> From: Alex Williamson <alex.williamson@xxxxxxxxxx> > Sent: Wednesday, August 12, 2020 1:01 AM > > On Mon, 10 Aug 2020 07:32:24 +0000 > "Tian, Kevin" <kevin.tian@xxxxxxxxx> wrote: > > > > From: Jason Gunthorpe <jgg@xxxxxxxxxx> > > > Sent: Friday, August 7, 2020 8:20 PM > > > > > > On Wed, Aug 05, 2020 at 07:22:58PM -0600, Alex Williamson wrote: > > > > > > > If you see this as an abuse of the framework, then let's identify those > > > > specific issues and come up with a better approach. As we've discussed > > > > before, things like basic PCI config space emulation are acceptable > > > > overhead and low risk (imo) and some degree of register emulation is > > > > well within the territory of an mdev driver. > > > > > > What troubles me is that idxd already has a direct userspace interface > > > to its HW, and does userspace DMA. The purpose of this mdev is to > > > provide a second direct userspace interface that is a little different > > > and trivially plugs into the virtualization stack. > > > > No. Userspace DMA and subdevice passthrough (what mdev provides) > > are two distinct usages IMO (at least in idxd context). and this might > > be the main divergence between us, thus let me put more words here. > > If we could reach consensus in this matter, which direction to go > > would be clearer. > > > > First, a passthrough interface requires some unique requirements > > which are not commonly observed in an userspace DMA interface, e.g.: > > > > - Tracking DMA dirty pages for live migration; > > - A set of interfaces for using SVA inside guest; > > * PASID allocation/free (on some platforms); > > * bind/unbind guest mm/page table (nested translation); > > * invalidate IOMMU cache/iotlb for guest page table changes; > > * report page request from device to guest; > > * forward page response from guest to device; > > - Configuring irqbypass for posted interrupt; > > - ... > > > > Second, a passthrough interface requires delegating raw controllability > > of subdevice to guest driver, while the same delegation might not be > > required for implementing an userspace DMA interface (especially for > > modern devices which support SVA). For example, idxd allows following > > setting per wq (guest driver may configure them in any combination): > > - put in dedicated or shared mode; > > - enable/disable SVA; > > - Associate guest-provided PASID to MSI/IMS entry; > > - set threshold; > > - allow/deny privileged access; > > - allocate/free interrupt handle (enlightened for guest); > > - collect error status; > > - ... > > > > We plan to support idxd userspace DMA with SVA. The driver just needs > > to prepare a wq with a predefined configuration (e.g. shared, SVA, > > etc.), bind the process mm to IOMMU (non-nested) and then map > > the portal to userspace. The goal that userspace can do DMA to > > associated wq doesn't change the fact that the wq is still *owned* > > and *controlled* by kernel driver. However as far as passthrough > > is concerned, the wq is considered 'owned' by the guest driver thus > > we need an interface which can support low-level *controllability* > > from guest driver. It is sort of a mess in uAPI when mixing the > > two together. > > > > Based on above two reasons, we see distinct requirements between > > userspace DMA and passthrough interfaces, at least in idxd context > > (though other devices may have less distinction in-between). Therefore, > > we didn't see the value/necessity of reinventing the wheel that mdev > > already handles well to evolve an simple application-oriented usespace > > DMA interface to a complex guest-driver-oriented passthrough interface. > > The complexity of doing so would incur far more kernel-side changes > > than the portion of emulation code that you've been concerned about... > > > > > > > > I don't think VFIO should be the only entry point to > > > virtualization. If we say the universe of devices doing user space DMA > > > must also implement a VFIO mdev to plug into virtualization then it > > > will be alot of mdevs. > > > > Certainly VFIO will not be the only entry point. and This has to be a > > case-by-case decision. If an userspace DMA interface can be easily > > adapted to be a passthrough one, it might be the choice. But for idxd, > > we see mdev a much better fit here, given the big difference between > > what userspace DMA requires and what guest driver requires in this hw. > > > > > > > > I would prefer to see that the existing userspace interface have the > > > extra needed bits for virtualization (eg by having appropriate > > > internal kernel APIs to make this easy) and all the emulation to build > > > the synthetic PCI device be done in userspace. > > > > In the end what decides the direction is the amount of changes that > > we have to put in kernel, not whether we call it 'emulation'. For idxd, > > adding special passthrough requirements (guest SVA, dirty tracking, > > etc.) and raw controllability to the simple userspace DMA interface > > is for sure making kernel more complex than reusing the mdev > > framework (plus some degree of emulation mockup behind). Not to > > mention the merit of uAPI compatibility with mdev... > > I agree with a lot of this argument, exposing a device through a > userspace interface versus allowing user access to a device through a > userspace interface are different levels of abstraction and control. > In an ideal world, perhaps we could compose one from the other, but I > don't think the existence of one is proof that the other is redundant. > That's not to say that mdev/vfio isn't ripe for abuse in this space, > but I'm afraid the test for that abuse is probably much more subtle. > > I'll also remind folks that LPC is coming up in just a couple short > weeks and this might be something we should discuss (virtually) > in-person. uconf CfPs are currently open. </plug> Thanks, > Yes, LPC is a good place to reach consensus. btw I saw there is already one VFIO topic called "device assignment/sub-assignment". Do you think whether this can be covered under that topic, or makes more sense to be a new one? Thanks Kevin
