Il 16/05/2013 16:22, Vadim Rozenfeld ha scritto: >>>>>>>>>>> > >>>>> > > > > + addr = gfn_to_hva(kvm, gfn); >>>>>>>>>>> > >>>>> > > > > + if (kvm_is_error_hva(addr)) >>>>>>>>>>> > >>>>> > > > > + return 1; >>>>>>>>>>> > >>>>> > > > > + tsc_ref = 0; >> > >> > This should write 0xFFFFFFFF. > This should write 0 No. You have not writing sensible values to TscScale/TscOffset, hence the VM should fall back to another time source. Microsoft docs say "A special value of 0xFFFFFFFF is used to indicate that this facility is no longer a reliable source of reference time and the virtual machine must fall back to a different source (for example, the virtual PM timer)". So you need to write 0xFFFFFFFF here (though my suggestion would rather be to remove this part of the patch, and do everything in the next patch). The next patch should pick 0 if constant TSC is available, 0xFFFFFFFF if it is not. If the docs are wrong, I stand corrected but then you need a comment explaining that. Paolo -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html