[PATCH v2 7/7] x86/kvm: support Hyper-V reenlightenment

[Vitaly Kuznetsov]

When we run nested KVM on Hyper-V guests we need to update masterclocks for
all guests when L1 migrates to a host with different TSC frequency.
Implement the procedure in the following way:
- Pause all guests.
- Tell our host (Hyper-V) to stop emulating TSC accesses.
- Update our gtod copy, recompute clocks.
- Unpause all guests.

This is somewhat similar to cpufreq but we have two important differences:
we can only disable TSC emulation globally (on all CPUs) and we don't know
the new TSC frequency until we turn the emulation off so we can't
'prepare' ourselves to the event.

Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
---
 arch/x86/kvm/x86.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 843a8596f57e..d98e5165c1ad 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -68,6 +68,7 @@
 #include <asm/div64.h>
 #include <asm/irq_remapping.h>
 #include <asm/mshyperv.h>
+#include <asm/hypervisor.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -5932,6 +5933,43 @@ static void tsc_khz_changed(void *data)
 	__this_cpu_write(cpu_tsc_khz, khz);
 }
 
+void kvm_hyperv_tsc_notifier(void)
+{
+#ifdef CONFIG_X86_64
+	struct kvm *kvm;
+	struct kvm_vcpu *vcpu;
+	int cpu;
+
+	spin_lock(&kvm_lock);
+	list_for_each_entry(kvm, &vm_list, vm_list)
+		kvm_make_mclock_inprogress_request(kvm);
+
+	hyperv_stop_tsc_emulation();
+
+	/* TSC frequency always matches when on Hyper-V */
+	for_each_present_cpu(cpu)
+		per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
+	kvm_max_guest_tsc_khz = tsc_khz;
+
+	list_for_each_entry(kvm, &vm_list, vm_list) {
+		struct kvm_arch *ka = &kvm->arch;
+
+		spin_lock(&ka->pvclock_gtod_sync_lock);
+
+		pvclock_update_vm_gtod_copy(kvm);
+
+		kvm_for_each_vcpu(cpu, vcpu, kvm)
+			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
+
+		kvm_for_each_vcpu(cpu, vcpu, kvm)
+			kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);
+
+		spin_unlock(&ka->pvclock_gtod_sync_lock);
+	}
+	spin_unlock(&kvm_lock);
+#endif
+}
+
 static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 				     void *data)
 {
@@ -6217,6 +6255,9 @@ int kvm_arch_init(void *opaque)
 	kvm_lapic_init();
 #ifdef CONFIG_X86_64
 	pvclock_gtod_register_notifier(&pvclock_gtod_notifier);
+
+	if (x86_hyper_type == X86_HYPER_MS_HYPERV)
+		set_hv_tscchange_cb(kvm_hyperv_tsc_notifier);
 #endif
 
 	return 0;
@@ -6229,6 +6270,10 @@ int kvm_arch_init(void *opaque)
 
 void kvm_arch_exit(void)
 {
+#ifdef CONFIG_X86_64
+	if (x86_hyper_type == X86_HYPER_MS_HYPERV)
+		clear_hv_tscchange_cb();
+#endif
 	kvm_lapic_exit();
 	perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
 
-- 
2.14.3