Re: [Intel IOMMU][patch 8/8] Preserve some Virtual Address when devices cannot address entire range.

[Andi Kleen]

On Wednesday 25 April 2007 03:12:51 H. Peter Anvin wrote:

> You can probably find almost any possible bitmask if you look long 
> enough.  Hardware vendors are notorious for this kind of "optimizations".

The nice thing is if this was solved in the IOMMU code then we could drop
(or not initialize) GFP_DMA on systems with that hardware. I guess GFP_DMA32 
would still need to stay for the graphics devices though.

Not sure how much difference it would make though, but at least Christoph Lameter
seems to think it would.

-Andi
-
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/