Commit 5cfc2aab authored Jun 19, 2012 by Rik van Riel Committed by Marcelo Tosatti Jul 06, 2012

KVM: handle last_boosted_vcpu = 0 case



If last_boosted_vcpu == 0, then we fall through all test cases and
may end up with all VCPUs pouncing on vcpu 0.  With a large enough
guest, this can result in enormous runqueue lock contention, which
can prevent vcpu0 from running, leading to a livelock.

Changing < to <= makes sure we properly handle that case.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

parent 21b26c08

virt/kvm/kvm_main.c

+1 −1

Original line number	Original line	Diff line number	Diff line
	@@ -1598,7 +1598,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
	*/		*/
	for (pass = 0; pass < 2 && !yielded; pass++) {		for (pass = 0; pass < 2 && !yielded; pass++) {
	kvm_for_each_vcpu(i, vcpu, kvm) {		kvm_for_each_vcpu(i, vcpu, kvm) {
	if (!pass && i < last_boosted_vcpu) {		if (!pass && i <= last_boosted_vcpu) {
	i = last_boosted_vcpu;		i = last_boosted_vcpu;
	continue;		continue;
	} else if (pass && i > last_boosted_vcpu)		} else if (pass && i > last_boosted_vcpu)