[PATCH] block: fix bd_holder_dir kobject_create_and_add() error handling

Commit 83cbce957446 ("block: add error handling for device_add_disk /
add_disk") added error handling to device_add_disk(), however the goto
label for the bd_holder_dir kobject_create_and_add() failure did not set
the return value correctly, and so we can end up in a situation where
kobject_create_and_add() fails but we report success.

Fixes: 83cbce957446 ("block: add error handling for device_add_disk / add_disk")
Reported-by: Wu Bo <redacted>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 block/genhd.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/block/genhd.c b/block/genhd.c
index 2263f7862241..c5392cc24d37 100644
--- a/block/genhd.c
+++ b/block/genhd.c

@@ -472,8 +472,10 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 
 	disk->part0->bd_holder_dir =
 		kobject_create_and_add("holders", &ddev->kobj);
-	if (!disk->part0->bd_holder_dir)
+	if (!disk->part0->bd_holder_dir) {
+		ret = -ENOMEM;
 		goto out_del_integrity;
+	}
 	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
 	if (!disk->slave_dir) {
 		ret = -ENOMEM;

-- 
2.33.0

On 11/4/21 1:29 PM, Luis Chamberlain wrote:

Commit 83cbce957446 ("block: add error handling for device_add_disk /
add_disk") added error handling to device_add_disk(), however the goto
label for the bd_holder_dir kobject_create_and_add() failure did not set
the return value correctly, and so we can end up in a situation where
kobject_create_and_add() fails but we report success.

I'm just going to fold this one in, as it's top-of-tree.

-- 
Jens Axboe

On Thu, Nov 04, 2021 at 01:30:29PM -0600, Jens Axboe wrote:

On 11/4/21 1:29 PM, Luis Chamberlain wrote:

quoted

Commit 83cbce957446 ("block: add error handling for device_add_disk /
add_disk") added error handling to device_add_disk(), however the goto
label for the bd_holder_dir kobject_create_and_add() failure did not set
the return value correctly, and so we can end up in a situation where
kobject_create_and_add() fails but we report success.

I'm just going to fold this one in, as it's top-of-tree.

Makes sense.

  Luis