This patch switches usbhid_close() from flush_scheduled_work() to canceling
the outstanding work. This fixes a possible deadlock due to work taking
the mutex usbhid_close() holds. Lockdep reported the problem.
Signed-off-by: Oliver Neukum <oliver@neukum.org>
--
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
spin_lock_irq(&usbhid->lock);
if (!--hid->open) {
spin_unlock_irq(&usbhid->lock);
+ hid_cancel_delayed_stuff(usbhid);
usb_kill_urb(usbhid->urbin);
- flush_scheduled_work();
usbhid->intf->needs_remote_wakeup = 0;
} else {
spin_unlock_irq(&usbhid->lock);