Re: [RFC] page fault retry with NOPAGE_RETRY

[Benjamin Herrenschmidt]

On Thu, 2006-09-21 at 15:41 -0700, Andrew Morton wrote:
> On Fri, 22 Sep 2006 08:05:04 +1000
> Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx> wrote:
> 
> > > So I think there's a nasty DoS here if we permit infinite retries.  But
> > > it's not just that - there might be other situations under really heavy
> > > memory pressure where livelocks like this can occur.  It's just a general
> > > robustness-of-implementation issue.
> > 
> > Got it. Now, changing args to no_page() will be a pretty big task....
> > 
> 
> Not as big as removing the pt_regs arg from every interrupt handler ;)

Which is a change I'm not 100% convinced about btw ... I remember
actually using that in a few occasions... mostly for debugging though.
Bah, anyway, I suppose we can always have a per-cpu global with the last
irq pt_regs pointer if really needed for debug.
 
> But pretty mechanical.  Problem is, I don't think we have our mechanic.

Yup, we would need to decide what to put in there....

Ben.


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/