> 1st step shows we should NOT disable the iommu when it is already > enabled. But current code does disable-enable. So there is still works > to do. > The original kernel does a disable and re-enable , Bill's patchset removed the disable operation. > I think step 2 is necessary, because when the driver initializes, the > device need a new map, and the old data from the old kernel can not be > used for the new driver. > > Now I am trying to implement these ideas. > >> Thanks
