spapr: clock should count only if vm is running

This is a port to ppc of the i386 commit:
    00f4d64 kvmclock: clock should count only if vm is running

We remove timebase_post_load function, and use the VM state
change handler to save and restore the guest_timebase (on stop
and continue).

We keep timebase_pre_save to reduce the clock difference on
migration like in:
    6053a86 kvmclock: reduce kvmclock difference on migration

Time base offset has originally been introduced by commit
    98a8b52 spapr: Add support for time base offset migration

So while VM is paused, the time is stopped. This allows to have
the same result with date (based on Time Base Register) and
hwclock (based on "get-time-of-day" RTAS call).

Moreover in TCG mode, the Time Base is always paused, so this
patch also adjust the behavior between TCG and KVM.

VM state field "time_of_the_day_ns" is now useless but we keep
it to be able to migrate to older version of the machine.

As vmstate_ppc_timebase structure (with timebase_pre_save() and
timebase_post_load() functions) was only used by vmstate_spapr,
we register the VM state change handler only in ppc_spapr_init().

Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

2 files changed, 49 insertions, 23 deletions

diff --git a/hw/ppc/ppc.c b/hw/ppc/ppc.c
index f9a4b51d64..d171e60b5c 100644
--- a/hw/ppc/ppc.c
+++ b/hw/ppc/ppc.c
@@ -847,9 +847,8 @@ static void cpu_ppc_set_tb_clk (void *opaque, uint32_t freq)
     cpu_ppc_store_purr(cpu, 0x0000000000000000ULL);
 }
 
-static void timebase_pre_save(void *opaque)
+static void timebase_save(PPCTimebase *tb)
 {
-    PPCTimebase *tb = opaque;
     uint64_t ticks = cpu_get_host_ticks();
     PowerPCCPU *first_ppc_cpu = POWERPC_CPU(first_cpu);
 
@@ -858,43 +857,30 @@ static void timebase_pre_save(void *opaque)
         return;
     }
 
+    /* not used anymore, we keep it for compatibility */
     tb->time_of_the_day_ns = qemu_clock_get_ns(QEMU_CLOCK_HOST);
     /*
-     * tb_offset is only expected to be changed by migration so
+     * tb_offset is only expected to be changed by QEMU so
      * there is no need to update it from KVM here
      */
     tb->guest_timebase = ticks + first_ppc_cpu->env.tb_env->tb_offset;
 }
 
-static int timebase_post_load(void *opaque, int version_id)
+static void timebase_load(PPCTimebase *tb)
 {
-    PPCTimebase *tb_remote = opaque;
     CPUState *cpu;
     PowerPCCPU *first_ppc_cpu = POWERPC_CPU(first_cpu);
-    int64_t tb_off_adj, tb_off, ns_diff;
-    int64_t migration_duration_ns, migration_duration_tb, guest_tb, host_ns;
+    int64_t tb_off_adj, tb_off;
     unsigned long freq;
 
     if (!first_ppc_cpu->env.tb_env) {
         error_report("No timebase object");
-        return -1;
+        return;
     }
 
     freq = first_ppc_cpu->env.tb_env->tb_freq;
-    /*
-     * Calculate timebase on the destination side of migration.
-     * The destination timebase must be not less than the source timebase.
-     * We try to adjust timebase by downtime if host clocks are not
-     * too much out of sync (1 second for now).
-     */
-    host_ns = qemu_clock_get_ns(QEMU_CLOCK_HOST);
-    ns_diff = MAX(0, host_ns - tb_remote->time_of_the_day_ns);
-    migration_duration_ns = MIN(NANOSECONDS_PER_SECOND, ns_diff);
-    migration_duration_tb = muldiv64(freq, migration_duration_ns,
-                                     NANOSECONDS_PER_SECOND);
-    guest_tb = tb_remote->guest_timebase + MIN(0, migration_duration_tb);
 
-    tb_off_adj = guest_tb - cpu_get_host_ticks();
+    tb_off_adj = tb->guest_timebase - cpu_get_host_ticks();
 
     tb_off = first_ppc_cpu->env.tb_env->tb_offset;
     trace_ppc_tb_adjust(tb_off, tb_off_adj, tb_off_adj - tb_off,
@@ -904,9 +890,44 @@ static int timebase_post_load(void *opaque, int version_id)
     CPU_FOREACH(cpu) {
         PowerPCCPU *pcpu = POWERPC_CPU(cpu);
         pcpu->env.tb_env->tb_offset = tb_off_adj;
+#if defined(CONFIG_KVM)
+        kvm_set_one_reg(cpu, KVM_REG_PPC_TB_OFFSET,
+                        &pcpu->env.tb_env->tb_offset);
+#endif
     }
+}
 
-    return 0;
+void cpu_ppc_clock_vm_state_change(void *opaque, int running,
+                                   RunState state)
+{
+    PPCTimebase *tb = opaque;
+
+    if (running) {
+        timebase_load(tb);
+    } else {
+        timebase_save(tb);
+    }
+}
+
+/*
+ * When migrating, read the clock just before migration,
+ * so that the guest clock counts during the events
+ * between:
+ *
+ *  * vm_stop()
+ *  *
+ *  * pre_save()
+ *
+ *  This reduces clock difference on migration from 5s
+ *  to 0.1s (when max_downtime == 5s), because sending the
+ *  final pages of memory (which happens between vm_stop()
+ *  and pre_save()) takes max_downtime.
+ */
+static void timebase_pre_save(void *opaque)
+{
+    PPCTimebase *tb = opaque;
+
+    timebase_save(tb);
 }
 
 const VMStateDescription vmstate_ppc_timebase = {
@@ -915,7 +936,6 @@ const VMStateDescription vmstate_ppc_timebase = {
     .minimum_version_id = 1,
     .minimum_version_id_old = 1,
     .pre_save = timebase_pre_save,
-    .post_load = timebase_post_load,
     .fields      = (VMStateField []) {
         VMSTATE_UINT64(guest_timebase, PPCTimebase),
         VMSTATE_INT64(time_of_the_day_ns, PPCTimebase),
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index b71cd7aa43..9fc3fb90a1 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -2129,6 +2129,12 @@ static void ppc_spapr_init(MachineState *machine)
     qemu_register_reset(spapr_ccs_reset_hook, spapr);
 
     qemu_register_boot_set(spapr_boot_set, spapr);
+
+    /* to stop and start vmclock */
+    if (kvm_enabled()) {
+        qemu_add_vm_change_state_handler(cpu_ppc_clock_vm_state_change,
+                                         &spapr->tb);
+    }
 }
 
 static int spapr_kvm_type(const char *vm_type)