| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20251014164150.6935-3-prapal@linux.microsoft.com>
Date: Tue, 14 Oct 2025 11:41:21 -0500
From: Praveen K Paladugu <prapal@...ux.microsoft.com>
To: kys@...rosoft.com,
haiyangz@...rosoft.com,
wei.liu@...nel.org,
decui@...rosoft.com,
tglx@...utronix.de,
mingo@...hat.com,
linux-hyperv@...r.kernel.org,
linux-kernel@...r.kernel.org,
bp@...en8.de,
dave.hansen@...ux.intel.com,
x86@...nel.org,
hpa@...or.com,
arnd@...db.de
Cc: anbelski@...ux.microsoft.com,
prapal@...ux.microsoft.com,
easwar.hariharan@...ux.microsoft.com,
nunodasneves@...ux.microsoft.com,
skinsburskii@...ux.microsoft.com
Subject: [PATCH v2 2/2] hyperv: Enable clean shutdown for root partition with MSHV
When a shutdown is initiated in the root partition without configuring
sleep states, the call to `hv_call_enter_sleep_state` fails. In such cases
the root falls back to using legacy ACPI mechanisms to poweroff. This call
is intercepted by MSHV and will result in a Machine Check Exception (MCE).
Root 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, allowing
the root partition to shut down cleanly without triggering a panic.
Signed-off-by: Praveen K Paladugu <prapal@...ux.microsoft.com>
Co-developed-by: Anatol Belski <anbelski@...ux.microsoft.com>
Signed-off-by: Anatol Belski <anbelski@...ux.microsoft.com>
---
arch/x86/hyperv/hv_init.c | 7 ++
arch/x86/include/asm/mshyperv.h | 1 +
drivers/hv/hv_common.c | 119 ++++++++++++++++++++++++++++++++
3 files changed, 127 insertions(+)
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index afdbda2dd7b7..57bd96671ead 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -510,6 +510,13 @@ void __init hyperv_init(void)
memunmap(src);
hv_remap_tsc_clocksource();
+ /*
+ * 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.
+ */
+ (void)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 abc4659f5809..fb8d691193df 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -236,6 +236,7 @@ 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);
+int hv_sleep_notifiers_register(void);
#else
static inline void hv_apic_init(void) {}
#endif
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index e109a620c83f..cfba9ded7bcb 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -837,3 +837,122 @@ const char *hv_result_to_string(u64 status)
return "Unknown";
}
EXPORT_SYMBOL_GPL(hv_result_to_string);
+
+#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,
+};
+
+static int hv_acpi_sleep_handler(u8 sleep_state, u32 pm1a_cnt, u32 pm1b_cnt)
+{
+ int ret = 0;
+
+ if (sleep_state == ACPI_STATE_S5)
+ ret = hv_call_enter_sleep_state(HV_SLEEP_STATE_S5);
+
+ return ret == 0 ? 1 : -1;
+}
+
+static int hv_acpi_extended_sleep_handler(u8 sleep_state, u32 val_a, u32 val_b)
+{
+ return hv_acpi_sleep_handler(sleep_state, val_a, val_b);
+}
+
+int hv_sleep_notifiers_register(void)
+{
+ int ret;
+
+ acpi_os_set_prepare_sleep(&hv_acpi_sleep_handler);
+ acpi_os_set_prepare_extended_sleep(&hv_acpi_extended_sleep_handler);
+
+ ret = register_reboot_notifier(&hv_reboot_notifier);
+ if (ret)
+ pr_err("%s: cannot register reboot notifier %d\n",
+ __func__, ret);
+
+ return ret;
+}
+#endif
--
2.51.0
Powered by blists - more mailing lists