diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 490c8cb8cc8d0bcba74fb7810e9ab951c7c48d35..e95e7a9e4d53fc700e4aefab7a6ddf708a7cb41e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -235,9 +235,13 @@ static void ack_flush(void *_completed)
 {
 }
 
-static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait)
+static inline bool kvm_kick_many_cpus(cpumask_var_t tmp, bool wait)
 {
-	if (unlikely(!cpus))
+	const struct cpumask *cpus;
+
+	if (likely(cpumask_available(tmp)))
+		cpus = tmp;
+	else
 		cpus = cpu_online_mask;
 
 	if (cpumask_empty(cpus))
@@ -267,6 +271,14 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
 		if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu))
 			continue;
 
+		/*
+		 * tmp can be "unavailable" if cpumasks are allocated off stack
+		 * as allocation of the mask is deliberately not fatal and is
+		 * handled by falling back to kicking all online CPUs.
+		 */
+		if (!cpumask_available(tmp))
+			continue;
+
 		/*
 		 * Note, the vCPU could get migrated to a different pCPU at any
 		 * point after kvm_request_needs_ipi(), which could result in
@@ -278,7 +290,7 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
 		 * were reading SPTEs _before_ any changes were finalized.  See
 		 * kvm_vcpu_kick() for more details on handling requests.
 		 */
-		if (tmp != NULL && kvm_request_needs_ipi(vcpu, req)) {
+		if (kvm_request_needs_ipi(vcpu, req)) {
 			cpu = READ_ONCE(vcpu->cpu);
 			if (cpu != -1 && cpu != me)
 				__cpumask_set_cpu(cpu, tmp);