Re: [XenPPC] [pushed][ppc] process all interrupts that may be in the PIC

[Hollis Blanchard <hollisb@xxxxxxxxxx>]

On Wednesday 29 March 2006 11:34, jimix@xxxxxxxxxxxxxx wrote:
> changeset:   9665:adf9242cac67
> user:        jimix@xxxxxxxxxxxxxxxxxxxxx
> date:        Wed Mar 29 12:31:15 2006 -0500
> summary:     [ppc] process all interrupts that may be in the PIC
> 
> diff -r 7c52c6507ea3 -r adf9242cac67 xen/arch/ppc/external.c
> --- a/xen/arch/ppc/external.c Wed Mar 29 12:28:58 2006 -0500
> +++ b/xen/arch/ppc/external.c Wed Mar 29 12:31:15 2006 -0500
> @@ -75,13 +75,22 @@ void do_external(struct cpu_user_regs *r
>  {
>      int vec;
>  
> -    local_irq_disable();
> -    vec = mpic_get_one_irq(mpic, regs);
> -
> -    DBG("EE:0x%lx isrc: %d\n", regs->msr, vec);
> -    if (vec != -1) {
> -        regs->entry_vector = vec;
> -        do_IRQ(regs);
> +    BUG_ON(!(regs->msr & MSR_EE));
> +    BUG_ON(mfmsr() & MSR_EE);
> +
> +    for (;;) {
> +        vec = mpic_get_one_irq(mpic, regs);
> +
> +        if (vec != -1) {
> +            DBG("EE:0x%lx isrc: %d\n", regs->msr, vec);
> +            regs->entry_vector = vec;
> +            do_IRQ(regs);
> +
> +            BUG_ON(mfmsr() & MSR_EE);
> +
> +            continue;
> +        }
> +        break;
>      }
>  }

Linux used to loop until there were no more interrupts pending, but it moved 
away from that behavior. Anton explained there were two reasons for that:
1) statistically speaking, there is almost never more than one interrupt 
pendings, and
2) the cost of an MMIO to find out if there is another interrupt exceeds the 
cost of taking another EE exception

Accordingly, I don't like this patch.

-- 
Hollis Blanchard
IBM Linux Technology Center

_______________________________________________
Xen-ppc-devel mailing list
Xen-ppc-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ppc-devel