On 21 November 2011 10:07, Alexander Graf <ag...@suse.de> wrote: > On 21.11.2011, at 10:59, Peter Maydell wrote: >> You can hit this bug even single-threaded or in system mode: >> it's just that aggressively multi-threaded user apps are the >> easiest way to trigger it. So I don't think we can ever use >> the tb-unlinking code safely. > > Not sure I understand. I thought it's a race between multiple >threads trying to chain/unchain TBs at the same time? How can > that happen in system or single-threaded mode?
It's a race between (a) a thread executing code and (b) any other thread or signal handler that calls cpu_exit(). So (b) can be the IO thread, or the linux-user host_signal_handler(). -- PMM