2016-10-17 15:45+0800, Wanpeng Li:
> From: Wanpeng Li <wanpeng...@hotmail.com>
>
> Most windows guests still utilize APIC Timer periodic/oneshot mode
> instead of tsc-deadline mode, and the APIC Timer periodic/oneshot
> mode are still emulated by high overhead hrtimer on host. This patch
> converts the expected expire time of the periodic/oneshot mode to
> guest deadline tsc in order to leverage VMX preemption timer logic
> for APIC Timer tsc-deadline mode. After each preemption timer vmexit
> preemption timer is restarted to emulate LVTT current-count register
> is automatically reloaded from the initial-count register when the
> count reaches 0. This patch reduces ~3800 cycles for each APIC Timer
> periodic mode operation virtualization.
>
> Cc: Paolo Bonzini <pbonz...@redhat.com>
> Cc: Radim Krčmář <rkrc...@redhat.com>
> Cc: Yunhong Jiang <yunhong.ji...@intel.com>
> Signed-off-by: Wanpeng Li <wanpeng...@hotmail.com>
> ---
> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> @@ -1090,7 +1090,7 @@ static void apic_send_ipi(struct kvm_lapic *apic)
>
> static u32 apic_get_tmcct(struct kvm_lapic *apic)
> {
> - ktime_t remaining;
> + ktime_t remaining, now;
> s64 ns;
> u32 tmcct;
>
> @@ -1101,7 +1101,8 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
> apic->lapic_timer.period == 0)
> return 0;
>
> - remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
> + now = apic->lapic_timer.timer.base->get_time();
> + remaining = ktime_sub(apic->lapic_timer.target_expiration, now);
Periodic timer does not advance apic->lapic_timer.target_expiration,
when rearming the hrtimer, so this would incorrectly return 0 in
subsequent periods.
> if (ktime_to_ns(remaining) < 0)
> remaining = ktime_set(0, 0);
>
> @@ -1438,14 +1447,42 @@ static bool start_hv_timer(struct kvm_lapic *apic)
> return apic->lapic_timer.hv_timer_in_use;
> }
>
> +void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
> +{
> + struct kvm_lapic *apic = vcpu->arch.apic;
> +
> + WARN_ON(!apic->lapic_timer.hv_timer_in_use);
> + WARN_ON(swait_active(&vcpu->wq));
> + cancel_hv_timer(apic);
> + apic_timer_expired(apic);
> +
> + if (apic_lvtt_period(apic) &&
> + set_target_expiration(apic) &&
> + !start_hv_timer(apic))
> + start_sw_period(apic);
> +}
> +EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer);
> +
> void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu)
> {
> struct kvm_lapic *apic = vcpu->arch.apic;
>
> WARN_ON(apic->lapic_timer.hv_timer_in_use);
>
> - if (apic_lvtt_tscdeadline(apic))
> - start_hv_timer(apic);
> + if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) {
> + ktime_t remaining, now;
> + u64 tscl = rdtsc();
> +
> + now = apic->lapic_timer.timer.base->get_time();
> + remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
> + if (ktime_to_ns(remaining) < 0)
> + remaining = ktime_set(0, 0);
> +
> + apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu,
> tscl) +
> + nsec_to_cycles(apic->vcpu, ktime_to_ns(remaining));
> + apic->lapic_timer.target_expiration = ktime_add_ns(now,
> ktime_to_ns(remaining));
For oneshot timer, there is no need to hrtimer_get_remaining(), because
apic->lapic_timer.tscdeadline and apic->lapic_timer.target_expiration
are already correct, so we could just use them.
The same could be true for the periodic timer as well, but
apic->lapic_timer.target_expiration nor apic->lapic_timer.tscdeadline is
advanced in apic_timer_fn(), so they are soon incorrect.
I think it would be better to add a function to advance the periodic
timer and use it in kvm_lapic_expired_hv_timer() and in apic_timer_fn().
The function can be simpler than set_target_expiration(), because it
just adds the period to an existing timer. Periodic timer will also be
better then, because the period will not depend on KVM's latency when
rearming.
> + }
> + start_hv_timer(apic);
> }
> EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_hv_timer);
>
> @@ -1462,7 +1499,10 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu
> *vcpu)
> if (atomic_read(&apic->lapic_timer.pending))
> return;
>
> - start_sw_tscdeadline(apic);
> + if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic))
> + start_sw_period(apic);
> + else if (apic_lvtt_tscdeadline(apic))
> + start_sw_tscdeadline(apic);
> }
> EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer);
>
> @@ -1470,9 +1510,11 @@ static void start_apic_timer(struct kvm_lapic *apic)
> {
> atomic_set(&apic->lapic_timer.pending, 0);
>
> - if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic))
> - start_sw_period(apic);
> - else if (apic_lvtt_tscdeadline(apic)) {
> + if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) {
> + if (set_target_expiration(apic) &&
> + !(kvm_x86_ops->set_hv_timer && start_hv_timer(apic)))
> + start_sw_period(apic);
> + } else if (apic_lvtt_tscdeadline(apic)) {
> if (!(kvm_x86_ops->set_hv_timer && start_hv_timer(apic)))
> start_sw_tscdeadline(apic);
> }
> @@ -2005,8 +2047,11 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
>
> if (atomic_read(&apic->lapic_timer.pending) > 0) {
> kvm_apic_local_deliver(apic, APIC_LVTT);
> - if (apic_lvtt_tscdeadline(apic))
> + if (!(apic_lvtt_period(apic) &&
> + kvm_lapic_hv_timer_in_use(vcpu))) {
This would zero apic->lapic_timer.target_expiration of
apic_lvtt_period() when !kvm_lapic_hv_timer_in_use().
I think we don't want to ever do that, so we want
if (!(apic_lvtt_period(apic)) {
or maybe even better
if (apic_lvtt_tscdeadline(apic))
apic->lapic_timer.tscdeadline = 0;
if (apic_lvtt_oneshot(apic)) {
apic->lapic_timer.tscdeadline = 0;
apic->lapic_timer.target_expiration = ktime_set(0, 0);
}
> apic->lapic_timer.tscdeadline = 0;
> + apic->lapic_timer.target_expiration = ktime_set(0, 0);
> + }
> atomic_set(&apic->lapic_timer.pending, 0);
> }
> }
