1 files changed, 70 insertions, 10 deletions

diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index ea6064696fe4..9aaa35dd9144 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -34,6 +34,11 @@ static struct timecounter *timecounter;
 static struct workqueue_struct *wqueue;
 static unsigned int host_vtimer_irq;
 
+void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.timer_cpu.active_cleared_last = false;
+}
+
 static cycle_t kvm_phys_timer_read(void)
 {
 	return timecounter->cc->read(timecounter->cc);
@@ -86,6 +91,8 @@ static void kvm_timer_inject_irq_work(struct work_struct *work)
 	vcpu = container_of(work, struct kvm_vcpu, arch.timer_cpu.expired);
 	vcpu->arch.timer_cpu.armed = false;
 
+	WARN_ON(!kvm_timer_should_fire(vcpu));
+
 	/*
 	 * If the vcpu is blocked we want to wake it up so that it will see
 	 * the timer has expired when entering the guest.
@@ -93,10 +100,46 @@ static void kvm_timer_inject_irq_work(struct work_struct *work)
 	kvm_vcpu_kick(vcpu);
 }
 
+static u64 kvm_timer_compute_delta(struct kvm_vcpu *vcpu)
+{
+	cycle_t cval, now;
+
+	cval = vcpu->arch.timer_cpu.cntv_cval;
+	now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
+
+	if (now < cval) {
+		u64 ns;
+
+		ns = cyclecounter_cyc2ns(timecounter->cc,
+					 cval - now,
+					 timecounter->mask,
+					 &timecounter->frac);
+		return ns;
+	}
+
+	return 0;
+}
+
 static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt)
 {
 	struct arch_timer_cpu *timer;
+	struct kvm_vcpu *vcpu;
+	u64 ns;
+
 	timer = container_of(hrt, struct arch_timer_cpu, timer);
+	vcpu = container_of(timer, struct kvm_vcpu, arch.timer_cpu);
+
+	/*
+	 * Check that the timer has really expired from the guest's
+	 * PoV (NTP on the host may have forced it to expire
+	 * early). If we should have slept longer, restart it.
+	 */
+	ns = kvm_timer_compute_delta(vcpu);
+	if (unlikely(ns)) {
+		hrtimer_forward_now(hrt, ns_to_ktime(ns));
+		return HRTIMER_RESTART;
+	}
+
 	queue_work(wqueue, &timer->expired);
 	return HRTIMER_NORESTART;
 }
@@ -130,6 +173,7 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level)
 
 	BUG_ON(!vgic_initialized(vcpu->kvm));
 
+	timer->active_cleared_last = false;
 	timer->irq.level = new_level;
 	trace_kvm_timer_update_irq(vcpu->vcpu_id, timer->map->virt_irq,
 				   timer->irq.level);
@@ -170,8 +214,6 @@ static int kvm_timer_update_state(struct kvm_vcpu *vcpu)
 void kvm_timer_schedule(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
-	u64 ns;
-	cycle_t cval, now;
 
 	BUG_ON(timer_is_armed(timer));
 
@@ -191,14 +233,7 @@ void kvm_timer_schedule(struct kvm_vcpu *vcpu)
 		return;
 
 	/*  The timer has not yet expired, schedule a background timer */
-	cval = timer->cntv_cval;
-	now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
-
-	ns = cyclecounter_cyc2ns(timecounter->cc,
-				 cval - now,
-				 timecounter->mask,
-				 &timecounter->frac);
-	timer_arm(timer, ns);
+	timer_arm(timer, kvm_timer_compute_delta(vcpu));
 }
 
 void kvm_timer_unschedule(struct kvm_vcpu *vcpu)
@@ -245,10 +280,35 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
 	else
 		phys_active = false;
 
+	/*
+	 * We want to avoid hitting the (re)distributor as much as
+	 * possible, as this is a potentially expensive MMIO access
+	 * (not to mention locks in the irq layer), and a solution for
+	 * this is to cache the "active" state in memory.
+	 *
+	 * Things to consider: we cannot cache an "active set" state,
+	 * because the HW can change this behind our back (it becomes
+	 * "clear" in the HW). We must then restrict the caching to
+	 * the "clear" state.
+	 *
+	 * The cache is invalidated on:
+	 * - vcpu put, indicating that the HW cannot be trusted to be
+	 *   in a sane state on the next vcpu load,
+	 * - any change in the interrupt state
+	 *
+	 * Usage conditions:
+	 * - cached value is "active clear"
+	 * - value to be programmed is "active clear"
+	 */
+	if (timer->active_cleared_last && !phys_active)
+		return;
+
 	ret = irq_set_irqchip_state(timer->map->irq,
 				    IRQCHIP_STATE_ACTIVE,
 				    phys_active);
 	WARN_ON(ret);
+
+	timer->active_cleared_last = !phys_active;
 }
 
 /**