Re: 2.6.10-rc2-mm4

[Jes Sorensen]

>>>>> "Andrew" == Andrew Morton <akpm@xxxxxxxx> writes:

Andrew> Arjan van de Ven <arjan@xxxxxxxxxxxxx> wrote:
>> 
>> On Tue, 2004-11-30 at 09:50 -0800, Andrew Morton wrote:
>> >
>> http://www.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.10-rc2/2.6.10-rc2-mm4/
>> > 
>> > - Various fixes and cleanups
>> > 
>> > - A decent-sized x86_64 update.
>> > 
>> > - x86_64 supports a fourth VM zone: ZONE_DMA32.  This may affect
>> memory > reclaim, but shouldn't.
>> 
>> 
>> what is the purpose of such a zone ??

Andrew> For pages which have a physical address <4G.  I assume this
Andrew> was motivated by the lack of an IOMMU on ia32e?

If we really need such a special case, wouldn't it be about time we
introduced a mask based allocation API instead? There's hardware out
there with 31 bit and 40 bit restrictions.

Doing this solely for the sake of nvidia is certainly questionable.

Regards,
Jes
-
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/