KVM: x86: introduce get_kvmclock_ns
Introduce a function that reads the exact nanoseconds value that is
provided to the guest in kvmclock. This crystallizes the notion of
kvmclock as a thin veneer over a stable TSC, that the guest will
(hopefully) convert with NTP. In other words, kvmclock is *not* a
paravirtualized host-to-guest NTP.
Drop the get_kernel_ns() function, that was used both to get the base
value of the master clock and to get the current value of kvmclock.
The former use is replaced by ktime_get_boot_ns(), the latter is
the purpose of get_kernel_ns().
This also allows KVM to provide a Hyper-V time reference counter that
is synchronized with the time that is computed from the TSC page.
Reviewed-by: Roman Kagan <rkagan@virtuozzo.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 00e569c..81e9945 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1431,7 +1431,7 @@
raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
offset = kvm_compute_tsc_offset(vcpu, data);
- ns = get_kernel_ns();
+ ns = ktime_get_boot_ns();
elapsed = ns - kvm->arch.last_tsc_nsec;
if (vcpu->arch.virtual_tsc_khz) {
@@ -1722,6 +1722,34 @@
#endif
}
+static u64 __get_kvmclock_ns(struct kvm *kvm)
+{
+ struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0);
+ struct kvm_arch *ka = &kvm->arch;
+ s64 ns;
+
+ if (vcpu->arch.hv_clock.flags & PVCLOCK_TSC_STABLE_BIT) {
+ u64 tsc = kvm_read_l1_tsc(vcpu, rdtsc());
+ ns = __pvclock_read_cycles(&vcpu->arch.hv_clock, tsc);
+ } else {
+ ns = ktime_get_boot_ns() + ka->kvmclock_offset;
+ }
+
+ return ns;
+}
+
+u64 get_kvmclock_ns(struct kvm *kvm)
+{
+ unsigned long flags;
+ s64 ns;
+
+ local_irq_save(flags);
+ ns = __get_kvmclock_ns(kvm);
+ local_irq_restore(flags);
+
+ return ns;
+}
+
static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
{
struct kvm_vcpu_arch *vcpu = &v->arch;
@@ -1811,7 +1839,7 @@
}
if (!use_master_clock) {
host_tsc = rdtsc();
- kernel_ns = get_kernel_ns();
+ kernel_ns = ktime_get_boot_ns();
}
tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);
@@ -4054,7 +4082,6 @@
case KVM_SET_CLOCK: {
struct kvm_clock_data user_ns;
u64 now_ns;
- s64 delta;
r = -EFAULT;
if (copy_from_user(&user_ns, argp, sizeof(user_ns)))
@@ -4066,10 +4093,9 @@
r = 0;
local_irq_disable();
- now_ns = get_kernel_ns();
- delta = user_ns.clock - now_ns;
+ now_ns = __get_kvmclock_ns(kvm);
+ kvm->arch.kvmclock_offset += user_ns.clock - now_ns;
local_irq_enable();
- kvm->arch.kvmclock_offset = delta;
kvm_gen_update_masterclock(kvm);
break;
}
@@ -4077,10 +4103,8 @@
struct kvm_clock_data user_ns;
u64 now_ns;
- local_irq_disable();
- now_ns = get_kernel_ns();
- user_ns.clock = kvm->arch.kvmclock_offset + now_ns;
- local_irq_enable();
+ now_ns = get_kvmclock_ns(kvm);
+ user_ns.clock = now_ns;
user_ns.flags = 0;
memset(&user_ns.pad, 0, sizeof(user_ns.pad));
@@ -7544,7 +7568,7 @@
* before any KVM threads can be running. Unfortunately, we can't
* bring the TSCs fully up to date with real time, as we aren't yet far
* enough into CPU bringup that we know how much real time has actually
- * elapsed; our helper function, get_kernel_ns() will be using boot
+ * elapsed; our helper function, ktime_get_boot_ns() will be using boot
* variables that haven't been updated yet.
*
* So we simply find the maximum observed TSC above, then record the
@@ -7779,7 +7803,7 @@
mutex_init(&kvm->arch.apic_map_lock);
spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
- kvm->arch.kvmclock_offset = -get_kernel_ns();
+ kvm->arch.kvmclock_offset = -ktime_get_boot_ns();
pvclock_update_vm_gtod_copy(kvm);
INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);