Messages in this thread | | | Date | Wed, 13 Jun 2012 20:56:18 +0200 (CEST) | From | Thomas Gleixner <> | Subject | Re: [RFC patch 2/5] smpboot: Provide infrastructure for percpu hotplug threads |
| |
On Wed, 13 Jun 2012, Paul E. McKenney wrote: > On Wed, Jun 13, 2012 at 11:00:54AM -0000, Thomas Gleixner wrote: > > So I am currently trying to apply this to RCU's per-CPU kthread. > I don't believe that I need to mess with RCU's per-rcu_node kthread > because it can just have its affinity adjusted when the first CPU > onlines and the last CPU offlines for the corresponding rcu_node. > > One question below about the order of parking. > > Also, I have not yet figured out how this avoids a parked thread waking > up while the CPU is offline, but I am probably still missing something.
If it's just a spurious wakeup then it goes back to sleep right away as nothing cleared the park bit.
If something calls unpark(), then it's toast. I should put a warning into the code somewhere to catch that case.
> > +void smpboot_park_threads(unsigned int cpu) > > +{ > > + struct smp_hotplug_thread *cur; > > + > > + mutex_lock(&smpboot_threads_lock); > > + list_for_each_entry(cur, &hotplug_threads, list) > > Shouldn't this be list_for_each_entry_reverse()? Yes, the notifiers > still run in the same order for both online and offline, but all uses > of smpboot_park_threads() would be new, so should be OK with the > proper ordering, right?
Duh, yes
Thanks,
tglx
| |