 {
 	while (num > 0) {
 		struct buffer_head *bh = *bhs;
 		struct bio *bio;
 
-		bio = bio_alloc(bh->b_bdev, num, op | op_flags, GFP_NOIO);
+		bio = bio_alloc(bh->b_bdev, num, opf, GFP_NOIO);
 		bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 		while (num > 0) {
 			bh = *bhs;
···
 		}
 	}
 
-	gfs2_submit_bhs(REQ_OP_READ, REQ_META | REQ_PRIO, bhs, num);
+	gfs2_submit_bhs(REQ_OP_READ | REQ_META | REQ_PRIO, bhs, num);
 	if (!(flags & DIO_WAIT))
 		return 0;
 
···
 	if (buffer_uptodate(first_bh))
 		goto out;
 	if (!buffer_locked(first_bh))
-		ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &first_bh);
+		ll_rw_block(REQ_OP_READ | REQ_META | REQ_PRIO, 1, &first_bh);
 
 	dblock++;
 	extlen--;
···
 		bh = gfs2_getbuf(gl, dblock, CREATE);
 
 		if (!buffer_uptodate(bh) && !buffer_locked(bh))
-			ll_rw_block(REQ_OP_READ,
-				    REQ_RAHEAD | REQ_META | REQ_PRIO,
-				    1, &bh);
+			ll_rw_block(REQ_OP_READ | REQ_RAHEAD | REQ_META |
+				    REQ_PRIO, 1, &bh);
 		brelse(bh);
 		dblock++;
 		extlen--;

fs/gfs2/quota.c

···
 		if (PageUptodate(page))
 			set_buffer_uptodate(bh);
 		if (!buffer_uptodate(bh)) {
-			ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &bh);
+			ll_rw_block(REQ_OP_READ | REQ_META | REQ_PRIO, 1, &bh);
 			wait_on_buffer(bh);
 			if (!buffer_uptodate(bh))
 				goto unlock_out;

fs/hfsplus/hfsplus_fs.h

···
 
 /* wrapper.c */
 int hfsplus_submit_bio(struct super_block *sb, sector_t sector, void *buf,
-		       void **data, int op, int op_flags);
+		       void **data, blk_opf_t opf);
 int hfsplus_read_wrapper(struct super_block *sb);
 
 /*

fs/hfsplus/part_tbl.c

···
 		if ((u8 *)pm - (u8 *)buf >= buf_size) {
 			res = hfsplus_submit_bio(sb,
 						 *part_start + HFS_PMAP_BLK + i,
-						 buf, (void **)&pm, REQ_OP_READ,
-						 0);
+						 buf, (void **)&pm, REQ_OP_READ);
 			if (res)
 				return res;
 		}
···
 		return -ENOMEM;
 
 	res = hfsplus_submit_bio(sb, *part_start + HFS_PMAP_BLK,
-				 buf, &data, REQ_OP_READ, 0);
+				 buf, &data, REQ_OP_READ);
 	if (res)
 		goto out;
 

fs/hfsplus/super.c

···
 
 	error2 = hfsplus_submit_bio(sb,
 				   sbi->part_start + HFSPLUS_VOLHEAD_SECTOR,
-				   sbi->s_vhdr_buf, NULL, REQ_OP_WRITE,
+				   sbi->s_vhdr_buf, NULL, REQ_OP_WRITE |
 				   REQ_SYNC);
 	if (!error)
 		error = error2;
···
 
 	error2 = hfsplus_submit_bio(sb,
 				  sbi->part_start + sbi->sect_count - 2,
-				  sbi->s_backup_vhdr_buf, NULL, REQ_OP_WRITE,
+				  sbi->s_backup_vhdr_buf, NULL, REQ_OP_WRITE |
 				  REQ_SYNC);
 	if (!error)
 		error2 = error;

fs/hfsplus/wrapper.c

···
  * will work correctly.
  */
 int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
-		       void *buf, void **data, int op, int op_flags)
+		       void *buf, void **data, blk_opf_t opf)
 {
+	const enum req_op op = opf & REQ_OP_MASK;
 	struct bio *bio;
 	int ret = 0;
 	u64 io_size;
···
 	offset = start & (io_size - 1);
 	sector &= ~((io_size >> HFSPLUS_SECTOR_SHIFT) - 1);
 
-	bio = bio_alloc(sb->s_bdev, 1, op | op_flags, GFP_NOIO);
+	bio = bio_alloc(sb->s_bdev, 1, opf, GFP_NOIO);
 	bio->bi_iter.bi_sector = sector;
 
-	if (op != WRITE && data)
+	if (op != REQ_OP_WRITE && data)
 		*data = (u8 *)buf + offset;
 
 	while (io_size > 0) {
···
 reread:
 	error = hfsplus_submit_bio(sb, part_start + HFSPLUS_VOLHEAD_SECTOR,
 				   sbi->s_vhdr_buf, (void **)&sbi->s_vhdr,
-				   REQ_OP_READ, 0);
+				   REQ_OP_READ);
 	if (error)
 		goto out_free_backup_vhdr;
 
···
 
 	error = hfsplus_submit_bio(sb, part_start + part_size - 2,
 				   sbi->s_backup_vhdr_buf,
-				   (void **)&sbi->s_backup_vhdr, REQ_OP_READ,
-				   0);
+				   (void **)&sbi->s_backup_vhdr, REQ_OP_READ);
 	if (error)
 		goto out_free_backup_vhdr;
 

fs/iomap/direct-io.c

···
 };
 
 static struct bio *iomap_dio_alloc_bio(const struct iomap_iter *iter,
-		struct iomap_dio *dio, unsigned short nr_vecs, unsigned int opf)
+		struct iomap_dio *dio, unsigned short nr_vecs, blk_opf_t opf)
 {
 	if (dio->dops && dio->dops->bio_set)
 		return bio_alloc_bioset(iter->iomap.bdev, nr_vecs, opf,
···
  * mapping, and whether or not we want FUA.  Note that we can end up
  * clearing the WRITE_FUA flag in the dio request.
  */
-static inline unsigned int iomap_dio_bio_opflags(struct iomap_dio *dio,
+static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio,
 		const struct iomap *iomap, bool use_fua)
 {
-	unsigned int opflags = REQ_SYNC | REQ_IDLE;
+	blk_opf_t opflags = REQ_SYNC | REQ_IDLE;
 
 	if (!(dio->flags & IOMAP_DIO_WRITE)) {
 		WARN_ON_ONCE(iomap->flags & IOMAP_F_ZONE_APPEND);
···
 	struct inode *inode = iter->inode;
 	unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev));
 	unsigned int fs_block_size = i_blocksize(inode), pad;
-	unsigned int align = iov_iter_alignment(dio->submit.iter);
 	loff_t length = iomap_length(iter);
 	loff_t pos = iter->pos;
-	unsigned int bio_opf;
+	blk_opf_t bio_opf;
 	struct bio *bio;
 	bool need_zeroout = false;
 	bool use_fua = false;
···
 	size_t copied = 0;
 	size_t orig_count;
 
-	if ((pos | length | align) & ((1 << blkbits) - 1))
+	if ((pos | length) & ((1 << blkbits) - 1) ||
+	    !bdev_iter_is_aligned(iomap->bdev, dio->submit.iter))
 		return -EINVAL;
 
 	if (iomap->type == IOMAP_UNWRITTEN) {

fs/isofs/compress.c

···
 		return 0;
 	}
 	haveblocks = isofs_get_blocks(inode, blocknum, bhs, needblocks);
-	ll_rw_block(REQ_OP_READ, 0, haveblocks, bhs);
+	ll_rw_block(REQ_OP_READ, haveblocks, bhs);
 
 	curbh = 0;
 	curpage = 0;

fs/jbd2/commit.c

···
 
 	if (journal->j_flags & JBD2_BARRIER &&
 	    !jbd2_has_feature_async_commit(journal))
-		ret = submit_bh(REQ_OP_WRITE,
-			REQ_SYNC | REQ_PREFLUSH | REQ_FUA, bh);
+		ret = submit_bh(REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH |
+				REQ_FUA, bh);
 	else
-		ret = submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
+		ret = submit_bh(REQ_OP_WRITE | REQ_SYNC, bh);
 
 	*cbh = bh;
 	return ret;
···
 				clear_buffer_dirty(bh);
 				set_buffer_uptodate(bh);
 				bh->b_end_io = journal_end_buffer_io_sync;
-				submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
+				submit_bh(REQ_OP_WRITE | REQ_SYNC, bh);
 			}
 			cond_resched();
 

fs/jbd2/journal.c

···
 	if (!journal)
 		return NULL;
 
-	bdevname(journal->j_dev, journal->j_devname);
+	snprintf(journal->j_devname, sizeof(journal->j_devname),
+		 "%pg", journal->j_dev);
 	strreplace(journal->j_devname, '/', '!');
 	jbd2_stats_proc_init(journal);
 
···
 		return NULL;
 
 	journal->j_inode = inode;
-	bdevname(journal->j_dev, journal->j_devname);
+	snprintf(journal->j_devname, sizeof(journal->j_devname),
+		 "%pg", journal->j_dev);
 	p = strreplace(journal->j_devname, '/', '!');
 	sprintf(p, "-%lu", journal->j_inode->i_ino);
 	jbd2_stats_proc_init(journal);
···
  * This function expects that the caller will have locked the journal
  * buffer head, and will return with it unlocked
  */
-static int jbd2_write_superblock(journal_t *journal, int write_flags)
+static int jbd2_write_superblock(journal_t *journal, blk_opf_t write_flags)
 {
 	struct buffer_head *bh = journal->j_sb_buffer;
 	journal_superblock_t *sb = journal->j_superblock;
···
 		sb->s_checksum = jbd2_superblock_csum(journal, sb);
 	get_bh(bh);
 	bh->b_end_io = end_buffer_write_sync;
-	ret = submit_bh(REQ_OP_WRITE, write_flags, bh);
+	ret = submit_bh(REQ_OP_WRITE | write_flags, bh);
 	wait_on_buffer(bh);
 	if (buffer_write_io_error(bh)) {
 		clear_buffer_write_io_error(bh);
···
  * @journal: The journal to update.
  * @tail_tid: TID of the new transaction at the tail of the log
  * @tail_block: The first block of the transaction at the tail of the log
- * @write_op: With which operation should we write the journal sb
+ * @write_flags: Flags for the journal sb write operation
  *
  * Update a journal's superblock information about log tail and write it to
  * disk, waiting for the IO to complete.
  */
 int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
-				     unsigned long tail_block, int write_op)
+				    unsigned long tail_block,
+				    blk_opf_t write_flags)
 {
 	journal_superblock_t *sb = journal->j_superblock;
 	int ret;
···
 	sb->s_sequence = cpu_to_be32(tail_tid);
 	sb->s_start    = cpu_to_be32(tail_block);
 
-	ret = jbd2_write_superblock(journal, write_op);
+	ret = jbd2_write_superblock(journal, write_flags);
 	if (ret)
 		goto out;
 
···
 /**
  * jbd2_mark_journal_empty() - Mark on disk journal as empty.
  * @journal: The journal to update.
- * @write_op: With which operation should we write the journal sb
+ * @write_flags: Flags for the journal sb write operation
  *
  * Update a journal's dynamic superblock fields to show that journal is empty.
  * Write updated superblock to disk waiting for IO to complete.
  */
-static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
+static void jbd2_mark_journal_empty(journal_t *journal, blk_opf_t write_flags)
 {
 	journal_superblock_t *sb = journal->j_superblock;
 	bool had_fast_commit = false;
···
 		had_fast_commit = true;
 	}
 
-	jbd2_write_superblock(journal, write_op);
+	jbd2_write_superblock(journal, write_flags);
 
 	if (had_fast_commit)
 		jbd2_set_feature_fast_commit(journal);
···
 
 	J_ASSERT(bh != NULL);
 	if (!buffer_uptodate(bh)) {
-		ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+		ll_rw_block(REQ_OP_READ, 1, &bh);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
 			printk(KERN_ERR

fs/jbd2/recovery.c

···
 		if (!buffer_uptodate(bh) && !buffer_locked(bh)) {
 			bufs[nbufs++] = bh;
 			if (nbufs == MAXBUF) {
-				ll_rw_block(REQ_OP_READ, 0, nbufs, bufs);
+				ll_rw_block(REQ_OP_READ, nbufs, bufs);
 				journal_brelse_array(bufs, nbufs);
 				nbufs = 0;
 			}
···
 	}
 
 	if (nbufs)
-		ll_rw_block(REQ_OP_READ, 0, nbufs, bufs);
+		ll_rw_block(REQ_OP_READ, nbufs, bufs);
 	err = 0;
 
 failed:

fs/mpage.c

···
 	struct block_device *bdev = NULL;
 	int length;
 	int fully_mapped = 1;
-	int op = REQ_OP_READ;
+	blk_opf_t opf = REQ_OP_READ;
 	unsigned nblocks;
 	unsigned relative_block;
 	gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
 
 	if (args->is_readahead) {
-		op |= REQ_RAHEAD;
+		opf |= REQ_RAHEAD;
 		gfp |= __GFP_NORETRY | __GFP_NOWARN;
 	}
 
···
 								page))
 				goto out;
 		}
-		args->bio = bio_alloc(bdev, bio_max_segs(args->nr_pages), op,
+		args->bio = bio_alloc(bdev, bio_max_segs(args->nr_pages), opf,
 				      gfp);
 		if (args->bio == NULL)
 			goto confused;

fs/nfs/blocklayout/blocklayout.c

···
 }
 
 static struct bio *
-do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect,
+do_add_page_to_bio(struct bio *bio, int npg, enum req_op op, sector_t isect,
 		struct page *page, struct pnfs_block_dev_map *map,
 		struct pnfs_block_extent *be, bio_end_io_t end_io,
 		struct parallel_io *par, unsigned int offset, int *len)
···
 	u64 disk_addr, end;
 
 	dprintk("%s: npg %d rw %d isect %llu offset %u len %d\n", __func__,
-		npg, rw, (unsigned long long)isect, offset, *len);
+		npg, (__force u32)op, (unsigned long long)isect, offset, *len);
 
 	/* translate to device offset */
 	isect += be->be_v_offset;
···
 
 retry:
 	if (!bio) {
-		bio = bio_alloc(map->bdev, bio_max_segs(npg), rw, GFP_NOIO);
+		bio = bio_alloc(map->bdev, bio_max_segs(npg), op, GFP_NOIO);
 		bio->bi_iter.bi_sector = disk_addr >> SECTOR_SHIFT;
 		bio->bi_end_io = end_io;
 		bio->bi_private = par;
···
 		} else {
 			bio = do_add_page_to_bio(bio,
 						 header->page_array.npages - i,
-						 READ,
+						 REQ_OP_READ,
 						 isect, pages[i], &map, &be,
 						 bl_end_io_read, par,
 						 pg_offset, &pg_len);
···
 
 		pg_len = PAGE_SIZE;
 		bio = do_add_page_to_bio(bio, header->page_array.npages - i,
-					 WRITE, isect, pages[i], &map, &be,
-					 bl_end_io_write, par,
-					 0, &pg_len);
+					 REQ_OP_WRITE, isect, pages[i], &map,
+					 &be, bl_end_io_write, par, 0, &pg_len);
 		if (IS_ERR(bio)) {
 			header->pnfs_error = PTR_ERR(bio);
 			bio = NULL;

fs/nilfs2/btnode.c

···
 }
 
 int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
-			      sector_t pblocknr, int mode, int mode_flags,
+			      sector_t pblocknr, blk_opf_t opf,
 			      struct buffer_head **pbh, sector_t *submit_ptr)
 {
 	struct buffer_head *bh;
···
 		}
 	}
 
-	if (mode_flags & REQ_RAHEAD) {
+	if (opf & REQ_RAHEAD) {
 		if (pblocknr != *submit_ptr + 1 || !trylock_buffer(bh)) {
 			err = -EBUSY; /* internal code */
 			brelse(bh);
 			goto out_locked;
 		}
-	} else { /* mode == READ */
+	} else { /* opf == REQ_OP_READ */
 		lock_buffer(bh);
 	}
 	if (buffer_uptodate(bh)) {
···
 	bh->b_blocknr = pblocknr; /* set block address for read */
 	bh->b_end_io = end_buffer_read_sync;
 	get_bh(bh);
-	submit_bh(mode, mode_flags, bh);
+	submit_bh(opf, bh);
 	bh->b_blocknr = blocknr; /* set back to the given block address */
 	*submit_ptr = pblocknr;
 	err = 0;

fs/nilfs2/btnode.h

···
 void nilfs_btnode_cache_clear(struct address_space *);
 struct buffer_head *nilfs_btnode_create_block(struct address_space *btnc,
 					      __u64 blocknr);
-int nilfs_btnode_submit_block(struct address_space *, __u64, sector_t, int,
-			      int, struct buffer_head **, sector_t *);
+int nilfs_btnode_submit_block(struct address_space *, __u64, sector_t,
+			      blk_opf_t, struct buffer_head **, sector_t *);
 void nilfs_btnode_delete(struct buffer_head *);
 int nilfs_btnode_prepare_change_key(struct address_space *,
 				    struct nilfs_btnode_chkey_ctxt *);

fs/nilfs2/btree.c

···
 	sector_t submit_ptr = 0;
 	int ret;
 
-	ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, 0, &bh,
+	ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, &bh,
 					&submit_ptr);
 	if (ret) {
 		if (ret != -EEXIST)
···
 			ptr2 = nilfs_btree_node_get_ptr(ra->node, i, ra->ncmax);
 
 			ret = nilfs_btnode_submit_block(btnc, ptr2, 0,
-							REQ_OP_READ, REQ_RAHEAD,
-							&ra_bh, &submit_ptr);
+						REQ_OP_READ | REQ_RAHEAD,
+						&ra_bh, &submit_ptr);
 			if (likely(!ret || ret == -EEXIST))
 				brelse(ra_bh);
 			else if (ret != -EBUSY)

fs/nilfs2/gcinode.c

···
 	bh->b_blocknr = pbn;
 	bh->b_end_io = end_buffer_read_sync;
 	get_bh(bh);
-	submit_bh(REQ_OP_READ, 0, bh);
+	submit_bh(REQ_OP_READ, bh);
 	if (vbn)
 		bh->b_blocknr = vbn;
  out:
···
 	struct inode *btnc_inode = NILFS_I(inode)->i_assoc_inode;
 	int ret;
 
-	ret = nilfs_btnode_submit_block(btnc_inode->i_mapping,
-					vbn ? : pbn, pbn, REQ_OP_READ, 0,
-					out_bh, &pbn);
+	ret = nilfs_btnode_submit_block(btnc_inode->i_mapping, vbn ? : pbn, pbn,
+					REQ_OP_READ, out_bh, &pbn);
 	if (ret == -EEXIST) /* internal code (cache hit) */
 		ret = 0;
 	return ret;

fs/nilfs2/mdt.c

···
 }
 
 static int
-nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff,
-		       int mode, int mode_flags, struct buffer_head **out_bh)
+nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff, blk_opf_t opf,
+		       struct buffer_head **out_bh)
 {
 	struct buffer_head *bh;
 	__u64 blknum = 0;
···
 	if (buffer_uptodate(bh))
 		goto out;
 
-	if (mode_flags & REQ_RAHEAD) {
+	if (opf & REQ_RAHEAD) {
 		if (!trylock_buffer(bh)) {
 			ret = -EBUSY;
 			goto failed_bh;
 		}
-	} else /* mode == READ */
+	} else /* opf == REQ_OP_READ */
 		lock_buffer(bh);
 
 	if (buffer_uptodate(bh)) {
···
 
 	bh->b_end_io = end_buffer_read_sync;
 	get_bh(bh);
-	submit_bh(mode, mode_flags, bh);
+	submit_bh(opf, bh);
 	ret = 0;
 
-	trace_nilfs2_mdt_submit_block(inode, inode->i_ino, blkoff, mode);
+	trace_nilfs2_mdt_submit_block(inode, inode->i_ino, blkoff,
+				      opf & REQ_OP_MASK);
  out:
 	get_bh(bh);
 	*out_bh = bh;
···
 	int i, nr_ra_blocks = NILFS_MDT_MAX_RA_BLOCKS;
 	int err;
 
-	err = nilfs_mdt_submit_block(inode, block, REQ_OP_READ, 0, &first_bh);
+	err = nilfs_mdt_submit_block(inode, block, REQ_OP_READ, &first_bh);
 	if (err == -EEXIST) /* internal code */
 		goto out;
 
···
 	if (readahead) {
 		blkoff = block + 1;
 		for (i = 0; i < nr_ra_blocks; i++, blkoff++) {
-			err = nilfs_mdt_submit_block(inode, blkoff, REQ_OP_READ,
-						     REQ_RAHEAD, &bh);
+			err = nilfs_mdt_submit_block(inode, blkoff,
+						REQ_OP_READ | REQ_RAHEAD, &bh);
 			if (likely(!err || err == -EEXIST))
 				brelse(bh);
 			else if (err != -EBUSY)

fs/ntfs/aops.c

···
 		for (i = 0; i < nr; i++) {
 			tbh = arr[i];
 			if (likely(!buffer_uptodate(tbh)))
-				submit_bh(REQ_OP_READ, 0, tbh);
+				submit_bh(REQ_OP_READ, tbh);
 			else
 				ntfs_end_buffer_async_read(tbh, 1);
 		}
···
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh(REQ_OP_WRITE, 0, bh);
+			submit_bh(REQ_OP_WRITE, bh);
 			need_end_writeback = false;
 		}
 		bh = next;
···
 		BUG_ON(!buffer_mapped(tbh));
 		get_bh(tbh);
 		tbh->b_end_io = end_buffer_write_sync;
-		submit_bh(REQ_OP_WRITE, 0, tbh);
+		submit_bh(REQ_OP_WRITE, tbh);
 	}
 	/* Synchronize the mft mirror now if not @sync. */
 	if (is_mft && !sync)

fs/ntfs/compress.c

···
 		}
 		get_bh(tbh);
 		tbh->b_end_io = end_buffer_read_sync;
-		submit_bh(REQ_OP_READ, 0, tbh);
+		submit_bh(REQ_OP_READ, tbh);
 	}
 
 	/* Wait for io completion on all buffer heads. */

fs/ntfs/file.c

···
 	lock_buffer(bh);
 	get_bh(bh);
 	bh->b_end_io = end_buffer_read_sync;
-	return submit_bh(REQ_OP_READ, 0, bh);
+	return submit_bh(REQ_OP_READ, bh);
 }
 
 /**

fs/ntfs/logfile.c

···
 			 * completed ignore errors afterwards as we can assume
 			 * that if one buffer worked all of them will work.
 			 */
-			submit_bh(REQ_OP_WRITE, 0, bh);
+			submit_bh(REQ_OP_WRITE, bh);
 			if (should_wait) {
 				should_wait = false;
 				wait_on_buffer(bh);

fs/ntfs/mft.c

···
 			clear_buffer_dirty(tbh);
 			get_bh(tbh);
 			tbh->b_end_io = end_buffer_write_sync;
-			submit_bh(REQ_OP_WRITE, 0, tbh);
+			submit_bh(REQ_OP_WRITE, tbh);
 		}
 		/* Wait on i/o completion of buffers. */
 		for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
···
 		clear_buffer_dirty(tbh);
 		get_bh(tbh);
 		tbh->b_end_io = end_buffer_write_sync;
-		submit_bh(REQ_OP_WRITE, 0, tbh);
+		submit_bh(REQ_OP_WRITE, tbh);
 	}
 	/* Synchronize the mft mirror now if not @sync. */
 	if (!sync && ni->mft_no < vol->mftmirr_size)

fs/ntfs3/file.c

···
 				lock_buffer(bh);
 				bh->b_end_io = end_buffer_read_sync;
 				get_bh(bh);
-				submit_bh(REQ_OP_READ, 0, bh);
+				submit_bh(REQ_OP_READ, bh);
 
 				wait_on_buffer(bh);
 				if (!buffer_uptodate(bh)) {

fs/ntfs3/fsntfs.c

···
  */
 int ntfs_bio_pages(struct ntfs_sb_info *sbi, const struct runs_tree *run,
 		   struct page **pages, u32 nr_pages, u64 vbo, u32 bytes,
-		   u32 op)
+		   enum req_op op)
 {
 	int err = 0;
 	struct bio *new, *bio = NULL;

fs/ntfs3/inode.c

···
 			bh->b_size = block_size;
 			off = vbo & (PAGE_SIZE - 1);
 			set_bh_page(bh, page, off);
-			ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+			ll_rw_block(REQ_OP_READ, 1, &bh);
 			wait_on_buffer(bh);
 			if (!buffer_uptodate(bh)) {
 				err = -EIO;

fs/ntfs3/ntfs_fs.h

···
 		  struct ntfs_buffers *nb, int sync);
 int ntfs_bio_pages(struct ntfs_sb_info *sbi, const struct runs_tree *run,
 		   struct page **pages, u32 nr_pages, u64 vbo, u32 bytes,
-		   u32 op);
+		   enum req_op op);
 int ntfs_bio_fill_1(struct ntfs_sb_info *sbi, const struct runs_tree *run);
 int ntfs_vbo_to_lbo(struct ntfs_sb_info *sbi, const struct runs_tree *run,
 		    u64 vbo, u64 *lbo, u64 *bytes);

fs/ocfs2/aops.c

···
 			   !buffer_new(bh) &&
 			   ocfs2_should_read_blk(inode, page, block_start) &&
 			   (block_start < from || block_end > to)) {
-			ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+			ll_rw_block(REQ_OP_READ, 1, &bh);
 			*wait_bh++=bh;
 		}
 

fs/ocfs2/buffer_head_io.c

···
 
 	get_bh(bh); /* for end_buffer_write_sync() */
 	bh->b_end_io = end_buffer_write_sync;
-	submit_bh(REQ_OP_WRITE, 0, bh);
+	submit_bh(REQ_OP_WRITE, bh);
 
 	wait_on_buffer(bh);
 
···
 
 		get_bh(bh); /* for end_buffer_read_sync() */
 		bh->b_end_io = end_buffer_read_sync;
-		submit_bh(REQ_OP_READ, 0, bh);
+		submit_bh(REQ_OP_READ, bh);
 	}
 
 read_failure:
···
 			if (validate)
 				set_buffer_needs_validate(bh);
 			bh->b_end_io = end_buffer_read_sync;
-			submit_bh(REQ_OP_READ, 0, bh);
+			submit_bh(REQ_OP_READ, bh);
 			continue;
 		}
 	}
···
 	get_bh(bh); /* for end_buffer_write_sync() */
 	bh->b_end_io = end_buffer_write_sync;
 	ocfs2_compute_meta_ecc(osb->sb, bh->b_data, &di->i_check);
-	submit_bh(REQ_OP_WRITE, 0, bh);
+	submit_bh(REQ_OP_WRITE, bh);
 
 	wait_on_buffer(bh);
 

fs/ocfs2/cluster/heartbeat.c

···
 	 * (hr_steady_iterations == 0) within hr_unsteady_iterations */
 	atomic_t		hr_unsteady_iterations;
 
-	char			hr_dev_name[BDEVNAME_SIZE];
-
 	unsigned int		hr_timeout_ms;
 
 	/* randomized as the region goes up and down so that a node
···
 		container_of(work, struct o2hb_region,
 			     hr_write_timeout_work.work);
 
-	mlog(ML_ERROR, "Heartbeat write timeout to device %s after %u "
-	     "milliseconds\n", reg->hr_dev_name,
+	mlog(ML_ERROR, "Heartbeat write timeout to device %pg after %u "
+	     "milliseconds\n", reg->hr_bdev,
 	     jiffies_to_msecs(jiffies - reg->hr_last_timeout_start));
 
 	if (o2hb_global_heartbeat_active()) {
···
 
 	if (master_node == o2nm_this_node()) {
 		if (!test_bit(master_node, reg->hr_nego_node_bitmap)) {
-			printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%s).\n",
+			printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%pg).\n",
 				o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000,
-				config_item_name(&reg->hr_item), reg->hr_dev_name);
+				config_item_name(&reg->hr_item), reg->hr_bdev);
 			set_bit(master_node, reg->hr_nego_node_bitmap);
 		}
 		if (memcmp(reg->hr_nego_node_bitmap, live_node_bitmap,
···
 			return;
 		}
 
-		printk(KERN_NOTICE "o2hb: all nodes hb write hung, maybe region %s (%s) is down.\n",
-			config_item_name(&reg->hr_item), reg->hr_dev_name);
+		printk(KERN_NOTICE "o2hb: all nodes hb write hung, maybe region %s (%pg) is down.\n",
+			config_item_name(&reg->hr_item), reg->hr_bdev);
 		/* approve negotiate timeout request. */
 		o2hb_arm_timeout(reg);
 
···
 		}
 	} else {
 		/* negotiate timeout with master node. */
-		printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%s), negotiate timeout with node %d.\n",
+		printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%pg), negotiate timeout with node %d.\n",
 			o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000, config_item_name(&reg->hr_item),
-			reg->hr_dev_name, master_node);
+			reg->hr_bdev, master_node);
 		ret = o2hb_send_nego_msg(reg->hr_key, O2HB_NEGO_TIMEOUT_MSG,
 				master_node);
 		if (ret)
···
 	struct o2hb_nego_msg *nego_msg;
 
 	nego_msg = (struct o2hb_nego_msg *)msg->buf;
-	printk(KERN_NOTICE "o2hb: receive negotiate timeout message from node %d on region %s (%s).\n",
-		nego_msg->node_num, config_item_name(&reg->hr_item), reg->hr_dev_name);
+	printk(KERN_NOTICE "o2hb: receive negotiate timeout message from node %d on region %s (%pg).\n",
+		nego_msg->node_num, config_item_name(&reg->hr_item), reg->hr_bdev);
 	if (nego_msg->node_num < O2NM_MAX_NODES)
 		set_bit(nego_msg->node_num, reg->hr_nego_node_bitmap);
 	else
···
 {
 	struct o2hb_region *reg = data;
 
-	printk(KERN_NOTICE "o2hb: negotiate timeout approved by master node on region %s (%s).\n",
-		config_item_name(&reg->hr_item), reg->hr_dev_name);
+	printk(KERN_NOTICE "o2hb: negotiate timeout approved by master node on region %s (%pg).\n",
+		config_item_name(&reg->hr_item), reg->hr_bdev);
 	o2hb_arm_timeout(reg);
 	return 0;
 }
···
 static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 				      struct o2hb_bio_wait_ctxt *wc,
 				      unsigned int *current_slot,
-				      unsigned int max_slots, int op,
-				      int op_flags)
+				      unsigned int max_slots, blk_opf_t opf)
 {
 	int len, current_page;
 	unsigned int vec_len, vec_start;
···
 	 * GFP_KERNEL that the local node can get fenced. It would be
 	 * nicest if we could pre-allocate these bios and avoid this
 	 * all together. */
-	bio = bio_alloc(reg->hr_bdev, 16, op | op_flags, GFP_ATOMIC);
+	bio = bio_alloc(reg->hr_bdev, 16, opf, GFP_ATOMIC);
 	if (!bio) {
 		mlog(ML_ERROR, "Could not alloc slots BIO!\n");
 		bio = ERR_PTR(-ENOMEM);
···
 
 	while(current_slot < max_slots) {
 		bio = o2hb_setup_one_bio(reg, &wc, &current_slot, max_slots,
-					 REQ_OP_READ, 0);
+					 REQ_OP_READ);
 		if (IS_ERR(bio)) {
 			status = PTR_ERR(bio);
 			mlog_errno(status);
···
 
 	slot = o2nm_this_node();
 
-	bio = o2hb_setup_one_bio(reg, write_wc, &slot, slot+1, REQ_OP_WRITE,
-				 REQ_SYNC);
+	bio = o2hb_setup_one_bio(reg, write_wc, &slot, slot+1,
+				 REQ_OP_WRITE | REQ_SYNC);
 	if (IS_ERR(bio)) {
 		status = PTR_ERR(bio);
 		mlog_errno(status);
···
 	else
 		errstr = ERRSTR3;
 
-	mlog(ML_ERROR, "%s (%s): expected(%u:0x%llx, 0x%llx), "
-	     "ondisk(%u:0x%llx, 0x%llx)\n", errstr, reg->hr_dev_name,
+	mlog(ML_ERROR, "%s (%pg): expected(%u:0x%llx, 0x%llx), "
+	     "ondisk(%u:0x%llx, 0x%llx)\n", errstr, reg->hr_bdev,
 	     slot->ds_node_num, (unsigned long long)slot->ds_last_generation,
 	     (unsigned long long)slot->ds_last_time, hb_block->hb_node,
 	     (unsigned long long)le64_to_cpu(hb_block->hb_generation),
···
 		   sizeof(o2hb_live_node_bitmap)))
 		goto unlock;
 
-	printk(KERN_NOTICE "o2hb: Region %s (%s) is now a quorum device\n",
-	       config_item_name(&reg->hr_item), reg->hr_dev_name);
+	printk(KERN_NOTICE "o2hb: Region %s (%pg) is now a quorum device\n",
+	       config_item_name(&reg->hr_item), reg->hr_bdev);
 
 	set_bit(reg->hr_region_num, o2hb_quorum_region_bitmap);
 
···
 		/* The node is live but pushed out a bad crc. We
 		 * consider it a transient miss but don't populate any
 		 * other values as they may be junk. */
-		mlog(ML_ERROR, "Node %d has written a bad crc to %s\n",
-		     slot->ds_node_num, reg->hr_dev_name);
+		mlog(ML_ERROR, "Node %d has written a bad crc to %pg\n",
+		     slot->ds_node_num, reg->hr_bdev);
 		o2hb_dump_slot(hb_block);
 
 		slot->ds_equal_samples++;
···
 		slot_dead_ms = le32_to_cpu(hb_block->hb_dead_ms);
 		if (slot_dead_ms && slot_dead_ms != dead_ms) {
 			/* TODO: Perhaps we can fail the region here. */
-			mlog(ML_ERROR, "Node %d on device %s has a dead count "
+			mlog(ML_ERROR, "Node %d on device %pg has a dead count "
 			     "of %u ms, but our count is %u ms.\n"
 			     "Please double check your configuration values "
 			     "for 'O2CB_HEARTBEAT_THRESHOLD'\n",
-			     slot->ds_node_num, reg->hr_dev_name, slot_dead_ms,
+			     slot->ds_node_num, reg->hr_bdev, slot_dead_ms,
 			     dead_ms);
 		}
 		goto out;
···
 		/* Do not re-arm the write timeout on I/O error - we
 		 * can't be sure that the new block ever made it to
 		 * disk */
-		mlog(ML_ERROR, "Write error %d on device \"%s\"\n",
-		     write_wc.wc_error, reg->hr_dev_name);
+		mlog(ML_ERROR, "Write error %d on device \"%pg\"\n",
+		     write_wc.wc_error, reg->hr_bdev);
 		ret = write_wc.wc_error;
 		goto bail;
 	}
···
 	if (atomic_read(&reg->hr_steady_iterations) != 0) {
 		if (atomic_dec_and_test(&reg->hr_unsteady_iterations)) {
 			printk(KERN_NOTICE "o2hb: Unable to stabilize "
-			       "heartbeat on region %s (%s)\n",
+			       "heartbeat on region %s (%pg)\n",
 			       config_item_name(&reg->hr_item),
-			       reg->hr_dev_name);
+			       reg->hr_bdev);
 			atomic_set(&reg->hr_steady_iterations, 0);
 			reg->hr_aborted_start = 1;
 			wake_up(&o2hb_steady_queue);
···
 	struct page *page;
 	struct o2hb_region *reg = to_o2hb_region(item);
 
-	mlog(ML_HEARTBEAT, "hb region release (%s)\n", reg->hr_dev_name);
+	mlog(ML_HEARTBEAT, "hb region release (%pg)\n", reg->hr_bdev);
 
 	kfree(reg->hr_tmp_block);
 
···
 	unsigned int ret = 0;
 
 	if (to_o2hb_region(item)->hr_bdev)
-		ret = sprintf(page, "%s\n", to_o2hb_region(item)->hr_dev_name);
+		ret = sprintf(page, "%pg\n", to_o2hb_region(item)->hr_bdev);
 
 	return ret;
 }
···
 		goto out2;
 	}
 
-	bdevname(reg->hr_bdev, reg->hr_dev_name);
-
 	sectsize = bdev_logical_block_size(reg->hr_bdev);
 	if (sectsize != reg->hr_block_bytes) {
 		mlog(ML_ERROR,
···
 		ret = -EIO;
 
 	if (hb_task && o2hb_global_heartbeat_active())
-		printk(KERN_NOTICE "o2hb: Heartbeat started on region %s (%s)\n",
-		       config_item_name(&reg->hr_item), reg->hr_dev_name);
+		printk(KERN_NOTICE "o2hb: Heartbeat started on region %s (%pg)\n",
+		       config_item_name(&reg->hr_item), reg->hr_bdev);
 
 out3:
 	if (ret < 0) {
···
 			quorum_region = 1;
 		clear_bit(reg->hr_region_num, o2hb_quorum_region_bitmap);
 		spin_unlock(&o2hb_live_lock);
-		printk(KERN_NOTICE "o2hb: Heartbeat %s on region %s (%s)\n",
+		printk(KERN_NOTICE "o2hb: Heartbeat %s on region %s (%pg)\n",
 		       ((atomic_read(&reg->hr_steady_iterations) == 0) ?
 			"stopped" : "start aborted"), config_item_name(item),
-		       reg->hr_dev_name);
+		       reg->hr_bdev);
 	}
 
 	/*

fs/ocfs2/super.c

···
 	if (!buffer_dirty(*bh))
 		clear_buffer_uptodate(*bh);
 	unlock_buffer(*bh);
-	ll_rw_block(REQ_OP_READ, 0, 1, bh);
+	ll_rw_block(REQ_OP_READ, 1, bh);
 	wait_on_buffer(*bh);
 	if (!buffer_uptodate(*bh)) {
 		mlog_errno(-EIO);

fs/reiserfs/inode.c

···
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh(REQ_OP_WRITE, 0, bh);
+			submit_bh(REQ_OP_WRITE, bh);
 			nr++;
 		}
 		put_bh(bh);
···
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
 			clear_buffer_dirty(bh);
-			submit_bh(REQ_OP_WRITE, 0, bh);
+			submit_bh(REQ_OP_WRITE, bh);
 			nr++;
 		}
 		put_bh(bh);

fs/reiserfs/journal.c

···
 		BUG();
 	if (!buffer_uptodate(bh))
 		BUG();
-	submit_bh(REQ_OP_WRITE, 0, bh);
+	submit_bh(REQ_OP_WRITE, bh);
 }
 
 static void submit_ordered_buffer(struct buffer_head *bh)
···
 	clear_buffer_dirty(bh);
 	if (!buffer_uptodate(bh))
 		BUG();
-	submit_bh(REQ_OP_WRITE, 0, bh);
+	submit_bh(REQ_OP_WRITE, bh);
 }
 
 #define CHUNK_SIZE 32
···
 		 */
 		if (buffer_dirty(bh) && unlikely(bh->b_page->mapping == NULL)) {
 			spin_unlock(lock);
-			ll_rw_block(REQ_OP_WRITE, 0, 1, &bh);
+			ll_rw_block(REQ_OP_WRITE, 1, &bh);
 			spin_lock(lock);
 		}
 		put_bh(bh);
···
 		if (tbh) {
 			if (buffer_dirty(tbh)) {
 		            depth = reiserfs_write_unlock_nested(s);
-			    ll_rw_block(REQ_OP_WRITE, 0, 1, &tbh);
+			    ll_rw_block(REQ_OP_WRITE, 1, &tbh);
 			    reiserfs_write_lock_nested(s, depth);
 			}
 			put_bh(tbh) ;
···
 		}
 	}
 	/* read in the log blocks, memcpy to the corresponding real block */
-	ll_rw_block(REQ_OP_READ, 0, get_desc_trans_len(desc), log_blocks);
+	ll_rw_block(REQ_OP_READ, get_desc_trans_len(desc), log_blocks);
 	for (i = 0; i < get_desc_trans_len(desc); i++) {
 
 		wait_on_buffer(log_blocks[i]);
···
 		} else
 			bhlist[j++] = bh;
 	}
-	ll_rw_block(REQ_OP_READ, 0, j, bhlist);
+	ll_rw_block(REQ_OP_READ, j, bhlist);
 	for (i = 1; i < j; i++)
 		brelse(bhlist[i]);
 	bh = bhlist[0];

fs/reiserfs/stree.c

···
 		if (!buffer_uptodate(bh[j])) {
 			if (depth == -1)
 				depth = reiserfs_write_unlock_nested(s);
-			ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, bh + j);
+			ll_rw_block(REQ_OP_READ | REQ_RAHEAD, 1, bh + j);
 		}
 		brelse(bh[j]);
 	}
···
 			if (!buffer_uptodate(bh) && depth == -1)
 				depth = reiserfs_write_unlock_nested(sb);
 
-			ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+			ll_rw_block(REQ_OP_READ, 1, &bh);
 			wait_on_buffer(bh);
 
 			if (depth != -1)

fs/reiserfs/super.c

···
 /* after journal replay, reread all bitmap and super blocks */
 static int reread_meta_blocks(struct super_block *s)
 {
-	ll_rw_block(REQ_OP_READ, 0, 1, &SB_BUFFER_WITH_SB(s));
+	ll_rw_block(REQ_OP_READ, 1, &SB_BUFFER_WITH_SB(s));
 	wait_on_buffer(SB_BUFFER_WITH_SB(s));
 	if (!buffer_uptodate(SB_BUFFER_WITH_SB(s))) {
 		reiserfs_warning(s, "reiserfs-2504", "error reading the super");

fs/udf/dir.c

···
 					brelse(tmp);
 			}
 			if (num) {
-				ll_rw_block(REQ_OP_READ, REQ_RAHEAD, num, bha);
+				ll_rw_block(REQ_OP_READ | REQ_RAHEAD, num, bha);
 				for (i = 0; i < num; i++)
 					brelse(bha[i]);
 			}

fs/udf/directory.c

···
 					brelse(tmp);
 			}
 			if (num) {
-				ll_rw_block(REQ_OP_READ, REQ_RAHEAD, num, bha);
+				ll_rw_block(REQ_OP_READ | REQ_RAHEAD, num, bha);
 				for (i = 0; i < num; i++)
 					brelse(bha[i]);
 			}

fs/udf/inode.c

···
 	if (buffer_uptodate(bh))
 		return bh;
 
-	ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+	ll_rw_block(REQ_OP_READ, 1, &bh);
 
 	wait_on_buffer(bh);
 	if (buffer_uptodate(bh))

fs/ufs/balloc.c

···
 			if (!buffer_mapped(bh))
 					map_bh(bh, inode->i_sb, oldb + pos);
 			if (!buffer_uptodate(bh)) {
-				ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+				ll_rw_block(REQ_OP_READ, 1, &bh);
 				wait_on_buffer(bh);
 				if (!buffer_uptodate(bh)) {
 					ufs_error(inode->i_sb, __func__,

fs/xfs/xfs_bio_io.c

···
 	sector_t		sector,
 	unsigned int		count,
 	char			*data,
-	unsigned int		op)
+	enum req_op		op)
 
 {
 	unsigned int		is_vmalloc = is_vmalloc_addr(data);

fs/xfs/xfs_buf.c

···
 	int		map,
 	int		*buf_offset,
 	int		*count,
-	int		op)
+	blk_opf_t	op)
 {
 	int		page_index;
 	unsigned int	total_nr_pages = bp->b_page_count;
···
 	struct xfs_buf	*bp)
 {
 	struct blk_plug	plug;
-	int		op;
+	blk_opf_t	op;
 	int		offset;
 	int		size;
 	int		i;

fs/xfs/xfs_linux.h

···
 }
 
 int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count,
-		char *data, unsigned int op);
+		char *data, enum req_op op);
 
 #define ASSERT_ALWAYS(expr)	\
 	(likely(expr) ? (void)0 : assfail(NULL, #expr, __FILE__, __LINE__))

fs/xfs/xfs_log_recover.c

···
 	xfs_daddr_t		blk_no,
 	unsigned int		nbblks,
 	char			*data,
-	unsigned int		op)
+	enum req_op		op)
 {
 	int			error;
 

fs/zonefs/super.c

···
 	}
 }
 
-static inline int zonefs_zone_mgmt(struct inode *inode,
-				   enum req_opf op)
+static inline int zonefs_zone_mgmt(struct inode *inode, enum req_op op)
 {
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 	int ret;
···
 {
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 	loff_t old_isize;
-	enum req_opf op;
+	enum req_op op;
 	int ret = 0;
 
 	/*
···
 {
 	struct super_block *sb = parent->i_sb;
 
-	inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk) + type + 1;
+	inode->i_ino = bdev_nr_zones(sb->s_bdev) + type + 1;
 	inode_init_owner(&init_user_ns, inode, parent, S_IFDIR | 0555);
 	inode->i_op = &zonefs_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
···
 	/*
 	 * The first zone contains the super block: skip it.
 	 */
-	end = zd->zones + blkdev_nr_zones(sb->s_bdev->bd_disk);
+	end = zd->zones + bdev_nr_zones(sb->s_bdev);
 	for (zone = &zd->zones[1]; zone < end; zone = next) {
 
 		next = zone + 1;
···
 	struct block_device *bdev = zd->sb->s_bdev;
 	int ret;
 
-	zd->zones = kvcalloc(blkdev_nr_zones(bdev->bd_disk),
-			     sizeof(struct blk_zone), GFP_KERNEL);
+	zd->zones = kvcalloc(bdev_nr_zones(bdev), sizeof(struct blk_zone),
+			     GFP_KERNEL);
 	if (!zd->zones)
 		return -ENOMEM;
 
···
 		return ret;
 	}
 
-	if (ret != blkdev_nr_zones(bdev->bd_disk)) {
+	if (ret != bdev_nr_zones(bdev)) {
 		zonefs_err(zd->sb, "Invalid zone report (%d/%u zones)\n",
-			   ret, blkdev_nr_zones(bdev->bd_disk));
+			   ret, bdev_nr_zones(bdev));
 		return -EIO;
 	}
 
···
 	if (ret)
 		goto cleanup;
 
-	zonefs_info(sb, "Mounting %u zones",
-		    blkdev_nr_zones(sb->s_bdev->bd_disk));
+	zonefs_info(sb, "Mounting %u zones", bdev_nr_zones(sb->s_bdev));
 
 	if (!sbi->s_max_wro_seq_files &&
 	    !sbi->s_max_active_seq_files &&
···
 	if (!inode)
 		goto cleanup;
 
-	inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk);
+	inode->i_ino = bdev_nr_zones(sb->s_bdev);
 	inode->i_mode = S_IFDIR | 0555;
 	inode->i_ctime = inode->i_mtime = inode->i_atime = current_time(inode);
 	inode->i_op = &zonefs_dir_inode_operations;

fs/zonefs/trace.h

···
 #define show_dev(dev) MAJOR(dev), MINOR(dev)
 
 TRACE_EVENT(zonefs_zone_mgmt,
-	    TP_PROTO(struct inode *inode, enum req_opf op),
+	    TP_PROTO(struct inode *inode, enum req_op op),
 	    TP_ARGS(inode, op),
 	    TP_STRUCT__entry(
 			     __field(dev_t, dev)
 			     __field(ino_t, ino)
-			     __field(int, op)
+			     __field(enum req_op, op)
 			     __field(sector_t, sector)
 			     __field(sector_t, nr_sectors)
 	    ),

include/linux/bio.h

···
 extern int biovec_init_pool(mempool_t *pool, int pool_entries);
 
 struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
-			     unsigned int opf, gfp_t gfp_mask,
+			     blk_opf_t opf, gfp_t gfp_mask,
 			     struct bio_set *bs);
 struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask);
 extern void bio_put(struct bio *);
···
 extern struct bio_set fs_bio_set;
 
 static inline struct bio *bio_alloc(struct block_device *bdev,
-		unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask)
+		unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp_mask)
 {
 	return bio_alloc_bioset(bdev, nr_vecs, opf, gfp_mask, &fs_bio_set);
 }
···
 
 extern int submit_bio_wait(struct bio *bio);
 void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table,
-	      unsigned short max_vecs, unsigned int opf);
+	      unsigned short max_vecs, blk_opf_t opf);
 extern void bio_uninit(struct bio *);
-void bio_reset(struct bio *bio, struct block_device *bdev, unsigned int opf);
+void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf);
 void bio_chain(struct bio *, struct bio *);
 
 int bio_add_page(struct bio *, struct page *, unsigned len, unsigned off);
···
 }
 
 struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
-		unsigned int nr_pages, unsigned int opf, gfp_t gfp);
+		unsigned int nr_pages, blk_opf_t opf, gfp_t gfp);
 
 #endif /* __LINUX_BIO_H */

include/linux/blk-mq.h

···
 #define RQF_TIMED_OUT		((__force req_flags_t)(1 << 21))
 /* queue has elevator attached */
 #define RQF_ELV			((__force req_flags_t)(1 << 22))
+#define RQF_RESV			((__force req_flags_t)(1 << 23))
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \
···
 	struct blk_mq_ctx *mq_ctx;
 	struct blk_mq_hw_ctx *mq_hctx;
 
-	unsigned int cmd_flags;		/* op and common flags */
+	blk_opf_t cmd_flags;		/* op and common flags */
 	req_flags_t rq_flags;
 
 	int tag;
···
 	void *end_io_data;
 };
 
-#define req_op(req) \
-	((req)->cmd_flags & REQ_OP_MASK)
+static inline enum req_op req_op(const struct request *req)
+{
+	return req->cmd_flags & REQ_OP_MASK;
+}
 
 static inline bool blk_rq_is_passthrough(struct request *rq)
 {
···
 	bool last;
 };
 
-typedef bool (busy_tag_iter_fn)(struct request *, void *, bool);
+typedef bool (busy_tag_iter_fn)(struct request *, void *);
 
 /**
  * struct blk_mq_ops - Callback functions that implements block driver
···
 	/**
 	 * @timeout: Called on request timeout.
 	 */
-	enum blk_eh_timer_return (*timeout)(struct request *, bool);
+	enum blk_eh_timer_return (*timeout)(struct request *);
 
 	/**
 	 * @poll: Called to poll for completion of a specific tag.
···
 									\
 	__blk_mq_alloc_disk(set, queuedata, &__key);			\
 })
+struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q,
+		struct lock_class_key *lkclass);
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
 int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		struct request_queue *q);
-void blk_mq_unregister_dev(struct device *, struct request_queue *);
+void blk_mq_destroy_queue(struct request_queue *);
 
 int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set);
 int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set,
···
 	BLK_MQ_REQ_PM		= (__force blk_mq_req_flags_t)(1 << 2),
 };
 
-struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
+struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf,
 		blk_mq_req_flags_t flags);
 struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
-		unsigned int op, blk_mq_req_flags_t flags,
+		blk_opf_t opf, blk_mq_req_flags_t flags,
 		unsigned int hctx_idx);
 
 /*
···
 static inline bool blk_mq_need_time_stamp(struct request *rq)
 {
 	return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV));
+}
+
+static inline bool blk_mq_is_reserved_rq(struct request *rq)
+{
+	return rq->rq_flags & RQF_RESV;
 }
 
 /*
···
 #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));
+	return disk_zone_no(rq->q->disk, 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));
+	return disk_zone_is_seq(rq->q->disk, blk_rq_pos(rq));
 }
 
 bool blk_req_needs_zone_write_lock(struct request *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);
+	return rq->q->disk->seq_zones_wlock &&
+		test_bit(blk_rq_zone_no(rq), rq->q->disk->seq_zones_wlock);
 }
 
 static inline bool blk_req_can_dispatch_to_zone(struct request *rq)

include/linux/blk_types.h

···
 			((u64)size << BIO_ISSUE_SIZE_SHIFT));
 }
 
+typedef __u32 __bitwise blk_opf_t;
+
 typedef unsigned int blk_qc_t;
 #define BLK_QC_T_NONE		-1U
 
···
 struct bio {
 	struct bio		*bi_next;	/* request queue link */
 	struct block_device	*bi_bdev;
-	unsigned int		bi_opf;		/* bottom bits REQ_OP, top bits
+	blk_opf_t		bi_opf;		/* bottom bits REQ_OP, top bits
 						 * req_flags.
 						 */
 	unsigned short		bi_flags;	/* BIO_* below */
···
 
 typedef __u32 __bitwise blk_mq_req_flags_t;
 
-/*
- * Operations and flags common to the bio and request structures.
+#define REQ_OP_BITS	8
+#define REQ_OP_MASK	(__force blk_opf_t)((1 << REQ_OP_BITS) - 1)
+#define REQ_FLAG_BITS	24
+
+/**
+ * enum req_op - Operations common to the bio and request structures.
  * We use 8 bits for encoding the operation, and the remaining 24 for flags.
  *
  * The least significant bit of the operation number indicates the data
···
  * If a operation does not transfer data the least significant bit has no
  * meaning.
  */
-#define REQ_OP_BITS	8
-#define REQ_OP_MASK	((1 << REQ_OP_BITS) - 1)
-#define REQ_FLAG_BITS	24
-
-enum req_opf {
+enum req_op {
 	/* read sectors from the device */
-	REQ_OP_READ		= 0,
+	REQ_OP_READ		= (__force blk_opf_t)0,
 	/* write sectors to the device */
-	REQ_OP_WRITE		= 1,
+	REQ_OP_WRITE		= (__force blk_opf_t)1,
 	/* flush the volatile write cache */
-	REQ_OP_FLUSH		= 2,
+	REQ_OP_FLUSH		= (__force blk_opf_t)2,
 	/* discard sectors */
-	REQ_OP_DISCARD		= 3,
+	REQ_OP_DISCARD		= (__force blk_opf_t)3,
 	/* securely erase sectors */
-	REQ_OP_SECURE_ERASE	= 5,
+	REQ_OP_SECURE_ERASE	= (__force blk_opf_t)5,
 	/* write the zero filled sector many times */
-	REQ_OP_WRITE_ZEROES	= 9,
+	REQ_OP_WRITE_ZEROES	= (__force blk_opf_t)9,
 	/* Open a zone */
-	REQ_OP_ZONE_OPEN	= 10,
+	REQ_OP_ZONE_OPEN	= (__force blk_opf_t)10,
 	/* Close a zone */
-	REQ_OP_ZONE_CLOSE	= 11,
+	REQ_OP_ZONE_CLOSE	= (__force blk_opf_t)11,
 	/* Transition a zone to full */
-	REQ_OP_ZONE_FINISH	= 12,
+	REQ_OP_ZONE_FINISH	= (__force blk_opf_t)12,
 	/* write data at the current zone write pointer */
-	REQ_OP_ZONE_APPEND	= 13,
+	REQ_OP_ZONE_APPEND	= (__force blk_opf_t)13,
 	/* reset a zone write pointer */
-	REQ_OP_ZONE_RESET	= 15,
+	REQ_OP_ZONE_RESET	= (__force blk_opf_t)15,
 	/* reset all the zone present on the device */
-	REQ_OP_ZONE_RESET_ALL	= 17,
+	REQ_OP_ZONE_RESET_ALL	= (__force blk_opf_t)17,
 
 	/* Driver private requests */
-	REQ_OP_DRV_IN		= 34,
-	REQ_OP_DRV_OUT		= 35,
+	REQ_OP_DRV_IN		= (__force blk_opf_t)34,
+	REQ_OP_DRV_OUT		= (__force blk_opf_t)35,
 
-	REQ_OP_LAST,
+	REQ_OP_LAST		= (__force blk_opf_t)36,
 };
 
 enum req_flag_bits {
···
 	__REQ_NR_BITS,		/* stops here */
 };
 
-#define REQ_FAILFAST_DEV	(1ULL << __REQ_FAILFAST_DEV)
-#define REQ_FAILFAST_TRANSPORT	(1ULL << __REQ_FAILFAST_TRANSPORT)
-#define REQ_FAILFAST_DRIVER	(1ULL << __REQ_FAILFAST_DRIVER)
-#define REQ_SYNC		(1ULL << __REQ_SYNC)
-#define REQ_META		(1ULL << __REQ_META)
-#define REQ_PRIO		(1ULL << __REQ_PRIO)
-#define REQ_NOMERGE		(1ULL << __REQ_NOMERGE)
-#define REQ_IDLE		(1ULL << __REQ_IDLE)
-#define REQ_INTEGRITY		(1ULL << __REQ_INTEGRITY)
-#define REQ_FUA			(1ULL << __REQ_FUA)
-#define REQ_PREFLUSH		(1ULL << __REQ_PREFLUSH)
-#define REQ_RAHEAD		(1ULL << __REQ_RAHEAD)
-#define REQ_BACKGROUND		(1ULL << __REQ_BACKGROUND)
-#define REQ_NOWAIT		(1ULL << __REQ_NOWAIT)
-#define REQ_CGROUP_PUNT		(1ULL << __REQ_CGROUP_PUNT)
+#define REQ_FAILFAST_DEV	\
+			(__force blk_opf_t)(1ULL << __REQ_FAILFAST_DEV)
+#define REQ_FAILFAST_TRANSPORT	\
+			(__force blk_opf_t)(1ULL << __REQ_FAILFAST_TRANSPORT)
+#define REQ_FAILFAST_DRIVER	\
+			(__force blk_opf_t)(1ULL << __REQ_FAILFAST_DRIVER)
+#define REQ_SYNC	(__force blk_opf_t)(1ULL << __REQ_SYNC)
+#define REQ_META	(__force blk_opf_t)(1ULL << __REQ_META)
+#define REQ_PRIO	(__force blk_opf_t)(1ULL << __REQ_PRIO)
+#define REQ_NOMERGE	(__force blk_opf_t)(1ULL << __REQ_NOMERGE)
+#define REQ_IDLE	(__force blk_opf_t)(1ULL << __REQ_IDLE)
+#define REQ_INTEGRITY	(__force blk_opf_t)(1ULL << __REQ_INTEGRITY)
+#define REQ_FUA		(__force blk_opf_t)(1ULL << __REQ_FUA)
+#define REQ_PREFLUSH	(__force blk_opf_t)(1ULL << __REQ_PREFLUSH)
+#define REQ_RAHEAD	(__force blk_opf_t)(1ULL << __REQ_RAHEAD)
+#define REQ_BACKGROUND	(__force blk_opf_t)(1ULL << __REQ_BACKGROUND)
+#define REQ_NOWAIT	(__force blk_opf_t)(1ULL << __REQ_NOWAIT)
+#define REQ_CGROUP_PUNT	(__force blk_opf_t)(1ULL << __REQ_CGROUP_PUNT)
 
-#define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
-#define REQ_POLLED		(1ULL << __REQ_POLLED)
-#define REQ_ALLOC_CACHE		(1ULL << __REQ_ALLOC_CACHE)
+#define REQ_NOUNMAP	(__force blk_opf_t)(1ULL << __REQ_NOUNMAP)
+#define REQ_POLLED	(__force blk_opf_t)(1ULL << __REQ_POLLED)
+#define REQ_ALLOC_CACHE	(__force blk_opf_t)(1ULL << __REQ_ALLOC_CACHE)
 
-#define REQ_DRV			(1ULL << __REQ_DRV)
-#define REQ_SWAP		(1ULL << __REQ_SWAP)
+#define REQ_DRV		(__force blk_opf_t)(1ULL << __REQ_DRV)
+#define REQ_SWAP	(__force blk_opf_t)(1ULL << __REQ_SWAP)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
···
 	NR_STAT_GROUPS
 };
 
-#define bio_op(bio) \
-	((bio)->bi_opf & REQ_OP_MASK)
+static inline enum req_op bio_op(const struct bio *bio)
+{
+	return bio->bi_opf & REQ_OP_MASK;
+}
 
 /* obsolete, don't use in new code */
-static inline void bio_set_op_attrs(struct bio *bio, unsigned op,
-		unsigned op_flags)
+static inline void bio_set_op_attrs(struct bio *bio, enum req_op op,
+				    blk_opf_t op_flags)
 {
 	bio->bi_opf = op | op_flags;
 }
 
-static inline bool op_is_write(unsigned int op)
+static inline bool op_is_write(blk_opf_t op)
 {
-	return (op & 1);
+	return !!(op & (__force blk_opf_t)1);
 }
 
 /*
  * Check if the bio or request is one that needs special treatment in the
  * flush state machine.
  */
-static inline bool op_is_flush(unsigned int op)
+static inline bool op_is_flush(blk_opf_t op)
 {
 	return op & (REQ_FUA | REQ_PREFLUSH);
 }
···
  * PREFLUSH flag.  Other operations may be marked as synchronous using the
  * REQ_SYNC flag.
  */
-static inline bool op_is_sync(unsigned int op)
+static inline bool op_is_sync(blk_opf_t op)
 {
 	return (op & REQ_OP_MASK) == REQ_OP_READ ||
 		(op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH));
 }
 
-static inline bool op_is_discard(unsigned int op)
+static inline bool op_is_discard(blk_opf_t op)
 {
 	return (op & REQ_OP_MASK) == REQ_OP_DISCARD;
 }
···
  * due to its different handling in the block layer and device response in
  * case of command failure.
  */
-static inline bool op_is_zone_mgmt(enum req_opf op)
+static inline bool op_is_zone_mgmt(enum req_op op)
 {
 	switch (op & REQ_OP_MASK) {
 	case REQ_OP_ZONE_RESET:
···
 	}
 }
 
-static inline int op_stat_group(unsigned int op)
+static inline int op_stat_group(enum req_op op)
 {
 	if (op_is_discard(op))
 		return STAT_DISCARD;

include/linux/blkdev.h

···
 #define GD_NATIVE_CAPACITY		3
 #define GD_ADDED			4
 #define GD_SUPPRESS_PART_SCAN		5
+#define GD_OWNS_QUEUE			6
 
 	struct mutex open_mutex;	/* open/close mutex */
 	unsigned open_partitions;	/* number of open partitions */
···
 #ifdef  CONFIG_BLK_DEV_INTEGRITY
 	struct kobject integrity_kobj;
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
+
+#ifdef CONFIG_BLK_DEV_ZONED
+	/*
+	 * Zoned block device information for request dispatch control.
+	 * nr_zones is the total number of zones of the device. This is always
+	 * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones
+	 * bits which indicates if a zone is conventional (bit set) or
+	 * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones
+	 * bits which indicates if a zone is write locked, that is, if a write
+	 * request targeting the zone was dispatched.
+	 *
+	 * Reads of this information must be protected with blk_queue_enter() /
+	 * blk_queue_exit(). Modifying this information is only allowed while
+	 * no requests are being processed. See also blk_mq_freeze_queue() and
+	 * blk_mq_unfreeze_queue().
+	 */
+	unsigned int		nr_zones;
+	unsigned int		max_open_zones;
+	unsigned int		max_active_zones;
+	unsigned long		*conv_zones_bitmap;
+	unsigned long		*seq_zones_wlock;
+#endif /* CONFIG_BLK_DEV_ZONED */
+
 #if IS_ENABLED(CONFIG_CDROM)
 	struct cdrom_device_info *cdi;
 #endif
···
 	struct badblocks *bb;
 	struct lockdep_map lockdep_map;
 	u64 diskseq;
+
+	/*
+	 * 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;
 };
 
 static inline bool disk_live(struct gendisk *disk)
···
 	return 0;
 }
 
-static inline bool blk_op_is_passthrough(unsigned int op)
+static inline bool blk_op_is_passthrough(blk_opf_t op)
 {
 	op &= REQ_OP_MASK;
 	return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
···
 typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
 			       void *data);
 
-void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model);
+void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model);
 
 #ifdef CONFIG_BLK_DEV_ZONED
 
 #define BLK_ALL_ZONES  ((unsigned int)-1)
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 			unsigned int nr_zones, report_zones_cb cb, void *data);
-unsigned int blkdev_nr_zones(struct gendisk *disk);
-extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
+unsigned int bdev_nr_zones(struct block_device *bdev);
+extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
 			    sector_t sectors, sector_t nr_sectors,
 			    gfp_t gfp_mask);
 int blk_revalidate_disk_zones(struct gendisk *disk,
···
 
 #else /* CONFIG_BLK_DEV_ZONED */
 
-static inline unsigned int blkdev_nr_zones(struct gendisk *disk)
+static inline unsigned int bdev_nr_zones(struct block_device *bdev)
 {
 	return 0;
 }
···
 	unsigned long		nr_requests;	/* Max # of requests */
 
 	unsigned int		dma_pad_mask;
+	/*
+	 * Drivers that set dma_alignment to less than 511 must be prepared to
+	 * handle individual bvec's that are not a multiple of a SECTOR_SIZE
+	 * due to possible offsets.
+	 */
 	unsigned int		dma_alignment;
 
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
···
 	struct queue_limits	limits;
 
 	unsigned int		required_elevator_features;
-
-#ifdef CONFIG_BLK_DEV_ZONED
-	/*
-	 * Zoned block device information for request dispatch control.
-	 * nr_zones is the total number of zones of the device. This is always
-	 * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones
-	 * bits which indicates if a zone is conventional (bit set) or
-	 * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones
-	 * bits which indicates if a zone is write locked, that is, if a write
-	 * request targeting the zone was dispatched. All three fields are
-	 * initialized by the low level device driver (e.g. scsi/sd.c).
-	 * Stacking drivers (device mappers) may or may not initialize
-	 * these fields.
-	 *
-	 * Reads of this information must be protected with blk_queue_enter() /
-	 * blk_queue_exit(). Modifying this information is only allowed while
-	 * no requests are being processed. See also blk_mq_freeze_queue() and
-	 * blk_mq_unfreeze_queue().
-	 */
-	unsigned int		nr_zones;
-	unsigned long		*conv_zones_bitmap;
-	unsigned long		*seq_zones_wlock;
-	unsigned int		max_open_zones;
-	unsigned int		max_active_zones;
-#endif /* CONFIG_BLK_DEV_ZONED */
 
 	int			node;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
···
 
 	bool			mq_sysfs_init_done;
 
-	/*
-	 * 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;
-
 	/**
 	 * @srcu: Sleepable RCU. Use as lock when type of the request queue
 	 * is blocking (BLK_MQ_F_BLOCKING). Must be the last member
···
 #define QUEUE_FLAG_NOXMERGES	9	/* No extended merges */
 #define QUEUE_FLAG_ADD_RANDOM	10	/* Contributes to random pool */
 #define QUEUE_FLAG_SAME_FORCE	12	/* force complete on same CPU */
-#define QUEUE_FLAG_DEAD		13	/* queue tear-down finished */
 #define QUEUE_FLAG_INIT_DONE	14	/* queue is initialized */
 #define QUEUE_FLAG_STABLE_WRITES 15	/* don't modify blks until WB is done */
 #define QUEUE_FLAG_POLL		16	/* IO polling enabled if set */
···
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_dying(q)	test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
 #define blk_queue_has_srcu(q)	test_bit(QUEUE_FLAG_HAS_SRCU, &(q)->queue_flags)
-#define blk_queue_dead(q)	test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags)
 #define blk_queue_init_done(q)	test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_noxmerges(q)	\
···
 	}
 }
 
-static inline sector_t blk_queue_zone_sectors(struct request_queue *q)
-{
-	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
-}
-
 #ifdef CONFIG_BLK_DEV_ZONED
-static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
-	return blk_queue_is_zoned(q) ? q->nr_zones : 0;
+	return blk_queue_is_zoned(disk->queue) ? disk->nr_zones : 0;
 }
 
-static inline unsigned int blk_queue_zone_no(struct request_queue *q,
-					     sector_t sector)
+static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 {
-	if (!blk_queue_is_zoned(q))
+	if (!blk_queue_is_zoned(disk->queue))
 		return 0;
-	return sector >> ilog2(q->limits.chunk_sectors);
+	return sector >> ilog2(disk->queue->limits.chunk_sectors);
 }
 
-static inline bool blk_queue_zone_is_seq(struct request_queue *q,
-					 sector_t sector)
+static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
 {
-	if (!blk_queue_is_zoned(q))
+	if (!blk_queue_is_zoned(disk->queue))
 		return false;
-	if (!q->conv_zones_bitmap)
+	if (!disk->conv_zones_bitmap)
 		return true;
-	return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap);
+	return !test_bit(disk_zone_no(disk, sector), disk->conv_zones_bitmap);
 }
 
-static inline void blk_queue_max_open_zones(struct request_queue *q,
+static inline void disk_set_max_open_zones(struct gendisk *disk,
 		unsigned int max_open_zones)
 {
-	q->max_open_zones = max_open_zones;
+	disk->max_open_zones = max_open_zones;
 }
 
-static inline unsigned int queue_max_open_zones(const struct request_queue *q)
-{
-	return q->max_open_zones;
-}
-
-static inline void blk_queue_max_active_zones(struct request_queue *q,
+static inline void disk_set_max_active_zones(struct gendisk *disk,
 		unsigned int max_active_zones)
 {
-	q->max_active_zones = max_active_zones;
+	disk->max_active_zones = max_active_zones;
 }
 
-static inline unsigned int queue_max_active_zones(const struct request_queue *q)
+static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
 {
-	return q->max_active_zones;
+	return bdev->bd_disk->max_open_zones;
 }
+
+static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
+{
+	return bdev->bd_disk->max_active_zones;
+}
+
 #else /* CONFIG_BLK_DEV_ZONED */
-static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
 	return 0;
 }
-static inline bool blk_queue_zone_is_seq(struct request_queue *q,
-					 sector_t sector)
+static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
 {
 	return false;
 }
-static inline unsigned int blk_queue_zone_no(struct request_queue *q,
-					     sector_t sector)
+static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 {
 	return 0;
 }
-static inline unsigned int queue_max_open_zones(const struct request_queue *q)
+static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
 {
 	return 0;
 }
-static inline unsigned int queue_max_active_zones(const struct request_queue *q)
+
+static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 {
 	return 0;
 }
···
 
 int bdev_disk_changed(struct gendisk *disk, bool invalidate);
 
-struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
-		struct lock_class_key *lkclass);
 void put_disk(struct gendisk *disk);
 struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass);
 
···
 									\
 	__blk_alloc_disk(node_id, &__key);				\
 })
-void blk_cleanup_disk(struct gendisk *disk);
 
 int __register_blkdev(unsigned int major, const char *name,
 		void (*probe)(dev_t devt));
···
 extern void blk_sync_queue(struct request_queue *q);
 
 /* Helper to convert REQ_OP_XXX to its string format XXX */
-extern const char *blk_op_str(unsigned int op);
+extern const char *blk_op_str(enum req_op op);
 
 int blk_status_to_errno(blk_status_t status);
 blk_status_t errno_to_blk_status(int errno);
···
 	return bdev->bd_queue;	/* this is never NULL */
 }
 
-#ifdef CONFIG_BLK_DEV_ZONED
-
 /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */
 const char *blk_zone_cond_str(enum blk_zone_cond zone_cond);
 
 static inline unsigned int bio_zone_no(struct bio *bio)
 {
-	return blk_queue_zone_no(bdev_get_queue(bio->bi_bdev),
-				 bio->bi_iter.bi_sector);
+	return disk_zone_no(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector);
 }
 
 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);
-}
-#endif /* CONFIG_BLK_DEV_ZONED */
-
-static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
-						     int op)
-{
-	if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE))
-		return min(q->limits.max_discard_sectors,
-			   UINT_MAX >> SECTOR_SHIFT);
-
-	if (unlikely(op == REQ_OP_WRITE_ZEROES))
-		return q->limits.max_write_zeroes_sectors;
-
-	return q->limits.max_sectors;
+	return disk_zone_is_seq(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector);
 }
 
 /*
- * Return maximum size of a request at given offset. Only valid for
- * file system requests.
+ * Return how much of the chunk is left to be used for I/O at a given offset.
  */
-static inline unsigned int blk_max_size_offset(struct request_queue *q,
-					       sector_t offset,
-					       unsigned int chunk_sectors)
+static inline unsigned int blk_chunk_sectors_left(sector_t offset,
+		unsigned int chunk_sectors)
 {
-	if (!chunk_sectors) {
-		if (q->limits.chunk_sectors)
-			chunk_sectors = q->limits.chunk_sectors;
-		else
-			return q->limits.max_sectors;
-	}
-
-	if (likely(is_power_of_2(chunk_sectors)))
-		chunk_sectors -= offset & (chunk_sectors - 1);
-	else
-		chunk_sectors -= sector_div(offset, chunk_sectors);
-
-	return min(q->limits.max_sectors, chunk_sectors);
+	if (unlikely(!is_power_of_2(chunk_sectors)))
+		return chunk_sectors - sector_div(offset, chunk_sectors);
+	return chunk_sectors - (offset & (chunk_sectors - 1));
 }
 
 /*
  * Access functions for manipulating queue properties
  */
-extern void blk_cleanup_queue(struct request_queue *);
 void blk_queue_bounce_limit(struct request_queue *q, enum blk_bounce limit);
 extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
···
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 
-	if (q)
-		return blk_queue_zone_sectors(q);
-	return 0;
-}
-
-static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q)
-		return queue_max_open_zones(q);
-	return 0;
-}
-
-static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q)
-		return queue_max_active_zones(q);
-	return 0;
+	if (!blk_queue_is_zoned(q))
+		return 0;
+	return q->limits.chunk_sectors;
 }
 
 static inline int queue_dma_alignment(const struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;
+}
+
+static inline unsigned int bdev_dma_alignment(struct block_device *bdev)
+{
+	return queue_dma_alignment(bdev_get_queue(bdev));
+}
+
+static inline bool bdev_iter_is_aligned(struct block_device *bdev,
+					struct iov_iter *iter)
+{
+	return iov_iter_is_aligned(iter, bdev_dma_alignment(bdev),
+				   bdev_logical_block_size(bdev) - 1);
 }
 
 static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr,
···
 			unsigned int flags);
 	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);
+	int (*rw_page)(struct block_device *, sector_t, struct page *, enum req_op);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	unsigned int (*check_events) (struct gendisk *disk,
···
 }
 
 unsigned long bdev_start_io_acct(struct block_device *bdev,
-				 unsigned int sectors, unsigned int op,
+				 unsigned int sectors, enum req_op op,
 				 unsigned long start_time);
-void bdev_end_io_acct(struct block_device *bdev, unsigned int op,
+void bdev_end_io_acct(struct block_device *bdev, enum req_op op,
 		unsigned long start_time);
 
 void bio_start_io_acct_time(struct bio *bio, unsigned long start_time);
···
 int bdev_read_only(struct block_device *bdev);
 int set_blocksize(struct block_device *bdev, int size);
 
-const char *bdevname(struct block_device *bdev, char *buffer);
 int lookup_bdev(const char *pathname, dev_t *dev);
 
 void blkdev_show(struct seq_file *seqf, off_t offset);

include/linux/blktrace_api.h

···
 #include <linux/compat.h>
 #include <uapi/linux/blktrace_api.h>
 #include <linux/list.h>
+#include <linux/blk_types.h>
 
 #if defined(CONFIG_BLK_DEV_IO_TRACE)
 
···
 			   char __user *arg);
 extern int blk_trace_startstop(struct request_queue *q, int start);
 extern int blk_trace_remove(struct request_queue *q);
-extern void blk_trace_remove_sysfs(struct device *dev);
-extern int blk_trace_init_sysfs(struct device *dev);
-
-extern struct attribute_group blk_trace_attr_group;
 
 #else /* !CONFIG_BLK_DEV_IO_TRACE */
 # define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
···
 # define blk_trace_remove(q)				(-ENOTTY)
 # define blk_add_trace_msg(q, fmt, ...)			do { } while (0)
 # define blk_add_cgroup_trace_msg(q, cg, fmt, ...)	do { } while (0)
-# define blk_trace_remove_sysfs(dev)			do { } while (0)
 # define blk_trace_note_message_enabled(q)		(false)
-static inline int blk_trace_init_sysfs(struct device *dev)
-{
-	return 0;
-}
-
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
 
 #ifdef CONFIG_COMPAT
···
 
 #endif
 
-void blk_fill_rwbs(char *rwbs, unsigned int op);
+void blk_fill_rwbs(char *rwbs, blk_opf_t opf);
 
 static inline sector_t blk_rq_trace_sector(struct request *rq)
 {

include/linux/buffer_head.h

···
 #define _LINUX_BUFFER_HEAD_H
 
 #include <linux/types.h>
+#include <linux/blk_types.h>
 #include <linux/fs.h>
 #include <linux/linkage.h>
 #include <linux/pagemap.h>
···
 void free_buffer_head(struct buffer_head * bh);
 void unlock_buffer(struct buffer_head *bh);
 void __lock_buffer(struct buffer_head *bh);
-void ll_rw_block(int, int, int, struct buffer_head * bh[]);
+void ll_rw_block(blk_opf_t, int, struct buffer_head * bh[]);
 int sync_dirty_buffer(struct buffer_head *bh);
-int __sync_dirty_buffer(struct buffer_head *bh, int op_flags);
-void write_dirty_buffer(struct buffer_head *bh, int op_flags);
-int submit_bh(int, int, struct buffer_head *);
+int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags);
+void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags);
+int submit_bh(blk_opf_t, struct buffer_head *);
 void write_boundary_block(struct block_device *bdev,
 			sector_t bblock, unsigned blocksize);
 int bh_uptodate_or_lock(struct buffer_head *bh);

include/linux/dm-io.h

···
 #ifdef __KERNEL__
 
 #include <linux/types.h>
+#include <linux/blk_types.h>
 
 struct dm_io_region {
 	struct block_device *bdev;
···
  */
 struct dm_io_client;
 struct dm_io_request {
-	int bi_op;			/* REQ_OP */
-	int bi_op_flags;		/* req_flag_bits */
+	blk_opf_t	    bi_opf;	/* Request type and flags */
 	struct dm_io_memory mem;	/* Memory to use for io */
 	struct dm_io_notify notify;	/* Synchronous if notify.fn is NULL */
 	struct dm_io_client *client;	/* Client memory handler */

include/linux/ioprio.h

···
 /*
  * Default IO priority.
  */
-#define IOPRIO_DEFAULT	IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_BE_NORM)
+#define IOPRIO_DEFAULT	IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0)
 
 /*
  * Check that a priority value has a valid class.
···
 		return IOPRIO_CLASS_BE;
 }
 
-/*
- * If the calling process has set an I/O priority, use that. Otherwise, return
- * the default I/O priority.
- */
-static inline int get_current_ioprio(void)
+#ifdef CONFIG_BLOCK
+int __get_task_ioprio(struct task_struct *p);
+#else
+static inline int __get_task_ioprio(struct task_struct *p)
 {
-	struct io_context *ioc = current->io_context;
-
-	if (ioc)
-		return ioc->ioprio;
 	return IOPRIO_DEFAULT;
 }
+#endif /* CONFIG_BLOCK */
 
-/*
- * For inheritance, return the highest of the two given priorities
- */
-extern int ioprio_best(unsigned short aprio, unsigned short bprio);
+static inline int get_current_ioprio(void)
+{
+	return __get_task_ioprio(current);
+}
 
 extern int set_task_ioprio(struct task_struct *task, int ioprio);
 

include/linux/jbd2.h

···
 extern int	   jbd2_journal_skip_recovery	(journal_t *);
 extern void	   jbd2_journal_update_sb_errno(journal_t *);
 extern int	   jbd2_journal_update_sb_log_tail	(journal_t *, tid_t,
-				unsigned long, int);
+				unsigned long, blk_opf_t);
 extern void	   jbd2_journal_abort      (journal_t *, int);
 extern int	   jbd2_journal_errno      (journal_t *);
 extern void	   jbd2_journal_ack_err    (journal_t *);

include/linux/uio.h

···
 #endif
 
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
+bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask,
+			unsigned len_mask);
 unsigned long iov_iter_alignment(const struct iov_iter *i);
 unsigned long iov_iter_gap_alignment(const struct iov_iter *i);
 void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov,

include/linux/writeback.h

···
 #endif
 };
 
-static inline int wbc_to_write_flags(struct writeback_control *wbc)
+static inline blk_opf_t wbc_to_write_flags(struct writeback_control *wbc)
 {
-	int flags = 0;
+	blk_opf_t flags = 0;
 
 	if (wbc->punt_to_cgroup)
 		flags = REQ_CGROUP_PUNT;

include/scsi/scsi_cmnd.h

···
 extern void scsi_build_sense(struct scsi_cmnd *scmd, int desc,
 			     u8 key, u8 asc, u8 ascq);
 
-struct request *scsi_alloc_request(struct request_queue *q,
-		unsigned int op, blk_mq_req_flags_t flags);
+struct request *scsi_alloc_request(struct request_queue *q, blk_opf_t opf,
+				   blk_mq_req_flags_t flags);
 
 #endif /* _SCSI_SCSI_CMND_H */

include/scsi/scsi_device.h

···
 extern int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 			int data_direction, void *buffer, unsigned bufflen,
 			unsigned char *sense, struct scsi_sense_hdr *sshdr,
-			int timeout, int retries, u64 flags,
+			int timeout, int retries, blk_opf_t flags,
 			req_flags_t rq_flags, int *resid);
 /* Make sure any sense buffer is the correct size. */
 #define scsi_execute(sdev, cmd, data_direction, buffer, bufflen, sense,	\

include/scsi/scsi_host.h

···
 extern int scsi_host_unblock(struct Scsi_Host *shost, int new_state);
 
 void scsi_host_busy_iter(struct Scsi_Host *,
-			 bool (*fn)(struct scsi_cmnd *, void *, bool), void *priv);
+			 bool (*fn)(struct scsi_cmnd *, void *), void *priv);
 
 struct class_container;
 

include/trace/events/f2fs.h

···
 
 #define F2FS_OP_FLAGS (REQ_RAHEAD | REQ_SYNC | REQ_META | REQ_PRIO |	\
 			REQ_PREFLUSH | REQ_FUA)
-#define F2FS_BIO_FLAG_MASK(t)	(t & F2FS_OP_FLAGS)
+#define F2FS_BIO_FLAG_MASK(t) (__force u32)((t) & F2FS_OP_FLAGS)
 
 #define show_bio_type(op,op_flags)	show_bio_op(op),		\
 						show_bio_op_flags(op_flags)
···
 
 #define show_bio_op_flags(flags)					\
 	__print_flags(F2FS_BIO_FLAG_MASK(flags), "|",			\
-		{ REQ_RAHEAD,		"R" },				\
-		{ REQ_SYNC,		"S" },				\
-		{ REQ_META,		"M" },				\
-		{ REQ_PRIO,		"P" },				\
-		{ REQ_PREFLUSH,		"PF" },				\
-		{ REQ_FUA,		"FUA" })
+		{ (__force u32)REQ_RAHEAD,	"R" },			\
+		{ (__force u32)REQ_SYNC,	"S" },			\
+		{ (__force u32)REQ_META,	"M" },			\
+		{ (__force u32)REQ_PRIO,	"P" },			\
+		{ (__force u32)REQ_PREFLUSH,	"PF" },			\
+		{ (__force u32)REQ_FUA,		"FUA" })
 
 #define show_data_type(type)						\
 	__print_symbolic(type,						\
···
 		__field(pgoff_t, index)
 		__field(block_t, old_blkaddr)
 		__field(block_t, new_blkaddr)
-		__field(int, op)
-		__field(int, op_flags)
+		__field(enum req_op, op)
+		__field(blk_opf_t, op_flags)
 		__field(int, temp)
 		__field(int, type)
 	),
···
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(dev_t,	target)
-		__field(int,	op)
-		__field(int,	op_flags)
+		__field(enum req_op,	op)
+		__field(blk_opf_t,	op_flags)
 		__field(int,	type)
 		__field(sector_t,	sector)
 		__field(unsigned int,	size)

include/trace/events/jbd2.h

···
 
 TRACE_EVENT(jbd2_write_superblock,
 
-	TP_PROTO(journal_t *journal, int write_op),
+	TP_PROTO(journal_t *journal, blk_opf_t write_flags),
 
-	TP_ARGS(journal, write_op),
+	TP_ARGS(journal, write_flags),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,  dev			)
-		__field(	  int,  write_op		)
+		__field(    blk_opf_t,  write_flags		)
 	),
 
 	TP_fast_assign(
 		__entry->dev		= journal->j_fs_dev->bd_dev;
-		__entry->write_op	= write_op;
+		__entry->write_flags	= write_flags;
 	),
 
-	TP_printk("dev %d,%d write_op %x", MAJOR(__entry->dev),
-		  MINOR(__entry->dev), __entry->write_op)
+	TP_printk("dev %d,%d write_flags %x", MAJOR(__entry->dev),
+		  MINOR(__entry->dev), (__force u32)__entry->write_flags)
 );
 
 TRACE_EVENT(jbd2_lock_buffer_stall,

include/trace/events/nilfs2.h

···
 	    TP_PROTO(struct inode *inode,
 		     unsigned long ino,
 		     unsigned long blkoff,
-		     int mode),
+		     enum req_op mode),
 
 	    TP_ARGS(inode, ino, blkoff, mode),
 
···
 		    __field(struct inode *, inode)
 		    __field(unsigned long, ino)
 		    __field(unsigned long, blkoff)
-		    __field(int, mode)
+		    __field(enum req_op, mode)
 	    ),
 
 	    TP_fast_assign(

include/uapi/linux/ublk_cmd.h

···
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef USER_BLK_DRV_CMD_INC_H
+#define USER_BLK_DRV_CMD_INC_H
+
+#include <linux/types.h>
+
+/* ublk server command definition */
+
+/*
+ * Admin commands, issued by ublk server, and handled by ublk driver.
+ */
+#define	UBLK_CMD_GET_QUEUE_AFFINITY	0x01
+#define	UBLK_CMD_GET_DEV_INFO	0x02
+#define	UBLK_CMD_ADD_DEV		0x04
+#define	UBLK_CMD_DEL_DEV		0x05
+#define	UBLK_CMD_START_DEV	0x06
+#define	UBLK_CMD_STOP_DEV	0x07
+
+/*
+ * IO commands, issued by ublk server, and handled by ublk driver.
+ *
+ * FETCH_REQ: issued via sqe(URING_CMD) beforehand for fetching IO request
+ *      from ublk driver, should be issued only when starting device. After
+ *      the associated cqe is returned, request's tag can be retrieved via
+ *      cqe->userdata.
+ *
+ * COMMIT_AND_FETCH_REQ: issued via sqe(URING_CMD) after ublkserver handled
+ *      this IO request, request's handling result is committed to ublk
+ *      driver, meantime FETCH_REQ is piggyback, and FETCH_REQ has to be
+ *      handled before completing io request.
+ */
+#define	UBLK_IO_FETCH_REQ		0x20
+#define	UBLK_IO_COMMIT_AND_FETCH_REQ	0x21
+
+/* only ABORT means that no re-fetch */
+#define UBLK_IO_RES_OK			0
+#define UBLK_IO_RES_ABORT		(-ENODEV)
+
+#define UBLKSRV_CMD_BUF_OFFSET	0
+#define UBLKSRV_IO_BUF_OFFSET	0x80000000
+
+/* tag bit is 12bit, so at most 4096 IOs for each queue */
+#define UBLK_MAX_QUEUE_DEPTH	4096
+
+/*
+ * zero copy requires 4k block size, and can remap ublk driver's io
+ * request into ublksrv's vm space
+ */
+#define UBLK_F_SUPPORT_ZERO_COPY	(1ULL << 0)
+
+/*
+ * Force to complete io cmd via io_uring_cmd_complete_in_task so that
+ * performance comparison is done easily with using task_work_add
+ */
+#define UBLK_F_URING_CMD_COMP_IN_TASK	(1ULL << 1)
+
+/* device state */
+#define UBLK_S_DEV_DEAD	0
+#define UBLK_S_DEV_LIVE	1
+
+/* shipped via sqe->cmd of io_uring command */
+struct ublksrv_ctrl_cmd {
+	/* sent to which device, must be valid */
+	__u32	dev_id;
+
+	/* sent to which queue, must be -1 if the cmd isn't for queue */
+	__u16	queue_id;
+	/*
+	 * cmd specific buffer, can be IN or OUT.
+	 */
+	__u16	len;
+	__u64	addr;
+
+	/* inline data */
+	__u64	data[2];
+};
+
+struct ublksrv_ctrl_dev_info {
+	__u16	nr_hw_queues;
+	__u16	queue_depth;
+	__u16	block_size;
+	__u16	state;
+
+	__u32	rq_max_blocks;
+	__u32	dev_id;
+
+	__u64   dev_blocks;
+
+	__s32	ublksrv_pid;
+	__s32	reserved0;
+	__u64	flags;
+	__u64	flags_reserved;
+
+	/* For ublksrv internal use, invisible to ublk driver */
+	__u64	ublksrv_flags;
+	__u64	reserved1[9];
+};
+
+#define		UBLK_IO_OP_READ		0
+#define		UBLK_IO_OP_WRITE		1
+#define		UBLK_IO_OP_FLUSH		2
+#define		UBLK_IO_OP_DISCARD	3
+#define		UBLK_IO_OP_WRITE_SAME	4
+#define		UBLK_IO_OP_WRITE_ZEROES	5
+
+#define		UBLK_IO_F_FAILFAST_DEV		(1U << 8)
+#define		UBLK_IO_F_FAILFAST_TRANSPORT	(1U << 9)
+#define		UBLK_IO_F_FAILFAST_DRIVER	(1U << 10)
+#define		UBLK_IO_F_META			(1U << 11)
+#define		UBLK_IO_F_FUA			(1U << 13)
+#define		UBLK_IO_F_NOUNMAP		(1U << 15)
+#define		UBLK_IO_F_SWAP			(1U << 16)
+
+/*
+ * io cmd is described by this structure, and stored in share memory, indexed
+ * by request tag.
+ *
+ * The data is stored by ublk driver, and read by ublksrv after one fetch command
+ * returns.
+ */
+struct ublksrv_io_desc {
+	/* op: bit 0-7, flags: bit 8-31 */
+	__u32		op_flags;
+
+	__u32		nr_sectors;
+
+	/* start sector for this io */
+	__u64		start_sector;
+
+	/* buffer address in ublksrv daemon vm space, from ublk driver */
+	__u64		addr;
+};
+
+static inline __u8 ublksrv_get_op(const struct ublksrv_io_desc *iod)
+{
+	return iod->op_flags & 0xff;
+}
+
+static inline __u32 ublksrv_get_flags(const struct ublksrv_io_desc *iod)
+{
+	return iod->op_flags >> 8;
+}
+
+/* issued to ublk driver via /dev/ublkcN */
+struct ublksrv_io_cmd {
+	__u16	q_id;
+
+	/* for fetch/commit which result */
+	__u16	tag;
+
+	/* io result, it is valid for COMMIT* command only */
+	__s32	result;
+
+	/*
+	 * userspace buffer address in ublksrv daemon process, valid for
+	 * FETCH* command only
+	 */
+	__u64	addr;
+};
+
+#endif

kernel/power/swap.c

···
 	bio_put(bio);
 }
 
-static int hib_submit_io(int op, int op_flags, pgoff_t page_off, void *addr,
-		struct hib_bio_batch *hb)
+static int hib_submit_io(blk_opf_t opf, pgoff_t page_off, void *addr,
+			 struct hib_bio_batch *hb)
 {
 	struct page *page = virt_to_page(addr);
 	struct bio *bio;
 	int error = 0;
 
-	bio = bio_alloc(hib_resume_bdev, 1, op | op_flags,
-			GFP_NOIO | __GFP_HIGH);
+	bio = bio_alloc(hib_resume_bdev, 1, opf, GFP_NOIO | __GFP_HIGH);
 	bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9);
 
 	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
···
 {
 	int error;
 
-	hib_submit_io(REQ_OP_READ, 0, swsusp_resume_block,
-		      swsusp_header, NULL);
+	hib_submit_io(REQ_OP_READ, swsusp_resume_block, swsusp_header, NULL);
 	if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) ||
 	    !memcmp("SWAPSPACE2",swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10);
···
 		swsusp_header->flags = flags;
 		if (flags & SF_CRC32_MODE)
 			swsusp_header->crc32 = handle->crc32;
-		error = hib_submit_io(REQ_OP_WRITE, REQ_SYNC,
+		error = hib_submit_io(REQ_OP_WRITE | REQ_SYNC,
 				      swsusp_resume_block, swsusp_header, NULL);
 	} else {
 		pr_err("Swap header not found!\n");
···
 	} else {
 		src = buf;
 	}
-	return hib_submit_io(REQ_OP_WRITE, REQ_SYNC, offset, src, hb);
+	return hib_submit_io(REQ_OP_WRITE | REQ_SYNC, offset, src, hb);
 }
 
 static void release_swap_writer(struct swap_map_handle *handle)
···
 			return -ENOMEM;
 		}
 
-		error = hib_submit_io(REQ_OP_READ, 0, offset, tmp->map, NULL);
+		error = hib_submit_io(REQ_OP_READ, offset, tmp->map, NULL);
 		if (error) {
 			release_swap_reader(handle);
 			return error;
···
 	offset = handle->cur->entries[handle->k];
 	if (!offset)
 		return -EFAULT;
-	error = hib_submit_io(REQ_OP_READ, 0, offset, buf, hb);
+	error = hib_submit_io(REQ_OP_READ, offset, buf, hb);
 	if (error)
 		return error;
 	if (++handle->k >= MAP_PAGE_ENTRIES) {
···
 	if (!IS_ERR(hib_resume_bdev)) {
 		set_blocksize(hib_resume_bdev, PAGE_SIZE);
 		clear_page(swsusp_header);
-		error = hib_submit_io(REQ_OP_READ, 0,
-					swsusp_resume_block,
+		error = hib_submit_io(REQ_OP_READ, swsusp_resume_block,
 					swsusp_header, NULL);
 		if (error)
 			goto put;
···
 		if (!memcmp(HIBERNATE_SIG, swsusp_header->sig, 10)) {
 			memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
 			/* Reset swap signature now */
-			error = hib_submit_io(REQ_OP_WRITE, REQ_SYNC,
+			error = hib_submit_io(REQ_OP_WRITE | REQ_SYNC,
 						swsusp_resume_block,
 						swsusp_header, NULL);
 		} else {
···
 {
 	int error;
 
-	hib_submit_io(REQ_OP_READ, 0, swsusp_resume_block,
-		      swsusp_header, NULL);
+	hib_submit_io(REQ_OP_READ, swsusp_resume_block,
+			swsusp_header, NULL);
 	if (!memcmp(HIBERNATE_SIG,swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->sig,swsusp_header->orig_sig, 10);
-		error = hib_submit_io(REQ_OP_WRITE, REQ_SYNC,
+		error = hib_submit_io(REQ_OP_WRITE | REQ_SYNC,
 					swsusp_resume_block,
 					swsusp_header, NULL);
 	} else {

kernel/trace/blktrace.c

···
 #define BLK_TC_PREFLUSH		BLK_TC_FLUSH
 
 /* The ilog2() calls fall out because they're constant */
-#define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \
+#define MASK_TC_BIT(rw, __name) ((__force u32)(rw & REQ_ ## __name) <<	\
 	  (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - __REQ_ ## __name))
 
 /*
···
  * blk_io_trace structure and places it in a per-cpu subbuffer.
  */
 static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
-		     int op, int op_flags, u32 what, int error, int pdu_len,
-		     void *pdu_data, u64 cgid)
+			    const blk_opf_t opf, u32 what, int error,
+			    int pdu_len, void *pdu_data, u64 cgid)
 {
 	struct task_struct *tsk = current;
 	struct ring_buffer_event *event = NULL;
···
 	int cpu;
 	bool blk_tracer = blk_tracer_enabled;
 	ssize_t cgid_len = cgid ? sizeof(cgid) : 0;
+	const enum req_op op = opf & REQ_OP_MASK;
 
 	if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
 		return;
 
 	what |= ddir_act[op_is_write(op) ? WRITE : READ];
-	what |= MASK_TC_BIT(op_flags, SYNC);
-	what |= MASK_TC_BIT(op_flags, RAHEAD);
-	what |= MASK_TC_BIT(op_flags, META);
-	what |= MASK_TC_BIT(op_flags, PREFLUSH);
-	what |= MASK_TC_BIT(op_flags, FUA);
+	what |= MASK_TC_BIT(opf, SYNC);
+	what |= MASK_TC_BIT(opf, RAHEAD);
+	what |= MASK_TC_BIT(opf, META);
+	what |= MASK_TC_BIT(opf, PREFLUSH);
+	what |= MASK_TC_BIT(opf, FUA);
 	if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)
 		what |= BLK_TC_ACT(BLK_TC_DISCARD);
 	if (op == REQ_OP_FLUSH)
···
 
 	switch (cmd) {
 	case BLKTRACESETUP:
-		bdevname(bdev, b);
+		snprintf(b, sizeof(b), "%pg", bdev);
 		ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
 		break;
 #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
 	case BLKTRACESETUP32:
-		bdevname(bdev, b);
+		snprintf(b, sizeof(b), "%pg", bdev);
 		ret = compat_blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
 		break;
 #endif
···
 	else
 		what |= BLK_TC_ACT(BLK_TC_FS);
 
-	__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
-			rq->cmd_flags, what, blk_status_to_errno(error), 0,
-			NULL, cgid);
+	__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, rq->cmd_flags,
+			what, blk_status_to_errno(error), 0, NULL, cgid);
 	rcu_read_unlock();
 }
 
···
 	}
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio_op(bio), bio->bi_opf, what, error, 0, NULL,
+			bio->bi_opf, what, error, 0, NULL,
 			blk_trace_bio_get_cgid(q, bio));
 	rcu_read_unlock();
 }
···
 	rcu_read_lock();
 	bt = rcu_dereference(q->blk_trace);
 	if (bt)
-		__blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0);
+		__blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0);
 	rcu_read_unlock();
 }
 
···
 		else
 			what = BLK_TA_UNPLUG_TIMER;
 
-		__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0);
+		__blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0);
 	}
 	rcu_read_unlock();
 }
···
 		__be64 rpdu = cpu_to_be64(pdu);
 
 		__blk_add_trace(bt, bio->bi_iter.bi_sector,
-				bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf,
-				BLK_TA_SPLIT,
+				bio->bi_iter.bi_size, bio->bi_opf, BLK_TA_SPLIT,
 				blk_status_to_errno(bio->bi_status),
 				sizeof(rpdu), &rpdu,
 				blk_trace_bio_get_cgid(q, bio));
···
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio_op(bio), bio->bi_opf, BLK_TA_REMAP,
+			bio->bi_opf, BLK_TA_REMAP,
 			blk_status_to_errno(bio->bi_status),
 			sizeof(r), &r, blk_trace_bio_get_cgid(q, bio));
 	rcu_read_unlock();
···
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
-			rq_data_dir(rq), 0, BLK_TA_REMAP, 0,
+			rq->cmd_flags, BLK_TA_REMAP, 0,
 			sizeof(r), &r, blk_trace_request_get_cgid(rq));
 	rcu_read_unlock();
 }
···
 		return;
 	}
 
-	__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0,
+	__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0,
 				BLK_TA_DRV_DATA, 0, len, data,
 				blk_trace_request_get_cgid(rq));
 	rcu_read_unlock();
···
 out:
 	return ret ? ret : count;
 }
-
-int blk_trace_init_sysfs(struct device *dev)
-{
-	return sysfs_create_group(&dev->kobj, &blk_trace_attr_group);
-}
-
-void blk_trace_remove_sysfs(struct device *dev)
-{
-	sysfs_remove_group(&dev->kobj, &blk_trace_attr_group);
-}
-
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
 
 #ifdef CONFIG_EVENT_TRACING
···
 /**
  * blk_fill_rwbs - Fill the buffer rwbs by mapping op to character string.
  * @rwbs:	buffer to be filled
- * @op:		REQ_OP_XXX for the tracepoint
+ * @opf:	request operation type (REQ_OP_XXX) and flags for the tracepoint
  *
  * Description:
- *     Maps the REQ_OP_XXX to character and fills the buffer provided by the
- *     caller with resulting string.
+ *     Maps each request operation and flag to a single character and fills the
+ *     buffer provided by the caller with resulting string.
  *
  **/
-void blk_fill_rwbs(char *rwbs, unsigned int op)
+void blk_fill_rwbs(char *rwbs, blk_opf_t opf)
 {
 	int i = 0;
 
-	if (op & REQ_PREFLUSH)
+	if (opf & REQ_PREFLUSH)
 		rwbs[i++] = 'F';
 
-	switch (op & REQ_OP_MASK) {
+	switch (opf & REQ_OP_MASK) {
 	case REQ_OP_WRITE:
 		rwbs[i++] = 'W';
 		break;
···
 		rwbs[i++] = 'N';
 	}
 
-	if (op & REQ_FUA)
+	if (opf & REQ_FUA)
 		rwbs[i++] = 'F';
-	if (op & REQ_RAHEAD)
+	if (opf & REQ_RAHEAD)
 		rwbs[i++] = 'A';
-	if (op & REQ_SYNC)
+	if (opf & REQ_SYNC)
 		rwbs[i++] = 'S';
-	if (op & REQ_META)
+	if (opf & REQ_META)
 		rwbs[i++] = 'M';
 
 	rwbs[i] = '\0';

lib/iov_iter.c

···
 }
 EXPORT_SYMBOL(iov_iter_discard);
 
+static bool iov_iter_aligned_iovec(const struct iov_iter *i, unsigned addr_mask,
+				   unsigned len_mask)
+{
+	size_t size = i->count;
+	size_t skip = i->iov_offset;
+	unsigned k;
+
+	for (k = 0; k < i->nr_segs; k++, skip = 0) {
+		size_t len = i->iov[k].iov_len - skip;
+
+		if (len > size)
+			len = size;
+		if (len & len_mask)
+			return false;
+		if ((unsigned long)(i->iov[k].iov_base + skip) & addr_mask)
+			return false;
+
+		size -= len;
+		if (!size)
+			break;
+	}
+	return true;
+}
+
+static bool iov_iter_aligned_bvec(const struct iov_iter *i, unsigned addr_mask,
+				  unsigned len_mask)
+{
+	size_t size = i->count;
+	unsigned skip = i->iov_offset;
+	unsigned k;
+
+	for (k = 0; k < i->nr_segs; k++, skip = 0) {
+		size_t len = i->bvec[k].bv_len - skip;
+
+		if (len > size)
+			len = size;
+		if (len & len_mask)
+			return false;
+		if ((unsigned long)(i->bvec[k].bv_offset + skip) & addr_mask)
+			return false;
+
+		size -= len;
+		if (!size)
+			break;
+	}
+	return true;
+}
+
+/**
+ * iov_iter_is_aligned() - Check if the addresses and lengths of each segments
+ * 	are aligned to the parameters.
+ *
+ * @i: &struct iov_iter to restore
+ * @addr_mask: bit mask to check against the iov element's addresses
+ * @len_mask: bit mask to check against the iov element's lengths
+ *
+ * Return: false if any addresses or lengths intersect with the provided masks
+ */
+bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask,
+			 unsigned len_mask)
+{
+	if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i)))
+		return iov_iter_aligned_iovec(i, addr_mask, len_mask);
+
+	if (iov_iter_is_bvec(i))
+		return iov_iter_aligned_bvec(i, addr_mask, len_mask);
+
+	if (iov_iter_is_pipe(i)) {
+		unsigned int p_mask = i->pipe->ring_size - 1;
+		size_t size = i->count;
+
+		if (size & len_mask)
+			return false;
+		if (size && allocated(&i->pipe->bufs[i->head & p_mask])) {
+			if (i->iov_offset & addr_mask)
+				return false;
+		}
+
+		return true;
+	}
+
+	if (iov_iter_is_xarray(i)) {
+		if (i->count & len_mask)
+			return false;
+		if ((i->xarray_start + i->iov_offset) & addr_mask)
+			return false;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(iov_iter_is_aligned);
+
 static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i)
 {
 	unsigned long res = 0;