On 30/10/2018 13:21, Alex Bennée wrote: > > Paolo Bonzini <pbonz...@redhat.com> writes: > >> This is a race that can happen when migrating TCG guests under load. >> It was introduced by the change to run vCPUs outside the big QEMU >> lock. > > Did this ever get re-spun?
No, the issue is that *without MTTCG* all work items must come from the same list, otherwise you get a deadlock. However the cleanup part of the series was applied. Paolo
