[PATCH 3.16 073/212] w1: don't leak refcount on slave attach failure in w1_attach_slave_device()

[Ben Hutchings]

3.16.44-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: "Maciej S. Szmigiero" <mail@xxxxxxxxxxxxxxxxxxxxx>

commit d2ce4ea1a0b0162e5d2d7e7942ab6f5cc2063d5a upstream.

Near the beginning of w1_attach_slave_device() we increment a w1 master
reference count.
Later, when we are going to exit this function without actually attaching
a slave device (due to failure of __w1_attach_slave_device()) we need to
decrement this reference count back.

Signed-off-by: Maciej S. Szmigiero <mail@xxxxxxxxxxxxxxxxxxxxx>
Fixes: 9fcbbac5ded489 ("w1: process w1 netlink commands in w1_process thread")
Cc: Evgeniy Polyakov <zbr@xxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
 drivers/w1/w1.c | 1 +
 1 file changed, 1 insertion(+)

--- a/drivers/w1/w1.c
+++ b/drivers/w1/w1.c
@@ -749,6 +749,7 @@ int w1_attach_slave_device(struct w1_mas
 		dev_err(&dev->dev, "%s: Attaching %s failed.\n", __func__,
 			 sl->name);
 		w1_family_put(sl->family);
+		atomic_dec(&sl->master->refcnt);
 		kfree(sl);
 		return err;
 	}