| Message ID | 20231101152311.181817-1-andrey.drobyshev@virtuozzo.com |
|---|---|
| State | New |
| Headers | show |
| Series | kvm: emit GUEST_PANICKED event in case of abnormal KVM exit | expand |
On 11/1/23 16:23, Andrey Drobyshev wrote: > Currently we emit GUEST_PANICKED event in case kvm_vcpu_ioctl() returns > KVM_EXIT_SYSTEM_EVENT with the event type KVM_SYSTEM_EVENT_CRASH. Let's > extend this scenario and emit GUEST_PANICKED in case of an abnormal KVM > exit. That's a natural thing to do since in this case guest is no > longer operational anyway. > > Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com> > Acked-by: Denis V. Lunev <den@virtuozzo.com> > --- > accel/kvm/kvm-all.c | 19 +++++++++++++++---- > 1 file changed, 15 insertions(+), 4 deletions(-) > > diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c > index e39a810a4e..d74b3f0b0e 100644 > --- a/accel/kvm/kvm-all.c > +++ b/accel/kvm/kvm-all.c > @@ -2816,6 +2816,14 @@ static void kvm_eat_signals(CPUState *cpu) > } while (sigismember(&chkset, SIG_IPI)); > } > > +static void kvm_emit_guest_crash(CPUState *cpu) > +{ > + kvm_cpu_synchronize_state(cpu); > + qemu_mutex_lock_iothread(); > + qemu_system_guest_panicked(cpu_get_crash_info(cpu)); > + qemu_mutex_unlock_iothread(); > +} > + > int kvm_cpu_exec(CPUState *cpu) > { > struct kvm_run *run = cpu->kvm_run; > @@ -2969,21 +2977,24 @@ int kvm_cpu_exec(CPUState *cpu) > ret = EXCP_INTERRUPT; > break; > case KVM_SYSTEM_EVENT_CRASH: > - kvm_cpu_synchronize_state(cpu); > - qemu_mutex_lock_iothread(); > - qemu_system_guest_panicked(cpu_get_crash_info(cpu)); > - qemu_mutex_unlock_iothread(); > + kvm_emit_guest_crash(cpu); > ret = 0; > break; > default: > DPRINTF("kvm_arch_handle_exit\n"); > ret = kvm_arch_handle_exit(cpu, run); > + if (ret < 0) { > + kvm_emit_guest_crash(cpu); > + } > break; > } > break; > default: > DPRINTF("kvm_arch_handle_exit\n"); > ret = kvm_arch_handle_exit(cpu, run); > + if (ret < 0) { > + kvm_emit_guest_crash(cpu); > + } > break; > } > } while (ret == 0); This allows to gracefully handle this problem in production and reset the guest using on_crash action in libvirt.
On 11/1/23 18:13, Denis V. Lunev wrote: > On 11/1/23 16:23, Andrey Drobyshev wrote: >> Currently we emit GUEST_PANICKED event in case kvm_vcpu_ioctl() returns >> KVM_EXIT_SYSTEM_EVENT with the event type KVM_SYSTEM_EVENT_CRASH. Let's >> extend this scenario and emit GUEST_PANICKED in case of an abnormal KVM >> exit. That's a natural thing to do since in this case guest is no >> longer operational anyway. >> >> Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com> >> Acked-by: Denis V. Lunev <den@virtuozzo.com> >> --- >> accel/kvm/kvm-all.c | 19 +++++++++++++++---- >> 1 file changed, 15 insertions(+), 4 deletions(-) >> >> diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c >> index e39a810a4e..d74b3f0b0e 100644 >> --- a/accel/kvm/kvm-all.c >> +++ b/accel/kvm/kvm-all.c >> @@ -2816,6 +2816,14 @@ static void kvm_eat_signals(CPUState *cpu) >> } while (sigismember(&chkset, SIG_IPI)); >> } >> +static void kvm_emit_guest_crash(CPUState *cpu) >> +{ >> + kvm_cpu_synchronize_state(cpu); >> + qemu_mutex_lock_iothread(); >> + qemu_system_guest_panicked(cpu_get_crash_info(cpu)); >> + qemu_mutex_unlock_iothread(); >> +} >> + >> int kvm_cpu_exec(CPUState *cpu) >> { >> struct kvm_run *run = cpu->kvm_run; >> @@ -2969,21 +2977,24 @@ int kvm_cpu_exec(CPUState *cpu) >> ret = EXCP_INTERRUPT; >> break; >> case KVM_SYSTEM_EVENT_CRASH: >> - kvm_cpu_synchronize_state(cpu); >> - qemu_mutex_lock_iothread(); >> - qemu_system_guest_panicked(cpu_get_crash_info(cpu)); >> - qemu_mutex_unlock_iothread(); >> + kvm_emit_guest_crash(cpu); >> ret = 0; >> break; >> default: >> DPRINTF("kvm_arch_handle_exit\n"); >> ret = kvm_arch_handle_exit(cpu, run); >> + if (ret < 0) { >> + kvm_emit_guest_crash(cpu); >> + } >> break; >> } >> break; >> default: >> DPRINTF("kvm_arch_handle_exit\n"); >> ret = kvm_arch_handle_exit(cpu, run); >> + if (ret < 0) { >> + kvm_emit_guest_crash(cpu); >> + } >> break; >> } >> } while (ret == 0); > This allows to gracefully handle this problem in production > and reset the guest using on_crash action in libvirt. Ping
On 11/1/23 18:13, Denis V. Lunev wrote: > On 11/1/23 16:23, Andrey Drobyshev wrote: >> Currently we emit GUEST_PANICKED event in case kvm_vcpu_ioctl() returns >> KVM_EXIT_SYSTEM_EVENT with the event type KVM_SYSTEM_EVENT_CRASH. Let's >> extend this scenario and emit GUEST_PANICKED in case of an abnormal KVM >> exit. That's a natural thing to do since in this case guest is no >> longer operational anyway. >> >> Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com> >> Acked-by: Denis V. Lunev <den@virtuozzo.com> >> --- >> accel/kvm/kvm-all.c | 19 +++++++++++++++---- >> 1 file changed, 15 insertions(+), 4 deletions(-) >> >> diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c >> index e39a810a4e..d74b3f0b0e 100644 >> --- a/accel/kvm/kvm-all.c >> +++ b/accel/kvm/kvm-all.c >> @@ -2816,6 +2816,14 @@ static void kvm_eat_signals(CPUState *cpu) >> } while (sigismember(&chkset, SIG_IPI)); >> } >> +static void kvm_emit_guest_crash(CPUState *cpu) >> +{ >> + kvm_cpu_synchronize_state(cpu); >> + qemu_mutex_lock_iothread(); >> + qemu_system_guest_panicked(cpu_get_crash_info(cpu)); >> + qemu_mutex_unlock_iothread(); >> +} >> + >> int kvm_cpu_exec(CPUState *cpu) >> { >> struct kvm_run *run = cpu->kvm_run; >> @@ -2969,21 +2977,24 @@ int kvm_cpu_exec(CPUState *cpu) >> ret = EXCP_INTERRUPT; >> break; >> case KVM_SYSTEM_EVENT_CRASH: >> - kvm_cpu_synchronize_state(cpu); >> - qemu_mutex_lock_iothread(); >> - qemu_system_guest_panicked(cpu_get_crash_info(cpu)); >> - qemu_mutex_unlock_iothread(); >> + kvm_emit_guest_crash(cpu); >> ret = 0; >> break; >> default: >> DPRINTF("kvm_arch_handle_exit\n"); >> ret = kvm_arch_handle_exit(cpu, run); >> + if (ret < 0) { >> + kvm_emit_guest_crash(cpu); >> + } >> break; >> } >> break; >> default: >> DPRINTF("kvm_arch_handle_exit\n"); >> ret = kvm_arch_handle_exit(cpu, run); >> + if (ret < 0) { >> + kvm_emit_guest_crash(cpu); >> + } >> break; >> } >> } while (ret == 0); > This allows to gracefully handle this problem in production > and reset the guest using on_crash action in libvirt. Ping
On 1/11/24 15:15, Andrey Drobyshev wrote: > On 11/1/23 18:13, Denis V. Lunev wrote: >> On 11/1/23 16:23, Andrey Drobyshev wrote: >>> Currently we emit GUEST_PANICKED event in case kvm_vcpu_ioctl() returns >>> KVM_EXIT_SYSTEM_EVENT with the event type KVM_SYSTEM_EVENT_CRASH. Let's >>> extend this scenario and emit GUEST_PANICKED in case of an abnormal KVM >>> exit. That's a natural thing to do since in this case guest is no >>> longer operational anyway. >>> >>> Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com> >>> Acked-by: Denis V. Lunev <den@virtuozzo.com> >>> --- >>> accel/kvm/kvm-all.c | 19 +++++++++++++++---- >>> 1 file changed, 15 insertions(+), 4 deletions(-) >>> >>> diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c >>> index e39a810a4e..d74b3f0b0e 100644 >>> --- a/accel/kvm/kvm-all.c >>> +++ b/accel/kvm/kvm-all.c >>> @@ -2816,6 +2816,14 @@ static void kvm_eat_signals(CPUState *cpu) >>> } while (sigismember(&chkset, SIG_IPI)); >>> } >>> +static void kvm_emit_guest_crash(CPUState *cpu) >>> +{ >>> + kvm_cpu_synchronize_state(cpu); >>> + qemu_mutex_lock_iothread(); >>> + qemu_system_guest_panicked(cpu_get_crash_info(cpu)); >>> + qemu_mutex_unlock_iothread(); >>> +} >>> + >>> int kvm_cpu_exec(CPUState *cpu) >>> { >>> struct kvm_run *run = cpu->kvm_run; >>> @@ -2969,21 +2977,24 @@ int kvm_cpu_exec(CPUState *cpu) >>> ret = EXCP_INTERRUPT; >>> break; >>> case KVM_SYSTEM_EVENT_CRASH: >>> - kvm_cpu_synchronize_state(cpu); >>> - qemu_mutex_lock_iothread(); >>> - qemu_system_guest_panicked(cpu_get_crash_info(cpu)); >>> - qemu_mutex_unlock_iothread(); >>> + kvm_emit_guest_crash(cpu); >>> ret = 0; >>> break; >>> default: >>> DPRINTF("kvm_arch_handle_exit\n"); >>> ret = kvm_arch_handle_exit(cpu, run); >>> + if (ret < 0) { >>> + kvm_emit_guest_crash(cpu); >>> + } >>> break; >>> } >>> break; >>> default: >>> DPRINTF("kvm_arch_handle_exit\n"); >>> ret = kvm_arch_handle_exit(cpu, run); >>> + if (ret < 0) { >>> + kvm_emit_guest_crash(cpu); >>> + } >>> break; >>> } >>> } while (ret == 0); >> This allows to gracefully handle this problem in production >> and reset the guest using on_crash action in libvirt. > > Ping Ping
On 1/25/24 18:36, Andrey Drobyshev wrote: > On 1/11/24 15:15, Andrey Drobyshev wrote: >> On 11/1/23 18:13, Denis V. Lunev wrote: >>> On 11/1/23 16:23, Andrey Drobyshev wrote: >>>> Currently we emit GUEST_PANICKED event in case kvm_vcpu_ioctl() returns >>>> KVM_EXIT_SYSTEM_EVENT with the event type KVM_SYSTEM_EVENT_CRASH. Let's >>>> extend this scenario and emit GUEST_PANICKED in case of an abnormal KVM >>>> exit. That's a natural thing to do since in this case guest is no >>>> longer operational anyway. >>>> >>>> Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com> >>>> Acked-by: Denis V. Lunev <den@virtuozzo.com> >>>> --- >>>> accel/kvm/kvm-all.c | 19 +++++++++++++++---- >>>> 1 file changed, 15 insertions(+), 4 deletions(-) >>>> >>>> diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c >>>> index e39a810a4e..d74b3f0b0e 100644 >>>> --- a/accel/kvm/kvm-all.c >>>> +++ b/accel/kvm/kvm-all.c >>>> @@ -2816,6 +2816,14 @@ static void kvm_eat_signals(CPUState *cpu) >>>> } while (sigismember(&chkset, SIG_IPI)); >>>> } >>>> +static void kvm_emit_guest_crash(CPUState *cpu) >>>> +{ >>>> + kvm_cpu_synchronize_state(cpu); >>>> + qemu_mutex_lock_iothread(); >>>> + qemu_system_guest_panicked(cpu_get_crash_info(cpu)); >>>> + qemu_mutex_unlock_iothread(); >>>> +} >>>> + >>>> int kvm_cpu_exec(CPUState *cpu) >>>> { >>>> struct kvm_run *run = cpu->kvm_run; >>>> @@ -2969,21 +2977,24 @@ int kvm_cpu_exec(CPUState *cpu) >>>> ret = EXCP_INTERRUPT; >>>> break; >>>> case KVM_SYSTEM_EVENT_CRASH: >>>> - kvm_cpu_synchronize_state(cpu); >>>> - qemu_mutex_lock_iothread(); >>>> - qemu_system_guest_panicked(cpu_get_crash_info(cpu)); >>>> - qemu_mutex_unlock_iothread(); >>>> + kvm_emit_guest_crash(cpu); >>>> ret = 0; >>>> break; >>>> default: >>>> DPRINTF("kvm_arch_handle_exit\n"); >>>> ret = kvm_arch_handle_exit(cpu, run); >>>> + if (ret < 0) { >>>> + kvm_emit_guest_crash(cpu); >>>> + } >>>> break; >>>> } >>>> break; >>>> default: >>>> DPRINTF("kvm_arch_handle_exit\n"); >>>> ret = kvm_arch_handle_exit(cpu, run); >>>> + if (ret < 0) { >>>> + kvm_emit_guest_crash(cpu); >>>> + } >>>> break; >>>> } >>>> } while (ret == 0); >>> This allows to gracefully handle this problem in production >>> and reset the guest using on_crash action in libvirt. >> >> Ping > > Ping Yet another ping
Andrey Drobyshev <andrey.drobyshev@virtuozzo.com> writes: (Add kvm@vger to CC for wider review) > Currently we emit GUEST_PANICKED event in case kvm_vcpu_ioctl() returns > KVM_EXIT_SYSTEM_EVENT with the event type KVM_SYSTEM_EVENT_CRASH. Let's > extend this scenario and emit GUEST_PANICKED in case of an abnormal KVM > exit. That's a natural thing to do since in this case guest is no > longer operational anyway. > > Signed-off-by: Andrey Drobyshev <andrey.drobyshev@virtuozzo.com> > Acked-by: Denis V. Lunev <den@virtuozzo.com> > --- > accel/kvm/kvm-all.c | 19 +++++++++++++++---- > 1 file changed, 15 insertions(+), 4 deletions(-) > > diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c > index e39a810a4e..d74b3f0b0e 100644 > --- a/accel/kvm/kvm-all.c > +++ b/accel/kvm/kvm-all.c > @@ -2816,6 +2816,14 @@ static void kvm_eat_signals(CPUState *cpu) > } while (sigismember(&chkset, SIG_IPI)); > } > > +static void kvm_emit_guest_crash(CPUState *cpu) > +{ > + kvm_cpu_synchronize_state(cpu); > + qemu_mutex_lock_iothread(); > + qemu_system_guest_panicked(cpu_get_crash_info(cpu)); > + qemu_mutex_unlock_iothread(); > +} > + > int kvm_cpu_exec(CPUState *cpu) > { > struct kvm_run *run = cpu->kvm_run; > @@ -2969,21 +2977,24 @@ int kvm_cpu_exec(CPUState *cpu) > ret = EXCP_INTERRUPT; > break; > case KVM_SYSTEM_EVENT_CRASH: > - kvm_cpu_synchronize_state(cpu); > - qemu_mutex_lock_iothread(); > - qemu_system_guest_panicked(cpu_get_crash_info(cpu)); > - qemu_mutex_unlock_iothread(); > + kvm_emit_guest_crash(cpu); > ret = 0; > break; > default: > DPRINTF("kvm_arch_handle_exit\n"); > ret = kvm_arch_handle_exit(cpu, run); > + if (ret < 0) { > + kvm_emit_guest_crash(cpu); > + } > break; > } > break; > default: > DPRINTF("kvm_arch_handle_exit\n"); > ret = kvm_arch_handle_exit(cpu, run); > + if (ret < 0) { > + kvm_emit_guest_crash(cpu); > + } > break; > } > } while (ret == 0);
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index e39a810a4e..d74b3f0b0e 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -2816,6 +2816,14 @@ static void kvm_eat_signals(CPUState *cpu) } while (sigismember(&chkset, SIG_IPI)); } +static void kvm_emit_guest_crash(CPUState *cpu) +{ + kvm_cpu_synchronize_state(cpu); + qemu_mutex_lock_iothread(); + qemu_system_guest_panicked(cpu_get_crash_info(cpu)); + qemu_mutex_unlock_iothread(); +} + int kvm_cpu_exec(CPUState *cpu) { struct kvm_run *run = cpu->kvm_run; @@ -2969,21 +2977,24 @@ int kvm_cpu_exec(CPUState *cpu) ret = EXCP_INTERRUPT; break; case KVM_SYSTEM_EVENT_CRASH: - kvm_cpu_synchronize_state(cpu); - qemu_mutex_lock_iothread(); - qemu_system_guest_panicked(cpu_get_crash_info(cpu)); - qemu_mutex_unlock_iothread(); + kvm_emit_guest_crash(cpu); ret = 0; break; default: DPRINTF("kvm_arch_handle_exit\n"); ret = kvm_arch_handle_exit(cpu, run); + if (ret < 0) { + kvm_emit_guest_crash(cpu); + } break; } break; default: DPRINTF("kvm_arch_handle_exit\n"); ret = kvm_arch_handle_exit(cpu, run); + if (ret < 0) { + kvm_emit_guest_crash(cpu); + } break; } } while (ret == 0);