Messages in this thread | | | Subject | Re: [rfc] "fair" rw spinlocks | From | Peter Zijlstra <> | Date | Mon, 07 Dec 2009 21:38:40 +0100 |
| |
On Mon, 2009-12-07 at 19:32 +0100, Oleg Nesterov wrote: > On 12/05, Eric W. Biederman wrote: > > > > Atomically sending signal to every member of a process group, is the > > big fly in the ointment I am aware of. Last time I looked I could > > not see how to convert it rcu. > > I am not sure, but iirc we can do this lockless (under rcu_lock). > We need to modify pid_link to use list_entry and attach_pid() should > add the new task to the end. Of course we need more changes, but > (again iirc) this is not too hard. > > > This is a pain because we occasionally signal a process group from > > interrupt context. > > Only send_sigio/etc does so, right? > > > I didn't read the previous discussion yet (will try tomorrow), sorry > if I am off-topic. But I think the nastiest problem with tasklist > is that it protects parent/child relationship. We need per-process > lock, but first we should change ptrace to avoid this lock somehow. > (this is one of the goals of ptrace-utrace, but not "immediate").
Didn't Thomas and you also come up with a scheme to push most signal processing into task context?
| |