Generic IOMMU pooled allocator

[Benjamin Herrenschmidt]

On Mon, 2015-03-23 at 21:44 -0400, David Miller wrote:
> From: Benjamin Herrenschmidt <benh at kernel.crashing.org>
> Date: Tue, 24 Mar 2015 09:21:05 +1100
> 
> > Dave, what's your feeling there ? Does anybody around still have
> > some HW that we can test with ?
> 
> I don't see what the actual problem is.
> 
> Even if you use multiple pools, which we should for scalability on
> sun4u too, just do the flush when allocation in _any_ pool wraps
> around.
> 
> That's still better than not doing the optimization at all.

I agree, I wasn't sure it was good enough for you, so was just putting
other options on the table.

> That is always going to be correct, and you can use a separate
> spinlock to make sure only one thread of control does the full
> IOMMU flush at a time.

That would have to be done inside the of the flush callback but I don't
see a big issue there.

For the large pool, we don't keep a hint so we don't know it's wrapped,
in fact we purposefully don't use a hint to limit fragmentation on it,
but then, it should be used rarely enough that flushing always is, I
suspect, a good option.

Cheers,
Ben.