Messages in this thread | | | Subject | Re: [PATCH] intel-iommu: Obey coherent_dma_mask for alloc_coherent on passthrough | From | Alex Williamson <> | Date | Thu, 05 Nov 2009 21:09:08 -0700 |
| |
On Fri, 2009-11-06 at 12:34 +0900, FUJITA Tomonori wrote: > On Thu, 05 Nov 2009 20:19:52 -0700 > Alex Williamson <alex.williamson@hp.com> wrote: > > On Fri, 2009-11-06 at 11:41 +0900, FUJITA Tomonori wrote: > > > > > This is fine for 2.6.32 but we'll cleanly fix this by using > > > swiotlb_dma_ops later, right? > > > > I'm open to suggestions. I don't really understand why we dropped > > swiotlb for passthrough mode in 2.6.32 to start with. It seems like we > > now have a couple corner cases where we have to either hope for the best > > or effectively ignore the request to use passthrough. Thanks, > > I think that the cleanest solution is setting up swiotlb_dma_ops for > passthrough devices (and devices not behind pci, etc). Calgary IOMMU > does the same for years.
intel-iommu was using swiotlb for the global dma_ops when in passthrough mode until 19943b0e (2.6.31 and earlier). I would say the next step would be to use per device dma_ops so we can point passthrough devices to swiotlb, as you suggest, but that seems to work against part of what 19943b0e was trying to accomplish.
Alex
| |