Re: [PATCH] i386/x86-64: Fix timer SMP bootup race

[Andi Kleen <ak@suse.de>]

On Sun, Jan 16, 2005 at 03:20:47PM +1100, Rusty Russell wrote:
> On Sat, 2005-01-15 at 08:59 +0100, Andi Kleen wrote: 
> > I think my patch is better. It at least keeps all the 
> > baggage out of the normal run paths. Doing this check at each timer interrupt
> > doesn't make much sense.
> 
> It doesn't penalize the architectures which do the right thing already.
> If this weren't i386 we were talking about...
> 
> But adding a bizarro "pre-prepare" notifier verged on nonsensical 8(.  I

I don't see the big issue. Preparse is just not as early as you thought.


> prefer an explicit "init_timers_early()" call as a workaround; I'll code
> that up and test tomorrow, when I'm back in the office with an SMP box
> to test.
> 
> I'm also not clear on why we need to enable interrupts around
> calibrate_delay() on secondary processors, but I'll try that too and
> find out 8)

Because you cannot calibrate the timer without a timer tick.

Even if you changed that it wouldn't help because the race can
as well happen in the idle loop on the secondaries.

-Andi