Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 9b62e5b1 authored by Jan Blunck's avatar Jan Blunck Committed by Avi Kivity
Browse files

KVM: Wake up waitqueue before calling get_cpu() 



This moves the get_cpu() call down to be called after we wake up the
waiters. Therefore the waitqueue locks can safely be rt mutex.

Signed-off-by: default avatarJan Blunck <jblunck@suse.de>
Signed-off-by: default avatarSven-Thorsten Dietrich <sven@thebigcorporation.com>
Signed-off-by: default avatarMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: default avatarAvi Kivity <avi@redhat.com>
parent 14d0bc1f

arch/x86/kvm/x86.c

+2 −1
Original line number Diff line number Diff line
@@ -4569,7 +4569,7 @@ static void vcpu_kick_intr(void *info) 
void kvm_vcpu_kick(struct kvm_vcpu *vcpu)

{

	int ipi_pcpu = vcpu->cpu;

	int cpu = get_cpu();

	int cpu;



	if (waitqueue_active(&vcpu->wq)) {

		wake_up_interruptible(&vcpu->wq);
@@ -4579,6 +4579,7 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) 
	 * We may be called synchronously with irqs disabled in guest mode,

	 * So need not to call smp_call_function_single() in that case.

	 */

	cpu = get_cpu();

	if (vcpu->guest_mode && vcpu->cpu != cpu)

		smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0);

	put_cpu();