Re: [RFC PATCH 1/3] content: Add VIRTIO_F_SWIOTLB to negotiate use of SWIOTLB bounce buffers

[Christoph Hellwig <hch@infradead.org>]

On Thu, Apr 03, 2025 at 11:44:40PM -0700, Christoph Hellwig wrote:
> That's what NVMe currently does in it's second attempt to get things
> wrong.  It mostly works for the current use cases, but there might
> actually not be a single canonical address where it is mapped.  This
> was mostly theoretical, but with SVM and especially SIOV it is becoming
> a real thing now.
> 
> In the worst case you might have to limit yourself to one address space
> per request.  Or have a bitmap which buffer in the request uses which
> address space.

Also with unordered I/O in the newer PCIe specs we might need another
such address space bit to force use of that for certain ranges, although
system use cases for UIO are still not finalized.