Messages in this thread | | | Date | Tue, 14 Mar 2017 18:43:45 +0100 (CET) | From | Thomas Gleixner <> | Subject | Re: [PATCH] cpu/hotplug: Serialize callback invocations proper |
| |
On Tue, 14 Mar 2017, Bart Van Assche wrote: > On Tue, 2017-03-14 at 16:06 +0100, Sebastian Andrzej Siewior wrote: > > The setup/remove_state/instance() functions in the hotplug core code are > > serialized against concurrent CPU hotplug, but unfortunately not serialized > > against themself. > > > > As a consequence a concurrent invocation of these function results in > > corruption of the callback machinery because two instances try to invoke > > callbacks on remote cpus at the same time. This results in missing callback > > invocations and initiator threads waiting forever on the completion. > > > > The obvious solution to replace get_cpu_online() with cpu_hotplug_begin() > > is not possible because at least one callsite calls into these functions > > from a get_online_cpu() locked region. > > > > Extend the protection scope of the cpuhp_state_mutex from solely protecting > > the state arrays to cover the callback invocation machinery as well. > > > > Reported-by: Bart Van Assche <Bart.VanAssche@sandisk.com> > > Fixes: 5b7aa87e0482 ("cpu/hotplug: Implement setup/removal interface") > > Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> > > Tested-by: Bart Van Assche <Bart.VanAssche@sandisk.com> > > So this regression was introduced in kernel v4.6? Anyway, thanks for the patch!
And it's very timing sensitive ....
Thanks for trying to bisect this!
tglx
| |