mshv: Cleanly shutdown root partition with MSHV

Root partitions running on MSHV currently attempt ACPI power-off, which
MSHV intercepts and triggers a Machine Check Exception (MCE), leading
to a kernel panic.

Root partitions panic 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 avoid this, configure the sleep state in the hypervisor and invoke
the HVCALL_ENTER_SLEEP_STATE hypercall as the final step in the shutdown
sequence. This ensures a clean and safe shutdown of 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>
Acked-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>

arch/x86/include/asm/mshyperv.h

@@ -178,6 +178,7 @@ int hyperv_fill_flush_guest_mapping_list(
 		struct hv_guest_mapping_flush_list *flush,
 		u64 start_gfn, u64 end_gfn);
 void hv_sleep_notifiers_register(void);
+void hv_machine_power_off(void);
 
 #ifdef CONFIG_X86_64
 void hv_apic_init(void);

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

drivers/hv/mshv_common.c

@@ -216,3 +216,24 @@ 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);
+
+	/* should never reach here */
+	BUG();
+
+}