On Thu, Dec 29, 2016 at 07:38:38AM +0000, Liu, Yi L wrote: > > Before this one we only invalidate context cache when we receive context > > entry invalidations. However it's possible that the invalidation also > > contains a domain switch (only if cache-mode is enabled for vIOMMU). In > > that case we need to notify all the registered components about the new > > mapping. > > > > Signed-off-by: Peter Xu <address@hidden> > > --- > > hw/i386/intel_iommu.c | 1 + > > 1 file changed, 1 insertion(+) > > > > diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c > > index 2fcd7af..0220e63 100644 > > --- a/hw/i386/intel_iommu.c > > +++ b/hw/i386/intel_iommu.c > > @@ -1188,6 +1188,7 @@ static void > > vtd_context_device_invalidate(IntelIOMMUState > > *s, > > trace_vtd_inv_desc_cc_device(bus_n, (devfn_it >> 3) & 0x1f, > > devfn_it & 3); > > vtd_as->context_cache_entry.context_cache_gen = 0; > > + memory_region_iommu_replay_all(&vtd_as->iommu); > > Hi Peter, > > It looks like all the device context invalidation would result in replay even > the > device is not an assigned device. Is it necessary to do replay for a virtual > device?
Normal emulated devices won't register for IOMMU notifier. For these devices, MemoryRegion.iommu_notify will be empty. So replay on those memory regions should not affect them at all. Thanks, -- peterx
