kvm/clock: add support for confidential guest reset

Confidential guests change the KVM VM file descriptor upon reset and also create
new VCPU file descriptors against the new KVM VM file descriptor. We need to
save the clock state from kvm before KVM VM file descriptor changes and restore
it after. Also after VCPU file descriptors changed, we must call
KVM_KVMCLOCK_CTRL on the VCPU file descriptor to inform KVM that the VCPU is
in paused state.

Signed-off-by: Ani Sinha <anisinha@redhat.com>
Link: https://lore.kernel.org/r/20260225035000.385950-32-anisinha@redhat.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/hw/i386/kvm/clock.c b/hw/i386/kvm/clock.c
index aba6842a22c38eb6deb52f59b1d54f6e9db2caca..10d34254f02949ab6ca3072ba73905f98f5c4005 100644 (file)
--- a/hw/i386/kvm/clock.c
+++ b/hw/i386/kvm/clock.c
@@ -50,6 +50,9 @@ struct KVMClockState {
     /* whether the 'clock' value was obtained in a host with
      * reliable KVM_GET_CLOCK */
     bool clock_is_reliable;
+
+    NotifierWithReturn kvmclock_vcpufd_change_notifier;
+    NotifierWithReturn kvmclock_vmfd_change_notifier;
 };
 
 struct pvclock_vcpu_time_info {
@@ -63,6 +66,9 @@ struct pvclock_vcpu_time_info {
     uint8_t    pad[2];
 } __attribute__((__packed__)); /* 32 bytes */
 
+static int kvmclock_set_clock(NotifierWithReturn *notifier,
+                              void *data, Error** errp);
+
 static uint64_t kvmclock_current_nsec(KVMClockState *s)
 {
     CPUState *cpu = first_cpu;
@@ -219,6 +225,54 @@ static void kvmclock_vm_state_change(void *opaque, bool running,
     }
 }
 
+static int kvmclock_save_clock(NotifierWithReturn *notifier,
+                               void *data, Error** errp)
+{
+    if (!((VmfdChangeNotifier *)data)->pre) {
+        return 0;
+    }
+    KVMClockState *s = container_of(notifier, KVMClockState,
+                                    kvmclock_vmfd_change_notifier);
+    kvm_update_clock(s);
+    return 0;
+}
+
+static int kvmclock_set_clock(NotifierWithReturn *notifier,
+                              void *data, Error** errp)
+{
+    struct kvm_clock_data clock_data = {};
+    CPUState *cpu;
+    int ret;
+    KVMClockState *s = container_of(notifier, KVMClockState,
+                                    kvmclock_vcpufd_change_notifier);
+    int cap_clock_ctrl = kvm_check_extension(kvm_state, KVM_CAP_KVMCLOCK_CTRL);
+
+    if (!s->clock_is_reliable) {
+        uint64_t pvclock_via_mem = kvmclock_current_nsec(s);
+        /* saved clock value before vmfd change is not reliable */
+        if (pvclock_via_mem) {
+            s->clock = pvclock_via_mem;
+        }
+    }
+
+    clock_data.clock = s->clock;
+    ret = kvm_vm_ioctl(kvm_state, KVM_SET_CLOCK, &clock_data);
+    if (ret < 0) {
+        fprintf(stderr, "KVM_SET_CLOCK failed: %s\n", strerror(-ret));
+        abort();
+    }
+
+    if (!cap_clock_ctrl) {
+        return 0;
+    }
+    CPU_FOREACH(cpu) {
+        run_on_cpu(cpu, do_kvmclock_ctrl, RUN_ON_CPU_NULL);
+    }
+
+    return 0;
+}
+
+
 static void kvmclock_realize(DeviceState *dev, Error **errp)
 {
     KVMClockState *s = KVM_CLOCK(dev);
@@ -230,7 +284,12 @@ static void kvmclock_realize(DeviceState *dev, Error **errp)
 
     kvm_update_clock(s);
 
+    s->kvmclock_vcpufd_change_notifier.notify = kvmclock_set_clock;
+    s->kvmclock_vmfd_change_notifier.notify = kvmclock_save_clock;
+
     qemu_add_vm_change_state_handler(kvmclock_vm_state_change, s);
+    kvm_vcpufd_add_change_notifier(&s->kvmclock_vcpufd_change_notifier);
+    kvm_vmfd_add_change_notifier(&s->kvmclock_vmfd_change_notifier);
 }
 
 static bool kvmclock_clock_is_reliable_needed(void *opaque)