1 files changed, 187 insertions, 159 deletions

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 0ae2b3676293..c17d4517af22 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -168,14 +168,14 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 {
 	const char *err;
 	struct cache_sb_disk *s;
-	struct page *page;
+	struct folio *folio;
 	unsigned int i;
 
-	page = read_cache_page_gfp(bdev->bd_inode->i_mapping,
-				   SB_OFFSET >> PAGE_SHIFT, GFP_KERNEL);
-	if (IS_ERR(page))
+	folio = mapping_read_folio_gfp(bdev->bd_mapping,
+			SB_OFFSET >> PAGE_SHIFT, GFP_KERNEL);
+	if (IS_ERR(folio))
 		return "IO error";
-	s = page_address(page) + offset_in_page(SB_OFFSET);
+	s = folio_address(folio) + offset_in_folio(folio, SB_OFFSET);
 
 	sb->offset		= le64_to_cpu(s->offset);
 	sb->version		= le64_to_cpu(s->version);
@@ -272,7 +272,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 	*res = s;
 	return NULL;
 err:
-	put_page(page);
+	folio_put(folio);
 	return err;
 }
 
@@ -293,8 +293,7 @@ static void __write_super(struct cache_sb *sb, struct cache_sb_disk *out,
 
 	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_META;
 	bio->bi_iter.bi_sector	= SB_SECTOR;
-	__bio_add_page(bio, virt_to_page(out), SB_SIZE,
-			offset_in_page(out));
+	bio_add_virt_nofail(bio, out, SB_SIZE);
 
 	out->offset		= cpu_to_le64(sb->offset);
 
@@ -327,9 +326,9 @@ static void __write_super(struct cache_sb *sb, struct cache_sb_disk *out,
 	submit_bio(bio);
 }
 
-static void bch_write_bdev_super_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(bch_write_bdev_super_unlock)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, sb_write);
+	closure_type(dc, struct cached_dev, sb_write);
 
 	up(&dc->sb_write_mutex);
 }
@@ -363,9 +362,9 @@ static void write_super_endio(struct bio *bio)
 	closure_put(&ca->set->sb_write);
 }
 
-static void bcache_write_super_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(bcache_write_super_unlock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, sb_write);
+	closure_type(c, struct cache_set, sb_write);
 
 	up(&c->sb_write_mutex);
 }
@@ -407,9 +406,9 @@ static void uuid_endio(struct bio *bio)
 	closure_put(cl);
 }
 
-static void uuid_io_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(uuid_io_unlock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, uuid_write);
+	closure_type(c, struct cache_set, uuid_write);
 
 	up(&c->uuid_write_mutex);
 }
@@ -546,7 +545,8 @@ static struct uuid_entry *uuid_find(struct cache_set *c, const char *uuid)
 
 static struct uuid_entry *uuid_find_empty(struct cache_set *c)
 {
-	static const char zero_uuid[16] = "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0";
+	static const char zero_uuid[16] __nonstring =
+		{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
 
 	return uuid_find(c, zero_uuid);
 }
@@ -881,8 +881,8 @@ static void bcache_device_free(struct bcache_device *d)
 		bcache_device_detach(d);
 
 	if (disk) {
-		ida_simple_remove(&bcache_device_idx,
-				  first_minor_to_idx(disk->first_minor));
+		ida_free(&bcache_device_idx,
+			 first_minor_to_idx(disk->first_minor));
 		put_disk(disk);
 	}
 
@@ -897,14 +897,30 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 		sector_t sectors, struct block_device *cached_bdev,
 		const struct block_device_operations *ops)
 {
-	struct request_queue *q;
 	const size_t max_stripes = min_t(size_t, INT_MAX,
 					 SIZE_MAX / sizeof(atomic_t));
+	struct queue_limits lim = {
+		.max_hw_sectors		= UINT_MAX,
+		.max_sectors		= UINT_MAX,
+		.max_segment_size	= UINT_MAX,
+		.max_segments		= BIO_MAX_VECS,
+		.max_hw_discard_sectors	= UINT_MAX,
+		.io_min			= block_size,
+		.logical_block_size	= block_size,
+		.physical_block_size	= block_size,
+		.features		= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA,
+	};
 	uint64_t n;
 	int idx;
 
+	if (cached_bdev) {
+		d->stripe_size = bdev_io_opt(cached_bdev) >> SECTOR_SHIFT;
+		lim.io_opt = umax(block_size, bdev_io_opt(cached_bdev));
+	}
 	if (!d->stripe_size)
 		d->stripe_size = 1 << 31;
+	else if (d->stripe_size < BCH_MIN_STRIPE_SZ)
+		d->stripe_size = roundup(BCH_MIN_STRIPE_SZ, d->stripe_size);
 
 	n = DIV_ROUND_UP_ULL(sectors, d->stripe_size);
 	if (!n || n > max_stripes) {
@@ -924,8 +940,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	if (!d->full_dirty_stripes)
 		goto out_free_stripe_sectors_dirty;
 
-	idx = ida_simple_get(&bcache_device_idx, 0,
-				BCACHE_DEVICE_IDX_MAX, GFP_KERNEL);
+	idx = ida_alloc_max(&bcache_device_idx, BCACHE_DEVICE_IDX_MAX - 1,
+			    GFP_KERNEL);
 	if (idx < 0)
 		goto out_free_full_dirty_stripes;
 
@@ -933,53 +949,37 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
 		goto out_ida_remove;
 
-	d->disk = blk_alloc_disk(NUMA_NO_NODE);
-	if (!d->disk)
-		goto out_bioset_exit;
-
-	set_capacity(d->disk, sectors);
-	snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", idx);
-
-	d->disk->major		= bcache_major;
-	d->disk->first_minor	= idx_to_first_minor(idx);
-	d->disk->minors		= BCACHE_MINORS;
-	d->disk->fops		= ops;
-	d->disk->private_data	= d;
-
-	q = d->disk->queue;
-	q->limits.max_hw_sectors	= UINT_MAX;
-	q->limits.max_sectors		= UINT_MAX;
-	q->limits.max_segment_size	= UINT_MAX;
-	q->limits.max_segments		= BIO_MAX_VECS;
-	blk_queue_max_discard_sectors(q, UINT_MAX);
-	q->limits.discard_granularity	= 512;
-	q->limits.io_min		= block_size;
-	q->limits.logical_block_size	= block_size;
-	q->limits.physical_block_size	= block_size;
-
-	if (q->limits.logical_block_size > PAGE_SIZE && cached_bdev) {
+	if (lim.logical_block_size > PAGE_SIZE && cached_bdev) {
 		/*
 		 * This should only happen with BCACHE_SB_VERSION_BDEV.
 		 * Block/page size is checked for BCACHE_SB_VERSION_CDEV.
 		 */
-		pr_info("%s: sb/logical block size (%u) greater than page size (%lu) falling back to device logical block size (%u)\n",
-			d->disk->disk_name, q->limits.logical_block_size,
+		pr_info("bcache%i: sb/logical block size (%u) greater than page size (%lu) falling back to device logical block size (%u)\n",
+			idx, lim.logical_block_size,
 			PAGE_SIZE, bdev_logical_block_size(cached_bdev));
 
 		/* This also adjusts physical block size/min io size if needed */
-		blk_queue_logical_block_size(q, bdev_logical_block_size(cached_bdev));
+		lim.logical_block_size = bdev_logical_block_size(cached_bdev);
 	}
 
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue);
+	d->disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
+	if (IS_ERR(d->disk))
+		goto out_bioset_exit;
 
-	blk_queue_write_cache(q, true, true);
+	set_capacity(d->disk, sectors);
+	snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", idx);
 
+	d->disk->major		= bcache_major;
+	d->disk->first_minor	= idx_to_first_minor(idx);
+	d->disk->minors		= BCACHE_MINORS;
+	d->disk->fops		= ops;
+	d->disk->private_data	= d;
 	return 0;
 
 out_bioset_exit:
 	bioset_exit(&d->bio_split);
 out_ida_remove:
-	ida_simple_remove(&bcache_device_idx, idx);
+	ida_free(&bcache_device_idx, idx);
 out_free_full_dirty_stripes:
 	kvfree(d->full_dirty_stripes);
 out_free_stripe_sectors_dirty:
@@ -1342,9 +1342,9 @@ void bch_cached_dev_release(struct kobject *kobj)
 	module_put(THIS_MODULE);
 }
 
-static void cached_dev_free(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_free)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
+	closure_type(dc, struct cached_dev, disk.cl);
 
 	if (test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags))
 		cancel_writeback_rate_update_dwork(dc);
@@ -1366,19 +1366,19 @@ static void cached_dev_free(struct closure *cl)
 	mutex_unlock(&bch_register_lock);
 
 	if (dc->sb_disk)
-		put_page(virt_to_page(dc->sb_disk));
+		folio_put(virt_to_folio(dc->sb_disk));
 
-	if (!IS_ERR_OR_NULL(dc->bdev))
-		blkdev_put(dc->bdev, dc);
+	if (dc->bdev_file)
+		fput(dc->bdev_file);
 
 	wake_up(&unregister_wait);
 
 	kobject_put(&dc->disk.kobj);
 }
 
-static void cached_dev_flush(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_flush)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
+	closure_type(dc, struct cached_dev, disk.cl);
 	struct bcache_device *d = &dc->disk;
 
 	mutex_lock(&bch_register_lock);
@@ -1388,7 +1388,7 @@ static void cached_dev_flush(struct closure *cl)
 	bch_cache_accounting_destroy(&dc->accounting);
 	kobject_del(&d->kobj);
 
-	continue_at(cl, cached_dev_free, system_wq);
+	continue_at(cl, cached_dev_free, system_percpu_wq);
 }
 
 static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
@@ -1400,7 +1400,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 	__module_get(THIS_MODULE);
 	INIT_LIST_HEAD(&dc->list);
 	closure_init(&dc->disk.cl, NULL);
-	set_closure_fn(&dc->disk.cl, cached_dev_flush, system_wq);
+	set_closure_fn(&dc->disk.cl, cached_dev_flush, system_percpu_wq);
 	kobject_init(&dc->disk.kobj, &bch_cached_dev_ktype);
 	INIT_WORK(&dc->detach, cached_dev_detach_finish);
 	sema_init(&dc->sb_write_mutex, 1);
@@ -1415,11 +1415,9 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 		hlist_add_head(&io->hash, dc->io_hash + RECENT_IO);
 	}
 
-	dc->disk.stripe_size = q->limits.io_opt >> 9;
-
-	if (dc->disk.stripe_size)
-		dc->partial_stripes_expensive =
-			q->limits.raid_partial_stripes_expensive;
+	if (bdev_io_opt(dc->bdev))
+		dc->partial_stripes_expensive = !!(q->limits.features &
+			BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE);
 
 	ret = bcache_device_init(&dc->disk, block_size,
 			 bdev_nr_sectors(dc->bdev) - dc->sb.data_offset,
@@ -1427,9 +1425,6 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 	if (ret)
 		return ret;
 
-	blk_queue_io_opt(dc->disk.disk->queue,
-		max(queue_io_opt(dc->disk.disk->queue), queue_io_opt(q)));
-
 	atomic_set(&dc->io_errors, 0);
 	dc->io_disable = false;
 	dc->error_limit = DEFAULT_CACHED_DEV_ERROR_LIMIT;
@@ -1444,7 +1439,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 /* Cached device - bcache superblock */
 
 static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
-				 struct block_device *bdev,
+				 struct file *bdev_file,
 				 struct cached_dev *dc)
 {
 	const char *err = "cannot allocate memory";
@@ -1452,14 +1447,15 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 	int ret = -ENOMEM;
 
 	memcpy(&dc->sb, sb, sizeof(struct cache_sb));
-	dc->bdev = bdev;
+	dc->bdev_file = bdev_file;
+	dc->bdev = file_bdev(bdev_file);
 	dc->sb_disk = sb_disk;
 
 	if (cached_dev_init(dc, sb->block_size << 9))
 		goto err;
 
 	err = "error creating kobject";
-	if (kobject_add(&dc->disk.kobj, bdev_kobj(bdev), "bcache"))
+	if (kobject_add(&dc->disk.kobj, bdev_kobj(dc->bdev), "bcache"))
 		goto err;
 	if (bch_cache_accounting_add_kobjs(&dc->accounting, &dc->disk.kobj))
 		goto err;
@@ -1496,9 +1492,9 @@ void bch_flash_dev_release(struct kobject *kobj)
 	kfree(d);
 }
 
-static void flash_dev_free(struct closure *cl)
+static CLOSURE_CALLBACK(flash_dev_free)
 {
-	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
+	closure_type(d, struct bcache_device, cl);
 
 	mutex_lock(&bch_register_lock);
 	atomic_long_sub(bcache_dev_sectors_dirty(d),
@@ -1509,15 +1505,15 @@ static void flash_dev_free(struct closure *cl)
 	kobject_put(&d->kobj);
 }
 
-static void flash_dev_flush(struct closure *cl)
+static CLOSURE_CALLBACK(flash_dev_flush)
 {
-	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
+	closure_type(d, struct bcache_device, cl);
 
 	mutex_lock(&bch_register_lock);
 	bcache_device_unlink(d);
 	mutex_unlock(&bch_register_lock);
 	kobject_del(&d->kobj);
-	continue_at(cl, flash_dev_free, system_wq);
+	continue_at(cl, flash_dev_free, system_percpu_wq);
 }
 
 static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
@@ -1529,7 +1525,7 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
 		goto err_ret;
 
 	closure_init(&d->cl, NULL);
-	set_closure_fn(&d->cl, flash_dev_flush, system_wq);
+	set_closure_fn(&d->cl, flash_dev_flush, system_percpu_wq);
 
 	kobject_init(&d->kobj, &bch_flash_dev_ktype);
 
@@ -1667,9 +1663,9 @@ void bch_cache_set_release(struct kobject *kobj)
 	module_put(THIS_MODULE);
 }
 
-static void cache_set_free(struct closure *cl)
+static CLOSURE_CALLBACK(cache_set_free)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, cl);
+	closure_type(c, struct cache_set, cl);
 	struct cache *ca;
 
 	debugfs_remove(c->debug);
@@ -1708,9 +1704,9 @@ static void cache_set_free(struct closure *cl)
 	kobject_put(&c->kobj);
 }
 
-static void cache_set_flush(struct closure *cl)
+static CLOSURE_CALLBACK(cache_set_flush)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, caching);
+	closure_type(c, struct cache_set, caching);
 	struct cache *ca = c->cache;
 	struct btree *b;
 
@@ -1722,7 +1718,7 @@ static void cache_set_flush(struct closure *cl)
 	if (!IS_ERR_OR_NULL(c->gc_thread))
 		kthread_stop(c->gc_thread);
 
-	if (!IS_ERR(c->root))
+	if (!IS_ERR_OR_NULL(c->root))
 		list_add(&c->root->list, &c->btree_cache);
 
 	/*
@@ -1737,7 +1733,12 @@ static void cache_set_flush(struct closure *cl)
 			mutex_unlock(&b->write_lock);
 		}
 
-	if (ca->alloc_thread)
+	/*
+	 * If the register_cache_set() call to bch_cache_set_alloc() failed,
+	 * ca has not been assigned a value and return error.
+	 * So we need check ca is not NULL during bch_cache_set_unregister().
+	 */
+	if (ca && ca->alloc_thread)
 		kthread_stop(ca->alloc_thread);
 
 	if (c->journal.cur) {
@@ -1805,9 +1806,9 @@ static void conditional_stop_bcache_device(struct cache_set *c,
 	}
 }
 
-static void __cache_set_unregister(struct closure *cl)
+static CLOSURE_CALLBACK(__cache_set_unregister)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, caching);
+	closure_type(c, struct cache_set, caching);
 	struct cached_dev *dc;
 	struct bcache_device *d;
 	size_t i;
@@ -1832,7 +1833,7 @@ static void __cache_set_unregister(struct closure *cl)
 
 	mutex_unlock(&bch_register_lock);
 
-	continue_at(cl, cache_set_flush, system_wq);
+	continue_at(cl, cache_set_flush, system_percpu_wq);
 }
 
 void bch_cache_set_stop(struct cache_set *c)
@@ -1862,10 +1863,10 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 
 	__module_get(THIS_MODULE);
 	closure_init(&c->cl, NULL);
-	set_closure_fn(&c->cl, cache_set_free, system_wq);
+	set_closure_fn(&c->cl, cache_set_free, system_percpu_wq);
 
 	closure_init(&c->caching, &c->cl);
-	set_closure_fn(&c->caching, __cache_set_unregister, system_wq);
+	set_closure_fn(&c->caching, __cache_set_unregister, system_percpu_wq);
 
 	/* Maybe create continue_at_noreturn() and use it here? */
 	closure_set_stopped(&c->cl);
@@ -1911,8 +1912,9 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	INIT_LIST_HEAD(&c->btree_cache_freed);
 	INIT_LIST_HEAD(&c->data_buckets);
 
-	iter_size = ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size + 1) *
-		sizeof(struct btree_iter_set);
+	iter_size = sizeof(struct btree_iter) +
+		    ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) *
+			    sizeof(struct btree_iter_set);
 
 	c->devices = kcalloc(c->nr_uuids, sizeof(void *), GFP_KERNEL);
 	if (!c->devices)
@@ -1937,7 +1939,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	if (!c->uuids)
 		goto err;
 
-	c->moving_gc_wq = alloc_workqueue("bcache_gc", WQ_MEM_RECLAIM, 0);
+	c->moving_gc_wq = alloc_workqueue("bcache_gc",
+					  WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!c->moving_gc_wq)
 		goto err;
 
@@ -2015,7 +2018,7 @@ static int run_cache_set(struct cache_set *c)
 		c->root = bch_btree_node_get(c, NULL, k,
 					     j->btree_level,
 					     true, NULL);
-		if (IS_ERR_OR_NULL(c->root))
+		if (IS_ERR(c->root))
 			goto err;
 
 		list_del_init(&c->root->list);
@@ -2214,10 +2217,10 @@ void bch_cache_release(struct kobject *kobj)
 		free_fifo(&ca->free[i]);
 
 	if (ca->sb_disk)
-		put_page(virt_to_page(ca->sb_disk));
+		folio_put(virt_to_folio(ca->sb_disk));
 
-	if (!IS_ERR_OR_NULL(ca->bdev))
-		blkdev_put(ca->bdev, ca);
+	if (ca->bdev_file)
+		fput(ca->bdev_file);
 
 	kfree(ca);
 	module_put(THIS_MODULE);
@@ -2234,18 +2237,50 @@ static int cache_alloc(struct cache *ca)
 	__module_get(THIS_MODULE);
 	kobject_init(&ca->kobj, &bch_cache_ktype);
 
-	bio_init(&ca->journal.bio, NULL, ca->journal.bio.bi_inline_vecs, 8, 0);
+	bio_init_inline(&ca->journal.bio, NULL, 8, 0);
 
 	/*
-	 * when ca->sb.njournal_buckets is not zero, journal exists,
-	 * and in bch_journal_replay(), tree node may split,
-	 * so bucket of RESERVE_BTREE type is needed,
-	 * the worst situation is all journal buckets are valid journal,
-	 * and all the keys need to replay,
-	 * so the number of  RESERVE_BTREE type buckets should be as much
-	 * as journal buckets
+	 * When the cache disk is first registered, ca->sb.njournal_buckets
+	 * is zero, and it is assigned in run_cache_set().
+	 *
+	 * When ca->sb.njournal_buckets is not zero, journal exists,
+	 * and in bch_journal_replay(), tree node may split.
+	 * The worst situation is all journal buckets are valid journal,
+	 * and all the keys need to replay, so the number of RESERVE_BTREE
+	 * type buckets should be as much as journal buckets.
+	 *
+	 * If the number of RESERVE_BTREE type buckets is too few, the
+	 * bch_allocator_thread() may hang up and unable to allocate
+	 * bucket. The situation is roughly as follows:
+	 *
+	 * 1. In bch_data_insert_keys(), if the operation is not op->replace,
+	 *    it will call the bch_journal(), which increments the journal_ref
+	 *    counter. This counter is only decremented after bch_btree_insert
+	 *    completes.
+	 *
+	 * 2. When calling bch_btree_insert, if the btree needs to split,
+	 *    it will call btree_split() and btree_check_reserve() to check
+	 *    whether there are enough reserved buckets in the RESERVE_BTREE
+	 *    slot. If not enough, bcache_btree_root() will repeatedly retry.
+	 *
+	 * 3. Normally, the bch_allocator_thread is responsible for filling
+	 *    the reservation slots from the free_inc bucket list. When the
+	 *    free_inc bucket list is exhausted, the bch_allocator_thread
+	 *    will call invalidate_buckets() until free_inc is refilled.
+	 *    Then bch_allocator_thread calls bch_prio_write() once. and
+	 *    bch_prio_write() will call bch_journal_meta() and waits for
+	 *    the journal write to complete.
+	 *
+	 * 4. During journal_write, journal_write_unlocked() is be called.
+	 *    If journal full occurs, journal_reclaim() and btree_flush_write()
+	 *    will be called sequentially, then retry journal_write.
+	 *
+	 * 5. When 2 and 4 occur together, IO will hung up and cannot recover.
+	 *
+	 * Therefore, reserve more RESERVE_BTREE type buckets.
 	 */
-	btree_buckets = ca->sb.njournal_buckets ?: 8;
+	btree_buckets = clamp_t(size_t, ca->sb.nbuckets >> 7,
+				32, SB_JOURNAL_BUCKETS);
 	free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
 	if (!free) {
 		ret = -EPERM;
@@ -2337,38 +2372,39 @@ err_free:
 }
 
 static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
-				struct block_device *bdev, struct cache *ca)
+				struct file *bdev_file,
+				struct cache *ca)
 {
 	const char *err = NULL; /* must be set for any error case */
 	int ret = 0;
 
 	memcpy(&ca->sb, sb, sizeof(struct cache_sb));
-	ca->bdev = bdev;
+	ca->bdev_file = bdev_file;
+	ca->bdev = file_bdev(bdev_file);
 	ca->sb_disk = sb_disk;
 
-	if (bdev_max_discard_sectors((bdev)))
-		ca->discard = CACHE_DISCARD(&ca->sb);
-
 	ret = cache_alloc(ca);
 	if (ret != 0) {
-		/*
-		 * If we failed here, it means ca->kobj is not initialized yet,
-		 * kobject_put() won't be called and there is no chance to
-		 * call blkdev_put() to bdev in bch_cache_release(). So we
-		 * explicitly call blkdev_put() here.
-		 */
-		blkdev_put(bdev, ca);
 		if (ret == -ENOMEM)
 			err = "cache_alloc(): -ENOMEM";
 		else if (ret == -EPERM)
 			err = "cache_alloc(): cache device is too small";
 		else
 			err = "cache_alloc(): unknown error";
-		goto err;
+		pr_notice("error %pg: %s\n", file_bdev(bdev_file), err);
+		/*
+		 * If we failed here, it means ca->kobj is not initialized yet,
+		 * kobject_put() won't be called and there is no chance to
+		 * call fput() to bdev in bch_cache_release(). So
+		 * we explicitly call fput() on the block device here.
+		 */
+		fput(bdev_file);
+		return ret;
 	}
 
-	if (kobject_add(&ca->kobj, bdev_kobj(bdev), "bcache")) {
-		err = "error calling kobject_add";
+	if (kobject_add(&ca->kobj, bdev_kobj(file_bdev(bdev_file)), "bcache")) {
+		pr_notice("error %pg: error calling kobject_add\n",
+			  file_bdev(bdev_file));
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -2382,15 +2418,10 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 		goto out;
 	}
 
-	pr_info("registered cache device %pg\n", ca->bdev);
+	pr_info("registered cache device %pg\n", file_bdev(ca->bdev_file));
 
 out:
 	kobject_put(&ca->kobj);
-
-err:
-	if (err)
-		pr_notice("error %pg: %s\n", ca->bdev, err);
-
 	return ret;
 }
 
@@ -2445,7 +2476,7 @@ struct async_reg_args {
 	char *path;
 	struct cache_sb *sb;
 	struct cache_sb_disk *sb_disk;
-	struct block_device *bdev;
+	struct file *bdev_file;
 	void *holder;
 };
 
@@ -2456,8 +2487,8 @@ static void register_bdev_worker(struct work_struct *work)
 		container_of(work, struct async_reg_args, reg_work.work);
 
 	mutex_lock(&bch_register_lock);
-	if (register_bdev(args->sb, args->sb_disk, args->bdev, args->holder)
-	    < 0)
+	if (register_bdev(args->sb, args->sb_disk, args->bdev_file,
+			  args->holder) < 0)
 		fail = true;
 	mutex_unlock(&bch_register_lock);
 
@@ -2477,7 +2508,8 @@ static void register_cache_worker(struct work_struct *work)
 		container_of(work, struct async_reg_args, reg_work.work);
 
 	/* blkdev_put() will be called in bch_cache_release() */
-	if (register_cache(args->sb, args->sb_disk, args->bdev, args->holder))
+	if (register_cache(args->sb, args->sb_disk, args->bdev_file,
+			   args->holder))
 		fail = true;
 
 	if (fail)
@@ -2497,7 +2529,7 @@ static void register_device_async(struct async_reg_args *args)
 		INIT_DELAYED_WORK(&args->reg_work, register_cache_worker);
 
 	/* 10 jiffies is enough for a delay */
-	queue_delayed_work(system_wq, &args->reg_work, 10);
+	queue_delayed_work(system_percpu_wq, &args->reg_work, 10);
 }
 
 static void *alloc_holder_object(struct cache_sb *sb)
@@ -2514,7 +2546,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	char *path = NULL;
 	struct cache_sb *sb;
 	struct cache_sb_disk *sb_disk;
-	struct block_device *bdev, *bdev2;
+	struct file *bdev_file, *bdev_file2;
 	void *holder = NULL;
 	ssize_t ret;
 	bool async_registration = false;
@@ -2547,15 +2579,11 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 
 	ret = -EINVAL;
 	err = "failed to open device";
-	bdev = blkdev_get_by_path(strim(path), BLK_OPEN_READ, NULL, NULL);
-	if (IS_ERR(bdev))
+	bdev_file = bdev_file_open_by_path(strim(path), BLK_OPEN_READ, NULL, NULL);
+	if (IS_ERR(bdev_file))
 		goto out_free_sb;
 
-	err = "failed to set blocksize";
-	if (set_blocksize(bdev, 4096))
-		goto out_blkdev_put;
-
-	err = read_super(sb, bdev, &sb_disk);
+	err = read_super(sb, file_bdev(bdev_file), &sb_disk);
 	if (err)
 		goto out_blkdev_put;
 
@@ -2563,17 +2591,17 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	if (!holder) {
 		ret = -ENOMEM;
 		err = "cannot allocate memory";
-		goto out_put_sb_page;
+		goto out_put_sb_folio;
 	}
 
 	/* Now reopen in exclusive mode with proper holder */
-	bdev2 = blkdev_get_by_dev(bdev->bd_dev, BLK_OPEN_READ | BLK_OPEN_WRITE,
-				  holder, NULL);
-	blkdev_put(bdev, NULL);
-	bdev = bdev2;
-	if (IS_ERR(bdev)) {
-		ret = PTR_ERR(bdev);
-		bdev = NULL;
+	bdev_file2 = bdev_file_open_by_dev(file_bdev(bdev_file)->bd_dev,
+			BLK_OPEN_READ | BLK_OPEN_WRITE, holder, NULL);
+	fput(bdev_file);
+	bdev_file = bdev_file2;
+	if (IS_ERR(bdev_file)) {
+		ret = PTR_ERR(bdev_file);
+		bdev_file = NULL;
 		if (ret == -EBUSY) {
 			dev_t dev;
 
@@ -2608,7 +2636,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 		args->path	= path;
 		args->sb	= sb;
 		args->sb_disk	= sb_disk;
-		args->bdev	= bdev;
+		args->bdev_file	= bdev_file;
 		args->holder	= holder;
 		register_device_async(args);
 		/* No wait and returns to user space */
@@ -2617,14 +2645,14 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 
 	if (SB_IS_BDEV(sb)) {
 		mutex_lock(&bch_register_lock);
-		ret = register_bdev(sb, sb_disk, bdev, holder);
+		ret = register_bdev(sb, sb_disk, bdev_file, holder);
 		mutex_unlock(&bch_register_lock);
 		/* blkdev_put() will be called in cached_dev_free() */
 		if (ret < 0)
 			goto out_free_sb;
 	} else {
 		/* blkdev_put() will be called in bch_cache_release() */
-		ret = register_cache(sb, sb_disk, bdev, holder);
+		ret = register_cache(sb, sb_disk, bdev_file, holder);
 		if (ret)
 			goto out_free_sb;
 	}
@@ -2637,11 +2665,11 @@ async_done:
 
 out_free_holder:
 	kfree(holder);
-out_put_sb_page:
-	put_page(virt_to_page(sb_disk));
+out_put_sb_folio:
+	folio_put(virt_to_folio(sb_disk));
 out_blkdev_put:
-	if (bdev)
-		blkdev_put(bdev, holder);
+	if (bdev_file)
+		fput(bdev_file);
 out_free_sb:
 	kfree(sb);
 out_free_path:
@@ -2875,24 +2903,25 @@ static int __init bcache_init(void)
 	if (bch_btree_init())
 		goto err;
 
-	bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0);
+	bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!bcache_wq)
 		goto err;
 
 	/*
 	 * Let's not make this `WQ_MEM_RECLAIM` for the following reasons:
 	 *
-	 * 1. It used `system_wq` before which also does no memory reclaim.
+	 * 1. It used `system_percpu_wq` before which also does no memory reclaim.
 	 * 2. With `WQ_MEM_RECLAIM` desktop stalls, increased boot times, and
 	 *    reduced throughput can be observed.
 	 *
-	 * We still want to user our own queue to not congest the `system_wq`.
+	 * We still want to user our own queue to not congest the `system_percpu_wq`.
 	 */
-	bch_flush_wq = alloc_workqueue("bch_flush", 0, 0);
+	bch_flush_wq = alloc_workqueue("bch_flush", WQ_PERCPU, 0);
 	if (!bch_flush_wq)
 		goto err;
 
-	bch_journal_wq = alloc_workqueue("bch_journal", WQ_MEM_RECLAIM, 0);
+	bch_journal_wq = alloc_workqueue("bch_journal",
+					 WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!bch_journal_wq)
 		goto err;
 
@@ -2905,7 +2934,6 @@ static int __init bcache_init(void)
 		goto err;
 
 	bch_debug_init();
-	closure_debug_init();
 
 	bcache_is_reboot = false;