Merge series 'Open block devices as files' of https://lore.kernel.org/r/20240123-vfs-bdev-file-v2-0-adbd023e19cc@kernel.org

Pull block devices as files from Christian Brauner:

This opens block devices as files. Instead of introducing a separate
indirection into bdev_open_by_*() vis struct bdev_handle we can just
make bdev_file_open_by_*() return a struct file. Opening and closing a
block device from setup_bdev_super() and in all other places just
becomes equivalent to opening and closing a file.

This has held up in xfstests and in blktests so far and it seems stable
and clean. The equivalence of opening and closing block devices to
regular files is a win in and of itself imho. Added to that is the
ability to do away with struct bdev_handle completely and make various
low-level helpers private to the block layer.

All places were we currently stash a struct bdev_handle we just stash a
file and use an accessor such as file_bdev() akin to I_BDEV() to get to
the block device.

It's now also possible to use file->f_mapping as a replacement for
bdev->bd_inode->i_mapping and file->f_inode or file->f_mapping->host as
an alternative to bdev->bd_inode allowing us to significantly reduce or
even fully remove bdev->bd_inode in follow-up patches.

In addition, we could get rid of sb->s_bdev and various other places
that stash the block device directly and instead stash the block device
file. Again, this is follow-up work if we want this.

* series 'Open block devices as files' of https://lore.kernel.org/r/20240123-vfs-bdev-file-v2-0-adbd023e19cc@kernel.org: (35 commits)
  file: add alloc_file_pseudo_noaccount()
  file: prepare for new helper
  init: flush async file closing
  block: remove bdev_handle completely
  block: don't rely on BLK_OPEN_RESTRICT_WRITES when yielding write access
  bdev: remove bdev pointer from struct bdev_handle
  bdev: make struct bdev_handle private to the block layer
  bdev: make bdev_{release, open_by_dev}() private to block layer
  bdev: remove bdev_open_by_path()
  reiserfs: port block device access to file
  ocfs2: port block device access to file
  nfs: port block device access to files
  jfs: port block device access to file
  f2fs: port block device access to files
  ext4: port block device access to file
  erofs: port device access to file
  btrfs: port device access to file
  bcachefs: port block device access to file
  target: port block device access to file
  s390: port block device access to file
  nvme: port block device access to file
  block2mtd: port device access to files
  bcache: port block device access to files
  ...

Signed-off-by: Christian Brauner <brauner@kernel.org>

3 files changed, 15 insertions, 3 deletions

diff --git a/init/do_mounts.c b/init/do_mounts.c
index 279ad28bf4fb..3c5fd993bc7e 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -208,6 +208,9 @@ retry:
 				goto out;
 			case -EACCES:
 			case -EINVAL:
+#ifdef CONFIG_BLOCK
+				init_flush_fput();
+#endif
 				continue;
 		}
 	        /*
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 15e372b00ce7..6069ea3eb80d 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -9,6 +9,8 @@
 #include <linux/major.h>
 #include <linux/root_dev.h>
 #include <linux/init_syscalls.h>
+#include <linux/task_work.h>
+#include <linux/file.h>
 
 void  mount_root_generic(char *name, char *pretty_name, int flags);
 void  mount_root(char *root_device_name);
@@ -41,3 +43,10 @@ static inline bool initrd_load(char *root_device_name)
 	}
 
 #endif
+
+/* Ensure that async file closing finished to prevent spurious errors. */
+static inline void init_flush_fput(void)
+{
+	flush_delayed_fput();
+	task_work_run();
+}
diff --git a/init/initramfs.c b/init/initramfs.c
index 76deb48c38cb..6554f28fa2da 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -16,9 +16,10 @@
 #include <linux/mm.h>
 #include <linux/namei.h>
 #include <linux/init_syscalls.h>
-#include <linux/task_work.h>
 #include <linux/umh.h>
 
+#include "do_mounts.h"
+
 static __initdata bool csum_present;
 static __initdata u32 io_csum;
 
@@ -736,8 +737,7 @@ done:
 	initrd_start = 0;
 	initrd_end = 0;
 
-	flush_delayed_fput();
-	task_work_run();
+	init_flush_fput();
 }
 
 static ASYNC_DOMAIN_EXCLUSIVE(initramfs_domain);