On Fri, Sep 23, 2022 at 11:42:39AM -0300, Jason Gunthorpe wrote: > On Fri, Sep 23, 2022 at 07:18:42AM -0700, Dave Hansen wrote: > > On 9/23/22 04:46, Jason Gunthorpe wrote: > > > On Fri, Sep 23, 2022 at 12:38:26PM +0300, Kirill A. Shutemov wrote: > > >>> So I would assume an untagged pointer should just be fine for the IOMMU > > >>> to walk. IOMMU currently wants canonical addresses for VA. > > >> Right. But it means that LAM compatibility can be block on two layers: > > >> IOMMU and device. IOMMU is not the only HW entity that has to be aware of > > >> tagged pointers. > > > Why does a device need to care about this? What do you imagine a > > > device doing with it? > > > > > > The userspace should program the device with the tagged address, the > > > device should present the tagged address on the bus, the IOMMU should > > > translate the tagged address the same as the CPU by ignoring the upper > > > bits. > > > > Is this how *every* access works? Every single device access to the > > address space goes through the IOMMU? > > > > I thought devices also cached address translation responses from the > > IOMMU and stashed them in their own device-local TLB. > > Ah, you are worried about invalidation. > > There is an optional PCI feature called ATS that is this caching, and > it is mandatory if the IOMMU will use the CPU page table. > > In ATS the invalidation is triggered by the iommu driver in a device > agnostic way. > > The PCI spec has no provision to invalidate with a mask, only linear > chunks of address space can be invalidated. This part is currently being worked on in the PCI SIG. Once we have something like this we can teach which portion of the VA to mask. Ofcourse this will take a while before PCI sig standardizes it and we will start seeing devices that support them. BTW, this is a problem for all vendors that support SVM and LAM/MTT. I see ARM in the SMMU 3.1 doc states it doesn't support MTT at the moment, just like the Intel IOMMU. I hope the API we develop must work across all vendors.
