KVM: close timer injection race window in __vcpu_run

If a timer fires after kvm_inject_pending_timer_irqs() but before
local_irq_disable() the code will enter guest mode and only inject such
timer interrupt the next time an unrelated event causes an exit.

It would be simpler if the timer->pending irq conversion could be done
with IRQ's disabled, so that the above problem cannot happen.

For now introduce a new vcpu requests bit to cancel guest entry.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>

4 files changed, 9 insertions, 3 deletions

diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index f2f5d260874e..3829aa7b663f 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -200,9 +200,12 @@ int __pit_timer_fn(struct kvm_kpit_state *ps)
 
         atomic_inc(&pt->pending);
         smp_mb__after_atomic_inc();
-        if (vcpu0 && waitqueue_active(&vcpu0->wq)) {
-                vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
-                wake_up_interruptible(&vcpu0->wq);
+        if (vcpu0) {
+                set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests);
+                if (waitqueue_active(&vcpu0->wq)) {
+                        vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+                        wake_up_interruptible(&vcpu0->wq);
+                }
         }
 
         pt->timer.expires = ktime_add_ns(pt->timer.expires, pt->period);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c297c50eba63..ebc03f5ae162 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -940,6 +940,7 @@ static int __apic_timer_fn(struct kvm_lapic *apic)
         wait_queue_head_t *q = &apic->vcpu->wq;
 
         atomic_inc(&apic->timer.pending);
+        set_bit(KVM_REQ_PENDING_TIMER, &apic->vcpu->requests);
         if (waitqueue_active(q)) {
                 apic->vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
                 wake_up_interruptible(q);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b90744a1dc3a..b08812d6b34c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2774,6 +2774,7 @@ again:
                 }
         }
 
+        clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
         kvm_inject_pending_timer_irqs(vcpu);
 
         preempt_disable();
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 092b1b25291d..de9d1df4bba2 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -33,6 +33,7 @@
 #define KVM_REQ_REPORT_TPR_ACCESS  2
 #define KVM_REQ_MMU_RELOAD         3
 #define KVM_REQ_TRIPLE_FAULT       4
+#define KVM_REQ_PENDING_TIMER      5
 
 struct kvm_vcpu;
 extern struct kmem_cache *kvm_vcpu_cache;