by Marcelo Tosatti

[permalink] [raw]

Subject: Re: [PATCH v8] kvm: notify host when the guest is panicked

On Wed, Aug 08, 2012 at 10:43:01AM +0800, Wen Congyang wrote:
> We can know the guest is panicked when the guest runs on xen.
> But we do not have such feature on kvm.
>
> Another purpose of this feature is: management app(for example:
> libvirt) can do auto dump when the guest is panicked. If management
> app does not do auto dump, the guest's user can do dump by hand if
> he sees the guest is panicked.
>
> We have three solutions to implement this feature:
> 1. use vmcall
> 2. use I/O port
> 3. use virtio-serial.
>
> We have decided to avoid touching hypervisor. The reason why I choose
> choose the I/O port is:
> 1. it is easier to implememt
> 2. it does not depend any virtual device
> 3. it can work when starting the kernel

How about searching for the "Kernel panic - not syncing" string
in the guests serial output? Say libvirtd could take an action upon
that?

Advantages:
- It works for all architectures.
- It does not depend on any virtual device.
- It works as early as serial console output does (panics before
that should be rare).
- It allows you to see why the guest panicked.

> Signed-off-by: Wen Congyang <[email protected]>
> ---
> Documentation/virtual/kvm/pv_event.txt | 32 ++++++++++++++++++++++++++++++++
> arch/ia64/include/asm/kvm_para.h | 14 ++++++++++++++
> arch/powerpc/include/asm/kvm_para.h | 14 ++++++++++++++
> arch/s390/include/asm/kvm_para.h | 14 ++++++++++++++
> arch/x86/include/asm/kvm_para.h | 27 +++++++++++++++++++++++++++
> arch/x86/kernel/kvm.c | 25 +++++++++++++++++++++++++
> include/linux/kvm_para.h | 23 +++++++++++++++++++++++
> 7 files changed, 149 insertions(+), 0 deletions(-)
> create mode 100644 Documentation/virtual/kvm/pv_event.txt
>
> diff --git a/Documentation/virtual/kvm/pv_event.txt b/Documentation/virtual/kvm/pv_event.txt
> new file mode 100644
> index 0000000..0ebc890
> --- /dev/null
> +++ b/Documentation/virtual/kvm/pv_event.txt
> @@ -0,0 +1,32 @@
> +The KVM paravirtual event interface
> +=================================
> +
> +Initializing the paravirtual event interface
> +======================
> +kvm_pv_event_init()
> +Argiments:
> + None
> +
> +Return Value:
> + 0 : The guest kernel can't use paravirtual event interface.
> + -1: The guest kernel can use paravirtual event interface.
> +
> +Querying whether the event can be ejected
> +======================
> +kvm_pv_has_feature()
> +Arguments:
> + feature: The bit value of this paravirtual event to query
> +
> +Return Value:
> + 0: The guest kernel can't eject this paravirtual event.
> + 1: The guest kernel can eject this paravirtual event.
> +
> +
> +Ejecting paravirtual event
> +======================
> +kvm_pv_eject_event()
> +Arguments:
> + event: The event to be ejected.
> +
> +Return Value:
> + None
> diff --git a/arch/ia64/include/asm/kvm_para.h b/arch/ia64/include/asm/kvm_para.h
> index 2019cb9..b5ec658 100644
> --- a/arch/ia64/include/asm/kvm_para.h
> +++ b/arch/ia64/include/asm/kvm_para.h
> @@ -31,6 +31,20 @@ static inline bool kvm_check_and_clear_guest_paused(void)
> return false;
> }
>
> +static inline int kvm_arch_pv_event_init(void)
> +{
> + return 0;
> +}
> +
> +static inline unsigned int kvm_arch_pv_features(void)
> +{
> + return 0;
> +}
> +
> +static inline void kvm_arch_pv_eject_event(unsigned int event)
> +{
> +}
> +
> #endif
>
> #endif
> diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
> index c18916b..01b98c7 100644
> --- a/arch/powerpc/include/asm/kvm_para.h
> +++ b/arch/powerpc/include/asm/kvm_para.h
> @@ -211,6 +211,20 @@ static inline bool kvm_check_and_clear_guest_paused(void)
> return false;
> }
>
> +static inline int kvm_arch_pv_event_init(void)
> +{
> + return 0;
> +}
> +
> +static inline unsigned int kvm_arch_pv_features(void)
> +{
> + return 0;
> +}
> +
> +static inline void kvm_arch_pv_eject_event(unsigned int event)
> +{
> +}
> +
> #endif /* __KERNEL__ */
>
> #endif /* __POWERPC_KVM_PARA_H__ */
> diff --git a/arch/s390/include/asm/kvm_para.h b/arch/s390/include/asm/kvm_para.h
> index da44867..00ce058 100644
> --- a/arch/s390/include/asm/kvm_para.h
> +++ b/arch/s390/include/asm/kvm_para.h
> @@ -154,6 +154,20 @@ static inline bool kvm_check_and_clear_guest_paused(void)
> return false;
> }
>
> +static inline int kvm_arch_pv_event_init(void)
> +{
> + return 0;
> +}
> +
> +static inline unsigned int kvm_arch_pv_features(void)
> +{
> + return 0;
> +}
> +
> +static inline void kvm_arch_pv_eject_event(unsigned int event)
> +{
> +}
> +
> #endif
>
> #endif /* __S390_KVM_PARA_H */
> diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
> index 2f7712e..7d297f0 100644
> --- a/arch/x86/include/asm/kvm_para.h
> +++ b/arch/x86/include/asm/kvm_para.h
> @@ -96,8 +96,11 @@ struct kvm_vcpu_pv_apf_data {
> #define KVM_PV_EOI_ENABLED KVM_PV_EOI_MASK
> #define KVM_PV_EOI_DISABLED 0x0
>
> +#define KVM_PV_EVENT_PORT (0x505UL)
> +
> #ifdef __KERNEL__
> #include <asm/processor.h>
> +#include <linux/ioport.h>
>
> extern void kvmclock_init(void);
> extern int kvm_register_clock(char *txt);
> @@ -228,6 +231,30 @@ static inline void kvm_disable_steal_time(void)
> }
> #endif
>
> +static inline int kvm_arch_pv_event_init(void)
> +{
> + if (!request_region(KVM_PV_EVENT_PORT, 1, "KVM_PV_EVENT"))
> + return -1;
> +
> + return 0;
> +}
> +
> +static inline unsigned int kvm_arch_pv_features(void)
> +{
> + unsigned int features = inl(KVM_PV_EVENT_PORT);
> +
> + /* Reading from an invalid I/O port will return -1 */
> + if (features == ~0)
> + features = 0;
> +
> + return features;
> +}
> +
> +static inline void kvm_arch_pv_eject_event(unsigned int event)
> +{
> + outl(event, KVM_PV_EVENT_PORT);
> +}
> +
> #endif /* __KERNEL__ */
>
> #endif /* _ASM_X86_KVM_PARA_H */
> diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
> index c1d61ee..6129459 100644
> --- a/arch/x86/kernel/kvm.c
> +++ b/arch/x86/kernel/kvm.c
> @@ -368,6 +368,17 @@ static struct notifier_block kvm_pv_reboot_nb = {
> .notifier_call = kvm_pv_reboot_notify,
> };
>
> +static int
> +kvm_pv_panic_notify(struct notifier_block *nb, unsigned long code, void *unused)
> +{
> + kvm_pv_eject_event(KVM_PV_EVENT_PANICKED);
> + return NOTIFY_DONE;
> +}
> +
> +static struct notifier_block kvm_pv_panic_nb = {
> + .notifier_call = kvm_pv_panic_notify,
> +};
> +
> static u64 kvm_steal_clock(int cpu)
> {
> u64 steal;
> @@ -447,6 +458,20 @@ static void __init kvm_apf_trap_init(void)
> set_intr_gate(14, &async_page_fault);
> }
>
> +static void __init kvm_pv_panicked_event_init(void)
> +{
> + if (!kvm_para_available())
> + return;
> +
> + if (kvm_pv_event_init())
> + return;
> +
> + if (kvm_pv_has_feature(KVM_PV_FEATURE_PANICKED))
> + atomic_notifier_chain_register(&panic_notifier_list,
> + &kvm_pv_panic_nb);
> +}
> +arch_initcall(kvm_pv_panicked_event_init);
> +
> void __init kvm_guest_init(void)
> {
> int i;
> diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h
> index ff476dd..8e0fb81 100644
> --- a/include/linux/kvm_para.h
> +++ b/include/linux/kvm_para.h
> @@ -20,6 +20,12 @@
> #define KVM_HC_FEATURES 3
> #define KVM_HC_PPC_MAP_MAGIC_PAGE 4
>
> +/* The bit of supported pv event */
> +#define KVM_PV_FEATURE_PANICKED 0
> +
> +/* The pv event value */
> +#define KVM_PV_EVENT_PANICKED 1
> +
> /*
> * hypercalls use architecture specific
> */
> @@ -33,5 +39,22 @@ static inline int kvm_para_has_feature(unsigned int feature)
> return 1;
> return 0;
> }
> +
> +static inline int kvm_pv_event_init(void)
> +{
> + return kvm_arch_pv_event_init();
> +}
> +
> +static inline int kvm_pv_has_feature(unsigned int feature)
> +{
> + if (kvm_arch_pv_features() & (1UL << feature))
> + return 1;
> + return 0;
> +}
> +
> +static inline void kvm_pv_eject_event(unsigned int event)
> +{
> + kvm_arch_pv_eject_event(event);
> +}
> #endif /* __KERNEL__ */
> #endif /* __LINUX_KVM_PARA_H */
> --
> 1.7.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html

2012-08-13 19:48:57

On Wed, Aug 22, 2012 at 7:30 AM, Wen Congyang <[email protected]> wrote:
> At 08/09/2012 03:01 AM, Blue Swirl Wrote:
>> On Wed, Aug 8, 2012 at 2:47 AM, Wen Congyang <[email protected]> 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 <[email protected]>
>>> ---
>>> 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 <[email protected]>
>>> + *
>>> + * 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 <[email protected]>
>>> + *
>>> + * 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
>>>
>>>
>>
>