Messages in this thread | | | Subject | Re: [PATCH] lglock: make lg_lock_global() actually lock globally | From | Peter Zijlstra <> | Date | Thu, 26 Aug 2010 13:49:00 +0200 |
| |
On Thu, 2010-08-26 at 13:45 +0200, Peter Zijlstra wrote: > On Thu, 2010-08-26 at 21:38 +1000, Nick Piggin wrote: > > I think for CPU plug, stop_machine is reasonable (especially > > considering it is required in unload, which means any frequent > > amount of cpu plug activity already will require stop_machine to > > run anyway). > > How is it required? > > Its currently implemented as such, and its sure a lot easier to do that > way, but I could imagine that unplugging a CPU could be done without it.
Not that reworking unplug to not use stop_machine is anywhere near my todo list, but it would be really nice to have ;-)
| |