[Qemu-devel] [PATCH] kvmclock: clock should count only if vm is running

[Marcelo Tosatti <mtosatti@redhat.com>]

kvmclock should not count while vm is paused, because:

1) if the vm is paused for long periods, timekeeping 
math can overflow while converting the (large) clocksource 
delta to nanoseconds.

2) Users rely on CLOCK_MONOTONIC to count run time, that is, 
time which OS has been in a runnable state (see CLOCK_BOOTTIME).

Change kvmclock driver so as to save clock value when vm transitions
from runnable to stopped state, and to restore clock value from stopped
to runnable transition.

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

diff --git a/hw/i386/kvm/clock.c b/hw/i386/kvm/clock.c
index 87d4d0f..7d2d005 100644
--- a/hw/i386/kvm/clock.c
+++ b/hw/i386/kvm/clock.c
@@ -28,38 +28,6 @@ typedef struct KVMClockState {
     bool clock_valid;
 } KVMClockState;
 
-static void kvmclock_pre_save(void *opaque)
-{
-    KVMClockState *s = opaque;
-    struct kvm_clock_data data;
-    int ret;
-
-    if (s->clock_valid) {
-        return;
-    }
-    ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data);
-    if (ret < 0) {
-        fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(ret));
-        data.clock = 0;
-    }
-    s->clock = data.clock;
-    /*
-     * If the VM is stopped, declare the clock state valid to avoid re-reading
-     * it on next vmsave (which would return a different value). Will be reset
-     * when the VM is continued.
-     */
-    s->clock_valid = !runstate_is_running();
-}
-
-static int kvmclock_post_load(void *opaque, int version_id)
-{
-    KVMClockState *s = opaque;
-    struct kvm_clock_data data;
-
-    data.clock = s->clock;
-    data.flags = 0;
-    return kvm_vm_ioctl(kvm_state, KVM_SET_CLOCK, &data);
-}
 
 static void kvmclock_vm_state_change(void *opaque, int running,
                                      RunState state)
@@ -70,8 +38,18 @@ static void kvmclock_vm_state_change(void *opaque, int running,
     int ret;
 
     if (running) {
+        struct kvm_clock_data data;
+
         s->clock_valid = false;
 
+        data.clock = s->clock;
+        data.flags = 0;
+        ret = kvm_vm_ioctl(kvm_state, KVM_SET_CLOCK, &data);
+        if (ret < 0) {
+            fprintf(stderr, "KVM_SET_CLOCK failed: %s\n", strerror(ret));
+            abort();
+        }
+
         if (!cap_clock_ctrl) {
             return;
         }
@@ -84,6 +62,26 @@ static void kvmclock_vm_state_change(void *opaque, int running,
                 return;
             }
         }
+    } else {
+        struct kvm_clock_data data;
+        int ret;
+
+        if (s->clock_valid) {
+            return;
+        }
+        ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data);
+        if (ret < 0) {
+            fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(ret));
+            abort();
+        }
+        s->clock = data.clock;
+
+        /*
+         * If the VM is stopped, declare the clock state valid to
+         * avoid re-reading it on next vmsave (which would return
+         * a different value). Will be reset when the VM is continued.
+         */
+        s->clock_valid = !runstate_is_running();
     }
 }
 
@@ -100,8 +98,6 @@ static const VMStateDescription kvmclock_vmsd = {
     .version_id = 1,
     .minimum_version_id = 1,
     .minimum_version_id_old = 1,
-    .pre_save = kvmclock_pre_save,
-    .post_load = kvmclock_post_load,
     .fields = (VMStateField[]) {
         VMSTATE_UINT64(clock, KVMClockState),
         VMSTATE_END_OF_LIST()