Don't assume we have legacy PICs (i.e. 8259A in cascade) at the legacy

I/O port addresses. Even if we do, this is hardly the place to mask
interrupts. It's not clear that this was at all needed. The code came
with CVS revision 1.2 of nexus.c when interrupt support was first added.
What is known is that ia64 has always been designed around the IOSAPIC,
and that doing I/O like this prevents Altix from booting.
This commit is contained in:
Marcel Moolenaar 2012-05-04 23:16:29 +00:00
parent 93fba01290
commit a48b6a8585

View File

@ -65,9 +65,6 @@
#include <dev/acpica/acpivar.h>
#include <isa/isareg.h>
#include <sys/rtprio.h>
#include "clock_if.h"
static MALLOC_DEFINE(M_NEXUSDEV, "nexusdev", "Nexus device");
@ -191,12 +188,6 @@ static int
nexus_attach(device_t dev)
{
/*
* Mask the legacy PICs - we will use the I/O SAPIC for interrupt.
*/
outb(IO_ICU1+1, 0xff);
outb(IO_ICU2+1, 0xff);
if (acpi_identify() == 0)
BUS_ADD_CHILD(dev, 10, "acpi", 0);
clock_register(dev, 1000);