[Qemu-devel] Re: [PATCH 15/15] kvm: x86: Introduce kvmclock device to save/restore its state

[Glauber Costa <glommer@redhat.com>]

On Mon, 2011-02-07 at 12:19 +0100, Jan Kiszka wrote:
> 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>
> ---
>  Makefile.target |    4 +-
>  hw/kvmclock.c   |  125 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  hw/kvmclock.h   |   14 ++++++
>  hw/pc_piix.c    |   31 +++++++++++---
>  4 files changed, 165 insertions(+), 9 deletions(-)
>  create mode 100644 hw/kvmclock.c
>  create mode 100644 hw/kvmclock.h
> 
> diff --git a/Makefile.target b/Makefile.target
> index b0ba95f..30232fa 100644
> --- a/Makefile.target
> +++ b/Makefile.target
> @@ -37,7 +37,7 @@ ifndef CONFIG_HAIKU
>  LIBS+=-lm
>  endif
>  
> -kvm.o kvm-all.o vhost.o vhost_net.o: QEMU_CFLAGS+=$(KVM_CFLAGS)
> +kvm.o kvm-all.o vhost.o vhost_net.o kvmclock.o: QEMU_CFLAGS+=$(KVM_CFLAGS)
>  
>  config-target.h: config-target.h-timestamp
>  config-target.h-timestamp: config-target.mak
> @@ -218,7 +218,7 @@ obj-i386-y += cirrus_vga.o apic.o ioapic.o piix_pci.o
>  obj-i386-y += vmmouse.o vmport.o hpet.o applesmc.o
>  obj-i386-y += device-hotplug.o pci-hotplug.o smbios.o wdt_ib700.o
>  obj-i386-y += debugcon.o multiboot.o
> -obj-i386-y += pc_piix.o
> +obj-i386-y += pc_piix.o kvmclock.o
>  obj-i386-$(CONFIG_SPICE) += qxl.o qxl-logger.o qxl-render.o
>  
>  # shared objects
> diff --git a/hw/kvmclock.c b/hw/kvmclock.c
> new file mode 100644
> index 0000000..b6ceddf
> --- /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 0000000..7a83cbe
> --- /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 7b74473..9bc4659 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)
>  
What exactly is your motivation to that ? I think mid/long-term
we should be making machine initialization more common among
architectures, not introducing more arch specific, or even worse, kvm
specific parameters here.

I'd like to understand what do we gain from that, since opting kvmclock
in our out is done by cpuid anyway - no need for a specific machine.