KVM: x86: add option to advance tscdeadline hrtimer expiration

[deliverable/linux.git] / arch / x86 / kvm / lapic.c

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index fe8bae511e99fddcacb3ab511af178508c807e6f..e1c0befaa9f63a967ac8305fa8280bb3956bfd4a 100644 (file)
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -33,6 +33,7 @@
 #include <asm/page.h>
 #include <asm/current.h>
 #include <asm/apicdef.h>
+#include <asm/delay.h>
 #include <linux/atomic.h>
 #include <linux/jump_label.h>
 #include "kvm_cache_regs.h"
@@ -1073,6 +1074,7 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 {
        struct kvm_vcpu *vcpu = apic->vcpu;
        wait_queue_head_t *q = &vcpu->wq;
+       struct kvm_timer *ktimer = &apic->lapic_timer;
 
        /*
         * Note: KVM_REQ_PENDING_TIMER is implicitly checked in
@@ -1087,11 +1089,61 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 
        if (waitqueue_active(q))
                wake_up_interruptible(q);
+
+       if (apic_lvtt_tscdeadline(apic))
+               ktimer->expired_tscdeadline = ktimer->tscdeadline;
+}
+
+/*
+ * On APICv, this test will cause a busy wait
+ * during a higher-priority task.
+ */
+
+static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu)
+{
+       struct kvm_lapic *apic = vcpu->arch.apic;
+       u32 reg = kvm_apic_get_reg(apic, APIC_LVTT);
+
+       if (kvm_apic_hw_enabled(apic)) {
+               int vec = reg & APIC_VECTOR_MASK;
+
+               if (kvm_x86_ops->test_posted_interrupt)
+                       return kvm_x86_ops->test_posted_interrupt(vcpu, vec);
+               else {
+                       if (apic_test_vector(vec, apic->regs + APIC_ISR))
+                               return true;
+               }
+       }
+       return false;
+}
+
+void wait_lapic_expire(struct kvm_vcpu *vcpu)
+{
+       struct kvm_lapic *apic = vcpu->arch.apic;
+       u64 guest_tsc, tsc_deadline;
+
+       if (!kvm_vcpu_has_lapic(vcpu))
+               return;
+
+       if (apic->lapic_timer.expired_tscdeadline == 0)
+               return;
+
+       if (!lapic_timer_int_injected(vcpu))
+               return;
+
+       tsc_deadline = apic->lapic_timer.expired_tscdeadline;
+       apic->lapic_timer.expired_tscdeadline = 0;
+       guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc());
+
+       /* __delay is delay_tsc whenever the hardware has TSC, thus always.  */
+       if (guest_tsc < tsc_deadline)
+               __delay(tsc_deadline - guest_tsc);
 }
 
 static void start_apic_timer(struct kvm_lapic *apic)
 {
        ktime_t now;
+
        atomic_set(&apic->lapic_timer.pending, 0);
 
        if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) {
@@ -1137,6 +1189,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
                /* lapic timer in tsc deadline mode */
                u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline;
                u64 ns = 0;
+               ktime_t expire;
                struct kvm_vcpu *vcpu = apic->vcpu;
                unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz;
                unsigned long flags;
@@ -1151,8 +1204,10 @@ static void start_apic_timer(struct kvm_lapic *apic)
                if (likely(tscdeadline > guest_tsc)) {
                        ns = (tscdeadline - guest_tsc) * 1000000ULL;
                        do_div(ns, this_tsc_khz);
+                       expire = ktime_add_ns(now, ns);
+                       expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
                        hrtimer_start(&apic->lapic_timer.timer,
-                               ktime_add_ns(now, ns), HRTIMER_MODE_ABS);
+                                     expire, HRTIMER_MODE_ABS);
                } else
                        apic_timer_expired(apic);