Re: [Qemu-devel] [PATCH v8 5/6] introduce a new qom device to deal with panicked event

[Blue Swirl <blauwirbel@gmail.com>]

On Wed, Aug 22, 2012 at 7:30 AM, Wen Congyang <wency@cn.fujitsu.com> wrote:
> At 08/09/2012 03:01 AM, Blue Swirl Wrote:
>> On Wed, Aug 8, 2012 at 2:47 AM, Wen Congyang <wency@cn.fujitsu.com> wrote:
>>> If the target is x86/x86_64, the guest's kernel will write 0x01 to the
>>> port KVM_PV_EVENT_PORT when it is panciked. This patch introduces a new
>>> qom device kvm_pv_ioport to listen this I/O port, and deal with panicked
>>> event according to panicked_action's value. The possible actions are:
>>> 1. emit QEVENT_GUEST_PANICKED only
>>> 2. emit QEVENT_GUEST_PANICKED and pause the guest
>>> 3. emit QEVENT_GUEST_PANICKED and poweroff the guest
>>> 4. emit QEVENT_GUEST_PANICKED and reset the guest
>>>
>>> I/O ports does not work for some targets(for example: s390). And you
>>> can implement another qom device, and include it's code into pv_event.c
>>> for such target.
>>>
>>> Note: if we emit QEVENT_GUEST_PANICKED only, and the management
>>> application does not receive this event(the management may not
>>> run when the event is emitted), the management won't know the
>>> guest is panicked.
>>>
>>> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
>>> ---
>>>  hw/kvm/Makefile.objs |    2 +-
>>>  hw/kvm/pv_event.c    |  109 ++++++++++++++++++++++++++++++++++++++++++++++++++
>>>  hw/kvm/pv_ioport.c   |   93 ++++++++++++++++++++++++++++++++++++++++++
>>>  hw/pc_piix.c         |    9 ++++
>>>  kvm.h                |    2 +
>>>  5 files changed, 214 insertions(+), 1 deletions(-)
>>>  create mode 100644 hw/kvm/pv_event.c
>>>  create mode 100644 hw/kvm/pv_ioport.c
>>>
>>> diff --git a/hw/kvm/Makefile.objs b/hw/kvm/Makefile.objs
>>> index 226497a..23e3b30 100644
>>> --- a/hw/kvm/Makefile.objs
>>> +++ b/hw/kvm/Makefile.objs
>>> @@ -1 +1 @@
>>> -obj-$(CONFIG_KVM) += clock.o apic.o i8259.o ioapic.o i8254.o
>>> +obj-$(CONFIG_KVM) += clock.o apic.o i8259.o ioapic.o i8254.o pv_event.o
>>> diff --git a/hw/kvm/pv_event.c b/hw/kvm/pv_event.c
>>> new file mode 100644
>>> index 0000000..8897237
>>> --- /dev/null
>>> +++ b/hw/kvm/pv_event.c
>>> @@ -0,0 +1,109 @@
>>> +/*
>>> + * QEMU KVM support, paravirtual event device
>>> + *
>>> + * Copyright Fujitsu, Corp. 2012
>>> + *
>>> + * Authors:
>>> + *     Wen Congyang <wency@cn.fujitsu.com>
>>> + *
>>> + * This work is licensed under the terms of the GNU GPL, version 2 or later.
>>> + * See the COPYING file in the top-level directory.
>>> + *
>>> + */
>>> +
>>> +#include <linux/kvm_para.h>
>>> +#include <asm/kvm_para.h>
>>> +#include <qobject.h>
>>> +#include <qjson.h>
>>> +#include <monitor.h>
>>> +#include <sysemu.h>
>>> +#include <kvm.h>
>>> +
>>> +/* Possible values for action parameter. */
>>> +#define PANICKED_REPORT     1   /* emit QEVENT_GUEST_PANICKED only */
>>> +#define PANICKED_PAUSE      2   /* emit QEVENT_GUEST_PANICKED and pause VM */
>>> +#define PANICKED_POWEROFF   3   /* emit QEVENT_GUEST_PANICKED and quit VM */
>>> +#define PANICKED_RESET      4   /* emit QEVENT_GUEST_PANICKED and reset VM */
>>> +
>>> +#define PV_EVENT_DRIVER     "kvm_pv_event"
>>> +
>>> +struct pv_event_action {
>>
>> PVEventAction
>>
>>> +    char *panicked_action;
>>> +    int panicked_action_value;
>>> +};
>>> +
>>> +#define DEFINE_PV_EVENT_PROPERTIES(_state, _conf)   \
>>> +    DEFINE_PROP_STRING("panicked_action", _state, _conf.panicked_action)
>>> +
>>> +static void panicked_mon_event(const char *action)
>>> +{
>>> +    QObject *data;
>>> +
>>> +    data = qobject_from_jsonf("{ 'action': %s }", action);
>>> +    monitor_protocol_event(QEVENT_GUEST_PANICKED, data);
>>> +    qobject_decref(data);
>>> +}
>>> +
>>> +static void panicked_perform_action(uint32_t panicked_action)
>>> +{
>>> +    switch (panicked_action) {
>>> +    case PANICKED_REPORT:
>>> +        panicked_mon_event("report");
>>> +        break;
>>> +
>>> +    case PANICKED_PAUSE:
>>> +        panicked_mon_event("pause");
>>> +        vm_stop(RUN_STATE_GUEST_PANICKED);
>>> +        break;
>>> +
>>> +    case PANICKED_POWEROFF:
>>> +        panicked_mon_event("poweroff");
>>> +        qemu_system_shutdown_request();
>>> +        break;
>>
>> Misses a line break unlike other cases.
>>
>>> +    case PANICKED_RESET:
>>> +        panicked_mon_event("reset");
>>> +        qemu_system_reset_request();
>>> +        break;
>>> +    }
>>> +}
>>> +
>>> +static uint64_t supported_event(void)
>>> +{
>>> +    return 1 << KVM_PV_FEATURE_PANICKED;
>>> +}
>>> +
>>> +static void handle_event(int event, struct pv_event_action *conf)
>>> +{
>>> +    if (event == KVM_PV_EVENT_PANICKED) {
>>> +        panicked_perform_action(conf->panicked_action_value);
>>> +    }
>>> +}
>>> +
>>> +static int pv_event_init(struct pv_event_action *conf)
>>> +{
>>> +    if (!conf->panicked_action) {
>>> +        conf->panicked_action_value = PANICKED_REPORT;
>>> +    } else if (strcasecmp(conf->panicked_action, "none") == 0) {
>>> +        conf->panicked_action_value = PANICKED_REPORT;
>>> +    } else if (strcasecmp(conf->panicked_action, "pause") == 0) {
>>> +        conf->panicked_action_value = PANICKED_PAUSE;
>>> +    } else if (strcasecmp(conf->panicked_action, "poweroff") == 0) {
>>> +        conf->panicked_action_value = PANICKED_POWEROFF;
>>> +    } else if (strcasecmp(conf->panicked_action, "reset") == 0) {
>>> +        conf->panicked_action_value = PANICKED_RESET;
>>> +    } else {
>>> +        return -1;
>>> +    }
>>> +
>>> +    return 0;
>>> +}
>>> +
>>> +#if defined(KVM_PV_EVENT_PORT)
>>> +
>>> +#include "pv_ioport.c"
>>
>> I'd rather not include any .c files but insert the contents here directly.
>>
>>> +
>>> +#else
>>> +void kvm_pv_event_init(void *opaque)
>>> +{
>>> +}
>>> +#endif
>>> diff --git a/hw/kvm/pv_ioport.c b/hw/kvm/pv_ioport.c
>>> new file mode 100644
>>> index 0000000..c2ed6b5
>>> --- /dev/null
>>> +++ b/hw/kvm/pv_ioport.c
>>> @@ -0,0 +1,93 @@
>>> +/*
>>> + * QEMU KVM support, paravirtual I/O port device
>>> + *
>>> + * Copyright Fujitsu, Corp. 2012
>>> + *
>>> + * Authors:
>>> + *     Wen Congyang <wency@cn.fujitsu.com>
>>> + *
>>> + * This work is licensed under the terms of the GNU GPL, version 2 or later.
>>> + * See the COPYING file in the top-level directory.
>>> + *
>>> + */
>>> +
>>> +#include "hw/isa.h"
>>> +
>>> +typedef struct {
>>> +    ISADevice dev;
>>> +    struct pv_event_action conf;
>>> +    MemoryRegion ioport;
>>> +} PVIOPortState;
>>> +
>>> +static uint64_t pv_io_read(void *opaque, target_phys_addr_t addr, unsigned size)
>>> +{
>>> +    return supported_event();
>>> +}
>>> +
>>> +static void pv_io_write(void *opaque, target_phys_addr_t addr, uint64_t val,
>>> +                        unsigned size)
>>> +{
>>> +    PVIOPortState *s = opaque;
>>> +
>>> +    handle_event(val, &s->conf);
>>> +}
>>> +
>>> +static const MemoryRegionOps pv_io_ops = {
>>> +    .read = pv_io_read,
>>> +    .write = pv_io_write,
>>> +    .impl = {
>>> +        .min_access_size = 4,
>>> +        .max_access_size = 4,
>>> +    },
>>> +};
>>> +
>>> +static int pv_ioport_initfn(ISADevice *dev)
>>> +{
>>> +    PVIOPortState *s = DO_UPCAST(PVIOPortState, dev, dev);
>>> +
>>> +    if (pv_event_init(&s->conf) < 0)
>>> +        return -1;
>>
>> Mandatory braces missing.
>>
>>> +
>>> +    memory_region_init_io(&s->ioport, &pv_io_ops, s, "pv_event", 1);
>>> +    isa_register_ioport(dev, &s->ioport, KVM_PV_EVENT_PORT);
>>> +
>>> +    return 0;
>>> +}
>>> +
>>> +static Property pv_ioport_properties[] = {
>>> +    DEFINE_PV_EVENT_PROPERTIES(PVIOPortState, conf),
>>> +    DEFINE_PROP_END_OF_LIST(),
>>> +};
>>> +
>>> +static void pv_ioport_class_init(ObjectClass *klass, void *data)
>>> +{
>>> +    DeviceClass *dc = DEVICE_CLASS(klass);
>>> +    ISADeviceClass *ic = ISA_DEVICE_CLASS(klass);
>>> +
>>> +    ic->init = pv_ioport_initfn;
>>> +    dc->no_user = 1;
>>> +    dc->props = pv_ioport_properties;
>>> +}
>>> +
>>> +static TypeInfo pv_ioport_info = {
>>> +    .name          = PV_EVENT_DRIVER,
>>> +    .parent        = TYPE_ISA_DEVICE,
>>> +    .instance_size = sizeof(PVIOPortState),
>>> +    .class_init    = pv_ioport_class_init,
>>> +};
>>> +
>>> +static void pv_ioport_register_types(void)
>>> +{
>>> +    type_register_static(&pv_ioport_info);
>>> +}
>>> +
>>> +type_init(pv_ioport_register_types)
>>> +
>>> +void kvm_pv_event_init(void *opaque)
>>> +{
>>> +    ISABus *bus = opaque;
>>> +    ISADevice *dev;
>>> +
>>> +    dev = isa_create(bus, PV_EVENT_DRIVER);
>>> +    qdev_init_nofail(&dev->qdev);
>>> +}
>>> diff --git a/hw/pc_piix.c b/hw/pc_piix.c
>>> index 0c0096f..4af8403 100644
>>> --- a/hw/pc_piix.c
>>> +++ b/hw/pc_piix.c
>>> @@ -46,6 +46,9 @@
>>>  #ifdef CONFIG_XEN
>>>  #  include <xen/hvm/hvm_info_table.h>
>>>  #endif
>>> +#ifdef CONFIG_KVM
>>> +#   include <asm/kvm_para.h>
>>> +#endif
>>
>> I'd remove this and the #ifdeffery below since a stub function is
>> provided. This is not performance critical.
>
> The stub function is in the file hw/kvm/pv_event.c, and this file
> will be complied only when CONFIG_KVM is y.

Usually the stubs are always provided, compare to for example
kvm-stub.c. Wouldn't that simplify the code?

>
> Thanks
> Wen Congyang
>
>>
>>>
>>>  #define MAX_IDE_BUS 2
>>>
>>> @@ -285,6 +288,12 @@ static void pc_init1(MemoryRegion *system_memory,
>>>      if (pci_enabled) {
>>>          pc_pci_device_init(pci_bus);
>>>      }
>>> +
>>> +#ifdef KVM_PV_EVENT_PORT
>>> +    if (kvm_enabled()) {
>>> +        kvm_pv_event_init(isa_bus);
>>> +    }
>>> +#endif
>>>  }
>>>
>>>  static void pc_init_pci(ram_addr_t ram_size,
>>> diff --git a/kvm.h b/kvm.h
>>> index 2617dd5..598dcbe 100644
>>> --- a/kvm.h
>>> +++ b/kvm.h
>>> @@ -222,4 +222,6 @@ int kvm_irqchip_add_irqfd(KVMState *s, int fd, int virq);
>>>  int kvm_irqchip_remove_irqfd(KVMState *s, int fd, int virq);
>>>  int kvm_irqchip_add_irq_notifier(KVMState *s, EventNotifier *n, int virq);
>>>  int kvm_irqchip_remove_irq_notifier(KVMState *s, EventNotifier *n, int virq);
>>> +
>>> +void kvm_pv_event_init(void *opaque);
>>>  #endif
>>> --
>>> 1.7.1
>>>
>>>
>>
>