Check for KVM_CAP_ADJUST_CLOCK capability KVM_CLOCK_TSC_STABLE, which
indicates that KVM_GET_CLOCK returns a value as seen by the guest at
that moment.
For new machine types, use this value rather than reading
from guest memory.
This reduces kvmclock difference on migration from 5s to 0.1s
(when max_downtime == 5s).
Signed-off-by: Marcelo Tosatti <mtosatti@xxxxxxxxxx>
---
hw/i386/kvm/clock.c | 108 ++++++++++++++++++++++++++++++++++++++++++-------
include/hw/i386/pc.h | 5 ++
target-i386/kvm.c | 7 +++
target-i386/kvm_i386.h | 1
4 files changed, 107 insertions(+), 14 deletions(-)
v2:
- improve variable names (Juan)
- consolidate code on kvm_get_clock function (Paolo)
- return mach_use_reliable_get_clock from needed function (Paolo)
Index: qemu-mig-advance-clock/hw/i386/kvm/clock.c
===================================================================
--- qemu-mig-advance-clock.orig/hw/i386/kvm/clock.c 2016-11-14 10:40:39.748116312 -0200
+++ qemu-mig-advance-clock/hw/i386/kvm/clock.c 2016-11-14 13:38:29.299955042 -0200
@@ -36,6 +36,12 @@
uint64_t clock;
bool clock_valid;
+
+ /* whether machine supports reliable KVM_GET_CLOCK */
+ bool mach_use_reliable_get_clock;
+
+ /* whether source host supported reliable KVM_GET_CLOCK */
+ bool src_use_reliable_get_clock;
} KVMClockState;
struct pvclock_vcpu_time_info {
@@ -81,6 +87,19 @@
return nsec + time.system_time;
}
+static uint64_t kvm_get_clock(void)
+{
+ struct kvm_clock_data data;
+ int ret;
+
+ ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data);
+ if (ret < 0) {
+ fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(ret));
+ abort();
+ }
+ return data.clock;
+}
+
static void kvmclock_vm_state_change(void *opaque, int running,
RunState state)
{
@@ -91,15 +110,37 @@
if (running) {
struct kvm_clock_data data = {};
- uint64_t time_at_migration = kvmclock_current_nsec(s);
+ uint64_t pvclock_via_mem = 0;
- s->clock_valid = false;
+ /* local (running VM) restore */
+ if (s->clock_valid) {
+ /*
+ * if host does not support reliable KVM_GET_CLOCK,
+ * read kvmclock value from memory
+ */
+ if (!kvm_has_adjust_clock_stable()) {
+ pvclock_via_mem = kvmclock_current_nsec(s);
+ }
+ /* migration/savevm/init restore */
+ } else {
+ /*
+ * use s->clock in case machine uses reliable
+ * get clock and source host supported
+ * reliable get clock
+ */
+ if (!(s->mach_use_reliable_get_clock &&
+ s->src_use_reliable_get_clock)) {
+ pvclock_via_mem = kvmclock_current_nsec(s);
+ }
+ }
- /* We can't rely on the migrated clock value, just discard it */
- if (time_at_migration) {
- s->clock = time_at_migration;
+ /* We can't rely on the saved clock value, just discard it */
+ if (pvclock_via_mem) {
+ s->clock = pvclock_via_mem;
}
+ s->clock_valid = false;
+
data.clock = s->clock;
ret = kvm_vm_ioctl(kvm_state, KVM_SET_CLOCK, &data);
if (ret < 0) {
@@ -120,8 +161,6 @@
}
}
} else {
- struct kvm_clock_data data;
- int ret;
if (s->clock_valid) {
return;
@@ -129,13 +168,7 @@
kvm_synchronize_all_tsc();
- 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;
-
+ s->clock = kvm_get_clock();
/*
* If the VM is stopped, declare the clock state valid to
* avoid re-reading it on next vmsave (which would return
@@ -152,22 +185,69 @@
qemu_add_vm_change_state_handler(kvmclock_vm_state_change, s);
}
+static bool kvmclock_src_use_reliable_get_clock(void *opaque)
+{
+ KVMClockState *s = opaque;
+
+ /*
+ * On machine types that support reliable KVM_GET_CLOCK,
+ * if host kernel does provide reliable KVM_GET_CLOCK,
+ * set src_use_reliable_get_clock=true so that destination
+ * avoids reading kvmclock from memory.
+ */
+ if (s->mach_use_reliable_get_clock && kvm_has_adjust_clock_stable()) {
+ s->src_use_reliable_get_clock = true;
+ }
+
+ return s->mach_use_reliable_get_clock;
+}
+
+static const VMStateDescription kvmclock_reliable_get_clock = {
+ .name = "kvmclock/src_use_reliable_get_clock",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = kvmclock_src_use_reliable_get_clock,
+ .fields = (VMStateField[]) {
+ VMSTATE_BOOL(src_use_reliable_get_clock, KVMClockState),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
+static void kvmclock_pre_save(void *opaque)
+{
+ KVMClockState *s = opaque;
+
+ s->clock = kvm_get_clock();
+}
+
static const VMStateDescription kvmclock_vmsd = {
.name = "kvmclock",
.version_id = 1,
.minimum_version_id = 1,
+ .pre_save = kvmclock_pre_save,
.fields = (VMStateField[]) {
VMSTATE_UINT64(clock, KVMClockState),
VMSTATE_END_OF_LIST()
+ },
+ .subsections = (const VMStateDescription * []) {
+ &kvmclock_reliable_get_clock,
+ NULL
}
};
+static Property kvmclock_properties[] = {
+ DEFINE_PROP_BOOL("mach_use_reliable_get_clock", KVMClockState,
+ mach_use_reliable_get_clock, true),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
static void kvmclock_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
dc->realize = kvmclock_realize;
dc->vmsd = &kvmclock_vmsd;
+ dc->props = kvmclock_properties;
}
static const TypeInfo kvmclock_info = {
Index: qemu-mig-advance-clock/include/hw/i386/pc.h
===================================================================
--- qemu-mig-advance-clock.orig/include/hw/i386/pc.h 2016-11-14 10:40:39.748116312 -0200
+++ qemu-mig-advance-clock/include/hw/i386/pc.h 2016-11-14 10:40:48.059128649 -0200
@@ -370,6 +370,11 @@
#define PC_COMPAT_2_7 \
HW_COMPAT_2_7 \
{\
+ .driver = "kvmclock",\
+ .property = "mach_use_reliable_get_clock",\
+ .value = "off",\
+ },\
+ {\
.driver = TYPE_X86_CPU,\
.property = "l3-cache",\
.value = "off",\
Index: qemu-mig-advance-clock/target-i386/kvm.c
===================================================================
--- qemu-mig-advance-clock.orig/target-i386/kvm.c 2016-11-14 10:40:39.750116314 -0200
+++ qemu-mig-advance-clock/target-i386/kvm.c 2016-11-14 10:40:48.061128652 -0200
@@ -117,6 +117,13 @@
return kvm_check_extension(kvm_state, KVM_CAP_X86_SMM);
}
+bool kvm_has_adjust_clock_stable(void)
+{
+ int ret = kvm_check_extension(kvm_state, KVM_CAP_ADJUST_CLOCK);
+
+ return (ret == KVM_CLOCK_TSC_STABLE);
+}
+
bool kvm_allows_irq0_override(void)
{
return !kvm_irqchip_in_kernel() || kvm_has_gsi_routing();
Index: qemu-mig-advance-clock/target-i386/kvm_i386.h
===================================================================
--- qemu-mig-advance-clock.orig/target-i386/kvm_i386.h 2016-11-14 10:40:39.751116316 -0200
+++ qemu-mig-advance-clock/target-i386/kvm_i386.h 2016-11-14 10:40:48.061128652 -0200
@@ -17,6 +17,7 @@
bool kvm_allows_irq0_override(void);
bool kvm_has_smm(void);
+bool kvm_has_adjust_clock_stable(void);
void kvm_synchronize_all_tsc(void);
void kvm_arch_reset_vcpu(X86CPU *cs);
void kvm_arch_do_init_vcpu(X86CPU *cs);
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
