2017-06-12 21:30+0800, Jay Zhou:
> Guest using kvmclock will be hanged when migrating from unstable
> tsc host to stable tsc host occasionally.
> Sometimes, the tsc timestamp saved at the source side will be
> backward when the guest stopped, and this value is transferred
> to the destination side. The guest at the destination side thought
> kvmclock is stable, so the protection mechanism against time
> going backwards is not used.
> When the first time vcpu0 enters the guest at the destination
> side to update the wall clock, the result of
> pvclock_clocksource_read will be backward occasionally,
> which results in the wall clock drift.
>
> Signed-off-by: Jay Zhou <jianjay.zhou@xxxxxxxxxx>
> ---
> diff --git a/hw/i386/kvm/clock.c b/hw/i386/kvm/clock.c
>
> if (running) {
> struct kvm_clock_data data = {};
> + uint8_t flags_at_migration;
>
> /*
> * If the host where s->clock was read did not support reliable
> * KVM_GET_CLOCK, read kvmclock value from memory.
> */
> if (!s->clock_is_reliable) {
'clock_is_reliable = true' on all newer KVMs (v4.9+), so I don't see a
reason to add a feature that can't be used.
> - uint64_t pvclock_via_mem = kvmclock_current_nsec(s);
> + uint64_t pvclock_via_mem = kvmclock_current_nsec(s,
> + &flags_at_migration);
kvmclock_current_nsec() was introduced to work around the problem with
backward time, so we should understand why it returns a time that is
backwards if we want to do something for old KVMs ...
Is pvclock_via_mem < s->clock?
Thanks.
> /* We can't rely on the saved clock value, just discard it */
> if (pvclock_via_mem) {
> s->clock = pvclock_via_mem;
> + /* whether src kvmclock has PVCLOCK_TSC_STABLE_BIT flag */
> + if (!(flags_at_migration & PVCLOCK_TSC_STABLE_BIT)) {
> + data.flags |= MIGRATION_PVCLOCK_TSC_UNSTABLE_BIT;
> + }
> }
> }
