diff options
author | Wanpeng Li <wanpeng.li@hotmail.com> | 2016-10-24 18:23:13 +0800 |
---|---|---|
committer | Paolo Bonzini <pbonzini@redhat.com> | 2016-11-02 21:32:17 +0100 |
commit | 8003c9ae204e21204e49816c5ea629357e283b06 (patch) | |
tree | 4972d819077e3a2e7d172ed4c799d76a5275e4f2 /arch/x86/kvm | |
parent | 7e810a38e6c7166b91968e83dee4cf7a4ef5dc80 (diff) |
KVM: LAPIC: add APIC Timer periodic/oneshot mode VMX preemption timer support
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 ~5600 cycles for each APIC Timer
periodic mode operation virtualization.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Yunhong Jiang <yunhong.jiang@intel.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
[Squashed with my fixes that were reviewed-by Paolo.]
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/lapic.c | 103 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.h | 1 |
2 files changed, 76 insertions, 28 deletions
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 0354a79fecd8..d1a2e60a1ef6 100644 --- 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); if (ktime_to_ns(remaining) < 0) remaining = ktime_set(0, 0); @@ -1349,15 +1350,33 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) static void start_sw_period(struct kvm_lapic *apic) { + if (!apic->lapic_timer.period) + return; + + if (apic_lvtt_oneshot(apic) && + ktime_after(apic->lapic_timer.timer.base->get_time(), + apic->lapic_timer.target_expiration)) { + apic_timer_expired(apic); + return; + } + + hrtimer_start(&apic->lapic_timer.timer, + apic->lapic_timer.target_expiration, + HRTIMER_MODE_ABS_PINNED); +} + +static bool set_target_expiration(struct kvm_lapic *apic) +{ ktime_t now; + u64 tscl = rdtsc(); - /* lapic timer in oneshot or periodic mode */ now = apic->lapic_timer.timer.base->get_time(); apic->lapic_timer.period = (u64)kvm_lapic_get_reg(apic, APIC_TMICT) - * APIC_BUS_CYCLE_NS * apic->divide_count; + * APIC_BUS_CYCLE_NS * apic->divide_count; if (!apic->lapic_timer.period) - return; + return false; + /* * Do not allow the guest to program periodic timers with small * interval, since the hrtimers are not throttled by the host @@ -1376,10 +1395,6 @@ static void start_sw_period(struct kvm_lapic *apic) } } - hrtimer_start(&apic->lapic_timer.timer, - ktime_add_ns(now, apic->lapic_timer.period), - HRTIMER_MODE_ABS_PINNED); - apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" PRIx64 ", " "timer initial count 0x%x, period %lldns, " @@ -1389,6 +1404,21 @@ static void start_sw_period(struct kvm_lapic *apic) apic->lapic_timer.period, ktime_to_ns(ktime_add_ns(now, apic->lapic_timer.period))); + + apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) + + nsec_to_cycles(apic->vcpu, apic->lapic_timer.period); + apic->lapic_timer.target_expiration = ktime_add_ns(now, apic->lapic_timer.period); + + return true; +} + +static void advance_periodic_target_expiration(struct kvm_lapic *apic) +{ + apic->lapic_timer.tscdeadline += + nsec_to_cycles(apic->vcpu, apic->lapic_timer.period); + apic->lapic_timer.target_expiration = + ktime_add_ns(apic->lapic_timer.target_expiration, + apic->lapic_timer.period); } bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu) @@ -1406,22 +1436,12 @@ static void cancel_hv_timer(struct kvm_lapic *apic) apic->lapic_timer.hv_timer_in_use = false; } -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); -} -EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer); - static bool start_hv_timer(struct kvm_lapic *apic) { u64 tscdeadline = apic->lapic_timer.tscdeadline; - if (atomic_read(&apic->lapic_timer.pending) || + if ((atomic_read(&apic->lapic_timer.pending) && + !apic_lvtt_period(apic)) || kvm_x86_ops->set_hv_timer(apic->vcpu, tscdeadline)) { if (apic->lapic_timer.hv_timer_in_use) cancel_hv_timer(apic); @@ -1430,7 +1450,8 @@ static bool start_hv_timer(struct kvm_lapic *apic) hrtimer_cancel(&apic->lapic_timer.timer); /* In case the sw timer triggered in the window */ - if (atomic_read(&apic->lapic_timer.pending)) + if (atomic_read(&apic->lapic_timer.pending) && + !apic_lvtt_period(apic)) cancel_hv_timer(apic); } trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, @@ -1438,14 +1459,30 @@ 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) && apic->lapic_timer.period) { + advance_periodic_target_expiration(apic); + if (!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); + 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); } @@ -1923,6 +1965,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data) apic_timer_expired(apic); if (lapic_is_periodic(apic)) { + advance_periodic_target_expiration(apic); hrtimer_add_expires_ns(&ktimer->timer, ktimer->period); return HRTIMER_RESTART; } else @@ -2007,6 +2050,10 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu) kvm_apic_local_deliver(apic, APIC_LVTT); 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); + } atomic_set(&apic->lapic_timer.pending, 0); } } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 031db2631a1a..e0c80233b3e1 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -15,6 +15,7 @@ struct kvm_timer { struct hrtimer timer; s64 period; /* unit: ns */ + ktime_t target_expiration; u32 timer_mode; u32 timer_mode_mask; u64 tscdeadline; |