[RFC 7/7] iommu/core: split mapping to page sizes as supported by the hardware

[KyongHo Cho]

Hi Ohad,

On Wed, Sep 7, 2011 at 6:16 PM, Ohad Ben-Cohen <ohad at wizery.com> wrote:
> Hmm this sounds a bit like a red herring to me; optimization of the
:) I agree. sorry.

> map function is not the main subject here. Especially not when we're
> discussing mapping of large physically contiguous memory regions which
> do not happen too often.
>
I've got your point but I thought that it is really needed.

> Another advantage for migrating s5p_iommu_map() over to the subject
> patch, is that s5p_iommu_map() doesn't support super sections yet. To
> support it, you'd need to add more code (duplicate another while
> loop). But if you migrated to the subject patch, then you would only
> need to flip the 16MB bit when you advertise page size capabilities
> and then that's it; you're done.

I did not implement that.
16MB page is less practical in Linux because Linux kernel is unable
to allocated larger physically contiguous memory than 4MB by default.
But I also think that it is needed to support 16MB mapping for IO
virtualization someday
and it is just trivial job.

And you pointed correctly that s5p_iommu_map() has duplicate similar codes.

Actually, I think your idea is good and does not cause performance degradation.
But I wondered if it is really useful.

>
> The caller of iommu_map() doesn't say anything about alignments. It
> just gives it a memory region to map, and expect things to just work.
>
The caller of iommu_map() gives gfp_order that is the size of the physical
memory to map.
I thought that it also means alignment of the physical memory.
Isn't it?

Regards,
KyongHo