[openib-general] mthca and DDR not hidden

[Hal Rosenstock]

On Sat, 2004-10-02 at 15:26, Michael S. Tsirkin wrote:
> I'd like to suggest that the mad layer could expose an allocator
> function that the user will call to grab the memory for the mad.
> This function would return the memory pointer and the appropriate
> lkey value.

Wouldn't the triple of lkey, start address, and size need to be returned
?

> This would make it possible to change the implementation to have
> even multiple MRs if needed (for example for tavor you need
> two MRs to cover the whole 64 bit address space).

How can it be determined whether a second MR is needed ?

> On systems like the Apple's G5 where enabling memory for DMA
> consumes IOMMU resources, it may even be a good idea to
> implement this by keeping a pool of MADs and allocate from there.

There was a discussion about a MAD pool or even multiple pools before
the ib_mad API was agreed upon. It seemed that consensus at the time was
against this, although I think the consensus might have been 51 to 49 on
this.

-- Hal