On 22/06/2016 16:24, Andrea Arcangeli wrote: > Linux could not possibly crash instead if host phys bits > guest phys > bits because it will never depend on GPF triggering if the must be > zero bits of the guest pagetables are set. Linux won't ever try to set > those bits and I'd be shocked if any other OS does.
Well, KVM does. It sets _all_ bits up to 51, not just one, but still we have a counterexample. The reason to do this is that you can distinguish a not-present from a present-reserved page fault, and handle the present-reserved page fault from a cache without having to walk the page tables. Paolo > So while not perfect emulation of the hardware, the risk with known OS > should be zero.
