Re: can device drivers return non-ram via vm_ops->nopage?

[Linus Torvalds]

On Mon, 22 Mar 2004, David Woodhouse wrote:
> 
> You are assuming that dma_alloc_coherent() will always return memory of
> that second kind -- host-side RAM, not PCI-side. That hasn't previously
> been a requirement, and there are machines out there on which it makes a
> lot more sense for dma_alloc_coherent() to use some SRAM which happens
> to be hanging off the I/O bus than it does to use host RAM.

So? Those architectures can just allocate "struct page" entries for that 
memory too. 

There is a point where we should not care about idiotic architectures any 
more. We should care about what happens in 99% of all architectures, and 
the rest get to work around their _own_ quirks. We do not make the VM 
uglier for some insane "it can happen" case.

		Linus
-
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/