RE: [PATCH v4 00/11] iommufd: Add vIOMMU infrastructure (Part-1)

2024-10-27 Thread Tian, Kevin
> From: Jason Gunthorpe > Sent: Friday, October 25, 2024 11:43 PM > > On Fri, Oct 25, 2024 at 08:34:05AM +, Tian, Kevin wrote: > > > The vIOMMU object should be seen as a slice of a physical IOMMU > instance > > > that is passed to or shared with a VM. That can be some HW/SW > resources: > >

Re: [PATCH v4 00/11] iommufd: Add vIOMMU infrastructure (Part-1)

2024-10-25 Thread Nicolin Chen
On Fri, Oct 25, 2024 at 08:34:05AM +, Tian, Kevin wrote: > > From: Nicolin Chen > > Sent: Tuesday, October 22, 2024 8:19 AM > > > > This series introduces a new vIOMMU infrastructure and related ioctls. > > > > IOMMUFD has been using the HWPT infrastructure for all cases, including a > > neste

Re: [PATCH v4 00/11] iommufd: Add vIOMMU infrastructure (Part-1)

2024-10-25 Thread Jason Gunthorpe
On Fri, Oct 25, 2024 at 08:34:05AM +, Tian, Kevin wrote: > > The vIOMMU object should be seen as a slice of a physical IOMMU instance > > that is passed to or shared with a VM. That can be some HW/SW resources: > > - Security namespace for guest owned ID, e.g. guest-controlled cache tags > >

RE: [PATCH v4 00/11] iommufd: Add vIOMMU infrastructure (Part-1)

2024-10-25 Thread Tian, Kevin
> From: Nicolin Chen > Sent: Tuesday, October 22, 2024 8:19 AM > > This series introduces a new vIOMMU infrastructure and related ioctls. > > IOMMUFD has been using the HWPT infrastructure for all cases, including a > nested IO page table support. Yet, there're limitations for an HWPT-based > st