Re: mutex vs. local irqs (Was: 2.6.18 -mm merge plans)

Ingo Molnar writes:

a better solution would be to install boot-time IRQ vectors that just do
nothing but return. They dont mask, they dont ACK nor EOI - they just
return.

How would that help? We'd just end up taking the interrupt over and
over again. We have to either poke the PIC to tell it to shut up
somehow (which we can't do before ioremap is available) or arrange for
interrupts to be disabled after the return (which means that
might_sleep() will scream at us).

Paul.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Relevant Pages

  • Re: mutex vs. local irqs (Was: 2.6.18 -mm merge plans)
    ... They dont mask, they dont ACK nor EOI - they just ... The only thing that could break this is a screaming interrupt, ... A screaming level interrupt will lockup the machine at least on some ...
    (Linux-Kernel)
  • Re: mutex vs. local irqs (Was: 2.6.18 -mm merge plans)
    ... They dont mask, they dont ACK nor EOI - they just ... all archs interrupt handling to make the situation safe vs. mutexes... ... Only those archs that want to delay interrupt initialization and they at ...
    (Linux-Kernel)
  • Re: mutex vs. local irqs (Was: 2.6.18 -mm merge plans)
    ... They dont mask, they dont ACK nor EOI - they just ... all archs interrupt handling to make the situation safe vs. mutexes... ... Only those archs that want to delay interrupt initialization and they at ...
    (Linux-Kernel)