fs,block: yield devices early

Currently a device is only really released once the umount returns to
userspace due to how file closing works. That ultimately could cause
an old umount assumption to be violated that concurrent umount and mount
don't fail. So an exclusively held device with a temporary holder should
be yielded before the filesystem is gone. Add a helper that allows
callers to do that. This also allows us to remove the two holder ops
that Linus wasn't excited about.

Link: https://lore.kernel.org/r/20240326-vfs-bdev-end_holder-v1-1-20af85202918@kernel.org
Fixes: f3a608827d1f ("bdev: open block device as files") # mainline only
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 56 insertions, 8 deletions

diff --git a/block/bdev.c b/block/bdev.c
index a1946a902df3..b8e32d933a63 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -583,9 +583,6 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder,
 	mutex_unlock(&bdev->bd_holder_lock);
 	bd_clear_claiming(whole, holder);
 	mutex_unlock(&bdev_lock);
-
-	if (hops && hops->get_holder)
-		hops->get_holder(holder);
 }
 
 /**
@@ -608,7 +605,6 @@ EXPORT_SYMBOL(bd_abort_claiming);
 static void bd_end_claim(struct block_device *bdev, void *holder)
 {
 	struct block_device *whole = bdev_whole(bdev);
-	const struct blk_holder_ops *hops = bdev->bd_holder_ops;
 	bool unblock = false;
 
 	/*
@@ -631,9 +627,6 @@ static void bd_end_claim(struct block_device *bdev, void *holder)
 		whole->bd_holder = NULL;
 	mutex_unlock(&bdev_lock);
 
-	if (hops && hops->put_holder)
-		hops->put_holder(holder);
-
 	/*
 	 * If this was the last claim, remove holder link and unblock evpoll if
 	 * it was a write holder.
@@ -813,6 +806,11 @@ static void bdev_claim_write_access(struct block_device *bdev, blk_mode_t mode)
 		bdev->bd_writers++;
 }
 
+static inline bool bdev_unclaimed(const struct file *bdev_file)
+{
+	return bdev_file->private_data == BDEV_I(bdev_file->f_mapping->host);
+}
+
 static void bdev_yield_write_access(struct file *bdev_file)
 {
 	struct block_device *bdev;
@@ -820,6 +818,9 @@ static void bdev_yield_write_access(struct file *bdev_file)
 	if (bdev_allow_write_mounted)
 		return;
 
+	if (bdev_unclaimed(bdev_file))
+		return;
+
 	bdev = file_bdev(bdev_file);
 
 	if (bdev_file->f_mode & FMODE_WRITE_RESTRICTED)
@@ -1012,6 +1013,20 @@ struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode,
 }
 EXPORT_SYMBOL(bdev_file_open_by_path);
 
+static inline void bd_yield_claim(struct file *bdev_file)
+{
+	struct block_device *bdev = file_bdev(bdev_file);
+	void *holder = bdev_file->private_data;
+
+	lockdep_assert_held(&bdev->bd_disk->open_mutex);
+
+	if (WARN_ON_ONCE(IS_ERR_OR_NULL(holder)))
+		return;
+
+	if (!bdev_unclaimed(bdev_file))
+		bd_end_claim(bdev, holder);
+}
+
 void bdev_release(struct file *bdev_file)
 {
 	struct block_device *bdev = file_bdev(bdev_file);
@@ -1036,7 +1051,7 @@ void bdev_release(struct file *bdev_file)
 	bdev_yield_write_access(bdev_file);
 
 	if (holder)
-		bd_end_claim(bdev, holder);
+		bd_yield_claim(bdev_file);
 
 	/*
 	 * Trigger event checking and tell drivers to flush MEDIA_CHANGE
@@ -1057,6 +1072,39 @@ put_no_open:
 }
 
 /**
+ * bdev_fput - yield claim to the block device and put the file
+ * @bdev_file: open block device
+ *
+ * Yield claim on the block device and put the file. Ensure that the
+ * block device can be reclaimed before the file is closed which is a
+ * deferred operation.
+ */
+void bdev_fput(struct file *bdev_file)
+{
+	if (WARN_ON_ONCE(bdev_file->f_op != &def_blk_fops))
+		return;
+
+	if (bdev_file->private_data) {
+		struct block_device *bdev = file_bdev(bdev_file);
+		struct gendisk *disk = bdev->bd_disk;
+
+		mutex_lock(&disk->open_mutex);
+		bdev_yield_write_access(bdev_file);
+		bd_yield_claim(bdev_file);
+		/*
+		 * Tell release we already gave up our hold on the
+		 * device and if write restrictions are available that
+		 * we already gave up write access to the device.
+		 */
+		bdev_file->private_data = BDEV_I(bdev_file->f_mapping->host);
+		mutex_unlock(&disk->open_mutex);
+	}
+
+	fput(bdev_file);
+}
+EXPORT_SYMBOL(bdev_fput);
+
+/**
  * lookup_bdev() - Look up a struct block_device by name.
  * @pathname: Name of the block device in the filesystem.
  * @dev: Pointer to the block device's dev_t, if found.