kvm: x86: Introduce kvmclock device to save/restore its state

If kvmclock is used, which implies the kernel supports it, register a
kvmclock device with the sysbus. Its main purpose is to save and restore
the kernel state on migration, but this will also allow to visualize it
one day.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
CC: Glauber Costa <glommer@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

3 files changed, 164 insertions, 7 deletions

diff --git a/hw/kvmclock.c b/hw/kvmclock.c
new file mode 100644
index 0000000000..b6ceddfba6
--- /dev/null
+++ b/hw/kvmclock.c
@@ -0,0 +1,125 @@
+/*
+ * QEMU KVM support, paravirtual clock device
+ *
+ * Copyright (C) 2011 Siemens AG
+ *
+ * Authors:
+ *  Jan Kiszka        <jan.kiszka@siemens.com>
+ *
+ * This work is licensed under the terms of the GNU GPL version 2.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu-common.h"
+#include "sysemu.h"
+#include "sysbus.h"
+#include "kvm.h"
+#include "kvmclock.h"
+
+#if defined(CONFIG_KVM_PARA) && defined(KVM_CAP_ADJUST_CLOCK)
+
+#include <linux/kvm.h>
+#include <linux/kvm_para.h>
+
+typedef struct KVMClockState {
+    SysBusDevice busdev;
+    uint64_t clock;
+    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 = !vm_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, int reason)
+{
+    KVMClockState *s = opaque;
+
+    if (running) {
+        s->clock_valid = false;
+    }
+}
+
+static int kvmclock_init(SysBusDevice *dev)
+{
+    KVMClockState *s = FROM_SYSBUS(KVMClockState, dev);
+
+    qemu_add_vm_change_state_handler(kvmclock_vm_state_change, s);
+    return 0;
+}
+
+static const VMStateDescription kvmclock_vmsd = {
+    .name = "kvmclock",
+    .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()
+    }
+};
+
+static SysBusDeviceInfo kvmclock_info = {
+    .qdev.name = "kvmclock",
+    .qdev.size = sizeof(KVMClockState),
+    .qdev.vmsd = &kvmclock_vmsd,
+    .qdev.no_user = 1,
+    .init = kvmclock_init,
+};
+
+/* Note: Must be called after VCPU initialization. */
+void kvmclock_create(void)
+{
+    if (kvm_enabled() &&
+        first_cpu->cpuid_kvm_features & (1ULL << KVM_FEATURE_CLOCKSOURCE)) {
+        sysbus_create_simple("kvmclock", -1, NULL);
+    }
+}
+
+static void kvmclock_register_device(void)
+{
+    if (kvm_enabled()) {
+        sysbus_register_withprop(&kvmclock_info);
+    }
+}
+
+device_init(kvmclock_register_device);
+
+#else /* !(CONFIG_KVM_PARA && KVM_CAP_ADJUST_CLOCK) */
+
+void kvmclock_create(void)
+{
+}
+#endif /* !(CONFIG_KVM_PARA && KVM_CAP_ADJUST_CLOCK) */
diff --git a/hw/kvmclock.h b/hw/kvmclock.h
new file mode 100644
index 0000000000..7a83cbe8f6
--- /dev/null
+++ b/hw/kvmclock.h
@@ -0,0 +1,14 @@
+/*
+ * QEMU KVM support, paravirtual clock device
+ *
+ * Copyright (C) 2011 Siemens AG
+ *
+ * Authors:
+ *  Jan Kiszka        <jan.kiszka@siemens.com>
+ *
+ * This work is licensed under the terms of the GNU GPL version 2.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+void kvmclock_create(void);
diff --git a/hw/pc_piix.c b/hw/pc_piix.c
index d0bd0cd1fa..291845478d 100644
--- a/hw/pc_piix.c
+++ b/hw/pc_piix.c
@@ -32,6 +32,7 @@
 #include "boards.h"
 #include "ide.h"
 #include "kvm.h"
+#include "kvmclock.h"
 #include "sysemu.h"
 #include "sysbus.h"
 #include "arch_init.h"
@@ -66,7 +67,8 @@ static void pc_init1(ram_addr_t ram_size,
                      const char *kernel_cmdline,
                      const char *initrd_filename,
                      const char *cpu_model,
-                     int pci_enabled)
+                     int pci_enabled,
+                     int kvmclock_enabled)
 {
     int i;
     ram_addr_t below_4g_mem_size, above_4g_mem_size;
@@ -86,6 +88,10 @@ static void pc_init1(ram_addr_t ram_size,
 
     pc_cpus_init(cpu_model);
 
+    if (kvmclock_enabled) {
+        kvmclock_create();
+    }
+
     /* allocate ram and load rom/bios */
     pc_memory_init(ram_size, kernel_filename, kernel_cmdline, initrd_filename,
                    &below_4g_mem_size, &above_4g_mem_size);
@@ -193,7 +199,19 @@ static void pc_init_pci(ram_addr_t ram_size,
 {
     pc_init1(ram_size, boot_device,
              kernel_filename, kernel_cmdline,
-             initrd_filename, cpu_model, 1);
+             initrd_filename, cpu_model, 1, 1);
+}
+
+static void pc_init_pci_no_kvmclock(ram_addr_t ram_size,
+                                    const char *boot_device,
+                                    const char *kernel_filename,
+                                    const char *kernel_cmdline,
+                                    const char *initrd_filename,
+                                    const char *cpu_model)
+{
+    pc_init1(ram_size, boot_device,
+             kernel_filename, kernel_cmdline,
+             initrd_filename, cpu_model, 1, 0);
 }
 
 static void pc_init_isa(ram_addr_t ram_size,
@@ -207,7 +225,7 @@ static void pc_init_isa(ram_addr_t ram_size,
         cpu_model = "486";
     pc_init1(ram_size, boot_device,
              kernel_filename, kernel_cmdline,
-             initrd_filename, cpu_model, 0);
+             initrd_filename, cpu_model, 0, 1);
 }
 
 static QEMUMachine pc_machine = {
@@ -222,7 +240,7 @@ static QEMUMachine pc_machine = {
 static QEMUMachine pc_machine_v0_13 = {
     .name = "pc-0.13",
     .desc = "Standard PC",
-    .init = pc_init_pci,
+    .init = pc_init_pci_no_kvmclock,
     .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         {
@@ -249,7 +267,7 @@ static QEMUMachine pc_machine_v0_13 = {
 static QEMUMachine pc_machine_v0_12 = {
     .name = "pc-0.12",
     .desc = "Standard PC",
-    .init = pc_init_pci,
+    .init = pc_init_pci_no_kvmclock,
     .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         {
@@ -280,7 +298,7 @@ static QEMUMachine pc_machine_v0_12 = {
 static QEMUMachine pc_machine_v0_11 = {
     .name = "pc-0.11",
     .desc = "Standard PC, qemu 0.11",
-    .init = pc_init_pci,
+    .init = pc_init_pci_no_kvmclock,
     .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         {
@@ -319,7 +337,7 @@ static QEMUMachine pc_machine_v0_11 = {
 static QEMUMachine pc_machine_v0_10 = {
     .name = "pc-0.10",
     .desc = "Standard PC, qemu 0.10",
-    .init = pc_init_pci,
+    .init = pc_init_pci_no_kvmclock,
     .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         {