[PATCH v5 0/3] Add support for clean shutdown with MSHV

[PATCH v5 0/3] Add support for clean shutdown with MSHV

[Praveen K Paladugu]

Add support for clean shutdown of the root partition when running on
MSHV Hypervisor.

v5: 
 - Fixed build errors
 - Padded struct hv_input_set_system_property for alignment
 - Dropped CONFIG_ACPI stub

v4:
 - Adopted machine_ops to order invoking HV_ENTER_SLEEP_STATE as the
   last step in shutdown sequence.
 - This ensures rest of the cleanups are done before powering off

v3:
 - Dropped acpi_sleep handlers as they are not used on mshv
 - Applied ordering for hv_reboot_notifier
 - Fixed build issues on i386, arm64 architectures

v2:
  - Addressed review comments from v1.
  - Moved all sleep state handling methods under CONFIG_ACPI stub
  - - This fixes build issues on non-x86 architectures.


Praveen K Paladugu (3):
  hyperv: Add definitions for MSHV sleep state configuration
  hyperv: Use reboot notifier to configure sleep state
  hyperv: Cleanly shutdown root partition with MSHV

 arch/x86/hyperv/hv_init.c       |  9 ++++
 arch/x86/include/asm/mshyperv.h |  4 ++
 drivers/hv/mshv_common.c        | 96 +++++++++++++++++++++++++++++++++
 include/hyperv/hvgdk_mini.h     |  4 +-
 include/hyperv/hvhdk_mini.h     | 40 ++++++++++++++
 5 files changed, 152 insertions(+), 1 deletion(-)

-- 
2.51.0

[PATCH v5 1/3] hyperv: Add definitions for MSHV sleep state configuration

[Praveen K Paladugu]

Add the definitions required to configure sleep states in mshv hypervsior.

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>
Reviewed-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
---
 include/hyperv/hvgdk_mini.h |  4 +++-
 include/hyperv/hvhdk_mini.h | 40 +++++++++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h
index 1d5ce11be8b6..04b18d0e37af 100644
--- a/include/hyperv/hvgdk_mini.h
+++ b/include/hyperv/hvgdk_mini.h
@@ -465,19 +465,21 @@ union hv_vp_assist_msr_contents {	 /* HV_REGISTER_VP_ASSIST_PAGE */
 #define HVCALL_RESET_DEBUG_SESSION			0x006b
 #define HVCALL_MAP_STATS_PAGE				0x006c
 #define HVCALL_UNMAP_STATS_PAGE				0x006d
+#define HVCALL_SET_SYSTEM_PROPERTY			0x006f
 #define HVCALL_ADD_LOGICAL_PROCESSOR			0x0076
 #define HVCALL_GET_SYSTEM_PROPERTY			0x007b
 #define HVCALL_MAP_DEVICE_INTERRUPT			0x007c
 #define HVCALL_UNMAP_DEVICE_INTERRUPT			0x007d
 #define HVCALL_RETARGET_INTERRUPT			0x007e
 #define HVCALL_NOTIFY_PARTITION_EVENT                   0x0087
+#define HVCALL_ENTER_SLEEP_STATE			0x0084
 #define HVCALL_NOTIFY_PORT_RING_EMPTY			0x008b
 #define HVCALL_REGISTER_INTERCEPT_RESULT		0x0091
 #define HVCALL_ASSERT_VIRTUAL_INTERRUPT			0x0094
 #define HVCALL_CREATE_PORT				0x0095
 #define HVCALL_CONNECT_PORT				0x0096
 #define HVCALL_START_VP					0x0099
-#define HVCALL_GET_VP_INDEX_FROM_APIC_ID			0x009a
+#define HVCALL_GET_VP_INDEX_FROM_APIC_ID		0x009a
 #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE	0x00af
 #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST	0x00b0
 #define HVCALL_SIGNAL_EVENT_DIRECT			0x00c0
diff --git a/include/hyperv/hvhdk_mini.h b/include/hyperv/hvhdk_mini.h
index f2d7b50de7a4..41a29bf8ec14 100644
--- a/include/hyperv/hvhdk_mini.h
+++ b/include/hyperv/hvhdk_mini.h
@@ -140,6 +140,7 @@ enum hv_snp_status {
 
 enum hv_system_property {
 	/* Add more values when needed */
+	HV_SYSTEM_PROPERTY_SLEEP_STATE = 3,
 	HV_SYSTEM_PROPERTY_SCHEDULER_TYPE = 15,
 	HV_DYNAMIC_PROCESSOR_FEATURE_PROPERTY = 21,
 	HV_SYSTEM_PROPERTY_CRASHDUMPAREA = 47,
@@ -155,6 +156,19 @@ union hv_pfn_range {            /* HV_SPA_PAGE_RANGE */
 	} __packed;
 };
 
+enum hv_sleep_state {
+	HV_SLEEP_STATE_S1 = 1,
+	HV_SLEEP_STATE_S2 = 2,
+	HV_SLEEP_STATE_S3 = 3,
+	HV_SLEEP_STATE_S4 = 4,
+	HV_SLEEP_STATE_S5 = 5,
+	/*
+	 * After hypervisor has received this, any follow up sleep
+	 * state registration requests will be rejected.
+	 */
+	HV_SLEEP_STATE_LOCK = 6
+};
+
 enum hv_dynamic_processor_feature_property {
 	/* Add more values when needed */
 	HV_X64_DYNAMIC_PROCESSOR_FEATURE_MAX_ENCRYPTED_PARTITIONS = 13,
@@ -184,6 +198,32 @@ struct hv_output_get_system_property {
 	};
 } __packed;
 
+struct hv_sleep_state_info {
+	u32 sleep_state; /* enum hv_sleep_state */
+	u8 pm1a_slp_typ;
+	u8 pm1b_slp_typ;
+} __packed;
+
+struct hv_input_set_system_property {
+	u32 property_id; /* enum hv_system_property */
+	u32 reserved;
+	union {
+		/* More fields to be filled in when needed */
+		struct hv_sleep_state_info set_sleep_state_info;
+
+		/*
+		 * Add a reserved field to ensure the union is 8-byte aligned as
+		 * existing members may not be. This is a temporary measure
+		 * until all remaining members are added.
+		 */
+		 u64 reserved0[8];
+	};
+} __packed;
+
+struct hv_input_enter_sleep_state {     /* HV_INPUT_ENTER_SLEEP_STATE */
+	u32 sleep_state;        /* enum hv_sleep_state */
+} __packed;
+
 struct hv_input_map_stats_page {
 	u32 type; /* enum hv_stats_object_type */
 	u32 padding;
-- 
2.51.0

[PATCH v5 2/3] hyperv: Use reboot notifier to configure sleep state

[Praveen K Paladugu]

Configure sleep state information in mshv hypervisor. This sleep state
information from ACPI will be used by hypervisor to poweroff the host.

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/hyperv/hv_init.c       |  7 +++
 arch/x86/include/asm/mshyperv.h |  2 +
 drivers/hv/mshv_common.c        | 78 +++++++++++++++++++++++++++++++++
 3 files changed, 87 insertions(+)

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index e28737ec7054..645b52dd732e 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -555,6 +555,13 @@ void __init hyperv_init(void)
 
 		hv_remap_tsc_clocksource();
 		hv_root_crash_init();
+		/*
+		 * The notifier registration might fail at various hops.
+		 * Corresponding error messages will land in dmesg. There is
+		 * otherwise nothing that can be specifically done to handle
+		 * failures here.
+		 */
+		hv_sleep_notifiers_register();
 	} else {
 		hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
 		wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 10037125099a..166053df0484 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -182,8 +182,10 @@ int hyperv_fill_flush_guest_mapping_list(
 void hv_apic_init(void);
 void __init hv_init_spinlocks(void);
 bool hv_vcpu_is_preempted(int vcpu);
+void hv_sleep_notifiers_register(void);
 #else
 static inline void hv_apic_init(void) {}
+static inline void hv_sleep_notifiers_register(void) {};
 #endif
 
 struct irq_domain *hv_create_pci_msi_domain(void);
diff --git a/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c
index aa2be51979fd..ee733ba1575e 100644
--- a/drivers/hv/mshv_common.c
+++ b/drivers/hv/mshv_common.c
@@ -14,6 +14,9 @@
 #include <asm/mshyperv.h>
 #include <linux/resume_user_mode.h>
 #include <linux/export.h>
+#include <linux/acpi.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
 
 #include "mshv.h"
 
@@ -138,3 +141,78 @@ int hv_call_get_partition_property(u64 partition_id,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(hv_call_get_partition_property);
+
+/*
+ * Corresponding sleep states have to be initialized in order for a subsequent
+ * HVCALL_ENTER_SLEEP_STATE call to succeed. Currently only S5 state as per
+ * ACPI 6.4 chapter 7.4.2 is relevant, while S1, S2 and S3 can be supported.
+ *
+ * In order to pass proper PM values to mshv, ACPI should be initialized and
+ * should support S5 sleep state when this method is invoked.
+ */
+static int hv_initialize_sleep_states(void)
+{
+	u64 status;
+	unsigned long flags;
+	struct hv_input_set_system_property *in;
+	acpi_status acpi_status;
+	u8 sleep_type_a, sleep_type_b;
+
+	if (!acpi_sleep_state_supported(ACPI_STATE_S5)) {
+		pr_err("%s: S5 sleep state not supported.\n", __func__);
+		return -ENODEV;
+	}
+
+	acpi_status = acpi_get_sleep_type_data(ACPI_STATE_S5, &sleep_type_a,
+					       &sleep_type_b);
+	if (ACPI_FAILURE(acpi_status))
+		return -ENODEV;
+
+	local_irq_save(flags);
+	in = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	memset(in, 0, sizeof(*in));
+
+	in->property_id = HV_SYSTEM_PROPERTY_SLEEP_STATE;
+	in->set_sleep_state_info.sleep_state = HV_SLEEP_STATE_S5;
+	in->set_sleep_state_info.pm1a_slp_typ = sleep_type_a;
+	in->set_sleep_state_info.pm1b_slp_typ = sleep_type_b;
+
+	status = hv_do_hypercall(HVCALL_SET_SYSTEM_PROPERTY, in, NULL);
+	local_irq_restore(flags);
+
+	if (!hv_result_success(status)) {
+		hv_status_err(status, "\n");
+		return hv_result_to_errno(status);
+	}
+
+	return 0;
+}
+
+/*
+ * This notifier initializes sleep states in mshv hypervisor which will be
+ * used during power off.
+ */
+static int hv_reboot_notifier_handler(struct notifier_block *this,
+				      unsigned long code, void *another)
+{
+	int ret = 0;
+
+	if (code == SYS_HALT || code == SYS_POWER_OFF)
+		ret = hv_initialize_sleep_states();
+
+	return ret ? NOTIFY_DONE : NOTIFY_OK;
+}
+
+static struct notifier_block hv_reboot_notifier = {
+	.notifier_call = hv_reboot_notifier_handler,
+};
+
+void hv_sleep_notifiers_register(void)
+{
+	int ret;
+
+	ret = register_reboot_notifier(&hv_reboot_notifier);
+	if (ret)
+		pr_err("%s: cannot register reboot notifier %d\n", __func__,
+		       ret);
+}
-- 
2.51.0

[PATCH v5 3/3] hyperv: Cleanly shutdown root partition with MSHV

[Praveen K Paladugu]

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/hyperv/hv_init.c       |  2 ++
 arch/x86/include/asm/mshyperv.h |  2 ++
 drivers/hv/mshv_common.c        | 18 ++++++++++++++++++
 3 files changed, 22 insertions(+)

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 645b52dd732e..24824534ff8d 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -34,6 +34,7 @@
 #include <clocksource/hyperv_timer.h>
 #include <linux/highmem.h>
 #include <linux/export.h>
+#include <asm/reboot.h>
 
 void *hv_hypercall_pg;
 
@@ -562,6 +563,7 @@ void __init hyperv_init(void)
 		 * failures here.
 		 */
 		hv_sleep_notifiers_register();
+		machine_ops.power_off = hv_machine_power_off;
 	} else {
 		hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
 		wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
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/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c
index ee733ba1575e..73505cbdc324 100644
--- a/drivers/hv/mshv_common.c
+++ b/drivers/hv/mshv_common.c
@@ -216,3 +216,21 @@ 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);
+
+}
-- 
2.51.0

Re: [PATCH v5 2/3] hyperv: Use reboot notifier to configure sleep state

[Stanislav Kinsburskii]

On Mon, Nov 17, 2025 at 03:08:17PM -0600, Praveen K Paladugu wrote:
> Configure sleep state information in mshv hypervisor. This sleep state
> information from ACPI will be used by hypervisor to poweroff the host.
> 
> 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/hyperv/hv_init.c       |  7 +++
>  arch/x86/include/asm/mshyperv.h |  2 +
>  drivers/hv/mshv_common.c        | 78 +++++++++++++++++++++++++++++++++
>  3 files changed, 87 insertions(+)
> 
> diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
> index e28737ec7054..645b52dd732e 100644
> --- a/arch/x86/hyperv/hv_init.c
> +++ b/arch/x86/hyperv/hv_init.c
> @@ -555,6 +555,13 @@ void __init hyperv_init(void)
>  
>  		hv_remap_tsc_clocksource();
>  		hv_root_crash_init();
> +		/*
> +		 * The notifier registration might fail at various hops.
> +		 * Corresponding error messages will land in dmesg. There is
> +		 * otherwise nothing that can be specifically done to handle
> +		 * failures here.
> +		 */

I'd suggest removing this comment: it doesn't bring much value.

Reviewed-by: Stansialv Kinsburskii <skinsburskii@linux.miscrosoft.com>

> +		hv_sleep_notifiers_register();
>  	} else {
>  		hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
>  		wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
> index 10037125099a..166053df0484 100644
> --- a/arch/x86/include/asm/mshyperv.h
> +++ b/arch/x86/include/asm/mshyperv.h
> @@ -182,8 +182,10 @@ int hyperv_fill_flush_guest_mapping_list(
>  void hv_apic_init(void);
>  void __init hv_init_spinlocks(void);
>  bool hv_vcpu_is_preempted(int vcpu);
> +void hv_sleep_notifiers_register(void);
>  #else
>  static inline void hv_apic_init(void) {}
> +static inline void hv_sleep_notifiers_register(void) {};
>  #endif
>  
>  struct irq_domain *hv_create_pci_msi_domain(void);
> diff --git a/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c
> index aa2be51979fd..ee733ba1575e 100644
> --- a/drivers/hv/mshv_common.c
> +++ b/drivers/hv/mshv_common.c
> @@ -14,6 +14,9 @@
>  #include <asm/mshyperv.h>
>  #include <linux/resume_user_mode.h>
>  #include <linux/export.h>
> +#include <linux/acpi.h>
> +#include <linux/notifier.h>
> +#include <linux/reboot.h>
>  
>  #include "mshv.h"
>  
> @@ -138,3 +141,78 @@ int hv_call_get_partition_property(u64 partition_id,
>  	return 0;
>  }
>  EXPORT_SYMBOL_GPL(hv_call_get_partition_property);
> +
> +/*
> + * Corresponding sleep states have to be initialized in order for a subsequent
> + * HVCALL_ENTER_SLEEP_STATE call to succeed. Currently only S5 state as per
> + * ACPI 6.4 chapter 7.4.2 is relevant, while S1, S2 and S3 can be supported.
> + *
> + * In order to pass proper PM values to mshv, ACPI should be initialized and
> + * should support S5 sleep state when this method is invoked.
> + */
> +static int hv_initialize_sleep_states(void)
> +{
> +	u64 status;
> +	unsigned long flags;
> +	struct hv_input_set_system_property *in;
> +	acpi_status acpi_status;
> +	u8 sleep_type_a, sleep_type_b;
> +
> +	if (!acpi_sleep_state_supported(ACPI_STATE_S5)) {
> +		pr_err("%s: S5 sleep state not supported.\n", __func__);
> +		return -ENODEV;
> +	}
> +
> +	acpi_status = acpi_get_sleep_type_data(ACPI_STATE_S5, &sleep_type_a,
> +					       &sleep_type_b);
> +	if (ACPI_FAILURE(acpi_status))
> +		return -ENODEV;
> +
> +	local_irq_save(flags);
> +	in = *this_cpu_ptr(hyperv_pcpu_input_arg);
> +	memset(in, 0, sizeof(*in));
> +
> +	in->property_id = HV_SYSTEM_PROPERTY_SLEEP_STATE;
> +	in->set_sleep_state_info.sleep_state = HV_SLEEP_STATE_S5;
> +	in->set_sleep_state_info.pm1a_slp_typ = sleep_type_a;
> +	in->set_sleep_state_info.pm1b_slp_typ = sleep_type_b;
> +
> +	status = hv_do_hypercall(HVCALL_SET_SYSTEM_PROPERTY, in, NULL);
> +	local_irq_restore(flags);
> +
> +	if (!hv_result_success(status)) {
> +		hv_status_err(status, "\n");
> +		return hv_result_to_errno(status);
> +	}
> +
> +	return 0;
> +}
> +
> +/*
> + * This notifier initializes sleep states in mshv hypervisor which will be
> + * used during power off.
> + */
> +static int hv_reboot_notifier_handler(struct notifier_block *this,
> +				      unsigned long code, void *another)
> +{
> +	int ret = 0;
> +
> +	if (code == SYS_HALT || code == SYS_POWER_OFF)
> +		ret = hv_initialize_sleep_states();
> +
> +	return ret ? NOTIFY_DONE : NOTIFY_OK;
> +}
> +
> +static struct notifier_block hv_reboot_notifier = {
> +	.notifier_call = hv_reboot_notifier_handler,
> +};
> +
> +void hv_sleep_notifiers_register(void)
> +{
> +	int ret;
> +
> +	ret = register_reboot_notifier(&hv_reboot_notifier);
> +	if (ret)
> +		pr_err("%s: cannot register reboot notifier %d\n", __func__,
> +		       ret);
> +}
> -- 
> 2.51.0

Re: [PATCH v5 3/3] hyperv: Cleanly shutdown root partition with MSHV

[Stanislav Kinsburskii]

On Mon, Nov 17, 2025 at 03:08:18PM -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/hyperv/hv_init.c       |  2 ++
>  arch/x86/include/asm/mshyperv.h |  2 ++
>  drivers/hv/mshv_common.c        | 18 ++++++++++++++++++
>  3 files changed, 22 insertions(+)
> 
> diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
> index 645b52dd732e..24824534ff8d 100644
> --- a/arch/x86/hyperv/hv_init.c
> +++ b/arch/x86/hyperv/hv_init.c
> @@ -34,6 +34,7 @@
>  #include <clocksource/hyperv_timer.h>
>  #include <linux/highmem.h>
>  #include <linux/export.h>
> +#include <asm/reboot.h>
>  
>  void *hv_hypercall_pg;
>  
> @@ -562,6 +563,7 @@ void __init hyperv_init(void)
>  		 * failures here.
>  		 */
>  		hv_sleep_notifiers_register();
> +		machine_ops.power_off = hv_machine_power_off;

It looks more natural to me to gather all the machine_ops hooks in one
place (meaning in ms_hyperv_init_platform).
It is better moving this assignment there and do the branching on the
partition type in the power_off callback instead.

Thanks,
Stanislav


>  	} else {
>  		hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
>  		wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
> 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/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c
> index ee733ba1575e..73505cbdc324 100644
> --- a/drivers/hv/mshv_common.c
> +++ b/drivers/hv/mshv_common.c
> @@ -216,3 +216,21 @@ 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);
> +
> +}
> -- 
> 2.51.0

Re: [PATCH v5 1/3] hyperv: Add definitions for MSHV sleep state configuration

[Stanislav Kinsburskii]

On Mon, Nov 17, 2025 at 03:08:16PM -0600, Praveen K Paladugu wrote:
> Add the definitions required to configure sleep states in mshv hypervsior.
> 
> 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>
> Reviewed-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
> ---
>  include/hyperv/hvgdk_mini.h |  4 +++-
>  include/hyperv/hvhdk_mini.h | 40 +++++++++++++++++++++++++++++++++++++
>  2 files changed, 43 insertions(+), 1 deletion(-)
> 
> diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h
> index 1d5ce11be8b6..04b18d0e37af 100644
> --- a/include/hyperv/hvgdk_mini.h
> +++ b/include/hyperv/hvgdk_mini.h
> @@ -465,19 +465,21 @@ union hv_vp_assist_msr_contents {	 /* HV_REGISTER_VP_ASSIST_PAGE */
>  #define HVCALL_RESET_DEBUG_SESSION			0x006b
>  #define HVCALL_MAP_STATS_PAGE				0x006c
>  #define HVCALL_UNMAP_STATS_PAGE				0x006d
> +#define HVCALL_SET_SYSTEM_PROPERTY			0x006f
>  #define HVCALL_ADD_LOGICAL_PROCESSOR			0x0076
>  #define HVCALL_GET_SYSTEM_PROPERTY			0x007b
>  #define HVCALL_MAP_DEVICE_INTERRUPT			0x007c
>  #define HVCALL_UNMAP_DEVICE_INTERRUPT			0x007d
>  #define HVCALL_RETARGET_INTERRUPT			0x007e
>  #define HVCALL_NOTIFY_PARTITION_EVENT                   0x0087
> +#define HVCALL_ENTER_SLEEP_STATE			0x0084
>  #define HVCALL_NOTIFY_PORT_RING_EMPTY			0x008b
>  #define HVCALL_REGISTER_INTERCEPT_RESULT		0x0091
>  #define HVCALL_ASSERT_VIRTUAL_INTERRUPT			0x0094
>  #define HVCALL_CREATE_PORT				0x0095
>  #define HVCALL_CONNECT_PORT				0x0096
>  #define HVCALL_START_VP					0x0099
> -#define HVCALL_GET_VP_INDEX_FROM_APIC_ID			0x009a
> +#define HVCALL_GET_VP_INDEX_FROM_APIC_ID		0x009a
>  #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE	0x00af
>  #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST	0x00b0
>  #define HVCALL_SIGNAL_EVENT_DIRECT			0x00c0
> diff --git a/include/hyperv/hvhdk_mini.h b/include/hyperv/hvhdk_mini.h
> index f2d7b50de7a4..41a29bf8ec14 100644
> --- a/include/hyperv/hvhdk_mini.h
> +++ b/include/hyperv/hvhdk_mini.h
> @@ -140,6 +140,7 @@ enum hv_snp_status {
>  
>  enum hv_system_property {
>  	/* Add more values when needed */
> +	HV_SYSTEM_PROPERTY_SLEEP_STATE = 3,
>  	HV_SYSTEM_PROPERTY_SCHEDULER_TYPE = 15,
>  	HV_DYNAMIC_PROCESSOR_FEATURE_PROPERTY = 21,
>  	HV_SYSTEM_PROPERTY_CRASHDUMPAREA = 47,
> @@ -155,6 +156,19 @@ union hv_pfn_range {            /* HV_SPA_PAGE_RANGE */
>  	} __packed;
>  };
>  
> +enum hv_sleep_state {
> +	HV_SLEEP_STATE_S1 = 1,
> +	HV_SLEEP_STATE_S2 = 2,
> +	HV_SLEEP_STATE_S3 = 3,
> +	HV_SLEEP_STATE_S4 = 4,

Why adding the unused states?
It's not aligned with the common approach for this driver where we add
only those definitions which are used.

Thanks,
Stanislav

> +	HV_SLEEP_STATE_S5 = 5,
> +	/*
> +	 * After hypervisor has received this, any follow up sleep
> +	 * state registration requests will be rejected.
> +	 */
> +	HV_SLEEP_STATE_LOCK = 6
> +};
> +
>  enum hv_dynamic_processor_feature_property {
>  	/* Add more values when needed */
>  	HV_X64_DYNAMIC_PROCESSOR_FEATURE_MAX_ENCRYPTED_PARTITIONS = 13,
> @@ -184,6 +198,32 @@ struct hv_output_get_system_property {
>  	};
>  } __packed;
>  
> +struct hv_sleep_state_info {
> +	u32 sleep_state; /* enum hv_sleep_state */
> +	u8 pm1a_slp_typ;
> +	u8 pm1b_slp_typ;
> +} __packed;
> +
> +struct hv_input_set_system_property {
> +	u32 property_id; /* enum hv_system_property */
> +	u32 reserved;
> +	union {
> +		/* More fields to be filled in when needed */
> +		struct hv_sleep_state_info set_sleep_state_info;
> +
> +		/*
> +		 * Add a reserved field to ensure the union is 8-byte aligned as
> +		 * existing members may not be. This is a temporary measure
> +		 * until all remaining members are added.
> +		 */
> +		 u64 reserved0[8];
> +	};
> +} __packed;
> +
> +struct hv_input_enter_sleep_state {     /* HV_INPUT_ENTER_SLEEP_STATE */
> +	u32 sleep_state;        /* enum hv_sleep_state */
> +} __packed;
> +
>  struct hv_input_map_stats_page {
>  	u32 type; /* enum hv_stats_object_type */
>  	u32 padding;
> -- 
> 2.51.0

Re: [PATCH v5 2/3] hyperv: Use reboot notifier to configure sleep state

[kernel test robot]

Hi Praveen,

kernel test robot noticed the following build errors:

[auto build test ERROR on next-20251117]
[cannot apply to tip/x86/core linus/master v6.18-rc6 v6.18-rc5 v6.18-rc4 v6.18-rc6]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Praveen-K-Paladugu/hyperv-Add-definitions-for-MSHV-sleep-state-configuration/20251118-051204
base:   next-20251117
patch link:    https://lore.kernel.org/r/20251117210855.108126-3-prapal%40linux.microsoft.com
patch subject: [PATCH v5 2/3] hyperv: Use reboot notifier to configure sleep state
config: i386-randconfig-141-20251118 (https://download.01.org/0day-ci/archive/20251118/202511182134.X8qi5PeT-lkp@intel.com/config)
compiler: clang version 20.1.8 (https://github.com/llvm/llvm-project 87f0227cb60147a26a1eeb4fb06e3b505e9c7261)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251118/202511182134.X8qi5PeT-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202511182134.X8qi5PeT-lkp@intel.com/

All errors (new ones prefixed by >>):

>> drivers/hv/mshv_common.c:210:6: error: redefinition of 'hv_sleep_notifiers_register'
     210 | void hv_sleep_notifiers_register(void)
         |      ^
   arch/x86/include/asm/mshyperv.h:188:20: note: previous definition is here
     188 | static inline void hv_sleep_notifiers_register(void) {};
         |                    ^
   1 error generated.


vim +/hv_sleep_notifiers_register +210 drivers/hv/mshv_common.c

   209	
 > 210	void hv_sleep_notifiers_register(void)

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH v5 2/3] hyperv: Use reboot notifier to configure sleep state

[kernel test robot]

Hi Praveen,

kernel test robot noticed the following build warnings:

[auto build test WARNING on next-20251117]
[cannot apply to tip/x86/core linus/master v6.18-rc6 v6.18-rc5 v6.18-rc4 v6.18-rc6]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Praveen-K-Paladugu/hyperv-Add-definitions-for-MSHV-sleep-state-configuration/20251118-051204
base:   next-20251117
patch link:    https://lore.kernel.org/r/20251117210855.108126-3-prapal%40linux.microsoft.com
patch subject: [PATCH v5 2/3] hyperv: Use reboot notifier to configure sleep state
config: arm64-randconfig-003-20251118 (https://download.01.org/0day-ci/archive/20251118/202511182118.ZOxiv0Fn-lkp@intel.com/config)
compiler: clang version 19.1.7 (https://github.com/llvm/llvm-project cd708029e0b2869e80abe31ddb175f7c35361f90)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251118/202511182118.ZOxiv0Fn-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202511182118.ZOxiv0Fn-lkp@intel.com/

All warnings (new ones prefixed by >>):

>> drivers/hv/mshv_common.c:210:6: warning: no previous prototype for function 'hv_sleep_notifiers_register' [-Wmissing-prototypes]
     210 | void hv_sleep_notifiers_register(void)
         |      ^
   drivers/hv/mshv_common.c:210:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
     210 | void hv_sleep_notifiers_register(void)
         | ^
         | static 
   1 warning generated.


vim +/hv_sleep_notifiers_register +210 drivers/hv/mshv_common.c

   209	
 > 210	void hv_sleep_notifiers_register(void)

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH v5 3/3] hyperv: Cleanly shutdown root partition with MSHV

[kernel test robot]

Hi Praveen,

kernel test robot noticed the following build warnings:

[auto build test WARNING on next-20251117]
[cannot apply to tip/x86/core linus/master v6.18-rc6 v6.18-rc5 v6.18-rc4 v6.18-rc6]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Praveen-K-Paladugu/hyperv-Add-definitions-for-MSHV-sleep-state-configuration/20251118-051204
base:   next-20251117
patch link:    https://lore.kernel.org/r/20251117210855.108126-4-prapal%40linux.microsoft.com
patch subject: [PATCH v5 3/3] hyperv: Cleanly shutdown root partition with MSHV
config: arm64-randconfig-003-20251118 (https://download.01.org/0day-ci/archive/20251118/202511182353.5FvVmUhR-lkp@intel.com/config)
compiler: clang version 19.1.7 (https://github.com/llvm/llvm-project cd708029e0b2869e80abe31ddb175f7c35361f90)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20251118/202511182353.5FvVmUhR-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202511182353.5FvVmUhR-lkp@intel.com/

All warnings (new ones prefixed by >>):

   drivers/hv/mshv_common.c:210:6: warning: no previous prototype for function 'hv_sleep_notifiers_register' [-Wmissing-prototypes]
     210 | void hv_sleep_notifiers_register(void)
         |      ^
   drivers/hv/mshv_common.c:210:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
     210 | void hv_sleep_notifiers_register(void)
         | ^
         | static 
>> drivers/hv/mshv_common.c:224:6: warning: no previous prototype for function 'hv_machine_power_off' [-Wmissing-prototypes]
     224 | void hv_machine_power_off(void)
         |      ^
   drivers/hv/mshv_common.c:224:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
     224 | void hv_machine_power_off(void)
         | ^
         | static 
   2 warnings generated.


vim +/hv_machine_power_off +224 drivers/hv/mshv_common.c

   219	
   220	/*
   221	 * Power off the machine by entering S5 sleep state via Hyper-V hypercall.
   222	 * This call does not return if successful.
   223	 */
 > 224	void hv_machine_power_off(void)
   225	{
   226		unsigned long flags;
   227		struct hv_input_enter_sleep_state *in;
   228	
   229		local_irq_save(flags);
   230		in = *this_cpu_ptr(hyperv_pcpu_input_arg);
   231		in->sleep_state = HV_SLEEP_STATE_S5;
   232	
   233		(void)hv_do_hypercall(HVCALL_ENTER_SLEEP_STATE, in, NULL);
   234		local_irq_restore(flags);
   235	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

RE: [PATCH v5 1/3] hyperv: Add definitions for MSHV sleep state configuration

[Michael Kelley]

From: Praveen K Paladugu <prapal@linux.microsoft.com> Sent: Monday, November 17, 2025 1:08 PM
> 
> Add the definitions required to configure sleep states in mshv hypervsior.
> 
> 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>
> Reviewed-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
> ---
>  include/hyperv/hvgdk_mini.h |  4 +++-
>  include/hyperv/hvhdk_mini.h | 40 +++++++++++++++++++++++++++++++++++++
>  2 files changed, 43 insertions(+), 1 deletion(-)
> 
> diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h
> index 1d5ce11be8b6..04b18d0e37af 100644
> --- a/include/hyperv/hvgdk_mini.h
> +++ b/include/hyperv/hvgdk_mini.h
> @@ -465,19 +465,21 @@ union hv_vp_assist_msr_contents {	 /*
> HV_REGISTER_VP_ASSIST_PAGE */
>  #define HVCALL_RESET_DEBUG_SESSION			0x006b
>  #define HVCALL_MAP_STATS_PAGE				0x006c
>  #define HVCALL_UNMAP_STATS_PAGE				0x006d
> +#define HVCALL_SET_SYSTEM_PROPERTY			0x006f
>  #define HVCALL_ADD_LOGICAL_PROCESSOR			0x0076
>  #define HVCALL_GET_SYSTEM_PROPERTY			0x007b
>  #define HVCALL_MAP_DEVICE_INTERRUPT			0x007c
>  #define HVCALL_UNMAP_DEVICE_INTERRUPT			0x007d
>  #define HVCALL_RETARGET_INTERRUPT			0x007e
>  #define HVCALL_NOTIFY_PARTITION_EVENT                   0x0087
> +#define HVCALL_ENTER_SLEEP_STATE			0x0084
>  #define HVCALL_NOTIFY_PORT_RING_EMPTY			0x008b
>  #define HVCALL_REGISTER_INTERCEPT_RESULT		0x0091
>  #define HVCALL_ASSERT_VIRTUAL_INTERRUPT			0x0094
>  #define HVCALL_CREATE_PORT				0x0095
>  #define HVCALL_CONNECT_PORT				0x0096
>  #define HVCALL_START_VP					0x0099
> -#define HVCALL_GET_VP_INDEX_FROM_APIC_ID			0x009a
> +#define HVCALL_GET_VP_INDEX_FROM_APIC_ID		0x009a
>  #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE	0x00af
>  #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST	0x00b0
>  #define HVCALL_SIGNAL_EVENT_DIRECT			0x00c0
> diff --git a/include/hyperv/hvhdk_mini.h b/include/hyperv/hvhdk_mini.h
> index f2d7b50de7a4..41a29bf8ec14 100644
> --- a/include/hyperv/hvhdk_mini.h
> +++ b/include/hyperv/hvhdk_mini.h
> @@ -140,6 +140,7 @@ enum hv_snp_status {
> 
>  enum hv_system_property {
>  	/* Add more values when needed */
> +	HV_SYSTEM_PROPERTY_SLEEP_STATE = 3,
>  	HV_SYSTEM_PROPERTY_SCHEDULER_TYPE = 15,
>  	HV_DYNAMIC_PROCESSOR_FEATURE_PROPERTY = 21,
>  	HV_SYSTEM_PROPERTY_CRASHDUMPAREA = 47,
> @@ -155,6 +156,19 @@ union hv_pfn_range {            /* HV_SPA_PAGE_RANGE */
>  	} __packed;
>  };
> 
> +enum hv_sleep_state {
> +	HV_SLEEP_STATE_S1 = 1,
> +	HV_SLEEP_STATE_S2 = 2,
> +	HV_SLEEP_STATE_S3 = 3,
> +	HV_SLEEP_STATE_S4 = 4,
> +	HV_SLEEP_STATE_S5 = 5,
> +	/*
> +	 * After hypervisor has received this, any follow up sleep
> +	 * state registration requests will be rejected.
> +	 */
> +	HV_SLEEP_STATE_LOCK = 6
> +};
> +
>  enum hv_dynamic_processor_feature_property {
>  	/* Add more values when needed */
>  	HV_X64_DYNAMIC_PROCESSOR_FEATURE_MAX_ENCRYPTED_PARTITIONS =
> 13,
> @@ -184,6 +198,32 @@ struct hv_output_get_system_property {
>  	};
>  } __packed;
> 
> +struct hv_sleep_state_info {
> +	u32 sleep_state; /* enum hv_sleep_state */
> +	u8 pm1a_slp_typ;
> +	u8 pm1b_slp_typ;
> +} __packed;
> +
> +struct hv_input_set_system_property {
> +	u32 property_id; /* enum hv_system_property */
> +	u32 reserved;
> +	union {
> +		/* More fields to be filled in when needed */
> +		struct hv_sleep_state_info set_sleep_state_info;
> +
> +		/*
> +		 * Add a reserved field to ensure the union is 8-byte aligned as
> +		 * existing members may not be. This is a temporary measure
> +		 * until all remaining members are added.
> +		 */
> +		 u64 reserved0[8];

I had expected a single u64 to pad out to 64-bit alignment. This is 512 bytes.

> +	};
> +} __packed;
> +
> +struct hv_input_enter_sleep_state {     /* HV_INPUT_ENTER_SLEEP_STATE */
> +	u32 sleep_state;        /* enum hv_sleep_state */
> +} __packed;
> +
>  struct hv_input_map_stats_page {
>  	u32 type; /* enum hv_stats_object_type */
>  	u32 padding;
> --
> 2.51.0
> 

Re: [PATCH v5 3/3] hyperv: Cleanly shutdown root partition with MSHV

[Praveen Paladugu]

On Mon, Nov 17, 2025 at 03:45:36PM -0800, Stanislav Kinsburskii wrote:
> On Mon, Nov 17, 2025 at 03:08:18PM -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/hyperv/hv_init.c       |  2 ++
> >  arch/x86/include/asm/mshyperv.h |  2 ++
> >  drivers/hv/mshv_common.c        | 18 ++++++++++++++++++
> >  3 files changed, 22 insertions(+)
> > 
> > diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
> > index 645b52dd732e..24824534ff8d 100644
> > --- a/arch/x86/hyperv/hv_init.c
> > +++ b/arch/x86/hyperv/hv_init.c
> > @@ -34,6 +34,7 @@
> >  #include <clocksource/hyperv_timer.h>
> >  #include <linux/highmem.h>
> >  #include <linux/export.h>
> > +#include <asm/reboot.h>
> >  
> >  void *hv_hypercall_pg;
> >  
> > @@ -562,6 +563,7 @@ void __init hyperv_init(void)
> >  		 * failures here.
> >  		 */
> >  		hv_sleep_notifiers_register();
> > +		machine_ops.power_off = hv_machine_power_off;
> 
> It looks more natural to me to gather all the machine_ops hooks in one
> place (meaning in ms_hyperv_init_platform).
> It is better moving this assignment there and do the branching on the
> partition type in the power_off callback instead.
>

Moving machine_ops hooks assignment to ms_hyperv_init_platform sounds
reasonable to me. I have a concern about doing the branching within the
callback though.

This assignment overwrites the default of using ACPI for poweroff.
By moving the branching into hv_machine_power_off, it would look like:

hv_machine_power_off {
    if not root {
        fallback to default
    } else {
        Use mshv hypercall to poweroff   
    }
}

I would rather do something cleaner like:

if root {
    machine_ops.power_off = hv_machine_power_off;
}

Praveen


> Thanks,
> Stanislav
> 
> 
> >  	} else {
> >  		hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
> >  		wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
> > 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/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c
> > index ee733ba1575e..73505cbdc324 100644
> > --- a/drivers/hv/mshv_common.c
> > +++ b/drivers/hv/mshv_common.c
> > @@ -216,3 +216,21 @@ 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);
> > +
> > +}
> > -- 
> > 2.51.0

Re: [PATCH v5 1/3] hyperv: Add definitions for MSHV sleep state configuration

[Praveen Paladugu]

On Tue, Nov 18, 2025 at 06:10:51PM +0000, Michael Kelley wrote:
> From: Praveen K Paladugu <prapal@linux.microsoft.com> Sent: Monday, November 17, 2025 1:08 PM
> > 
> > Add the definitions required to configure sleep states in mshv hypervsior.
> > 
> > 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>
> > Reviewed-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
> > ---
> >  include/hyperv/hvgdk_mini.h |  4 +++-
> >  include/hyperv/hvhdk_mini.h | 40 +++++++++++++++++++++++++++++++++++++
> >  2 files changed, 43 insertions(+), 1 deletion(-)
> > 
> > diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h
> > index 1d5ce11be8b6..04b18d0e37af 100644
> > --- a/include/hyperv/hvgdk_mini.h
> > +++ b/include/hyperv/hvgdk_mini.h
> > @@ -465,19 +465,21 @@ union hv_vp_assist_msr_contents {	 /*
> > HV_REGISTER_VP_ASSIST_PAGE */
> >  #define HVCALL_RESET_DEBUG_SESSION			0x006b
> >  #define HVCALL_MAP_STATS_PAGE				0x006c
> >  #define HVCALL_UNMAP_STATS_PAGE				0x006d
> > +#define HVCALL_SET_SYSTEM_PROPERTY			0x006f
> >  #define HVCALL_ADD_LOGICAL_PROCESSOR			0x0076
> >  #define HVCALL_GET_SYSTEM_PROPERTY			0x007b
> >  #define HVCALL_MAP_DEVICE_INTERRUPT			0x007c
> >  #define HVCALL_UNMAP_DEVICE_INTERRUPT			0x007d
> >  #define HVCALL_RETARGET_INTERRUPT			0x007e
> >  #define HVCALL_NOTIFY_PARTITION_EVENT                   0x0087
> > +#define HVCALL_ENTER_SLEEP_STATE			0x0084
> >  #define HVCALL_NOTIFY_PORT_RING_EMPTY			0x008b
> >  #define HVCALL_REGISTER_INTERCEPT_RESULT		0x0091
> >  #define HVCALL_ASSERT_VIRTUAL_INTERRUPT			0x0094
> >  #define HVCALL_CREATE_PORT				0x0095
> >  #define HVCALL_CONNECT_PORT				0x0096
> >  #define HVCALL_START_VP					0x0099
> > -#define HVCALL_GET_VP_INDEX_FROM_APIC_ID			0x009a
> > +#define HVCALL_GET_VP_INDEX_FROM_APIC_ID		0x009a
> >  #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE	0x00af
> >  #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST	0x00b0
> >  #define HVCALL_SIGNAL_EVENT_DIRECT			0x00c0
> > diff --git a/include/hyperv/hvhdk_mini.h b/include/hyperv/hvhdk_mini.h
> > index f2d7b50de7a4..41a29bf8ec14 100644
> > --- a/include/hyperv/hvhdk_mini.h
> > +++ b/include/hyperv/hvhdk_mini.h
> > @@ -140,6 +140,7 @@ enum hv_snp_status {
> > 
> >  enum hv_system_property {
> >  	/* Add more values when needed */
> > +	HV_SYSTEM_PROPERTY_SLEEP_STATE = 3,
> >  	HV_SYSTEM_PROPERTY_SCHEDULER_TYPE = 15,
> >  	HV_DYNAMIC_PROCESSOR_FEATURE_PROPERTY = 21,
> >  	HV_SYSTEM_PROPERTY_CRASHDUMPAREA = 47,
> > @@ -155,6 +156,19 @@ union hv_pfn_range {            /* HV_SPA_PAGE_RANGE */
> >  	} __packed;
> >  };
> > 
> > +enum hv_sleep_state {
> > +	HV_SLEEP_STATE_S1 = 1,
> > +	HV_SLEEP_STATE_S2 = 2,
> > +	HV_SLEEP_STATE_S3 = 3,
> > +	HV_SLEEP_STATE_S4 = 4,
> > +	HV_SLEEP_STATE_S5 = 5,
> > +	/*
> > +	 * After hypervisor has received this, any follow up sleep
> > +	 * state registration requests will be rejected.
> > +	 */
> > +	HV_SLEEP_STATE_LOCK = 6
> > +};
> > +
> >  enum hv_dynamic_processor_feature_property {
> >  	/* Add more values when needed */
> >  	HV_X64_DYNAMIC_PROCESSOR_FEATURE_MAX_ENCRYPTED_PARTITIONS =
> > 13,
> > @@ -184,6 +198,32 @@ struct hv_output_get_system_property {
> >  	};
> >  } __packed;
> > 
> > +struct hv_sleep_state_info {
> > +	u32 sleep_state; /* enum hv_sleep_state */
> > +	u8 pm1a_slp_typ;
> > +	u8 pm1b_slp_typ;
> > +} __packed;
> > +
> > +struct hv_input_set_system_property {
> > +	u32 property_id; /* enum hv_system_property */
> > +	u32 reserved;
> > +	union {
> > +		/* More fields to be filled in when needed */
> > +		struct hv_sleep_state_info set_sleep_state_info;
> > +
> > +		/*
> > +		 * Add a reserved field to ensure the union is 8-byte aligned as
> > +		 * existing members may not be. This is a temporary measure
> > +		 * until all remaining members are added.
> > +		 */
> > +		 u64 reserved0[8];
> 
> I had expected a single u64 to pad out to 64-bit alignment. This is 512 bytes.
>
I hear you Michael. I chose to this to keep this struct future-proof.
There are some entries in this union that are this big. To not run into
alignment issues when new entries are added to this union, I added this
reserved element which is of the size of the largest element in the
union.

> > +	};
> > +} __packed;
> > +
> > +struct hv_input_enter_sleep_state {     /* HV_INPUT_ENTER_SLEEP_STATE */
> > +	u32 sleep_state;        /* enum hv_sleep_state */
> > +} __packed;
> > +
> >  struct hv_input_map_stats_page {
> >  	u32 type; /* enum hv_stats_object_type */
> >  	u32 padding;
> > --
> > 2.51.0
> >