block: simplify bdev/disk lookup in blkdev_get

To simplify block device lookup and a few other upcoming areas, make sure
that we always have a struct block_device available for each disk and
each partition, and only find existing block devices in bdget.  The only
downside of this is that each device and partition uses a little more
memory.  The upside will be that a lot of code can be simplified.

With that all we need to look up the block device is to lookup the inode
and do a few sanity checks on the gendisk, instead of the separate lookup
for the gendisk.  For blk-cgroup which wants to access a gendisk without
opening it, a new blkdev_{get,put}_no_open low-level interface is added
to replace the previous get_gendisk use.

Note that the change to look up block device directly instead of the two
step lookup using struct gendisk causes a subtile change in behavior:
accessing a non-existing partition on an existing block device can now
cause a call to request_module.  That call is harmless, and in practice
no recent system will access these nodes as they aren't created by udev
and static /dev/ setups are unusual.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 17 insertions, 12 deletions

diff --git a/block/partitions/core.c b/block/partitions/core.c
index a02e22411594..696bd9ff63c6 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -340,12 +340,11 @@ void delete_partition(struct hd_struct *part)
 	device_del(part_to_dev(part));
 
 	/*
-	 * Remove gendisk pointer from idr so that it cannot be looked up
-	 * while RCU period before freeing gendisk is running to prevent
-	 * use-after-free issues. Note that the device number stays
-	 * "in-use" until we really free the gendisk.
+	 * Remove the block device from the inode hash, so that it cannot be
+	 * looked up any more even when openers still hold references.
 	 */
-	blk_invalidate_devt(part_devt(part));
+	remove_inode_hash(part->bdev->bd_inode);
+
 	percpu_ref_kill(&part->ref);
 }
 
@@ -368,6 +367,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	dev_t devt = MKDEV(0, 0);
 	struct device *ddev = disk_to_dev(disk);
 	struct device *pdev;
+	struct block_device *bdev;
 	struct disk_part_tbl *ptbl;
 	const char *dname;
 	int err;
@@ -402,11 +402,15 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	if (!p)
 		return ERR_PTR(-EBUSY);
 
+	err = -ENOMEM;
 	p->dkstats = alloc_percpu(struct disk_stats);
-	if (!p->dkstats) {
-		err = -ENOMEM;
+	if (!p->dkstats)
 		goto out_free;
-	}
+
+	bdev = bdev_alloc(disk, partno);
+	if (!bdev)
+		goto out_free_stats;
+	p->bdev = bdev;
 
 	hd_sects_seq_init(p);
 	pdev = part_to_dev(p);
@@ -420,10 +424,8 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 		struct partition_meta_info *pinfo;
 
 		pinfo = kzalloc_node(sizeof(*pinfo), GFP_KERNEL, disk->node_id);
-		if (!pinfo) {
-			err = -ENOMEM;
-			goto out_free_stats;
-		}
+		if (!pinfo)
+			goto out_bdput;
 		memcpy(pinfo, info, sizeof(*info));
 		p->info = pinfo;
 	}
@@ -470,6 +472,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	}
 
 	/* everything is up and running, commence */
+	bdev_add(bdev, devt);
 	rcu_assign_pointer(ptbl->part[partno], p);
 
 	/* suppress uevent if the disk suppresses it */
@@ -479,6 +482,8 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 
 out_free_info:
 	kfree(p->info);
+out_bdput:
+	bdput(bdev);
 out_free_stats:
 	free_percpu(p->dkstats);
 out_free: