Merge tag 'pull-bd_inode-1' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull bdev bd_inode updates from Al Viro:
 "Replacement of bdev->bd_inode with sane(r) set of primitives by me and
  Yu Kuai"

* tag 'pull-bd_inode-1' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  RIP ->bd_inode
  dasd_format(): killing the last remaining user of ->bd_inode
  nilfs_attach_log_writer(): use ->bd_mapping->host instead of ->bd_inode
  block/bdev.c: use the knowledge of inode/bdev coallocation
  gfs2: more obvious initializations of mapping->host
  fs/buffer.c: massage the remaining users of ->bd_inode to ->bd_mapping
  blk_ioctl_{discard,zeroout}(): we only want ->bd_inode->i_mapping here...
  grow_dev_folio(): we only want ->bd_inode->i_mapping there
  use ->bd_mapping instead of ->bd_inode->i_mapping
  block_device: add a pointer to struct address_space (page cache of bdev)
  missing helpers: bdev_unhash(), bdev_drop()
  block: move two helpers into bdev.c
  block2mtd: prevent direct access of bd_inode
  dm-vdo: use bdev_nr_bytes(bdev) instead of i_size_read(bdev->bd_inode)
  blkdev_write_iter(): saner way to get inode and bdev
  bcachefs: remove dead function bdev_sectors()
  ext4: remove block_device_ejected()
  erofs_buf: store address_space instead of inode
  erofs: switch erofs_bread() to passing offset instead of block number

7 files changed, 67 insertions, 39 deletions

diff --git a/block/bdev.c b/block/bdev.c
index 938580ca70a6..5a03c93ba222 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -43,6 +43,11 @@ static inline struct bdev_inode *BDEV_I(struct inode *inode)
 	return container_of(inode, struct bdev_inode, vfs_inode);
 }
 
+static inline struct inode *BD_INODE(struct block_device *bdev)
+{
+	return &container_of(bdev, struct bdev_inode, bdev)->vfs_inode;
+}
+
 struct block_device *I_BDEV(struct inode *inode)
 {
 	return &BDEV_I(inode)->bdev;
@@ -57,7 +62,7 @@ EXPORT_SYMBOL(file_bdev);
 
 static void bdev_write_inode(struct block_device *bdev)
 {
-	struct inode *inode = bdev->bd_inode;
+	struct inode *inode = BD_INODE(bdev);
 	int ret;
 
 	spin_lock(&inode->i_lock);
@@ -76,7 +81,7 @@ static void bdev_write_inode(struct block_device *bdev)
 /* Kill _all_ buffers and pagecache , dirty or not.. */
 static void kill_bdev(struct block_device *bdev)
 {
-	struct address_space *mapping = bdev->bd_inode->i_mapping;
+	struct address_space *mapping = bdev->bd_mapping;
 
 	if (mapping_empty(mapping))
 		return;
@@ -88,7 +93,7 @@ static void kill_bdev(struct block_device *bdev)
 /* Invalidate clean unused buffers and pagecache. */
 void invalidate_bdev(struct block_device *bdev)
 {
-	struct address_space *mapping = bdev->bd_inode->i_mapping;
+	struct address_space *mapping = bdev->bd_mapping;
 
 	if (mapping->nrpages) {
 		invalidate_bh_lrus();
@@ -116,7 +121,7 @@ int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode,
 			goto invalidate;
 	}
 
-	truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend);
+	truncate_inode_pages_range(bdev->bd_mapping, lstart, lend);
 	if (!(mode & BLK_OPEN_EXCL))
 		bd_abort_claiming(bdev, truncate_bdev_range);
 	return 0;
@@ -126,7 +131,7 @@ invalidate:
 	 * Someone else has handle exclusively open. Try invalidating instead.
 	 * The 'end' argument is inclusive so the rounding is safe.
 	 */
-	return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping,
+	return invalidate_inode_pages2_range(bdev->bd_mapping,
 					     lstart >> PAGE_SHIFT,
 					     lend >> PAGE_SHIFT);
 }
@@ -134,14 +139,14 @@ invalidate:
 static void set_init_blocksize(struct block_device *bdev)
 {
 	unsigned int bsize = bdev_logical_block_size(bdev);
-	loff_t size = i_size_read(bdev->bd_inode);
+	loff_t size = i_size_read(BD_INODE(bdev));
 
 	while (bsize < PAGE_SIZE) {
 		if (size & bsize)
 			break;
 		bsize <<= 1;
 	}
-	bdev->bd_inode->i_blkbits = blksize_bits(bsize);
+	BD_INODE(bdev)->i_blkbits = blksize_bits(bsize);
 }
 
 int set_blocksize(struct file *file, int size)
@@ -198,7 +203,7 @@ int sync_blockdev_nowait(struct block_device *bdev)
 {
 	if (!bdev)
 		return 0;
-	return filemap_flush(bdev->bd_inode->i_mapping);
+	return filemap_flush(bdev->bd_mapping);
 }
 EXPORT_SYMBOL_GPL(sync_blockdev_nowait);
 
@@ -210,13 +215,13 @@ int sync_blockdev(struct block_device *bdev)
 {
 	if (!bdev)
 		return 0;
-	return filemap_write_and_wait(bdev->bd_inode->i_mapping);
+	return filemap_write_and_wait(bdev->bd_mapping);
 }
 EXPORT_SYMBOL(sync_blockdev);
 
 int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend)
 {
-	return filemap_write_and_wait_range(bdev->bd_inode->i_mapping,
+	return filemap_write_and_wait_range(bdev->bd_mapping,
 			lstart, lend);
 }
 EXPORT_SYMBOL(sync_blockdev_range);
@@ -418,7 +423,7 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	spin_lock_init(&bdev->bd_size_lock);
 	mutex_init(&bdev->bd_holder_lock);
 	bdev->bd_partno = partno;
-	bdev->bd_inode = inode;
+	bdev->bd_mapping = &inode->i_data;
 	bdev->bd_queue = disk->queue;
 	if (partno)
 		bdev->bd_has_submit_bio = disk->part0->bd_has_submit_bio;
@@ -436,19 +441,30 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors)
 {
 	spin_lock(&bdev->bd_size_lock);
-	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
+	i_size_write(BD_INODE(bdev), (loff_t)sectors << SECTOR_SHIFT);
 	bdev->bd_nr_sectors = sectors;
 	spin_unlock(&bdev->bd_size_lock);
 }
 
 void bdev_add(struct block_device *bdev, dev_t dev)
 {
+	struct inode *inode = BD_INODE(bdev);
 	if (bdev_stable_writes(bdev))
-		mapping_set_stable_writes(bdev->bd_inode->i_mapping);
+		mapping_set_stable_writes(bdev->bd_mapping);
 	bdev->bd_dev = dev;
-	bdev->bd_inode->i_rdev = dev;
-	bdev->bd_inode->i_ino = dev;
-	insert_inode_hash(bdev->bd_inode);
+	inode->i_rdev = dev;
+	inode->i_ino = dev;
+	insert_inode_hash(inode);
+}
+
+void bdev_unhash(struct block_device *bdev)
+{
+	remove_inode_hash(BD_INODE(bdev));
+}
+
+void bdev_drop(struct block_device *bdev)
+{
+	iput(BD_INODE(bdev));
 }
 
 long nr_blockdev_pages(void)
@@ -923,7 +939,7 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
 		bdev_file->f_mode |= FMODE_NOWAIT;
 	if (mode & BLK_OPEN_RESTRICT_WRITES)
 		bdev_file->f_mode |= FMODE_WRITE_RESTRICTED;
-	bdev_file->f_mapping = bdev->bd_inode->i_mapping;
+	bdev_file->f_mapping = bdev->bd_mapping;
 	bdev_file->f_wb_err = filemap_sample_wb_err(bdev_file->f_mapping);
 	bdev_file->private_data = holder;
 
@@ -985,13 +1001,13 @@ struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 		return ERR_PTR(-ENXIO);
 
 	flags = blk_to_file_flags(mode);
-	bdev_file = alloc_file_pseudo_noaccount(bdev->bd_inode,
+	bdev_file = alloc_file_pseudo_noaccount(BD_INODE(bdev),
 			blockdev_mnt, "", flags | O_LARGEFILE, &def_blk_fops);
 	if (IS_ERR(bdev_file)) {
 		blkdev_put_no_open(bdev);
 		return bdev_file;
 	}
-	ihold(bdev->bd_inode);
+	ihold(BD_INODE(bdev));
 
 	ret = bdev_open(bdev, mode, holder, hops, bdev_file);
 	if (ret) {
@@ -1266,6 +1282,18 @@ void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
 	blkdev_put_no_open(bdev);
 }
 
+bool disk_live(struct gendisk *disk)
+{
+	return !inode_unhashed(BD_INODE(disk->part0));
+}
+EXPORT_SYMBOL_GPL(disk_live);
+
+unsigned int block_size(struct block_device *bdev)
+{
+	return 1 << BD_INODE(bdev)->i_blkbits;
+}
+EXPORT_SYMBOL_GPL(block_size);
+
 static int __init setup_bdev_allow_write_mounted(char *str)
 {
 	if (kstrtobool(str, &bdev_allow_write_mounted))
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 48e5e3bbb89c..57d367ada1f2 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -416,7 +416,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 		op = REQ_OP_ZONE_RESET;
 
 		/* Invalidate the page cache, including dirty pages. */
-		filemap_invalidate_lock(bdev->bd_inode->i_mapping);
+		filemap_invalidate_lock(bdev->bd_mapping);
 		ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
 		if (ret)
 			goto fail;
@@ -438,7 +438,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 
 fail:
 	if (cmd == BLKRESETZONE)
-		filemap_invalidate_unlock(bdev->bd_inode->i_mapping);
+		filemap_invalidate_unlock(bdev->bd_mapping);
 
 	return ret;
 }
diff --git a/block/blk.h b/block/blk.h
index 6e94c10af798..189bc25beb50 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -499,6 +499,8 @@ static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev,
 
 struct block_device *bdev_alloc(struct gendisk *disk, u8 partno);
 void bdev_add(struct block_device *bdev, dev_t dev);
+void bdev_unhash(struct block_device *bdev);
+void bdev_drop(struct block_device *bdev);
 
 int blk_alloc_ext_minor(void);
 void blk_free_ext_minor(unsigned int minor);
diff --git a/block/fops.c b/block/fops.c
index 7a163f7fe2d8..376265935714 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -663,8 +663,8 @@ static ssize_t blkdev_buffered_write(struct kiocb *iocb, struct iov_iter *from)
 static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
-	struct block_device *bdev = I_BDEV(file->f_mapping->host);
-	struct inode *bd_inode = bdev->bd_inode;
+	struct inode *bd_inode = bdev_file_inode(file);
+	struct block_device *bdev = I_BDEV(bd_inode);
 	loff_t size = bdev_nr_bytes(bdev);
 	size_t shorted = 0;
 	ssize_t ret;
diff --git a/block/genhd.c b/block/genhd.c
index 7f39fbe60753..0519097afa35 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -653,7 +653,7 @@ void del_gendisk(struct gendisk *disk)
 	 */
 	mutex_lock(&disk->open_mutex);
 	xa_for_each(&disk->part_tbl, idx, part)
-		remove_inode_hash(part->bd_inode);
+		bdev_unhash(part);
 	mutex_unlock(&disk->open_mutex);
 
 	/*
@@ -742,7 +742,7 @@ void invalidate_disk(struct gendisk *disk)
 	struct block_device *bdev = disk->part0;
 
 	invalidate_bdev(bdev);
-	bdev->bd_inode->i_mapping->wb_err = 0;
+	bdev->bd_mapping->wb_err = 0;
 	set_capacity(disk, 0);
 }
 EXPORT_SYMBOL(invalidate_disk);
@@ -1191,7 +1191,7 @@ static void disk_release(struct device *dev)
 	if (test_bit(GD_ADDED, &disk->state) && disk->fops->free_disk)
 		disk->fops->free_disk(disk);
 
-	iput(disk->part0->bd_inode);	/* frees the disk */
+	bdev_drop(disk->part0);	/* frees the disk */
 }
 
 static int block_uevent(const struct device *dev, struct kobj_uevent_env *env)
@@ -1379,7 +1379,7 @@ out_erase_part0:
 out_destroy_part_tbl:
 	xa_destroy(&disk->part_tbl);
 	disk->part0->bd_disk = NULL;
-	iput(disk->part0->bd_inode);
+	bdev_drop(disk->part0);
 out_free_bdi:
 	bdi_put(disk->bdi);
 out_free_bioset:
diff --git a/block/ioctl.c b/block/ioctl.c
index 615b6003fbb5..515f75fd0d83 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -96,7 +96,6 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
 		unsigned long arg)
 {
 	unsigned int bs_mask = bdev_logical_block_size(bdev) - 1;
-	struct inode *inode = bdev->bd_inode;
 	uint64_t range[2], start, len, end;
 	struct bio *prev = NULL, *bio;
 	sector_t sector, nr_sects;
@@ -126,7 +125,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
 	    end > bdev_nr_bytes(bdev))
 		return -EINVAL;
 
-	filemap_invalidate_lock(inode->i_mapping);
+	filemap_invalidate_lock(bdev->bd_mapping);
 	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
 	if (err)
 		goto fail;
@@ -157,7 +156,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
 out_unplug:
 	blk_finish_plug(&plug);
 fail:
-	filemap_invalidate_unlock(inode->i_mapping);
+	filemap_invalidate_unlock(bdev->bd_mapping);
 	return err;
 }
 
@@ -182,12 +181,12 @@ static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode,
 	if (start + len > bdev_nr_bytes(bdev))
 		return -EINVAL;
 
-	filemap_invalidate_lock(bdev->bd_inode->i_mapping);
+	filemap_invalidate_lock(bdev->bd_mapping);
 	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
 	if (!err)
 		err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9,
 						GFP_KERNEL);
-	filemap_invalidate_unlock(bdev->bd_inode->i_mapping);
+	filemap_invalidate_unlock(bdev->bd_mapping);
 	return err;
 }
 
@@ -197,7 +196,6 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
 {
 	uint64_t range[2];
 	uint64_t start, end, len;
-	struct inode *inode = bdev->bd_inode;
 	int err;
 
 	if (!(mode & BLK_OPEN_WRITE))
@@ -220,7 +218,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
 		return -EINVAL;
 
 	/* Invalidate the page cache, including dirty pages */
-	filemap_invalidate_lock(inode->i_mapping);
+	filemap_invalidate_lock(bdev->bd_mapping);
 	err = truncate_bdev_range(bdev, mode, start, end);
 	if (err)
 		goto fail;
@@ -229,7 +227,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
 				   BLKDEV_ZERO_NOUNMAP);
 
 fail:
-	filemap_invalidate_unlock(inode->i_mapping);
+	filemap_invalidate_unlock(bdev->bd_mapping);
 	return err;
 }
 
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 37b5f92d07fe..84023b82e5a1 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -243,7 +243,7 @@ static const struct attribute_group *part_attr_groups[] = {
 static void part_release(struct device *dev)
 {
 	put_disk(dev_to_bdev(dev)->bd_disk);
-	iput(dev_to_bdev(dev)->bd_inode);
+	bdev_drop(dev_to_bdev(dev));
 }
 
 static int part_uevent(const struct device *dev, struct kobj_uevent_env *env)
@@ -469,7 +469,7 @@ int bdev_del_partition(struct gendisk *disk, int partno)
 	 * Just delete the partition and invalidate it.
 	 */
 
-	remove_inode_hash(part->bd_inode);
+	bdev_unhash(part);
 	invalidate_bdev(part);
 	drop_partition(part);
 	ret = 0;
@@ -652,7 +652,7 @@ rescan:
 		 * it cannot be looked up any more even when openers
 		 * still hold references.
 		 */
-		remove_inode_hash(part->bd_inode);
+		bdev_unhash(part);
 
 		/*
 		 * If @disk->open_partitions isn't elevated but there's
@@ -701,7 +701,7 @@ EXPORT_SYMBOL_GPL(bdev_disk_changed);
 
 void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p)
 {
-	struct address_space *mapping = state->disk->part0->bd_inode->i_mapping;
+	struct address_space *mapping = state->disk->part0->bd_mapping;
 	struct folio *folio;
 
 	if (n >= get_capacity(state->disk)) {