Re: [PATCH] starfire reads irq before pci_enable_device.

[Alan Cox]

> It's amusing that a full receive copy is added without any concern, in
> the same discussion where zero-copy transmit is treated as a holy grail!

For non routing paths its virtually free because the DMA forced the lines
from cache anyway. Basically its a deficiency in the chipset. We don't support
chipsets with alignment rules well on cpus with alignment rules that clash

That shouldnt be a suprise