[PATCH v3 0/2] Add support for clean shutdown with MSHV

[PATCH v3 0/2] Add support for clean shutdown with MSHV

[Praveen K Paladugu]

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

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 (2):
  hyperv: Add definitions for MSHV sleep state configuration
  hyperv: Enable clean shutdown for root partition with MSHV

 arch/x86/hyperv/hv_init.c       |   8 +++
 arch/x86/include/asm/mshyperv.h |   2 +
 drivers/hv/mshv_common.c        | 103 ++++++++++++++++++++++++++++++++
 include/hyperv/hvgdk_mini.h     |   4 +-
 include/hyperv/hvhdk_mini.h     |  33 ++++++++++
 5 files changed, 149 insertions(+), 1 deletion(-)

-- 
2.51.0

[PATCH v3 1/2] 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 | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h
index 7499a679e60a..b43fa1c9ed2c 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..06cf30deb319 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 +198,25 @@ 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;
+	};
+} __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 v3 2/2] hyperv: Enable clean shutdown for root partition with MSHV

[Praveen K Paladugu]

Without configuing sleep state info within mshv, if a root partition is
shut down, it will try to shutdown by writing to ACPI regions. These
writes are intercepted by mshv and will result in a Machine Check
Exception (MCE).

Root 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 prevent this, properly configure sleep states within MSHV, enable a
reboot notifier, allowing the root partition to cleanly shut down without
any panics. Only S5 sleep state is enabled for now.

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>
---
 arch/x86/hyperv/hv_init.c       |   8 +++
 arch/x86/include/asm/mshyperv.h |   2 +
 drivers/hv/mshv_common.c        | 103 ++++++++++++++++++++++++++++++++
 3 files changed, 113 insertions(+)

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index e28737ec7054..0a8856009792 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -555,6 +555,14 @@ 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 1342d55c2545..fbc1233175ce 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -181,8 +181,10 @@ 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..12b248ea3498 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 +141,103 @@ int hv_call_get_partition_property(u64 partition_id,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(hv_call_get_partition_property);
+
+#if IS_ENABLED(CONFIG_ACPI)
+/*
+ * 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.
+ *
+ * ACPI should be initialized and should support S5 sleep state when this method
+ * is called, so that it can extract correct PM values and pass them to hv.
+ */
+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;
+}
+
+static int hv_call_enter_sleep_state(u32 sleep_state)
+{
+	u64 status;
+	int ret;
+	unsigned long flags;
+	struct hv_input_enter_sleep_state *in;
+
+	ret = hv_initialize_sleep_states();
+	if (ret)
+		return ret;
+
+	local_irq_save(flags);
+	in = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	in->sleep_state = sleep_state;
+
+	status = hv_do_hypercall(HVCALL_ENTER_SLEEP_STATE, in, NULL);
+	local_irq_restore(flags);
+
+	if (!hv_result_success(status)) {
+		hv_status_err(status, "\n");
+		return hv_result_to_errno(status);
+	}
+
+	return 0;
+}
+
+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_call_enter_sleep_state(HV_SLEEP_STATE_S5);
+
+	return ret ? NOTIFY_DONE : NOTIFY_OK;
+}
+
+static struct notifier_block hv_reboot_notifier = {
+	.notifier_call = hv_reboot_notifier_handler,
+	.priority = INT_MIN, /* may not return */
+};
+
+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);
+}
+#endif
-- 
2.51.0

Re: [PATCH v3 0/2] Add support for clean shutdown with MSHV

[Easwar Hariharan]

On 10/27/2025 1:28 PM, Praveen K Paladugu wrote:
> Add support for clean shutdown of the root partition when running on MSHV
> hypervisor.
> 
> 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 (2):
>   hyperv: Add definitions for MSHV sleep state configuration
>   hyperv: Enable clean shutdown for root partition with MSHV
> 
>  arch/x86/hyperv/hv_init.c       |   8 +++
>  arch/x86/include/asm/mshyperv.h |   2 +
>  drivers/hv/mshv_common.c        | 103 ++++++++++++++++++++++++++++++++
>  include/hyperv/hvgdk_mini.h     |   4 +-
>  include/hyperv/hvhdk_mini.h     |  33 ++++++++++
>  5 files changed, 149 insertions(+), 1 deletion(-)
> 

This series seems to assume that Mukesh's hypervisor crash series has been merged, but that's not the case.
I don't see any code context or logical dependency on that series, but correct me if I'm wrong. If there's no
dependency, can you send a v4 based on Linus' tree or hyperv-next to avoid a merge conflict?

Thanks,
Easwar (he/him)

Re: [PATCH v3 0/2] Add support for clean shutdown with MSHV

[Praveen K Paladugu]

On 10/27/2025 3:56 PM, Easwar Hariharan wrote:
> On 10/27/2025 1:28 PM, Praveen K Paladugu wrote:
>> Add support for clean shutdown of the root partition when running on MSHV
>> hypervisor.
>>
>> 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 (2):
>>    hyperv: Add definitions for MSHV sleep state configuration
>>    hyperv: Enable clean shutdown for root partition with MSHV
>>
>>   arch/x86/hyperv/hv_init.c       |   8 +++
>>   arch/x86/include/asm/mshyperv.h |   2 +
>>   drivers/hv/mshv_common.c        | 103 ++++++++++++++++++++++++++++++++
>>   include/hyperv/hvgdk_mini.h     |   4 +-
>>   include/hyperv/hvhdk_mini.h     |  33 ++++++++++
>>   5 files changed, 149 insertions(+), 1 deletion(-)
>>
> 
> This series seems to assume that Mukesh's hypervisor crash series has been merged, but that's not the case.
> I don't see any code context or logical dependency on that series, but correct me if I'm wrong. If there's no
> dependency, can you send a v4 based on Linus' tree or hyperv-next to avoid a merge conflict?
> 

I rebased this patchset on top of hyperv/hyperv-next branch, which has 
crashdump patches: 
https://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git/log/?h=hyperv-next

Let me know if I missed/misunderstood anything.


> Thanks,
> Easwar (he/him)

Re: [PATCH v3 0/2] Add support for clean shutdown with MSHV

[Easwar Hariharan]

On 10/27/2025 2:11 PM, Praveen K Paladugu wrote:
> 
> 
> On 10/27/2025 3:56 PM, Easwar Hariharan wrote:
>> On 10/27/2025 1:28 PM, Praveen K Paladugu wrote:
>>> Add support for clean shutdown of the root partition when running on MSHV
>>> hypervisor.
>>>
>>> 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 (2):
>>>    hyperv: Add definitions for MSHV sleep state configuration
>>>    hyperv: Enable clean shutdown for root partition with MSHV
>>>
>>>   arch/x86/hyperv/hv_init.c       |   8 +++
>>>   arch/x86/include/asm/mshyperv.h |   2 +
>>>   drivers/hv/mshv_common.c        | 103 ++++++++++++++++++++++++++++++++
>>>   include/hyperv/hvgdk_mini.h     |   4 +-
>>>   include/hyperv/hvhdk_mini.h     |  33 ++++++++++
>>>   5 files changed, 149 insertions(+), 1 deletion(-)
>>>
>>
>> This series seems to assume that Mukesh's hypervisor crash series has been merged, but that's not the case.
>> I don't see any code context or logical dependency on that series, but correct me if I'm wrong. If there's no
>> dependency, can you send a v4 based on Linus' tree or hyperv-next to avoid a merge conflict?
>>
> 
> I rebased this patchset on top of hyperv/hyperv-next branch, which has crashdump patches: https://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git/log/?h=hyperv-next
> 
> Let me know if I missed/misunderstood anything.
>

Nope, a miss on my part. Sorry about the noise.

Thanks,
Easwar (he/him)

Re: [PATCH v3 2/2] hyperv: Enable clean shutdown for root partition with MSHV

[Easwar Hariharan]

On 10/27/2025 1:28 PM, Praveen K Paladugu wrote:
> Without configuing sleep state info within mshv, if a root partition is
> shut down, it will try to shutdown by writing to ACPI regions. These
> writes are intercepted by mshv and will result in a Machine Check
> Exception (MCE).
> 
> Root 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 prevent this, properly configure sleep states within MSHV, enable a
> reboot notifier, allowing the root partition to cleanly shut down without
> any panics. Only S5 sleep state is enabled for now.
> 
> 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>
> ---
>  arch/x86/hyperv/hv_init.c       |   8 +++
>  arch/x86/include/asm/mshyperv.h |   2 +
>  drivers/hv/mshv_common.c        | 103 ++++++++++++++++++++++++++++++++
>  3 files changed, 113 insertions(+)
> 

Reviewed-by: Easwar Hariharan <easwar.hariharan@linux.microsoft.com>