Merge tag 'for-5.12/block-2021-02-17' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:
 "Another nice round of removing more code than what is added, mostly
  due to Christoph's relentless pursuit of tech debt removal/cleanups.
  This pull request contains:

   - Two series of BFQ improvements (Paolo, Jan, Jia)

   - Block iov_iter improvements (Pavel)

   - bsg error path fix (Pan)

   - blk-mq scheduler improvements (Jan)

   - -EBUSY discard fix (Jan)

   - bvec allocation improvements (Ming, Christoph)

   - bio allocation and init improvements (Christoph)

   - Store bdev pointer in bio instead of gendisk + partno (Christoph)

   - Block trace point cleanups (Christoph)

   - hard read-only vs read-only split (Christoph)

   - Block based swap cleanups (Christoph)

   - Zoned write granularity support (Damien)

   - Various fixes/tweaks (Chunguang, Guoqing, Lei, Lukas, Huhai)"

* tag 'for-5.12/block-2021-02-17' of git://git.kernel.dk/linux-block: (104 commits)
  mm: simplify swapdev_block
  sd_zbc: clear zone resources for non-zoned case
  block: introduce blk_queue_clear_zone_settings()
  zonefs: use zone write granularity as block size
  block: introduce zone_write_granularity limit
  block: use blk_queue_set_zoned in add_partition()
  nullb: use blk_queue_set_zoned() to setup zoned devices
  nvme: cleanup zone information initialization
  block: document zone_append_max_bytes attribute
  block: use bi_max_vecs to find the bvec pool
  md/raid10: remove dead code in reshape_request
  block: mark the bio as cloned in bio_iov_bvec_set
  block: set BIO_NO_PAGE_REF in bio_iov_bvec_set
  block: remove a layer of indentation in bio_iov_iter_get_pages
  block: turn the nr_iovecs argument to bio_alloc* into an unsigned short
  block: remove the 1 and 4 vec bvec_slabs entries
  block: streamline bvec_alloc
  block: factor out a bvec_alloc_gfp helper
  block: move struct biovec_slab to bio.c
  block: reuse BIO_INLINE_VECS for integrity bvecs
  ...

17 files changed, 138 insertions, 183 deletions

diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index b00fd08d696b..63e809f38e3f 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -114,7 +114,7 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
 	check = bio_kmalloc(GFP_NOIO, bio_segments(bio));
 	if (!check)
 		return;
-	check->bi_disk = bio->bi_disk;
+	bio_set_dev(check, bio->bi_bdev);
 	check->bi_opf = REQ_OP_READ;
 	check->bi_iter.bi_sector = bio->bi_iter.bi_sector;
 	check->bi_iter.bi_size = bio->bi_iter.bi_size;
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 85b1f2a9b72d..29c231758293 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -475,7 +475,7 @@ struct search {
 	unsigned int		read_dirty_data:1;
 	unsigned int		cache_missed:1;
 
-	struct block_device	*part;
+	struct block_device	*orig_bdev;
 	unsigned long		start_time;
 
 	struct btree_op		op;
@@ -670,8 +670,8 @@ static void bio_complete(struct search *s)
 {
 	if (s->orig_bio) {
 		/* Count on bcache device */
-		part_end_io_acct(s->part, s->orig_bio, s->start_time);
-
+		bio_end_io_acct_remapped(s->orig_bio, s->start_time,
+					 s->orig_bdev);
 		trace_bcache_request_end(s->d, s->orig_bio);
 		s->orig_bio->bi_status = s->iop.status;
 		bio_endio(s->orig_bio);
@@ -714,7 +714,8 @@ static void search_free(struct closure *cl)
 }
 
 static inline struct search *search_alloc(struct bio *bio,
-					  struct bcache_device *d)
+		struct bcache_device *d, struct block_device *orig_bdev,
+		unsigned long start_time)
 {
 	struct search *s;
 
@@ -732,7 +733,8 @@ static inline struct search *search_alloc(struct bio *bio,
 	s->write		= op_is_write(bio_op(bio));
 	s->read_dirty_data	= 0;
 	/* Count on the bcache device */
-	s->start_time		= part_start_io_acct(d->disk, &s->part, bio);
+	s->orig_bdev		= orig_bdev;
+	s->start_time		= start_time;
 	s->iop.c		= d->c;
 	s->iop.bio		= NULL;
 	s->iop.inode		= d->id;
@@ -894,7 +896,8 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	    !(bio->bi_opf & (REQ_META|REQ_PRIO)) &&
 	    s->iop.c->gc_stats.in_use < CUTOFF_CACHE_READA)
 		reada = min_t(sector_t, dc->readahead >> 9,
-			      get_capacity(bio->bi_disk) - bio_end_sector(bio));
+			      get_capacity(bio->bi_bdev->bd_disk) -
+			      bio_end_sector(bio));
 
 	s->insert_bio_sectors = min(sectors, bio_sectors(bio) + reada);
 
@@ -1073,7 +1076,7 @@ struct detached_dev_io_private {
 	unsigned long		start_time;
 	bio_end_io_t		*bi_end_io;
 	void			*bi_private;
-	struct block_device	*part;
+	struct block_device	*orig_bdev;
 };
 
 static void detached_dev_end_io(struct bio *bio)
@@ -1085,7 +1088,7 @@ static void detached_dev_end_io(struct bio *bio)
 	bio->bi_private = ddip->bi_private;
 
 	/* Count on the bcache device */
-	part_end_io_acct(ddip->part, bio, ddip->start_time);
+	bio_end_io_acct_remapped(bio, ddip->start_time, ddip->orig_bdev);
 
 	if (bio->bi_status) {
 		struct cached_dev *dc = container_of(ddip->d,
@@ -1098,7 +1101,8 @@ static void detached_dev_end_io(struct bio *bio)
 	bio->bi_end_io(bio);
 }
 
-static void detached_dev_do_request(struct bcache_device *d, struct bio *bio)
+static void detached_dev_do_request(struct bcache_device *d, struct bio *bio,
+		struct block_device *orig_bdev, unsigned long start_time)
 {
 	struct detached_dev_io_private *ddip;
 	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
@@ -1111,7 +1115,8 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio)
 	ddip = kzalloc(sizeof(struct detached_dev_io_private), GFP_NOIO);
 	ddip->d = d;
 	/* Count on the bcache device */
-	ddip->start_time = part_start_io_acct(d->disk, &ddip->part, bio);
+	ddip->orig_bdev = orig_bdev;
+	ddip->start_time = start_time;
 	ddip->bi_end_io = bio->bi_end_io;
 	ddip->bi_private = bio->bi_private;
 	bio->bi_end_io = detached_dev_end_io;
@@ -1167,8 +1172,10 @@ static void quit_max_writeback_rate(struct cache_set *c,
 blk_qc_t cached_dev_submit_bio(struct bio *bio)
 {
 	struct search *s;
-	struct bcache_device *d = bio->bi_disk->private_data;
+	struct block_device *orig_bdev = bio->bi_bdev;
+	struct bcache_device *d = orig_bdev->bd_disk->private_data;
 	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
+	unsigned long start_time;
 	int rw = bio_data_dir(bio);
 
 	if (unlikely((d->c && test_bit(CACHE_SET_IO_DISABLE, &d->c->flags)) ||
@@ -1193,11 +1200,13 @@ blk_qc_t cached_dev_submit_bio(struct bio *bio)
 		}
 	}
 
+	start_time = bio_start_io_acct(bio);
+
 	bio_set_dev(bio, dc->bdev);
 	bio->bi_iter.bi_sector += dc->sb.data_offset;
 
 	if (cached_dev_get(dc)) {
-		s = search_alloc(bio, d);
+		s = search_alloc(bio, d, orig_bdev, start_time);
 		trace_bcache_request_start(s->d, bio);
 
 		if (!bio->bi_iter.bi_size) {
@@ -1218,7 +1227,7 @@ blk_qc_t cached_dev_submit_bio(struct bio *bio)
 		}
 	} else
 		/* I/O request sent to backing device */
-		detached_dev_do_request(d, bio);
+		detached_dev_do_request(d, bio, orig_bdev, start_time);
 
 	return BLK_QC_T_NONE;
 }
@@ -1274,7 +1283,7 @@ blk_qc_t flash_dev_submit_bio(struct bio *bio)
 {
 	struct search *s;
 	struct closure *cl;
-	struct bcache_device *d = bio->bi_disk->private_data;
+	struct bcache_device *d = bio->bi_bdev->bd_disk->private_data;
 
 	if (unlikely(d->c && test_bit(CACHE_SET_IO_DISABLE, &d->c->flags))) {
 		bio->bi_status = BLK_STS_IOERR;
@@ -1282,7 +1291,7 @@ blk_qc_t flash_dev_submit_bio(struct bio *bio)
 		return BLK_QC_T_NONE;
 	}
 
-	s = search_alloc(bio, d);
+	s = search_alloc(bio, d, bio->bi_bdev, bio_start_io_acct(bio));
 	cl = &s->cl;
 	bio = &s->bio.bio;
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 2047a9cccdb5..193fe7652329 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1939,7 +1939,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 		goto err;
 
 	if (bioset_init(&c->bio_split, 4, offsetof(struct bbio, bio),
-			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
+			BIOSET_NEED_RESCUER))
 		goto err;
 
 	c->uuids = alloc_meta_bucket_pages(GFP_KERNEL, sb);
diff --git a/drivers/md/dm-bio-record.h b/drivers/md/dm-bio-record.h
index 2ea0360108e1..a3b71350eec8 100644
--- a/drivers/md/dm-bio-record.h
+++ b/drivers/md/dm-bio-record.h
@@ -18,8 +18,7 @@
  */
 
 struct dm_bio_details {
-	struct gendisk *bi_disk;
-	u8 bi_partno;
+	struct block_device *bi_bdev;
 	int __bi_remaining;
 	unsigned long bi_flags;
 	struct bvec_iter bi_iter;
@@ -31,8 +30,7 @@ struct dm_bio_details {
 
 static inline void dm_bio_record(struct dm_bio_details *bd, struct bio *bio)
 {
-	bd->bi_disk = bio->bi_disk;
-	bd->bi_partno = bio->bi_partno;
+	bd->bi_bdev = bio->bi_bdev;
 	bd->bi_flags = bio->bi_flags;
 	bd->bi_iter = bio->bi_iter;
 	bd->__bi_remaining = atomic_read(&bio->__bi_remaining);
@@ -44,8 +42,7 @@ static inline void dm_bio_record(struct dm_bio_details *bd, struct bio *bio)
 
 static inline void dm_bio_restore(struct dm_bio_details *bd, struct bio *bio)
 {
-	bio->bi_disk = bd->bi_disk;
-	bio->bi_partno = bd->bi_partno;
+	bio->bi_bdev = bd->bi_bdev;
 	bio->bi_flags = bd->bi_flags;
 	bio->bi_iter = bd->bi_iter;
 	atomic_set(&bio->__bi_remaining, bd->__bi_remaining);
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index af6d4f898e4c..89a73204dbf4 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -449,7 +449,7 @@ static int __check_incompat_features(struct cache_disk_superblock *disk_super,
 	/*
 	 * Check for read-only metadata to skip the following RDWR checks.
 	 */
-	if (get_disk_ro(cmd->bdev->bd_disk))
+	if (bdev_read_only(cmd->bdev))
 		return 0;
 
 	features = le32_to_cpu(disk_super->compat_ro_flags) & ~DM_CACHE_FEATURE_COMPAT_RO_SUPP;
diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c
index bdb255edc200..a90bdf9b2ca6 100644
--- a/drivers/md/dm-clone-target.c
+++ b/drivers/md/dm-clone-target.c
@@ -85,12 +85,6 @@ struct clone {
 
 	struct dm_clone_metadata *cmd;
 
-	/*
-	 * bio used to flush the destination device, before committing the
-	 * metadata.
-	 */
-	struct bio flush_bio;
-
 	/* Region hydration hash table */
 	struct hash_table_bucket *ht;
 
@@ -1155,11 +1149,7 @@ static int commit_metadata(struct clone *clone, bool *dest_dev_flushed)
 		goto out;
 	}
 
-	bio_reset(&clone->flush_bio);
-	bio_set_dev(&clone->flush_bio, clone->dest_dev->bdev);
-	clone->flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
-
-	r = submit_bio_wait(&clone->flush_bio);
+	r = blkdev_issue_flush(clone->dest_dev->bdev);
 	if (unlikely(r)) {
 		__metadata_operation_failed(clone, "flush destination device", r);
 		goto out;
@@ -1886,7 +1876,6 @@ static int clone_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	bio_list_init(&clone->deferred_flush_completions);
 	clone->hydration_offset = 0;
 	atomic_set(&clone->hydrations_in_flight, 0);
-	bio_init(&clone->flush_bio, NULL, 0);
 
 	clone->wq = alloc_workqueue("dm-" DM_MSG_PREFIX, WQ_MEM_RECLAIM, 0);
 	if (!clone->wq) {
@@ -1958,7 +1947,6 @@ static void clone_dtr(struct dm_target *ti)
 	struct clone *clone = ti->private;
 
 	mutex_destroy(&clone->commit_lock);
-	bio_uninit(&clone->flush_bio);
 
 	for (i = 0; i < clone->nr_ctr_args; i++)
 		kfree(clone->ctr_args[i]);
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index fa09bc4e4c54..b0a82f29a2e4 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -145,7 +145,7 @@ static void dispatch_bios(void *context, struct bio_list *bio_list)
 
 struct dm_raid1_bio_record {
 	struct mirror *m;
-	/* if details->bi_disk == NULL, details were not saved */
+	/* if details->bi_bdev == NULL, details were not saved */
 	struct dm_bio_details details;
 	region_t write_region;
 };
@@ -1190,7 +1190,7 @@ static int mirror_map(struct dm_target *ti, struct bio *bio)
 	struct dm_raid1_bio_record *bio_record =
 	  dm_per_bio_data(bio, sizeof(struct dm_raid1_bio_record));
 
-	bio_record->details.bi_disk = NULL;
+	bio_record->details.bi_bdev = NULL;
 
 	if (rw == WRITE) {
 		/* Save region for mirror_end_io() handler */
@@ -1257,7 +1257,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio,
 		goto out;
 
 	if (unlikely(*error)) {
-		if (!bio_record->details.bi_disk) {
+		if (!bio_record->details.bi_bdev) {
 			/*
 			 * There wasn't enough memory to record necessary
 			 * information for a retry or there was no other
@@ -1282,7 +1282,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio,
 			bd = &bio_record->details;
 
 			dm_bio_restore(bd, bio);
-			bio_record->details.bi_disk = NULL;
+			bio_record->details.bi_bdev = NULL;
 			bio->bi_status = 0;
 
 			queue_bio(ms, bio, rw);
@@ -1292,7 +1292,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio,
 	}
 
 out:
-	bio_record->details.bi_disk = NULL;
+	bio_record->details.bi_bdev = NULL;
 
 	return DM_ENDIO_DONE;
 }
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 6ebb2127f3e2..e75b20480e46 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -636,7 +636,7 @@ static int __check_incompat_features(struct thin_disk_superblock *disk_super,
 	/*
 	 * Check for read-only metadata to skip the following RDWR checks.
 	 */
-	if (get_disk_ro(pmd->bdev->bd_disk))
+	if (bdev_read_only(pmd->bdev))
 		return 0;
 
 	features = le32_to_cpu(disk_super->compat_ro_flags) & ~THIN_FEATURE_COMPAT_RO_SUPP;
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index b298fefb022e..039d17b28938 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -819,7 +819,7 @@ static int dmz_write_sb(struct dmz_metadata *zmd, unsigned int set)
 	ret = dmz_rdwr_block(dev, REQ_OP_WRITE, zmd->sb[set].block,
 			     mblk->page);
 	if (ret == 0)
-		ret = blkdev_issue_flush(dev->bdev, GFP_NOIO);
+		ret = blkdev_issue_flush(dev->bdev);
 
 	return ret;
 }
@@ -862,7 +862,7 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd,
 
 	/* Flush drive cache (this will also sync data) */
 	if (ret == 0)
-		ret = blkdev_issue_flush(dev->bdev, GFP_NOIO);
+		ret = blkdev_issue_flush(dev->bdev);
 
 	return ret;
 }
@@ -933,7 +933,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd)
 
 	/* If there are no dirty metadata blocks, just flush the device cache */
 	if (list_empty(&write_list)) {
-		ret = blkdev_issue_flush(dev->bdev, GFP_NOIO);
+		ret = blkdev_issue_flush(dev->bdev);
 		goto err;
 	}
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 7bac564f3faa..479ec5bea09e 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -977,16 +977,17 @@ static void clone_endio(struct bio *bio)
 	struct mapped_device *md = tio->io->md;
 	dm_endio_fn endio = tio->ti->type->end_io;
 	struct bio *orig_bio = io->orig_bio;
+	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
 
 	if (unlikely(error == BLK_STS_TARGET)) {
 		if (bio_op(bio) == REQ_OP_DISCARD &&
-		    !bio->bi_disk->queue->limits.max_discard_sectors)
+		    !q->limits.max_discard_sectors)
 			disable_discard(md);
 		else if (bio_op(bio) == REQ_OP_WRITE_SAME &&
-			 !bio->bi_disk->queue->limits.max_write_same_sectors)
+			 !q->limits.max_write_same_sectors)
 			disable_write_same(md);
 		else if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
-			 !bio->bi_disk->queue->limits.max_write_zeroes_sectors)
+			 !q->limits.max_write_zeroes_sectors)
 			disable_write_zeroes(md);
 	}
 
@@ -996,7 +997,7 @@ static void clone_endio(struct bio *bio)
 	 */
 	if (bio_op(orig_bio) == REQ_OP_ZONE_APPEND) {
 		sector_t written_sector = bio->bi_iter.bi_sector;
-		struct request_queue *q = orig_bio->bi_disk->queue;
+		struct request_queue *q = orig_bio->bi_bdev->bd_disk->queue;
 		u64 mask = (u64)blk_queue_zone_sectors(q) - 1;
 
 		orig_bio->bi_iter.bi_sector += written_sector & mask;
@@ -1422,8 +1423,7 @@ static int __send_empty_flush(struct clone_info *ci)
 	 */
 	bio_init(&flush_bio, NULL, 0);
 	flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
-	flush_bio.bi_disk = ci->io->md->disk;
-	bio_associate_blkg(&flush_bio);
+	bio_set_dev(&flush_bio, ci->io->md->disk->part0);
 
 	ci->bio = &flush_bio;
 	ci->sector_count = 0;
@@ -1626,7 +1626,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 
 static blk_qc_t dm_submit_bio(struct bio *bio)
 {
-	struct mapped_device *md = bio->bi_disk->private_data;
+	struct mapped_device *md = bio->bi_bdev->bd_disk->private_data;
 	blk_qc_t ret = BLK_QC_T_NONE;
 	int srcu_idx;
 	struct dm_table *map;
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 68cac7d19278..63ed8329a98d 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -252,7 +252,7 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 		start_sector + data_offset;
 
 	if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
-		     !blk_queue_discard(bio->bi_disk->queue))) {
+		     !blk_queue_discard(bio->bi_bdev->bd_disk->queue))) {
 		/* Just ignore it */
 		bio_endio(bio);
 	} else {
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 04384452a7ab..21da0c48f6c2 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -340,24 +340,6 @@ static int start_readonly;
  */
 static bool create_on_open = true;
 
-struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
-			    struct mddev *mddev)
-{
-	if (!mddev || !bioset_initialized(&mddev->bio_set))
-		return bio_alloc(gfp_mask, nr_iovecs);
-
-	return bio_alloc_bioset(gfp_mask, nr_iovecs, &mddev->bio_set);
-}
-EXPORT_SYMBOL_GPL(bio_alloc_mddev);
-
-static struct bio *md_bio_alloc_sync(struct mddev *mddev)
-{
-	if (!mddev || !bioset_initialized(&mddev->sync_set))
-		return bio_alloc(GFP_NOIO, 1);
-
-	return bio_alloc_bioset(GFP_NOIO, 1, &mddev->sync_set);
-}
-
 /*
  * We have a system wide 'event count' that is incremented
  * on any 'interesting' event, and readers of /proc/mdstat
@@ -463,8 +445,8 @@ struct md_io {
 	struct mddev *mddev;
 	bio_end_io_t *orig_bi_end_io;
 	void *orig_bi_private;
+	struct block_device *orig_bi_bdev;
 	unsigned long start_time;
-	struct block_device *part;
 };
 
 static void md_end_io(struct bio *bio)
@@ -472,7 +454,7 @@ static void md_end_io(struct bio *bio)
 	struct md_io *md_io = bio->bi_private;
 	struct mddev *mddev = md_io->mddev;
 
-	part_end_io_acct(md_io->part, bio, md_io->start_time);
+	bio_end_io_acct_remapped(bio, md_io->start_time, md_io->orig_bi_bdev);
 
 	bio->bi_end_io = md_io->orig_bi_end_io;
 	bio->bi_private = md_io->orig_bi_private;
@@ -486,7 +468,7 @@ static void md_end_io(struct bio *bio)
 static blk_qc_t md_submit_bio(struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);
-	struct mddev *mddev = bio->bi_disk->private_data;
+	struct mddev *mddev = bio->bi_bdev->bd_disk->private_data;
 
 	if (mddev == NULL || mddev->pers == NULL) {
 		bio_io_error(bio);
@@ -514,12 +496,12 @@ static blk_qc_t md_submit_bio(struct bio *bio)
 		md_io->mddev = mddev;
 		md_io->orig_bi_end_io = bio->bi_end_io;
 		md_io->orig_bi_private = bio->bi_private;
+		md_io->orig_bi_bdev = bio->bi_bdev;
 
 		bio->bi_end_io = md_end_io;
 		bio->bi_private = md_io;
 
-		md_io->start_time = part_start_io_acct(mddev->gendisk,
-						       &md_io->part, bio);
+		md_io->start_time = bio_start_io_acct(bio);
 	}
 
 	/* bio could be mergeable after passing to underlayer */
@@ -613,7 +595,7 @@ static void submit_flushes(struct work_struct *ws)
 			atomic_inc(&rdev->nr_pending);
 			atomic_inc(&rdev->nr_pending);
 			rcu_read_unlock();
-			bi = bio_alloc_mddev(GFP_NOIO, 0, mddev);
+			bi = bio_alloc_bioset(GFP_NOIO, 0, &mddev->bio_set);
 			bi->bi_end_io = md_end_flush;
 			bi->bi_private = rdev;
 			bio_set_dev(bi, rdev->bdev);
@@ -999,7 +981,7 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 	if (test_bit(Faulty, &rdev->flags))
 		return;
 
-	bio = md_bio_alloc_sync(mddev);
+	bio = bio_alloc_bioset(GFP_NOIO, 1, &mddev->sync_set);
 
 	atomic_inc(&rdev->nr_pending);
 
@@ -1031,29 +1013,29 @@ int md_super_wait(struct mddev *mddev)
 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 bio *bio = md_bio_alloc_sync(rdev->mddev);
-	int ret;
+	struct bio bio;
+	struct bio_vec bvec;
+
+	bio_init(&bio, &bvec, 1);
 
 	if (metadata_op && rdev->meta_bdev)
-		bio_set_dev(bio, rdev->meta_bdev);
+		bio_set_dev(&bio, rdev->meta_bdev);
 	else
-		bio_set_dev(bio, rdev->bdev);
-	bio_set_op_attrs(bio, op, op_flags);
+		bio_set_dev(&bio, rdev->bdev);
+	bio.bi_opf = op | op_flags;
 	if (metadata_op)
-		bio->bi_iter.bi_sector = sector + rdev->sb_start;
+		bio.bi_iter.bi_sector = sector + rdev->sb_start;
 	else if (rdev->mddev->reshape_position != MaxSector &&
 		 (rdev->mddev->reshape_backwards ==
 		  (sector >= rdev->mddev->reshape_position)))
-		bio->bi_iter.bi_sector = sector + rdev->new_data_offset;
+		bio.bi_iter.bi_sector = sector + rdev->new_data_offset;
 	else
-		bio->bi_iter.bi_sector = sector + rdev->data_offset;
-	bio_add_page(bio, page, size, 0);
+		bio.bi_iter.bi_sector = sector + rdev->data_offset;
+	bio_add_page(&bio, page, size, 0);
 
-	submit_bio_wait(bio);
+	submit_bio_wait(&bio);
 
-	ret = !bio->bi_status;
-	bio_put(bio);
-	return ret;
+	return !bio.bi_status;
 }
 EXPORT_SYMBOL_GPL(sync_page_io);
 
@@ -2417,6 +2399,12 @@ int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
 }
 EXPORT_SYMBOL(md_integrity_add_rdev);
 
+static bool rdev_read_only(struct md_rdev *rdev)
+{
+	return bdev_read_only(rdev->bdev) ||
+		(rdev->meta_bdev && bdev_read_only(rdev->meta_bdev));
+}
+
 static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 {
 	char b[BDEVNAME_SIZE];
@@ -2426,8 +2414,7 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 	if (find_rdev(mddev, rdev->bdev->bd_dev))
 		return -EEXIST;
 
-	if ((bdev_read_only(rdev->bdev) || bdev_read_only(rdev->meta_bdev)) &&
-	    mddev->pers)
+	if (rdev_read_only(rdev) && mddev->pers)
 		return -EROFS;
 
 	/* make sure rdev->sectors exceeds mddev->dev_sectors */
@@ -5861,9 +5848,7 @@ int md_run(struct mddev *mddev)
 			continue;
 		sync_blockdev(rdev->bdev);
 		invalidate_bdev(rdev->bdev);
-		if (mddev->ro != 1 &&
-		    (bdev_read_only(rdev->bdev) ||
-		     bdev_read_only(rdev->meta_bdev))) {
+		if (mddev->ro != 1 && rdev_read_only(rdev)) {
 			mddev->ro = 1;
 			if (mddev->gendisk)
 				set_disk_ro(mddev->gendisk, 1);
@@ -6158,7 +6143,7 @@ static int restart_array(struct mddev *mddev)
 		if (test_bit(Journal, &rdev->flags) &&
 		    !test_bit(Faulty, &rdev->flags))
 			has_journal = true;
-		if (bdev_read_only(rdev->bdev))
+		if (rdev_read_only(rdev))
 			has_readonly = true;
 	}
 	rcu_read_unlock();
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 34070ab30a8a..bcbba1b5ec4a 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -556,7 +556,7 @@ static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sect
 
 static inline void md_sync_acct_bio(struct bio *bio, unsigned long nr_sectors)
 {
-	atomic_add(nr_sectors, &bio->bi_disk->sync_io);
+	md_sync_acct(bio->bi_bdev, nr_sectors);
 }
 
 struct md_personality
@@ -742,8 +742,6 @@ extern void md_rdev_clear(struct md_rdev *rdev);
 extern void md_handle_request(struct mddev *mddev, struct bio *bio);
 extern void mddev_suspend(struct mddev *mddev);
 extern void mddev_resume(struct mddev *mddev);
-extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
-				   struct mddev *mddev);
 
 extern void md_reload_sb(struct mddev *mddev, int raid_disk);
 extern void md_update_sb(struct mddev *mddev, int force);
@@ -793,14 +791,14 @@ static inline void mddev_clear_unsupported_flags(struct mddev *mddev,
 static inline void mddev_check_writesame(struct mddev *mddev, struct bio *bio)
 {
 	if (bio_op(bio) == REQ_OP_WRITE_SAME &&
-	    !bio->bi_disk->queue->limits.max_write_same_sectors)
+	    !bio->bi_bdev->bd_disk->queue->limits.max_write_same_sectors)
 		mddev->queue->limits.max_write_same_sectors = 0;
 }
 
 static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio)
 {
 	if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
-	    !bio->bi_disk->queue->limits.max_write_zeroes_sectors)
+	    !bio->bi_bdev->bd_disk->queue->limits.max_write_zeroes_sectors)
 		mddev->queue->limits.max_write_zeroes_sectors = 0;
 }
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index c0347997f6ff..d2378765dc15 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -794,13 +794,13 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio)
 
 	while (bio) { /* submit pending writes */
 		struct bio *next = bio->bi_next;
-		struct md_rdev *rdev = (void *)bio->bi_disk;
+		struct md_rdev *rdev = (void *)bio->bi_bdev;
 		bio->bi_next = NULL;
 		bio_set_dev(bio, rdev->bdev);
 		if (test_bit(Faulty, &rdev->flags)) {
 			bio_io_error(bio);
 		} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
-				    !blk_queue_discard(bio->bi_disk->queue)))
+				    !blk_queue_discard(bio->bi_bdev->bd_disk->queue)))
 			/* Just ignore it */
 			bio_endio(bio);
 		else
@@ -1104,7 +1104,7 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio,
 	int i = 0;
 	struct bio *behind_bio = NULL;
 
-	behind_bio = bio_alloc_mddev(GFP_NOIO, vcnt, r1_bio->mddev);
+	behind_bio = bio_alloc_bioset(GFP_NOIO, vcnt, &r1_bio->mddev->bio_set);
 	if (!behind_bio)
 		return;
 
@@ -1520,7 +1520,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			trace_block_bio_remap(mbio, disk_devt(mddev->gendisk),
 					      r1_bio->sector);
 		/* flush_pending_writes() needs access to the rdev so...*/
-		mbio->bi_disk = (void *)conf->mirrors[i].rdev;
+		mbio->bi_bdev = (void *)conf->mirrors[i].rdev;
 
 		cb = blk_check_plugged(raid1_unplug, mddev, sizeof(*plug));
 		if (cb)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index c5d88ef6a45c..a9ae7d113492 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -882,13 +882,13 @@ static void flush_pending_writes(struct r10conf *conf)
 
 		while (bio) { /* submit pending writes */
 			struct bio *next = bio->bi_next;
-			struct md_rdev *rdev = (void*)bio->bi_disk;
+			struct md_rdev *rdev = (void*)bio->bi_bdev;
 			bio->bi_next = NULL;
 			bio_set_dev(bio, rdev->bdev);
 			if (test_bit(Faulty, &rdev->flags)) {
 				bio_io_error(bio);
 			} else if (unlikely((bio_op(bio) ==  REQ_OP_DISCARD) &&
-					    !blk_queue_discard(bio->bi_disk->queue)))
+					    !blk_queue_discard(bio->bi_bdev->bd_disk->queue)))
 				/* Just ignore it */
 				bio_endio(bio);
 			else
@@ -1075,13 +1075,13 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 
 	while (bio) { /* submit pending writes */
 		struct bio *next = bio->bi_next;
-		struct md_rdev *rdev = (void*)bio->bi_disk;
+		struct md_rdev *rdev = (void*)bio->bi_bdev;
 		bio->bi_next = NULL;
 		bio_set_dev(bio, rdev->bdev);
 		if (test_bit(Faulty, &rdev->flags)) {
 			bio_io_error(bio);
 		} else if (unlikely((bio_op(bio) ==  REQ_OP_DISCARD) &&
-				    !blk_queue_discard(bio->bi_disk->queue)))
+				    !blk_queue_discard(bio->bi_bdev->bd_disk->queue)))
 			/* Just ignore it */
 			bio_endio(bio);
 		else
@@ -1253,7 +1253,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 		trace_block_bio_remap(mbio, disk_devt(conf->mddev->gendisk),
 				      r10_bio->sector);
 	/* flush_pending_writes() needs access to the rdev so...*/
-	mbio->bi_disk = (void *)rdev;
+	mbio->bi_bdev = (void *)rdev;
 
 	atomic_inc(&r10_bio->remaining);
 
@@ -3003,7 +3003,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 
 	/* Again, very different code for resync and recovery.
 	 * Both must result in an r10bio with a list of bios that
-	 * have bi_end_io, bi_sector, bi_disk set,
+	 * have bi_end_io, bi_sector, bi_bdev set,
 	 * and bi_private set to the r10bio.
 	 * For recovery, we may actually create several r10bios
 	 * with 2 bios in each, that correspond to the bios in the main one.
@@ -4531,7 +4531,7 @@ read_more:
 		return sectors_done;
 	}
 
-	read_bio = bio_alloc_mddev(GFP_KERNEL, RESYNC_PAGES, mddev);
+	read_bio = bio_alloc_bioset(GFP_KERNEL, RESYNC_PAGES, &mddev->bio_set);
 
 	bio_set_dev(read_bio, rdev->bdev);
 	read_bio->bi_iter.bi_sector = (r10_bio->devs[r10_bio->read_slot].addr
@@ -4539,10 +4539,6 @@ read_more:
 	read_bio->bi_private = r10_bio;
 	read_bio->bi_end_io = end_reshape_read;
 	bio_set_op_attrs(read_bio, REQ_OP_READ, 0);
-	read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
-	read_bio->bi_status = 0;
-	read_bio->bi_vcnt = 0;
-	read_bio->bi_iter.bi_size = 0;
 	r10_bio->master_bio = read_bio;
 	r10_bio->read_slot = r10_bio->devs[r10_bio->read_slot].devnum;
 
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index d0f540296fe9..e8c118e05dfd 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -1037,7 +1037,7 @@ static int ppl_recover(struct ppl_log *log, struct ppl_header *pplhdr,
 	}
 
 	/* flush the disk cache after recovery if necessary */
-	ret = blkdev_issue_flush(rdev->bdev, GFP_KERNEL);
+	ret = blkdev_issue_flush(rdev->bdev);
 out:
 	__free_page(page);
 	return ret;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 3a90cc0e43ca..a348b2adf2a9 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5310,7 +5310,7 @@ static int in_chunk_boundary(struct mddev *mddev, struct bio *bio)
 	unsigned int chunk_sectors;
 	unsigned int bio_sectors = bio_sectors(bio);
 
-	WARN_ON_ONCE(bio->bi_partno);
+	WARN_ON_ONCE(bio->bi_bdev->bd_partno);
 
 	chunk_sectors = min(conf->chunk_sectors, conf->prev_chunk_sectors);
 	return  chunk_sectors >=
@@ -5393,90 +5393,72 @@ static void raid5_align_endio(struct bio *bi)
 static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 {
 	struct r5conf *conf = mddev->private;
-	int dd_idx;
-	struct bio* align_bi;
+	struct bio *align_bio;
 	struct md_rdev *rdev;
-	sector_t end_sector;
+	sector_t sector, end_sector, first_bad;
+	int bad_sectors, dd_idx;
 
 	if (!in_chunk_boundary(mddev, raid_bio)) {
 		pr_debug("%s: non aligned\n", __func__);
 		return 0;
 	}
-	/*
-	 * use bio_clone_fast to make a copy of the bio
-	 */
-	align_bi = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->bio_set);
-	if (!align_bi)
-		return 0;
-	/*
-	 *   set bi_end_io to a new function, and set bi_private to the
-	 *     original bio.
-	 */
-	align_bi->bi_end_io  = raid5_align_endio;
-	align_bi->bi_private = raid_bio;
-	/*
-	 *	compute position
-	 */
-	align_bi->bi_iter.bi_sector =
-		raid5_compute_sector(conf, raid_bio->bi_iter.bi_sector,
-				     0, &dd_idx, NULL);
 
-	end_sector = bio_end_sector(align_bi);
+	sector = raid5_compute_sector(conf, raid_bio->bi_iter.bi_sector, 0,
+				      &dd_idx, NULL);
+	end_sector = bio_end_sector(raid_bio);
+
 	rcu_read_lock();
+	if (r5c_big_stripe_cached(conf, sector))
+		goto out_rcu_unlock;
+
 	rdev = rcu_dereference(conf->disks[dd_idx].replacement);
 	if (!rdev || test_bit(Faulty, &rdev->flags) ||
 	    rdev->recovery_offset < end_sector) {
 		rdev = rcu_dereference(conf->disks[dd_idx].rdev);
-		if (rdev &&
-		    (test_bit(Faulty, &rdev->flags) ||
+		if (!rdev)
+			goto out_rcu_unlock;
+		if (test_bit(Faulty, &rdev->flags) ||
 		    !(test_bit(In_sync, &rdev->flags) ||
-		      rdev->recovery_offset >= end_sector)))
-			rdev = NULL;
+		      rdev->recovery_offset >= end_sector))
+			goto out_rcu_unlock;
 	}
 
-	if (r5c_big_stripe_cached(conf, align_bi->bi_iter.bi_sector)) {
-		rcu_read_unlock();
-		bio_put(align_bi);
+	atomic_inc(&rdev->nr_pending);
+	rcu_read_unlock();
+
+	align_bio = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->bio_set);
+	bio_set_dev(align_bio, rdev->bdev);
+	align_bio->bi_end_io = raid5_align_endio;
+	align_bio->bi_private = raid_bio;
+	align_bio->bi_iter.bi_sector = sector;
+
+	raid_bio->bi_next = (void *)rdev;
+
+	if (is_badblock(rdev, sector, bio_sectors(align_bio), &first_bad,
+			&bad_sectors)) {
+		bio_put(align_bio);
+		rdev_dec_pending(rdev, mddev);
 		return 0;
 	}
 
-	if (rdev) {
-		sector_t first_bad;
-		int bad_sectors;
-
-		atomic_inc(&rdev->nr_pending);
-		rcu_read_unlock();
-		raid_bio->bi_next = (void*)rdev;
-		bio_set_dev(align_bi, rdev->bdev);
-
-		if (is_badblock(rdev, align_bi->bi_iter.bi_sector,
-				bio_sectors(align_bi),
-				&first_bad, &bad_sectors)) {
-			bio_put(align_bi);
-			rdev_dec_pending(rdev, mddev);
-			return 0;
-		}
+	/* No reshape active, so we can trust rdev->data_offset */
+	align_bio->bi_iter.bi_sector += rdev->data_offset;
 
-		/* No reshape active, so we can trust rdev->data_offset */
-		align_bi->bi_iter.bi_sector += rdev->data_offset;
+	spin_lock_irq(&conf->device_lock);
+	wait_event_lock_irq(conf->wait_for_quiescent, conf->quiesce == 0,
+			    conf->device_lock);
+	atomic_inc(&conf->active_aligned_reads);
+	spin_unlock_irq(&conf->device_lock);
 
-		spin_lock_irq(&conf->device_lock);
-		wait_event_lock_irq(conf->wait_for_quiescent,
-				    conf->quiesce == 0,
-				    conf->device_lock);
-		atomic_inc(&conf->active_aligned_reads);
-		spin_unlock_irq(&conf->device_lock);
+	if (mddev->gendisk)
+		trace_block_bio_remap(align_bio, disk_devt(mddev->gendisk),
+				      raid_bio->bi_iter.bi_sector);
+	submit_bio_noacct(align_bio);
+	return 1;
 
-		if (mddev->gendisk)
-			trace_block_bio_remap(align_bi, disk_devt(mddev->gendisk),
-					      raid_bio->bi_iter.bi_sector);
-		submit_bio_noacct(align_bi);
-		return 1;
-	} else {
-		rcu_read_unlock();
-		bio_put(align_bi);
-		return 0;
-	}
+out_rcu_unlock:
+	rcu_read_unlock();
+	return 0;
 }
 
 static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)