When a root partition running on MSHV is powered off, the default
behavior is to write ACPI registers to power-off. However, this ACPI
write is intercepted by MSHV and will result in a Machine Check
Exception(MCE).
The root partition eventually panics with a trace similar to:
[ 81.306348] reboot: Power down
[ 81.314709] mce: [Hardware Error]: CPU 0: Machine Check Exception: 4 Bank 0: b2000000c0060001
[ 81.314711] mce: [Hardware Error]: TSC 3b8cb60a66 PPIN 11d98332458e4ea9
[ 81.314713] mce: [Hardware Error]: PROCESSOR 0:606a6 TIME 1759339405 SOCKET 0 APIC 0 microcode ffffffff
[ 81.314715] mce: [Hardware Error]: Run the above through 'mcelog --ascii'
[ 81.314716] mce: [Hardware Error]: Machine check: Processor context corrupt
[ 81.314717] Kernel panic - not syncing: Fatal machine check
To correctly shutdown a root partition running on MSHV hypervisor, sleep
state information must be configured within the hypervsior. Later, the
HVCALL_ENTER_SLEEP_STATE hypercall should be invoked as the last step in
the shutdown sequence.
The previous patch configures the sleep state information and this patch
invokes HVCALL_ENTER_SLEEP_STATE hypercall to cleanly shutdown the root
partition.
Signed-off-by: Praveen K Paladugu <prapal@linux.microsoft.com>
Co-developed-by: Anatol Belski <anbelski@linux.microsoft.com>
Signed-off-by: Anatol Belski <anbelski@linux.microsoft.com>
Reviewed-by: Easwar Hariharan <easwar.hariharan@linux.microsoft.com>
---
arch/x86/include/asm/mshyperv.h | 2 ++
arch/x86/kernel/cpu/mshyperv.c | 2 ++
drivers/hv/mshv_common.c | 18 ++++++++++++++++++
3 files changed, 22 insertions(+)
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 166053df0484..4c22f3257368 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -183,9 +183,11 @@ void hv_apic_init(void);
void __init hv_init_spinlocks(void);
bool hv_vcpu_is_preempted(int vcpu);
void hv_sleep_notifiers_register(void);
+void hv_machine_power_off(void);
#else
static inline void hv_apic_init(void) {}
static inline void hv_sleep_notifiers_register(void) {};
+static inline void hv_machine_power_off(void) {};
#endif
struct irq_domain *hv_create_pci_msi_domain(void);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index fac9953a72ef..579fb2c64cfd 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -621,6 +621,8 @@ static void __init ms_hyperv_init_platform(void)
#endif
#if IS_ENABLED(CONFIG_HYPERV)
+ if (hv_root_partition())
+ machine_ops.power_off = hv_machine_power_off;
#if defined(CONFIG_KEXEC_CORE)
machine_ops.shutdown = hv_machine_shutdown;
#endif
diff --git a/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c
index f1d4e81107ee..28905e3ed9c0 100644
--- a/drivers/hv/mshv_common.c
+++ b/drivers/hv/mshv_common.c
@@ -217,4 +217,22 @@ void hv_sleep_notifiers_register(void)
pr_err("%s: cannot register reboot notifier %d\n", __func__,
ret);
}
+
+/*
+ * Power off the machine by entering S5 sleep state via Hyper-V hypercall.
+ * This call does not return if successful.
+ */
+void hv_machine_power_off(void)
+{
+ unsigned long flags;
+ struct hv_input_enter_sleep_state *in;
+
+ local_irq_save(flags);
+ in = *this_cpu_ptr(hyperv_pcpu_input_arg);
+ in->sleep_state = HV_SLEEP_STATE_S5;
+
+ (void)hv_do_hypercall(HVCALL_ENTER_SLEEP_STATE, in, NULL);
+ local_irq_restore(flags);
+
+}
#endif
--
2.51.0
On Wed, Nov 26, 2025 at 03:49:53PM -0600, Praveen K Paladugu wrote:
> When a root partition running on MSHV is powered off, the default
> behavior is to write ACPI registers to power-off. However, this ACPI
> write is intercepted by MSHV and will result in a Machine Check
> Exception(MCE).
>
> The root partition eventually panics with a trace similar to:
>
> [ 81.306348] reboot: Power down
> [ 81.314709] mce: [Hardware Error]: CPU 0: Machine Check Exception: 4 Bank 0: b2000000c0060001
> [ 81.314711] mce: [Hardware Error]: TSC 3b8cb60a66 PPIN 11d98332458e4ea9
> [ 81.314713] mce: [Hardware Error]: PROCESSOR 0:606a6 TIME 1759339405 SOCKET 0 APIC 0 microcode ffffffff
> [ 81.314715] mce: [Hardware Error]: Run the above through 'mcelog --ascii'
> [ 81.314716] mce: [Hardware Error]: Machine check: Processor context corrupt
> [ 81.314717] Kernel panic - not syncing: Fatal machine check
>
> To correctly shutdown a root partition running on MSHV hypervisor, sleep
> state information must be configured within the hypervsior. Later, the
> HVCALL_ENTER_SLEEP_STATE hypercall should be invoked as the last step in
> the shutdown sequence.
>
> The previous patch configures the sleep state information and this patch
> invokes HVCALL_ENTER_SLEEP_STATE hypercall to cleanly shutdown the root
> partition.
>
> Signed-off-by: Praveen K Paladugu <prapal@linux.microsoft.com>
> Co-developed-by: Anatol Belski <anbelski@linux.microsoft.com>
> Signed-off-by: Anatol Belski <anbelski@linux.microsoft.com>
> Reviewed-by: Easwar Hariharan <easwar.hariharan@linux.microsoft.com>
> ---
> arch/x86/include/asm/mshyperv.h | 2 ++
> arch/x86/kernel/cpu/mshyperv.c | 2 ++
> drivers/hv/mshv_common.c | 18 ++++++++++++++++++
> 3 files changed, 22 insertions(+)
>
> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
> index 166053df0484..4c22f3257368 100644
> --- a/arch/x86/include/asm/mshyperv.h
> +++ b/arch/x86/include/asm/mshyperv.h
> @@ -183,9 +183,11 @@ void hv_apic_init(void);
> void __init hv_init_spinlocks(void);
> bool hv_vcpu_is_preempted(int vcpu);
> void hv_sleep_notifiers_register(void);
> +void hv_machine_power_off(void);
> #else
> static inline void hv_apic_init(void) {}
> static inline void hv_sleep_notifiers_register(void) {};
> +static inline void hv_machine_power_off(void) {};
> #endif
>
> struct irq_domain *hv_create_pci_msi_domain(void);
> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
> index fac9953a72ef..579fb2c64cfd 100644
> --- a/arch/x86/kernel/cpu/mshyperv.c
> +++ b/arch/x86/kernel/cpu/mshyperv.c
> @@ -621,6 +621,8 @@ static void __init ms_hyperv_init_platform(void)
> #endif
>
> #if IS_ENABLED(CONFIG_HYPERV)
> + if (hv_root_partition())
> + machine_ops.power_off = hv_machine_power_off;
> #if defined(CONFIG_KEXEC_CORE)
> machine_ops.shutdown = hv_machine_shutdown;
> #endif
> diff --git a/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c
> index f1d4e81107ee..28905e3ed9c0 100644
> --- a/drivers/hv/mshv_common.c
> +++ b/drivers/hv/mshv_common.c
> @@ -217,4 +217,22 @@ void hv_sleep_notifiers_register(void)
> pr_err("%s: cannot register reboot notifier %d\n", __func__,
> ret);
> }
> +
> +/*
> + * Power off the machine by entering S5 sleep state via Hyper-V hypercall.
> + * This call does not return if successful.
> + */
> +void hv_machine_power_off(void)
> +{
> + unsigned long flags;
> + struct hv_input_enter_sleep_state *in;
> +
> + local_irq_save(flags);
> + in = *this_cpu_ptr(hyperv_pcpu_input_arg);
> + in->sleep_state = HV_SLEEP_STATE_S5;
> +
> + (void)hv_do_hypercall(HVCALL_ENTER_SLEEP_STATE, in, NULL);
Should this the error be printed?
Acked-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
> + local_irq_restore(flags);
> +
> +}
> #endif
> --
> 2.51.0
© 2016 - 2025 Red Hat, Inc.