x86: kvm: rate-limit global clock updates

When we update a vcpu's local clock it may pick up an NTP correction.
We can't wait an indeterminate amount of time for other vcpus to pick
up that correction, so commit 0061d53daf introduced a global clock
update. However, we can't request a global clock update on every vcpu
load either (which is what happens if the tsc is marked as unstable).
The solution is to rate-limit the global clock updates. Marcelo
calculated that we should delay the global clock updates no more
than 0.1s as follows:

Assume an NTP correction c is applied to one vcpu, but not the other,
then in n seconds the delta of the vcpu system_timestamps will be
c * n. If we assume a correction of 500ppm (worst-case), then the two
vcpus will diverge 50us in 0.1s, which is a considerable amount.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -598,6 +598,7 @@ struct kvm_arch {
 	bool use_master_clock;
 	u64 master_kernel_ns;
 	cycle_t master_cycle_now;
+	struct delayed_work kvmclock_update_work;
 
 	struct kvm_xen_hvm_config xen_hvm_config;
 

arch/x86/kvm/x86.c

@@ -1628,14 +1628,21 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
  * the others.
  *
  * So in those cases, request a kvmclock update for all vcpus.
- * The worst case for a remote vcpu to update its kvmclock
- * is then bounded by maximum nohz sleep latency.
+ * We need to rate-limit these requests though, as they can
+ * considerably slow guests that have a large number of vcpus.
+ * The time for a remote vcpu to update its kvmclock is bound
+ * by the delay we use to rate-limit the updates.
  */
 
-static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
+#define KVMCLOCK_UPDATE_DELAY msecs_to_jiffies(100)
+
+static void kvmclock_update_fn(struct work_struct *work)
 {
 	int i;
-	struct kvm *kvm = v->kvm;
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct kvm_arch *ka = container_of(dwork, struct kvm_arch,
+					   kvmclock_update_work);
+	struct kvm *kvm = container_of(ka, struct kvm, arch);
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -1644,6 +1651,15 @@ static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
 	}
 }
 
+static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
+{
+	struct kvm *kvm = v->kvm;
+
+	set_bit(KVM_REQ_CLOCK_UPDATE, &v->requests);
+	schedule_delayed_work(&kvm->arch.kvmclock_update_work,
+					KVMCLOCK_UPDATE_DELAY);
+}
+
 static bool msr_mtrr_valid(unsigned msr)
 {
 	switch (msr) {
@@ -7022,6 +7038,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	pvclock_update_vm_gtod_copy(kvm);
 
+	INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
+
 	return 0;
 }
 
@@ -7059,6 +7077,7 @@ static void kvm_free_vcpus(struct kvm *kvm)
 
 void kvm_arch_sync_events(struct kvm *kvm)
 {
+	cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work);
 	kvm_free_all_assigned_devices(kvm);
 	kvm_free_pit(kvm);
 }