Messages in this thread |  | | | Date | Mon, 3 Oct 2011 09:13:28 -0400 | | From | Don Zickus <> | | Subject | Re: [V6][PATCH 4/6] x86, nmi: add in logic to handle multiple events and unknown NMIs |
| |
On Sun, Oct 02, 2011 at 12:07:16PM +0200, Avi Kivity wrote: > >Right. Avi, Jeremy what was your objection that needed this optimization > >in the first place? > > > > First, iterating over all NMI sources is going to be slow, and a lot > more so in a guest. This reduces the performance of perf.
I understand and agree. The only positive I can offer is most machines will most likely only have two NMI handlers registered: perf and arch_backtrace. So any slowness should be minimal. We might even be able to code up arch_backtrace to register its NMI handler when it is called to minimize the the number of NMI sources even more.
Cheers, Don
> > Second, I wanted to use NMIs as a way of waking up a vcpu sleeping > with interrupts disabled (in the context of Jeremy's paravirt > spinlock patches). Looks like we'll have to use paravirtualization > for that.
> > -- > error compiling committee.c: too many arguments to function >
|  |