On Fri, 17 Feb 2017, Andy Lutomirski wrote: > On Fri, Feb 17, 2017 at 2:14 AM, Vitaly Kuznetsov <vkuznets@xxxxxxxxxx> wrote: > > Not only. As far as I understand (and I *think* K. Y. pointed this out) > > when VM is migrating to another host TSC page clocksource is disabled for > > extended period of time so we're better off reading from MSR than > > looping here. With regards to VDSO this means reverting to doing normal > > syscall. > > That's a crappy design. The guest really ought to be able to > distinguish "busy, try again" from "bail and use MSR". > > Thomas, I can see valid reasons why the hypervisor might want to > temporarily disable shared page-based timing, but I think it's silly > that it's conflated with indicating "retry". It's beyond silly if that's the case. > But if this is indeed the ABI, we're stuck with it. No argument. _______________________________________________ devel mailing list devel@xxxxxxxxxxxxxxxxxxxxxx http://driverdev.linuxdriverproject.org/mailman/listinfo/driverdev-devel
