[patch 1/2] KVM: hlt emulation should take in-kernel APIC/PIT timers into account

[Marcelo Tosatti <mtosatti@redhat.com>]

[-- Attachment #1: fix-timer-wakeup --]
[-- Type: text/plain, Size: 4695 bytes --]

Timers that fire between guest hlt and vcpu_block's add_wait_queue() are 
ignored, possibly resulting in hangs.

Also make sure that atomic_inc and waitqueue_active tests happen in the
specified order, otherwise the following race is open:

CPU0                                        CPU1
                                            if (waitqueue_active(wq))
add_wait_queue()                        
if (!atomic_read(pit_timer->pending))
    schedule()
                                            atomic_inc(pit_timer->pending)

Which is not an issue for the APIC timer due to migration logic.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Index: kvm/arch/x86/kvm/i8254.c
===================================================================
--- kvm.orig/arch/x86/kvm/i8254.c
+++ kvm/arch/x86/kvm/i8254.c
@@ -199,6 +199,7 @@ int __pit_timer_fn(struct kvm_kpit_state
 	struct kvm_kpit_timer *pt = &ps->pit_timer;
 
 	atomic_inc(&pt->pending);
+	smp_mb__after_atomic_inc();
 	if (vcpu0 && waitqueue_active(&vcpu0->wq)) {
 		vcpu0->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
 		wake_up_interruptible(&vcpu0->wq);
@@ -210,6 +211,16 @@ int __pit_timer_fn(struct kvm_kpit_state
 	return (pt->period == 0 ? 0 : 1);
 }
 
+int pit_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
+
+	if (pit && vcpu->vcpu_id == 0)
+		return atomic_read(&pit->pit_state.pit_timer.pending);
+
+	return 0;
+}
+
 static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 {
 	struct kvm_kpit_state *ps;
Index: kvm/arch/x86/kvm/irq.c
===================================================================
--- kvm.orig/arch/x86/kvm/irq.c
+++ kvm/arch/x86/kvm/irq.c
@@ -26,6 +26,21 @@
 #include "i8254.h"
 
 /*
+ * check if there are pending timer events
+ * to be processed.
+ */
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	ret = pit_has_pending_timer(vcpu);
+	ret |= apic_has_pending_timer(vcpu);
+
+	return ret;
+}
+EXPORT_SYMBOL(kvm_cpu_has_pending_timer);
+
+/*
  * check if there is pending interrupt without
  * intack.
  */
Index: kvm/arch/x86/kvm/irq.h
===================================================================
--- kvm.orig/arch/x86/kvm/irq.h
+++ kvm/arch/x86/kvm/irq.h
@@ -85,4 +85,7 @@ void kvm_inject_pending_timer_irqs(struc
 void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
 void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu);
 
+int pit_has_pending_timer(struct kvm_vcpu *vcpu);
+int apic_has_pending_timer(struct kvm_vcpu *vcpu);
+
 #endif
Index: kvm/arch/x86/kvm/lapic.c
===================================================================
--- kvm.orig/arch/x86/kvm/lapic.c
+++ kvm/arch/x86/kvm/lapic.c
@@ -952,6 +952,16 @@ static int __apic_timer_fn(struct kvm_la
 	return result;
 }
 
+int apic_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *lapic = vcpu->arch.apic;
+
+	if (lapic)
+		return atomic_read(&lapic->timer.pending);
+
+	return 0;
+}
+
 static int __inject_apic_timer_irq(struct kvm_lapic *apic)
 {
 	int vector;
Index: kvm/include/linux/kvm_host.h
===================================================================
--- kvm.orig/include/linux/kvm_host.h
+++ kvm/include/linux/kvm_host.h
@@ -272,6 +272,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm
 
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *v);
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
 
 static inline void kvm_guest_enter(void)
Index: kvm/virt/kvm/kvm_main.c
===================================================================
--- kvm.orig/virt/kvm/kvm_main.c
+++ kvm/virt/kvm/kvm_main.c
@@ -752,6 +752,7 @@ void mark_page_dirty(struct kvm *kvm, gf
 	}
 }
 
+#ifdef CONFIG_X86
 /*
  * The vCPU has executed a HLT instruction with in-kernel mode enabled.
  */
@@ -765,6 +766,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcp
 	 * We will block until either an interrupt or a signal wakes us up
 	 */
 	while (!kvm_cpu_has_interrupt(vcpu)
+	       && !kvm_cpu_has_pending_timer(vcpu)
 	       && !signal_pending(current)
 	       && !kvm_arch_vcpu_runnable(vcpu)) {
 		set_current_state(TASK_INTERRUPTIBLE);
@@ -776,6 +778,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcp
 	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(&vcpu->wq, &wait);
 }
+#endif
 
 void kvm_resched(struct kvm_vcpu *vcpu)
 {

-- 


-------------------------------------------------------------------------
This SF.net email is sponsored by the 2008 JavaOne(SM) Conference 
Don't miss this year's exciting event. There's still time to save $100. 
Use priority code J8TL2D2. 
http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javaone