bdev: open block device as files

Add two new helpers to allow opening block devices as files.
This is not the final infrastructure. This still opens the block device
before opening a struct a file. Until we have removed all references to
struct bdev_handle we can't switch the order:

* Introduce blk_to_file_flags() to translate from block specific to
  flags usable to pen a new file.
* Introduce bdev_file_open_by_{dev,path}().
* Introduce temporary sb_bdev_handle() helper to retrieve a struct
  bdev_handle from a block device file and update places that directly
  reference struct bdev_handle to rely on it.
* Don't count block device openes against the number of open files. A
  bdev_file_open_by_{dev,path}() file is never installed into any
  file descriptor table.

One idea that came to mind was to use kernel_tmpfile_open() which
would require us to pass a path and it would then call do_dentry_open()
going through the regular fops->open::blkdev_open() path. But then we're
back to the problem of routing block specific flags such as
BLK_OPEN_RESTRICT_WRITES through the open path and would have to waste
FMODE_* flags every time we add a new one. With this we can avoid using
a flag bit and we have more leeway in how we open block devices from
bdev_open_by_{dev,path}().

Link: https://lore.kernel.org/r/20240123-vfs-bdev-file-v2-1-adbd023e19cc@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

2 files changed, 15 insertions, 2 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 99e4f5e72213..76706aa47316 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -24,6 +24,7 @@
 #include <linux/sbitmap.h>
 #include <linux/uuid.h>
 #include <linux/xarray.h>
+#include <linux/file.h>
 
 struct module;
 struct request_queue;
@@ -1474,6 +1475,7 @@ extern const struct blk_holder_ops fs_holder_ops;
 	(BLK_OPEN_READ | BLK_OPEN_RESTRICT_WRITES | \
 	 (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE))
 
+/* @bdev_handle will be removed soon. */
 struct bdev_handle {
 	struct block_device *bdev;
 	void *holder;
@@ -1484,6 +1486,10 @@ struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 		const struct blk_holder_ops *hops);
 struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
 		void *holder, const struct blk_holder_ops *hops);
+struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
+		const struct blk_holder_ops *hops);
+struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode,
+		void *holder, const struct blk_holder_ops *hops);
 int bd_prepare_to_claim(struct block_device *bdev, void *holder,
 		const struct blk_holder_ops *hops);
 void bd_abort_claiming(struct block_device *bdev, void *holder);
@@ -1494,6 +1500,7 @@ struct block_device *blkdev_get_no_open(dev_t dev);
 void blkdev_put_no_open(struct block_device *bdev);
 
 struct block_device *I_BDEV(struct inode *inode);
+struct block_device *file_bdev(struct file *bdev_file);
 
 #ifdef CONFIG_BLOCK
 void invalidate_bdev(struct block_device *bdev);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ed5966a70495..e9291e27cc47 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1228,8 +1228,8 @@ struct super_block {
 #endif
 	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
-	struct block_device	*s_bdev;
-	struct bdev_handle	*s_bdev_handle;
+	struct block_device	*s_bdev;	/* can go away once we use an accessor for @s_bdev_file */
+	struct file		*s_bdev_file;
 	struct backing_dev_info *s_bdi;
 	struct mtd_info		*s_mtd;
 	struct hlist_node	s_instances;
@@ -1327,6 +1327,12 @@ struct super_block {
 	struct list_head	s_inodes_wb;	/* writeback inodes */
 } __randomize_layout;
 
+/* Temporary helper that will go away. */
+static inline struct bdev_handle *sb_bdev_handle(struct super_block *sb)
+{
+	return sb->s_bdev_file->private_data;
+}
+
 static inline struct user_namespace *i_user_ns(const struct inode *inode)
 {
 	return inode->i_sb->s_user_ns;