[RFC PATCH 1/7] block: Support creating a struct file from a block device

[Demi Marie Obenour <demi@invisiblethingslab.com>]

The newly added blkdev_get_file() function allows kernel code to create
a struct file for any block device.  The main use-case is for the
struct file to be exposed to userspace as a file descriptor.  A future
patch will modify the DM_DEV_CREATE_CREATE ioctl to allow userspace to
get a file descriptor to the newly created block device, avoiding nasty
race conditions.

Signed-off-by: Demi Marie Obenour <demi@invisiblethingslab.com>
---
 block/bdev.c           | 77 +++++++++++++++++++++++++++++++++++-------
 include/linux/blkdev.h |  5 +++
 2 files changed, 70 insertions(+), 12 deletions(-)

diff --git a/block/bdev.c b/block/bdev.c
index edc110d90df4041e7d337976951bd0d17525f1f7..09cb5ef900ca9ad5b21250bb63e64cc2a79f9289 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -459,10 +459,33 @@ static struct file_system_type bd_type = {
 struct super_block *blockdev_superblock __read_mostly;
 EXPORT_SYMBOL_GPL(blockdev_superblock);
 
+static struct vfsmount *bd_mnt __read_mostly;
+
+struct file *
+blkdev_get_file(struct block_device *bdev, fmode_t flags, void *holder)
+{
+	struct inode *inode;
+	struct file *filp;
+	int ret;
+
+	ret = blkdev_do_open(bdev, flags, holder);
+	if (ret)
+		return ERR_PTR(ret);
+	inode = bdev->bd_inode;
+	filp = alloc_file_pseudo(inode, bd_mnt, "[block]", flags | O_CLOEXEC, &def_blk_fops);
+	if (IS_ERR(filp)) {
+		blkdev_put(bdev, flags);
+	} else {
+		filp->f_mapping = inode->i_mapping;
+		filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
+	}
+	return filp;
+}
+EXPORT_SYMBOL(blkdev_get_file);
+
 void __init bdev_cache_init(void)
 {
 	int err;
-	static struct vfsmount *bd_mnt;
 
 	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
 			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
@@ -775,7 +798,7 @@ void blkdev_put_no_open(struct block_device *bdev)
  *
  * Use this interface ONLY if you really do not have anything better - i.e. when
  * you are behind a truly sucky interface and all you are given is a device
- * number.  Everything else should use blkdev_get_by_path().
+ * number.  Everything else should use blkdev_get_by_path() or blkdev_do_open().
  *
  * CONTEXT:
  * Might sleep.
@@ -785,9 +808,7 @@ void blkdev_put_no_open(struct block_device *bdev)
  */
 struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 {
-	bool unblock_events = true;
 	struct block_device *bdev;
-	struct gendisk *disk;
 	int ret;
 
 	ret = devcgroup_check_permission(DEVCG_DEV_BLOCK,
@@ -800,18 +821,52 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 	bdev = blkdev_get_no_open(dev);
 	if (!bdev)
 		return ERR_PTR(-ENXIO);
-	disk = bdev->bd_disk;
+
+	ret = blkdev_do_open(bdev, mode, holder);
+	if (ret) {
+		blkdev_put_no_open(bdev);
+		return ERR_PTR(ret);
+	}
+
+	return bdev;
+}
+EXPORT_SYMBOL(blkdev_get_by_dev);
+
+/**
+ * blkdev_do_open - open a block device by device pointer
+ * @bdev: pointer to the device to open
+ * @mode: FMODE_* mask
+ * @holder: exclusive holder identifier
+ *
+ * Open the block device pointed to by @bdev. If @mode includes
+ * %FMODE_EXCL, the block device is opened with exclusive access.  Specifying
+ * %FMODE_EXCL with a %NULL @holder is invalid.  Exclusive opens may nest for
+ * the same @holder.
+ *
+ * Unlike blkdev_get_by_dev() and bldev_get_by_path(), this function does not
+ * do any permission checks.  The most common use-case is where the device
+ * was freshly created by userspace.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * Reference 0 on success, -errno on failure.
+ */
+int blkdev_do_open(struct block_device *bdev, fmode_t mode, void *holder) {
+	struct gendisk *disk = bdev->bd_disk;
+	int ret = -ENXIO;
+	bool unblock_events = true;
 
 	if (mode & FMODE_EXCL) {
 		ret = bd_prepare_to_claim(bdev, holder);
 		if (ret)
-			goto put_blkdev;
+			return ret;
 	}
 
 	disk_block_events(disk);
 
 	mutex_lock(&disk->open_mutex);
-	ret = -ENXIO;
 	if (!disk_live(disk))
 		goto abort_claiming;
 	if (!try_module_get(disk->fops->owner))
@@ -842,7 +897,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 
 	if (unblock_events)
 		disk_unblock_events(disk);
-	return bdev;
+	return 0;
 put_module:
 	module_put(disk->fops->owner);
 abort_claiming:
@@ -850,11 +905,9 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 		bd_abort_claiming(bdev, holder);
 	mutex_unlock(&disk->open_mutex);
 	disk_unblock_events(disk);
-put_blkdev:
-	blkdev_put_no_open(bdev);
-	return ERR_PTR(ret);
+	return ret;
 }
-EXPORT_SYMBOL(blkdev_get_by_dev);
+EXPORT_SYMBOL(blkdev_do_open);
 
 /**
  * blkdev_get_by_path - open a block device by name
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 43d4e073b1115e4628a001081fbf08b296d342df..04635cb5ee29d22394a34c65eb34bea4e7847d8d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -325,6 +325,11 @@ typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
 
 void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model);
 
+struct file *
+blkdev_get_file(struct block_device *bdev, fmode_t flags, void *holder);
+
+int blkdev_do_open(struct block_device *bdev, fmode_t flags, void *holder);
+
 #ifdef CONFIG_BLK_DEV_ZONED
 
 #define BLK_ALL_ZONES  ((unsigned int)-1)
-- 
Sincerely,
Demi Marie Obenour (she/her/hers)
Invisible Things Lab