On Mon, Apr 15, 2019 at 04:55:25PM +0100, Chris Wilson wrote:
> Quoting Ville Syrjala (2019-04-15 16:49:00)
> > From: Ville Syrjälä <ville.syrjala@xxxxxxxxxxxxxxx>
> >
> > I never finished the irq ack+handler split for ilk+. Let's try to do
> > that now since people seem keen on cleaning up stuff in there. One
> > thing I didn't dare touch is gen11_gt_irq_handler() as that thing
> > looks a bit nuts.
> >
> > A bit of a downside:
> > Total: Before=39303, After=40393, chg +2.77%
> >
> > If we changed all _ack()s to raw_reg_{read,write} we'd get:
> > Total: Before=39303, After=39258, chg -0.11%
> > but that ignores the "hang when accessing registers in the
> > same cacheline" fail. So would need a bit more thought.
>
> Otoh, all irq registers should be guarded by either the
> dev_priv->irq_lock spinlock or be single threaded by the nature of
> interrupt dispatch (handwavy). So we might be able to argue that for the
> limited set of registers accessed here, we should be safe.
Hmm. Yes, I suppose you are correct. The only thing that might bite us
is some unguarded READ_FW()s etc. I guess we can hope those don't exist.
At least I can't immediately spot anything that looks dangerous.
--
Ville Syrjälä
Intel
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
