On Tue, Sep 15, 2020 at 03:45:10PM -0300, Jason Gunthorpe wrote: > On Tue, Sep 15, 2020 at 11:11:54AM -0700, Raj, Ashok wrote: > > > PASID applies widely to many device and needs to be introduced with a > > > wide community agreement so all scenarios will be supportable. > > > > True, reading some of the earlier replies I was clearly confused as I > > thought you were talking about mdev again. But now that you stay it, you > > have moved past mdev and its the PASID interfaces correct? > > Yes, we agreed mdev for IDXD at LPC, didn't talk about PASID. > > > For the native user applications have just 1 PASID per > > process. There is no need for a quota management. > > Yes, there is. There is a limited pool of HW PASID's. If one user fork > bombs it can easially claim an unreasonable number from that pool as > each process will claim a PASID. That can DOS the rest of the system. Not sure how you had this played out.. For PASID used in ENQCMD today for our SVM usages, we *DO* not automatically propagate or allocate new PASIDs. The new process needs to bind to get a PASID for its own use. For threads of same process the PASID is inherited. For forks(), we do not auto-allocate them. Since PASID isn't a sharable resource much like how you would not pass mmio mmap's to forked processes that cannot be shared correct? Such as your doorbell space for e.g. > > If PASID DOS is a worry then it must be solved at the IOMMU level for > all user applications that might trigger a PASID allocation. VFIO is > not special. Feels like you can simply avoid the PASID DOS rather than permit it to happen. > > > IIUC, you are asking that part of the interface to move to a API interface > > that potentially the new /dev/sva and VFIO could share? I think the API's > > for PASID management themselves are generic (Jean's patchset + Jacob's > > ioasid set management). > > Yes, the in kernel APIs are pretty generic now, and can be used by > many types of drivers. Good, so there is no new requirements here I suppose. > > As JasonW kicked this off, VDPA will need all this identical stuff > too. We already know this, and I think Intel VDPA HW will need it, so > it should concern you too :) This is one of those things that I would disagree and commit :-).. > > A PASID vIOMMU solution sharable with VDPA and VFIO, based on a PASID > control char dev (eg /dev/sva, or maybe /dev/iommu) seems like a > reasonable starting point for discussion. Looks like now we are getting closer to what we need. :-) Given that PASID api's are general purpose today and any driver can use it to take advantage. VFIO fortunately or unfortunately has the IOMMU things abstracted. I suppose that support is also mostly built on top of the generic iommu* api abstractions in a vendor neutral way? I'm still lost on what is missing that vDPA can't build on top of what is available? Cheers, Ashok
