Merge tag 'v6.6-vfs.super' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull superblock updates from Christian Brauner:
 "This contains the super rework that was ready for this cycle. The
  first part changes the order of how we open block devices and allocate
  superblocks, contains various cleanups, simplifications, and a new
  mechanism to wait on superblock state changes.

  This unblocks work to ultimately limit the number of writers to a
  block device. Jan has already scheduled follow-up work that will be
  ready for v6.7 and allows us to restrict the number of writers to a
  given block device. That series builds on this work right here.

  The second part contains filesystem freezing updates.

  Overview:

  The generic superblock changes are rougly organized as follows
  (ignoring additional minor cleanups):

   (1) Removal of the bd_super member from struct block_device.

       This was a very odd back pointer to struct super_block with
       unclear rules. For all relevant places we have other means to get
       the same information so just get rid of this.

   (2) Simplify rules for superblock cleanup.

       Roughly, everything that is allocated during fs_context
       initialization and that's stored in fs_context->s_fs_info needs
       to be cleaned up by the fs_context->free() implementation before
       the superblock allocation function has been called successfully.

       After sget_fc() returned fs_context->s_fs_info has been
       transferred to sb->s_fs_info at which point sb->kill_sb() if
       fully responsible for cleanup. Adhering to these rules means that
       cleanup of sb->s_fs_info in fill_super() is to be avoided as it's
       brittle and inconsistent.

       Cleanup shouldn't be duplicated between sb->put_super() as
       sb->put_super() is only called if sb->s_root has been set aka
       when the filesystem has been successfully born (SB_BORN). That
       complexity should be avoided.

       This also means that block devices are to be closed in
       sb->kill_sb() instead of sb->put_super(). More details in the
       lower section.

   (3) Make it possible to lookup or create a superblock before opening
       block devices

       There's a subtle dependency on (2) as some filesystems did rely
       on fill_super() to be called in order to correctly clean up
       sb->s_fs_info. All these filesystems have been fixed.

   (4) Switch most filesystem to follow the same logic as the generic
       mount code now does as outlined in (3).

   (5) Use the superblock as the holder of the block device. We can now
       easily go back from block device to owning superblock.

   (6) Export and extend the generic fs_holder_ops and use them as
       holder ops everywhere and remove the filesystem specific holder
       ops.

   (7) Call from the block layer up into the filesystem layer when the
       block device is removed, allowing to shut down the filesystem
       without risk of deadlocks.

   (8) Get rid of get_super().

       We can now easily go back from the block device to owning
       superblock and can call up from the block layer into the
       filesystem layer when the device is removed. So no need to wade
       through all registered superblock to find the owning superblock
       anymore"

Link: https://lore.kernel.org/lkml/20230824-prall-intakt-95dbffdee4a0@brauner/

* tag 'v6.6-vfs.super' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (47 commits)
  super: use higher-level helper for {freeze,thaw}
  super: wait until we passed kill super
  super: wait for nascent superblocks
  super: make locking naming consistent
  super: use locking helpers
  fs: simplify invalidate_inodes
  fs: remove get_super
  block: call into the file system for ioctl BLKFLSBUF
  block: call into the file system for bdev_mark_dead
  block: consolidate __invalidate_device and fsync_bdev
  block: drop the "busy inodes on changed media" log message
  dasd: also call __invalidate_device when setting the device offline
  amiflop: don't call fsync_bdev in FDFMTBEG
  floppy: call disk_force_media_change when changing the format
  block: simplify the disk_force_media_change interface
  nbd: call blk_mark_disk_dead in nbd_clear_sock_ioctl
  xfs use fs_holder_ops for the log and RT devices
  xfs: drop s_umount over opening the log and RT devices
  ext4: use fs_holder_ops for the log device
  ext4: drop s_umount over opening the log device
  ...

25 files changed, 935 insertions, 520 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 3aa2380a75e1..084a6ade108a 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1226,19 +1226,14 @@ EXPORT_SYMBOL(mark_buffer_dirty);
 
 void mark_buffer_write_io_error(struct buffer_head *bh)
 {
-	struct super_block *sb;
-
 	set_buffer_write_io_error(bh);
 	/* FIXME: do we need to set this in both places? */
 	if (bh->b_folio && bh->b_folio->mapping)
 		mapping_set_error(bh->b_folio->mapping, -EIO);
-	if (bh->b_assoc_map)
+	if (bh->b_assoc_map) {
 		mapping_set_error(bh->b_assoc_map, -EIO);
-	rcu_read_lock();
-	sb = READ_ONCE(bh->b_bdev->bd_super);
-	if (sb)
-		errseq_set(&sb->s_wb_err, -EIO);
-	rcu_read_unlock();
+		errseq_set(&bh->b_assoc_map->host->i_sb->s_wb_err, -EIO);
+	}
 }
 EXPORT_SYMBOL(mark_buffer_write_io_error);
 
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index e755b2223936..5ee7d7bbb361 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -486,12 +486,16 @@ static void cramfs_kill_sb(struct super_block *sb)
 {
 	struct cramfs_sb_info *sbi = CRAMFS_SB(sb);
 
+	generic_shutdown_super(sb);
+
 	if (IS_ENABLED(CONFIG_CRAMFS_MTD) && sb->s_mtd) {
 		if (sbi && sbi->mtd_point_size)
 			mtd_unpoint(sb->s_mtd, 0, sbi->mtd_point_size);
-		kill_mtd_super(sb);
+		put_mtd_device(sb->s_mtd);
+		sb->s_mtd = NULL;
 	} else if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV) && sb->s_bdev) {
-		kill_block_super(sb);
+		sync_blockdev(sb->s_bdev);
+		blkdev_put(sb->s_bdev, sb);
 	}
 	kfree(sbi);
 }
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 729ada9e26e8..f55498e5c23d 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -273,8 +273,6 @@ struct exfat_sb_info {
 
 	spinlock_t inode_hash_lock;
 	struct hlist_head inode_hashtable[EXFAT_HASH_SIZE];
-
-	struct rcu_head rcu;
 };
 
 #define EXFAT_CACHE_VALID	0
diff --git a/fs/exfat/super.c b/fs/exfat/super.c
index 8e0ca4b0fc8f..2778bd9b631e 100644
--- a/fs/exfat/super.c
+++ b/fs/exfat/super.c
@@ -31,16 +31,6 @@ static void exfat_free_iocharset(struct exfat_sb_info *sbi)
 		kfree(sbi->options.iocharset);
 }
 
-static void exfat_delayed_free(struct rcu_head *p)
-{
-	struct exfat_sb_info *sbi = container_of(p, struct exfat_sb_info, rcu);
-
-	unload_nls(sbi->nls_io);
-	exfat_free_iocharset(sbi);
-	exfat_free_upcase_table(sbi);
-	kfree(sbi);
-}
-
 static void exfat_put_super(struct super_block *sb)
 {
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
@@ -50,7 +40,8 @@ static void exfat_put_super(struct super_block *sb)
 	brelse(sbi->boot_bh);
 	mutex_unlock(&sbi->s_lock);
 
-	call_rcu(&sbi->rcu, exfat_delayed_free);
+	unload_nls(sbi->nls_io);
+	exfat_free_upcase_table(sbi);
 }
 
 static int exfat_sync_fs(struct super_block *sb, int wait)
@@ -709,9 +700,6 @@ free_table:
 
 check_nls_io:
 	unload_nls(sbi->nls_io);
-	exfat_free_iocharset(sbi);
-	sb->s_fs_info = NULL;
-	kfree(sbi);
 	return err;
 }
 
@@ -720,14 +708,18 @@ static int exfat_get_tree(struct fs_context *fc)
 	return get_tree_bdev(fc, exfat_fill_super);
 }
 
+static void exfat_free_sbi(struct exfat_sb_info *sbi)
+{
+	exfat_free_iocharset(sbi);
+	kfree(sbi);
+}
+
 static void exfat_free(struct fs_context *fc)
 {
 	struct exfat_sb_info *sbi = fc->s_fs_info;
 
-	if (sbi) {
-		exfat_free_iocharset(sbi);
-		kfree(sbi);
-	}
+	if (sbi)
+		exfat_free_sbi(sbi);
 }
 
 static int exfat_reconfigure(struct fs_context *fc)
@@ -772,12 +764,21 @@ static int exfat_init_fs_context(struct fs_context *fc)
 	return 0;
 }
 
+static void exfat_kill_sb(struct super_block *sb)
+{
+	struct exfat_sb_info *sbi = sb->s_fs_info;
+
+	kill_block_super(sb);
+	if (sbi)
+		exfat_free_sbi(sbi);
+}
+
 static struct file_system_type exfat_fs_type = {
 	.owner			= THIS_MODULE,
 	.name			= "exfat",
 	.init_fs_context	= exfat_init_fs_context,
 	.parameters		= exfat_parameters,
-	.kill_sb		= kill_block_super,
+	.kill_sb		= exfat_kill_sb,
 	.fs_flags		= FS_REQUIRES_DEV,
 };
 
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 77f318ec8abb..b38d59581411 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -234,8 +234,7 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line,
 
 	might_sleep();
 
-	if (bh->b_bdev->bd_super)
-		ext4_check_bdev_write_error(bh->b_bdev->bd_super);
+	ext4_check_bdev_write_error(sb);
 
 	if (ext4_handle_valid(handle)) {
 		err = jbd2_journal_get_write_access(handle, bh);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index cb1ff47af156..73547d2334fd 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -93,6 +93,7 @@ static int ext4_get_tree(struct fs_context *fc);
 static int ext4_reconfigure(struct fs_context *fc);
 static void ext4_fc_free(struct fs_context *fc);
 static int ext4_init_fs_context(struct fs_context *fc);
+static void ext4_kill_sb(struct super_block *sb);
 static const struct fs_parameter_spec ext4_param_specs[];
 
 /*
@@ -135,12 +136,12 @@ static struct file_system_type ext2_fs_type = {
 	.name			= "ext2",
 	.init_fs_context	= ext4_init_fs_context,
 	.parameters		= ext4_param_specs,
-	.kill_sb		= kill_block_super,
+	.kill_sb		= ext4_kill_sb,
 	.fs_flags		= FS_REQUIRES_DEV,
 };
 MODULE_ALIAS_FS("ext2");
 MODULE_ALIAS("ext2");
-#define IS_EXT2_SB(sb) ((sb)->s_bdev->bd_holder == &ext2_fs_type)
+#define IS_EXT2_SB(sb) ((sb)->s_type == &ext2_fs_type)
 #else
 #define IS_EXT2_SB(sb) (0)
 #endif
@@ -151,12 +152,12 @@ static struct file_system_type ext3_fs_type = {
 	.name			= "ext3",
 	.init_fs_context	= ext4_init_fs_context,
 	.parameters		= ext4_param_specs,
-	.kill_sb		= kill_block_super,
+	.kill_sb		= ext4_kill_sb,
 	.fs_flags		= FS_REQUIRES_DEV,
 };
 MODULE_ALIAS_FS("ext3");
 MODULE_ALIAS("ext3");
-#define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)
+#define IS_EXT3_SB(sb) ((sb)->s_type == &ext3_fs_type)
 
 
 static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
@@ -1096,15 +1097,6 @@ void ext4_update_dynamic_rev(struct super_block *sb)
 	 */
 }
 
-static void ext4_bdev_mark_dead(struct block_device *bdev)
-{
-	ext4_force_shutdown(bdev->bd_holder, EXT4_GOING_FLAGS_NOLOGFLUSH);
-}
-
-static const struct blk_holder_ops ext4_holder_ops = {
-	.mark_dead		= ext4_bdev_mark_dead,
-};
-
 /*
  * Open the external journal device
  */
@@ -1113,7 +1105,7 @@ static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb)
 	struct block_device *bdev;
 
 	bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, sb,
-				 &ext4_holder_ops);
+				 &fs_holder_ops);
 	if (IS_ERR(bdev))
 		goto fail;
 	return bdev;
@@ -1125,25 +1117,6 @@ fail:
 	return NULL;
 }
 
-/*
- * Release the journal device
- */
-static void ext4_blkdev_remove(struct ext4_sb_info *sbi)
-{
-	struct block_device *bdev;
-	bdev = sbi->s_journal_bdev;
-	if (bdev) {
-		/*
-		 * Invalidate the journal device's buffers.  We don't want them
-		 * floating about in memory - the physical journal device may
-		 * hotswapped, and it breaks the `ro-after' testing code.
-		 */
-		invalidate_bdev(bdev);
-		blkdev_put(bdev, sbi->s_sb);
-		sbi->s_journal_bdev = NULL;
-	}
-}
-
 static inline struct inode *orphan_list_entry(struct list_head *l)
 {
 	return &list_entry(l, struct ext4_inode_info, i_orphan)->vfs_inode;
@@ -1339,8 +1312,13 @@ static void ext4_put_super(struct super_block *sb)
 	sync_blockdev(sb->s_bdev);
 	invalidate_bdev(sb->s_bdev);
 	if (sbi->s_journal_bdev) {
+		/*
+		 * Invalidate the journal device's buffers.  We don't want them
+		 * floating about in memory - the physical journal device may
+		 * hotswapped, and it breaks the `ro-after' testing code.
+		 */
 		sync_blockdev(sbi->s_journal_bdev);
-		ext4_blkdev_remove(sbi);
+		invalidate_bdev(sbi->s_journal_bdev);
 	}
 
 	ext4_xattr_destroy_cache(sbi->s_ea_inode_cache);
@@ -5572,7 +5550,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	spin_lock_init(&sbi->s_bdev_wb_lock);
 	errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err,
 				 &sbi->s_bdev_wb_err);
-	sb->s_bdev->bd_super = sb;
 	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
 	ext4_orphan_cleanup(sb, es);
 	EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
@@ -5664,9 +5641,11 @@ failed_mount:
 		kfree(get_qf_name(sb, sbi, i));
 #endif
 	fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
-	/* ext4_blkdev_remove() calls kill_bdev(), release bh before it. */
 	brelse(sbi->s_sbh);
-	ext4_blkdev_remove(sbi);
+	if (sbi->s_journal_bdev) {
+		invalidate_bdev(sbi->s_journal_bdev);
+		blkdev_put(sbi->s_journal_bdev, sb);
+	}
 out_fail:
 	invalidate_bdev(sb->s_bdev);
 	sb->s_fs_info = NULL;
@@ -5854,7 +5833,10 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 	if (WARN_ON_ONCE(!ext4_has_feature_journal(sb)))
 		return NULL;
 
+	/* see get_tree_bdev why this is needed and safe */
+	up_write(&sb->s_umount);
 	bdev = ext4_blkdev_get(j_dev, sb);
+	down_write(&sb->s_umount);
 	if (bdev == NULL)
 		return NULL;
 
@@ -7273,12 +7255,23 @@ static inline int ext3_feature_set_ok(struct super_block *sb)
 	return 1;
 }
 
+static void ext4_kill_sb(struct super_block *sb)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct block_device *journal_bdev = sbi ? sbi->s_journal_bdev : NULL;
+
+	kill_block_super(sb);
+
+	if (journal_bdev)
+		blkdev_put(journal_bdev, sb);
+}
+
 static struct file_system_type ext4_fs_type = {
 	.owner			= THIS_MODULE,
 	.name			= "ext4",
 	.init_fs_context	= ext4_init_fs_context,
 	.parameters		= ext4_param_specs,
-	.kill_sb		= kill_block_super,
+	.kill_sb		= ext4_kill_sb,
 	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME,
 };
 MODULE_ALIAS_FS("ext4");
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 01effd3fcb6c..a1ca394bc327 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -2181,12 +2181,14 @@ out_drop_write:
 	if (err)
 		return err;
 
-	err = freeze_super(sbi->sb);
+	err = freeze_super(sbi->sb, FREEZE_HOLDER_USERSPACE);
 	if (err)
 		return err;
 
 	if (f2fs_readonly(sbi->sb)) {
-		thaw_super(sbi->sb);
+		err = thaw_super(sbi->sb, FREEZE_HOLDER_USERSPACE);
+		if (err)
+			return err;
 		return -EROFS;
 	}
 
@@ -2240,6 +2242,6 @@ recover_out:
 out_err:
 	f2fs_up_write(&sbi->cp_global_sem);
 	f2fs_up_write(&sbi->gc_lock);
-	thaw_super(sbi->sb);
+	thaw_super(sbi->sb, FREEZE_HOLDER_USERSPACE);
 	return err;
 }
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 28aeffc0048c..aa1f9a3a8037 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1561,7 +1561,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
 	int i;
 
 	for (i = 0; i < sbi->s_ndevs; i++) {
-		blkdev_put(FDEV(i).bdev, sbi->sb->s_type);
+		blkdev_put(FDEV(i).bdev, sbi->sb);
 #ifdef CONFIG_BLK_DEV_ZONED
 		kvfree(FDEV(i).blkz_seq);
 #endif
@@ -4198,7 +4198,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 			/* Single zoned block device mount */
 			FDEV(0).bdev =
 				blkdev_get_by_dev(sbi->sb->s_bdev->bd_dev, mode,
-						  sbi->sb->s_type, NULL);
+						  sbi->sb, NULL);
 		} else {
 			/* Multi-device mount */
 			memcpy(FDEV(i).path, RDEV(i).path, MAX_PATH_LEN);
@@ -4217,8 +4217,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 					sbi->log_blocks_per_seg) - 1;
 			}
 			FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path, mode,
-							  sbi->sb->s_type,
-							  NULL);
+							  sbi->sb, NULL);
 		}
 		if (IS_ERR(FDEV(i).bdev))
 			return PTR_ERR(FDEV(i).bdev);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index aca4b4811394..969ce991b0b0 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1953,9 +1953,9 @@ static long __writeback_inodes_wb(struct bdi_writeback *wb,
 		struct inode *inode = wb_inode(wb->b_io.prev);
 		struct super_block *sb = inode->i_sb;
 
-		if (!trylock_super(sb)) {
+		if (!super_trylock_shared(sb)) {
 			/*
-			 * trylock_super() may fail consistently due to
+			 * super_trylock_shared() may fail consistently due to
 			 * s_umount being grabbed by someone else. Don't use
 			 * requeue_io() to avoid busy retrying the inode/sb.
 			 */
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index ec0296b35dfe..2f701335e8ee 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -689,7 +689,7 @@ static int gfs2_freeze_locally(struct gfs2_sbd *sdp)
 	struct super_block *sb = sdp->sd_vfs;
 	int error;
 
-	error = freeze_super(sb);
+	error = freeze_super(sb, FREEZE_HOLDER_USERSPACE);
 	if (error)
 		return error;
 
@@ -697,7 +697,9 @@ static int gfs2_freeze_locally(struct gfs2_sbd *sdp)
 		gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE |
 			       GFS2_LFC_FREEZE_GO_SYNC);
 		if (gfs2_withdrawn(sdp)) {
-			thaw_super(sb);
+			error = thaw_super(sb, FREEZE_HOLDER_USERSPACE);
+			if (error)
+				return error;
 			return -EIO;
 		}
 	}
@@ -712,7 +714,7 @@ static int gfs2_do_thaw(struct gfs2_sbd *sdp)
 	error = gfs2_freeze_lock_shared(sdp);
 	if (error)
 		goto fail;
-	error = thaw_super(sb);
+	error = thaw_super(sb, FREEZE_HOLDER_USERSPACE);
 	if (!error)
 		return 0;
 
@@ -761,7 +763,7 @@ out:
  *
  */
 
-static int gfs2_freeze_super(struct super_block *sb)
+static int gfs2_freeze_super(struct super_block *sb, enum freeze_holder who)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	int error;
@@ -816,7 +818,7 @@ out:
  *
  */
 
-static int gfs2_thaw_super(struct super_block *sb)
+static int gfs2_thaw_super(struct super_block *sb, enum freeze_holder who)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	int error;
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 2dfbe2f188dd..c60bc7f628e1 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -168,10 +168,10 @@ static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
 
 	switch (n) {
 	case 0:
-		error = thaw_super(sdp->sd_vfs);
+		error = thaw_super(sdp->sd_vfs, FREEZE_HOLDER_USERSPACE);
 		break;
 	case 1:
-		error = freeze_super(sdp->sd_vfs);
+		error = freeze_super(sdp->sd_vfs, FREEZE_HOLDER_USERSPACE);
 		break;
 	default:
 		return -EINVAL;
diff --git a/fs/inode.c b/fs/inode.c
index 0ad4fb4b8fe9..35fd688168c5 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -751,16 +751,11 @@ EXPORT_SYMBOL_GPL(evict_inodes);
 /**
  * invalidate_inodes	- attempt to free all inodes on a superblock
  * @sb:		superblock to operate on
- * @kill_dirty: flag to guide handling of dirty inodes
  *
- * Attempts to free all inodes for a given superblock.  If there were any
- * busy inodes return a non-zero value, else zero.
- * If @kill_dirty is set, discard dirty inodes too, otherwise treat
- * them as busy.
+ * Attempts to free all inodes (including dirty inodes) for a given superblock.
  */
-int invalidate_inodes(struct super_block *sb, bool kill_dirty)
+void invalidate_inodes(struct super_block *sb)
 {
-	int busy = 0;
 	struct inode *inode, *next;
 	LIST_HEAD(dispose);
 
@@ -772,14 +767,8 @@ again:
 			spin_unlock(&inode->i_lock);
 			continue;
 		}
-		if (inode->i_state & I_DIRTY_ALL && !kill_dirty) {
-			spin_unlock(&inode->i_lock);
-			busy = 1;
-			continue;
-		}
 		if (atomic_read(&inode->i_count)) {
 			spin_unlock(&inode->i_lock);
-			busy = 1;
 			continue;
 		}
 
@@ -797,8 +786,6 @@ again:
 	spin_unlock(&sb->s_inode_list_lock);
 
 	dispose_list(&dispose);
-
-	return busy;
 }
 
 /*
diff --git a/fs/internal.h b/fs/internal.h
index f7a3dc111026..74d3b161dd2c 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -115,7 +115,7 @@ static inline void put_file_access(struct file *file)
  * super.c
  */
 extern int reconfigure_super(struct fs_context *);
-extern bool trylock_super(struct super_block *sb);
+extern bool super_trylock_shared(struct super_block *sb);
 struct super_block *user_get_super(dev_t, bool excl);
 void put_super(struct super_block *sb);
 extern bool mount_capable(struct fs_context *);
@@ -201,7 +201,7 @@ void lock_two_inodes(struct inode *inode1, struct inode *inode2,
  * fs-writeback.c
  */
 extern long get_nr_dirty_inodes(void);
-extern int invalidate_inodes(struct super_block *, bool);
+void invalidate_inodes(struct super_block *sb);
 
 /*
  * dcache.c
diff --git a/fs/ioctl.c b/fs/ioctl.c
index d413e0b8f6c2..f5fd99d6b0d4 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -397,8 +397,8 @@ static int ioctl_fsfreeze(struct file *filp)
 
 	/* Freeze */
 	if (sb->s_op->freeze_super)
-		return sb->s_op->freeze_super(sb);
-	return freeze_super(sb);
+		return sb->s_op->freeze_super(sb, FREEZE_HOLDER_USERSPACE);
+	return freeze_super(sb, FREEZE_HOLDER_USERSPACE);
 }
 
 static int ioctl_fsthaw(struct file *filp)
@@ -410,8 +410,8 @@ static int ioctl_fsthaw(struct file *filp)
 
 	/* Thaw */
 	if (sb->s_op->thaw_super)
-		return sb->s_op->thaw_super(sb);
-	return thaw_super(sb);
+		return sb->s_op->thaw_super(sb, FREEZE_HOLDER_USERSPACE);
+	return thaw_super(sb, FREEZE_HOLDER_USERSPACE);
 }
 
 static int ioctl_file_dedupe_range(struct file *file,
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 0ef8c71bde8e..a5d1fa4e7552 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -35,6 +35,7 @@
 #include <linux/writeback.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
+#include <linux/fs_context.h>
 #include "nilfs.h"
 #include "export.h"
 #include "mdt.h"
@@ -1216,7 +1217,6 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
 }
 
 struct nilfs_super_data {
-	struct block_device *bdev;
 	__u64 cno;
 	int flags;
 };
@@ -1283,64 +1283,49 @@ static int nilfs_identify(char *data, struct nilfs_super_data *sd)
 
 static int nilfs_set_bdev_super(struct super_block *s, void *data)
 {
-	s->s_bdev = data;
-	s->s_dev = s->s_bdev->bd_dev;
+	s->s_dev = *(dev_t *)data;
 	return 0;
 }
 
 static int nilfs_test_bdev_super(struct super_block *s, void *data)
 {
-	return (void *)s->s_bdev == data;
+	return !(s->s_iflags & SB_I_RETIRED) && s->s_dev == *(dev_t *)data;
 }
 
 static struct dentry *
 nilfs_mount(struct file_system_type *fs_type, int flags,
 	     const char *dev_name, void *data)
 {
-	struct nilfs_super_data sd;
+	struct nilfs_super_data sd = { .flags = flags };
 	struct super_block *s;
-	struct dentry *root_dentry;
-	int err, s_new = false;
+	dev_t dev;
+	int err;
 
-	sd.bdev = blkdev_get_by_path(dev_name, sb_open_mode(flags), fs_type,
-				     NULL);
-	if (IS_ERR(sd.bdev))
-		return ERR_CAST(sd.bdev);
+	if (nilfs_identify(data, &sd))
+		return ERR_PTR(-EINVAL);
 
-	sd.cno = 0;
-	sd.flags = flags;
-	if (nilfs_identify((char *)data, &sd)) {
-		err = -EINVAL;
-		goto failed;
-	}
+	err = lookup_bdev(dev_name, &dev);
+	if (err)
+		return ERR_PTR(err);
 
-	/*
-	 * once the super is inserted into the list by sget, s_umount
-	 * will protect the lockfs code from trying to start a snapshot
-	 * while we are mounting
-	 */
-	mutex_lock(&sd.bdev->bd_fsfreeze_mutex);
-	if (sd.bdev->bd_fsfreeze_count > 0) {
-		mutex_unlock(&sd.bdev->bd_fsfreeze_mutex);
-		err = -EBUSY;
-		goto failed;
-	}
 	s = sget(fs_type, nilfs_test_bdev_super, nilfs_set_bdev_super, flags,
-		 sd.bdev);
-	mutex_unlock(&sd.bdev->bd_fsfreeze_mutex);
-	if (IS_ERR(s)) {
-		err = PTR_ERR(s);
-		goto failed;
-	}
+		 &dev);
+	if (IS_ERR(s))
+		return ERR_CAST(s);
 
 	if (!s->s_root) {
-		s_new = true;
-
-		/* New superblock instance created */
-		snprintf(s->s_id, sizeof(s->s_id), "%pg", sd.bdev);
-		sb_set_blocksize(s, block_size(sd.bdev));
-
-		err = nilfs_fill_super(s, data, flags & SB_SILENT ? 1 : 0);
+		/*
+		 * We drop s_umount here because we need to open the bdev and
+		 * bdev->open_mutex ranks above s_umount (blkdev_put() ->
+		 * __invalidate_device()). It is safe because we have active sb
+		 * reference and SB_BORN is not set yet.
+		 */
+		up_write(&s->s_umount);
+		err = setup_bdev_super(s, flags, NULL);
+		down_write(&s->s_umount);
+		if (!err)
+			err = nilfs_fill_super(s, data,
+					       flags & SB_SILENT ? 1 : 0);
 		if (err)
 			goto failed_super;
 
@@ -1366,24 +1351,18 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
 	}
 
 	if (sd.cno) {
+		struct dentry *root_dentry;
+
 		err = nilfs_attach_snapshot(s, sd.cno, &root_dentry);
 		if (err)
 			goto failed_super;
-	} else {
-		root_dentry = dget(s->s_root);
+		return root_dentry;
 	}
 
-	if (!s_new)
-		blkdev_put(sd.bdev, fs_type);
-
-	return root_dentry;
+	return dget(s->s_root);
 
  failed_super:
 	deactivate_locked_super(s);
-
- failed:
-	if (!s_new)
-		blkdev_put(sd.bdev, fs_type);
 	return ERR_PTR(err);
 }
 
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 1a02072b6b0e..5fffddea554f 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -569,9 +569,9 @@ static void init_once(void *foo)
 }
 
 /*
- * put_ntfs - Noinline to reduce binary size.
+ * Noinline to reduce binary size.
  */
-static noinline void put_ntfs(struct ntfs_sb_info *sbi)
+static noinline void ntfs3_free_sbi(struct ntfs_sb_info *sbi)
 {
 	kfree(sbi->new_rec);
 	kvfree(ntfs_put_shared(sbi->upcase));
@@ -625,12 +625,6 @@ static void ntfs_put_super(struct super_block *sb)
 
 	/* Mark rw ntfs as clear, if possible. */
 	ntfs_set_state(sbi, NTFS_DIRTY_CLEAR);
-
-	put_mount_options(sbi->options);
-	put_ntfs(sbi);
-	sb->s_fs_info = NULL;
-
-	sync_blockdev(sb->s_bdev);
 }
 
 static int ntfs_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -1564,15 +1558,7 @@ load_root:
 put_inode_out:
 	iput(inode);
 out:
-	/*
-	 * Free resources here.
-	 * ntfs_fs_free will be called with fc->s_fs_info = NULL
-	 */
-	put_mount_options(sbi->options);
-	put_ntfs(sbi);
-	sb->s_fs_info = NULL;
 	kfree(boot2);
-
 	return err;
 }
 
@@ -1659,7 +1645,7 @@ static void ntfs_fs_free(struct fs_context *fc)
 	struct ntfs_sb_info *sbi = fc->s_fs_info;
 
 	if (sbi)
-		put_ntfs(sbi);
+		ntfs3_free_sbi(sbi);
 
 	if (opts)
 		put_mount_options(opts);
@@ -1728,13 +1714,24 @@ free_opts:
 	return -ENOMEM;
 }
 
+static void ntfs3_kill_sb(struct super_block *sb)
+{
+	struct ntfs_sb_info *sbi = sb->s_fs_info;
+
+	kill_block_super(sb);
+
+	if (sbi->options)
+		put_mount_options(sbi->options);
+	ntfs3_free_sbi(sbi);
+}
+
 // clang-format off
 static struct file_system_type ntfs_fs_type = {
 	.owner			= THIS_MODULE,
 	.name			= "ntfs3",
 	.init_fs_context	= ntfs_init_fs_context,
 	.parameters		= ntfs_fs_parameters,
-	.kill_sb		= kill_block_super,
+	.kill_sb		= ntfs3_kill_sb,
 	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
 };
 // clang-format on
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 25d8072ccfce..c19c730c26e2 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -557,7 +557,7 @@ static void ocfs2_abort_trigger(struct jbd2_buffer_trigger_type *triggers,
 	     (unsigned long)bh,
 	     (unsigned long long)bh->b_blocknr);
 
-	ocfs2_error(bh->b_bdev->bd_super,
+	ocfs2_error(bh->b_assoc_map->host->i_sb,
 		    "JBD2 has aborted our journal, ocfs2 cannot continue\n");
 }
 
@@ -780,14 +780,14 @@ void ocfs2_journal_dirty(handle_t *handle, struct buffer_head *bh)
 		mlog_errno(status);
 		if (!is_handle_aborted(handle)) {
 			journal_t *journal = handle->h_transaction->t_journal;
-			struct super_block *sb = bh->b_bdev->bd_super;