Messages in this thread | | | Date | Wed, 28 Sep 2005 21:34:26 -0600 | From | Grant Grundler <> | Subject | Re: [PATCH] MSI interrupts: disallow when no LAPIC/IOAPIC support |
| |
On Tue, Sep 27, 2005 at 11:37:50PM +0100, Alan Cox wrote: > On Maw, 2005-09-27 at 17:26 -0400, Jeff Garzik wrote: > > Grant Grundler wrote: > > > I've no clue why folks thought it was better to ignore > > > the IO APIC on UP kernels. > > > > Hysterical raisins: the -majority- of the early uniprocessor systems > > that claimed IOAPIC support were broken. > > Not really broken in most cases, but since nobody was using the APIC > board makers didn't bother wiring for it.
ok. Any clue how PCI IRQs got routed/handled on those boxes? Did UP boards have an 8259 PIC and an IRQ line to the CPU? Could an 8529 PIC even co-exist with an IO APIC?
Or was it something more silly like BIOS mfgs had no version of Windows that could grok a IRQ routing table and thus no incentive to enable that feature?
thanks, grant - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |