Merge tag 'vfs-6.7.super' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs

Pull vfs superblock updates from Christian Brauner:
 "This contains the work to make block device opening functions return a
  struct bdev_handle instead of just a struct block_device. The same
  struct bdev_handle is then also passed to block device closing
  functions.

  This allows us to propagate context from opening to closing a block
  device without having to modify all users everytime.

  Sidenote, in the future we might even want to try and have block
  device opening functions return a struct file directly but that's a
  series on top of this.

  These are further preparatory changes to be able to count writable
  opens and blocking writes to mounted block devices. That's a separate
  piece of work for next cycle and for that we absolutely need the
  changes to btrfs that have been quietly dropped somehow.

  Originally the series contained a patch that removed the old
  blkdev_*() helpers. But since this would've caused needles churn in
  -next for bcachefs we ended up delaying it.

  The second piece of work addresses one of the major annoyances about
  the work last cycle, namely that we required dropping s_umount
  whenever we used the superblock and fs_holder_ops for a block device.

  The reason for that requirement had been that in some codepaths
  s_umount could've been taken under disk->open_mutex (that's always
  been the case, at least theoretically). For example, on surprise block
  device removal or media change. And opening and closing block devices
  required grabbing disk->open_mutex as well.

  So we did the work and went through the block layer and fixed all
  those places so that s_umount is never taken under disk->open_mutex.
  This means no more brittle games where we yield and reacquire s_umount
  during block device opening and closing and no more requirements where
  block devices need to be closed. Filesystems don't need to care about
  this.

  There's a bunch of other follow-up work such as moving block device
  freezing and thawing to holder operations which makes it work for all
  block devices and not just the main block device just as we did for
  surprise removal. But that is for next cycle.

  Tested with fstests for all major fses, blktests, LTP"

* tag 'vfs-6.7.super' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs: (37 commits)
  porting: update locking requirements
  fs: assert that open_mutex isn't held over holder ops
  block: assert that we're not holding open_mutex over blk_report_disk_dead
  block: move bdev_mark_dead out of disk_check_media_change
  block: WARN_ON_ONCE() when we remove active partitions
  block: simplify bdev_del_partition()
  fs: Avoid grabbing sb->s_umount under bdev->bd_holder_lock
  jfs: fix log->bdev_handle null ptr deref in lbmStartIO
  bcache: Fixup error handling in register_cache()
  xfs: Convert to bdev_open_by_path()
  reiserfs: Convert to bdev_open_by_dev/path()
  ocfs2: Convert to use bdev_open_by_dev()
  nfs/blocklayout: Convert to use bdev_open_by_dev/path()
  jfs: Convert to bdev_open_by_dev()
  f2fs: Convert to bdev_open_by_dev/path()
  ext4: Convert to bdev_open_by_dev()
  erofs: Convert to use bdev_open_by_path()
  btrfs: Convert to bdev_open_by_path()
  fs: Convert to bdev_open_by_dev()
  mm/swap: Convert to use bdev_open_by_dev()
  ...

5 files changed, 17 insertions, 1 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index eef450f25982..51fa7ffdee83 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1479,14 +1479,25 @@ extern const struct blk_holder_ops fs_holder_ops;
 #define sb_open_mode(flags) \
 	(BLK_OPEN_READ | (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE))
 
+struct bdev_handle {
+	struct block_device *bdev;
+	void *holder;
+	blk_mode_t mode;
+};
+
 struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 		const struct blk_holder_ops *hops);
 struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode,
 		void *holder, const struct blk_holder_ops *hops);
+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);
 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);
 void blkdev_put(struct block_device *bdev, void *holder);
+void bdev_release(struct bdev_handle *handle);
 
 /* just for blk-cgroup, don't use elsewhere */
 struct block_device *blkdev_get_no_open(dev_t dev);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 69d0435c7ebb..772ab4d74d94 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -165,6 +165,7 @@ void dm_error(const char *message);
 
 struct dm_dev {
 	struct block_device *bdev;
+	struct bdev_handle *bdev_handle;
 	struct dax_device *dax_dev;
 	blk_mode_t mode;
 	char name[16];
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4a40823c3c67..fb5accebdcdf 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1221,6 +1221,7 @@ struct super_block {
 	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 backing_dev_info *s_bdi;
 	struct mtd_info		*s_mtd;
 	struct hlist_node	s_instances;
diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h
index 80cb00db42a4..79594aeb160d 100644
--- a/include/linux/pktcdvd.h
+++ b/include/linux/pktcdvd.h
@@ -154,7 +154,9 @@ struct packet_stacked_data
 
 struct pktcdvd_device
 {
-	struct block_device	*bdev;		/* dev attached */
+	struct bdev_handle	*bdev_handle;	/* dev attached */
+	/* handle acquired for bdev during pkt_open_dev() */
+	struct bdev_handle	*open_bdev_handle;
 	dev_t			pkt_dev;	/* our dev */
 	struct packet_settings	settings;
 	struct packet_stats	stats;
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 493487ed7c38..f6dd6575b905 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -298,6 +298,7 @@ struct swap_info_struct {
 	unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */
 	struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
 	struct rb_root swap_extent_root;/* root of the swap extent rbtree */
+	struct bdev_handle *bdev_handle;/* open handle of the bdev */
 	struct block_device *bdev;	/* swap device or bdev of swap file */
 	struct file *swap_file;		/* seldom referenced */
 	unsigned int old_block_size;	/* seldom referenced */