> > Move the BUG_ON()/RB_EMPTY_NODE() check under unlink_va() > > function, it means if an empty node gets freed it is a BUG > > thus is considered as faulty behaviour. > > Can we switch it to a WARN_ON(). We are trying to remove all BUG_ON()s. > If a user wants to crash on warning, there's a sysctl for that. But > crashing the system can make it hard to debug. Especially if it is hit > by someone without a serial console, and the machine just hangs in X. > That is very annoying. > > With a WARN_ON, you at least get a chance to see the crash dump. Yes we can. Even though it is considered as faulty behavior it is not a good reason to trigger a BUG. I will fix that. Thank you! -- Vlad Rezki
