[dpdk-dev] [PATCH] vfio/noiommu: Don't use iommu_present() to track fake groups

2016-01-27 Thread Santosh Shukla
On Wed, Jan 27, 2016 at 6:51 PM, Burakov, Anatoly wrote: > Hi Alex, > >> On 01/23/2016 04:23 AM, Alex Williamson wrote: >> > Using iommu_present() to determine whether an IOMMU group is real or >> > fake has some problems. First, apparently Power systems don't >> > register an IOMMU on the device

[dpdk-dev] [PATCH] vfio/noiommu: Don't use iommu_present() to track fake groups

2016-01-27 Thread Burakov, Anatoly
Hi Alex, > On 01/23/2016 04:23 AM, Alex Williamson wrote: > > Using iommu_present() to determine whether an IOMMU group is real or > > fake has some problems. First, apparently Power systems don't > > register an IOMMU on the device bus, so the groups and containers get > > marked as noiommu and

[dpdk-dev] [PATCH] vfio/noiommu: Don't use iommu_present() to track fake groups

2016-01-25 Thread Alexey Kardashevskiy
On 01/23/2016 04:23 AM, Alex Williamson wrote: > Using iommu_present() to determine whether an IOMMU group is real or > fake has some problems. First, apparently Power systems don't > register an IOMMU on the device bus, so the groups and containers get > marked as noiommu and then won't bind to t

[dpdk-dev] [PATCH] vfio/noiommu: Don't use iommu_present() to track fake groups

2016-01-22 Thread Alex Williamson
Using iommu_present() to determine whether an IOMMU group is real or fake has some problems. First, apparently Power systems don't register an IOMMU on the device bus, so the groups and containers get marked as noiommu and then won't bind to their actual IOMMU driver. Second, I expect we'll run in