KVM: x86: limit difference between kvmclock updates

kvmclock updates which are isolated to a given vcpu, such as vcpu->cpu
migration, should not allow system_timestamp from the rest of the vcpus
to remain static. Otherwise ntp frequency correction applies to one
vcpu's system_timestamp but not 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.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 094b5d96ab1468c1875a2a2a5e682245f2909db9..8d28810a5f8886ba6e4750dd8068f12392338f42 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1588,6 +1588,30 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
        return 0;
 }
 
+/*
+ * kvmclock updates which are isolated to a given vcpu, such as
+ * vcpu->cpu migration, should not allow system_timestamp from
+ * the rest of the vcpus to remain static. Otherwise ntp frequency
+ * correction applies to one vcpu's system_timestamp but not
+ * 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.
+ */
+
+static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
+{
+       int i;
+       struct kvm *kvm = v->kvm;
+       struct kvm_vcpu *vcpu;
+
+       kvm_for_each_vcpu(i, vcpu, kvm) {
+               set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+               kvm_vcpu_kick(vcpu);
+       }
+}
+
 static bool msr_mtrr_valid(unsigned msr)
 {
        switch (msr) {
@@ -1985,7 +2009,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
                kvmclock_reset(vcpu);
 
                vcpu->arch.time = data;
-               kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
+               kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
 
                /* we verify if the enable bit is set... */
                if (!(data & 1))
@@ -2702,7 +2726,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
                 * kvmclock on vcpu->cpu migration
                 */
                if (!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1)
-                       kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
+                       kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
                if (vcpu->cpu != cpu)
                        kvm_migrate_timers(vcpu);
                vcpu->cpu = cpu;
@@ -5703,6 +5727,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
                        __kvm_migrate_timers(vcpu);
                if (kvm_check_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu))
                        kvm_gen_update_masterclock(vcpu->kvm);
+               if (kvm_check_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu))
+                       kvm_gen_kvmclock_update(vcpu);
                if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu)) {
                        r = kvm_guest_time_update(vcpu);
                        if (unlikely(r))

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index f0eea07d2c2bb5168820443639af6e85a9d47850..d9a3c30eab2e3d14531df6f8ba8af8430b62ce71 100644 (file)
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -124,6 +124,7 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_MCLOCK_INPROGRESS 19
 #define KVM_REQ_EPR_EXIT          20
 #define KVM_REQ_SCAN_IOAPIC       21
+#define KVM_REQ_GLOBAL_CLOCK_UPDATE 22
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID            0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID       1