KVM: fix kvm_vcpu_kick vs __vcpu_run race

There is a window open between testing of pending IRQ's
and assignment of guest_mode in __vcpu_run.

Injection of IRQ's can race with __vcpu_run as follows:

CPU0                                CPU1
kvm_x86_ops->run()
vcpu->guest_mode = 0                SET_IRQ_LINE ioctl
..
kvm_x86_ops->inject_pending_irq
kvm_cpu_has_interrupt()

                                    apic_test_and_set_irr()
                                    kvm_vcpu_kick
                                    if (vcpu->guest_mode)
                                        send_ipi()

vcpu->guest_mode = 1

So move guest_mode=1 assignment before ->inject_pending_irq, and make
sure that it won't reorder after it.

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

1 files changed, 14 insertions, 2 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5c3c9d38c78..0ce556372a4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2802,6 +2802,13 @@ again:
                 goto out;
         }
 
+        vcpu->guest_mode = 1;
+        /*
+         * Make sure that guest_mode assignment won't happen after
+         * testing the pending IRQ vector bitmap.
+         */
+        smp_wmb();
+
         if (vcpu->arch.exception.pending)
                 __queue_exception(vcpu);
         else if (irqchip_in_kernel(vcpu->kvm))
@@ -2813,7 +2820,6 @@ again:
 
         up_read(&vcpu->kvm->slots_lock);
 
-        vcpu->guest_mode = 1;
         kvm_guest_enter();
 
         if (vcpu->requests)
@@ -3970,11 +3976,17 @@ static void vcpu_kick_intr(void *info)
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 {
         int ipi_pcpu = vcpu->cpu;
+        int cpu = get_cpu();
 
         if (waitqueue_active(&vcpu->wq)) {
                 wake_up_interruptible(&vcpu->wq);
                 ++vcpu->stat.halt_wakeup;
         }
-        if (vcpu->guest_mode)
+        /*
+         * We may be called synchronously with irqs disabled in guest mode,
+         * So need not to call smp_call_function_single() in that case.
+         */
+        if (vcpu->guest_mode && vcpu->cpu != cpu)
                 smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0, 0);
+        put_cpu();
 }