Re: [PATCH RFC v1 4/7] swiotlb: to implement io_tlb_high_mem

[Christoph Hellwig]

On Fri, Jun 10, 2022 at 02:56:08PM -0700, Dongli Zhang wrote:
> Since this patch file has 200+ lines, would you please help clarify what does
> 'this' indicate?

This indicates that any choice of a different swiotlb pools needs to
be hidden inside of ѕwiotlb.  The dma mapping API already provides
swiotlb the addressability requirement for the device.  Similarly we
already have a SWIOTLB_ANY flag that switches to a 64-bit buffer
by default, which we can change to, or replace with a flag that
allocates an additional buffer that is not addressing limited.