On 21.11.2011, at 10:59, Peter Maydell wrote: > On 21 November 2011 09:55, Alexander Graf <ag...@suse.de> wrote: >> On 21.11.2011, at 09:54, Peter Maydell wrote: >>> I think I sent you my work-in-progress patch, didn't I? >> >> I know that we talked about it. But I can't find it. That doesn't >> mean that you didn't send it, but either way I'd really like to see >> your patch somewhere where it can be found by more people than just >> me. How about the bug report? :) > > Good idea -- I'll attach it there today. > >> There's also always the chance of doing tricks like I did in my patch >> tonight, so you could do the unlinking code in single-threaded >> applications and switch to the more expensive flag check in >> multi-threaded ones. > > 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? Alex