Re: [PATCH] irqchip: gic: Allow interrupt level to be set for PPIs.

[Russell King - ARM Linux <linux@arm.linux.org.uk>]

On Mon, Dec 01, 2014 at 10:46:13AM +0000, Liviu Dudau wrote:
> On Mon, Dec 01, 2014 at 10:41:45AM +0000, Russell King - ARM Linux wrote:
> > On Fri, Nov 28, 2014 at 05:55:40PM +0000, Liviu Dudau wrote:
> > > +	/*
> > > +	 * PPIs are optionally configurable, but we cannot distinguish
> > > +	 * between high and low, nor falling and rising. Change the
> > > +	 * type so that it passes the next check.
> > 
> > This comment could do with a /lot/ of improvement.  It sounds like the
> > only reason this code exists is to bypass the check.  If that's all
> > that's being done, there's better ways to code it.
> 
> Hi Russell,
> 
> You are right, all I want to do is bypass the next check because *if*
> the PPIs can be configured, then any combination is valid (edge 
> raising/falling, level low/high). In real systems, PPIs tend to be
> configured with active level low. That falls the existing check.

 "fails" :)

If all you want to do is to bypass the following check, what's wrong
with actually doing that:

-	if (type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING)
+	if (gicirq >= 32 && type != IRQ_TYPE_LEVEL_HIGH &&
+	    type != IRQ_TYPE_EDGE_RISING)
		return -EINVAL;

-- 
FTTC broadband for 0.8mile line: currently at 9.5Mbps down 400kbps up
according to speedtest.net.