KVM: Use syscore_ops instead of reboot_notifier to hook restart/shutdown

Use syscore_ops.shutdown to disable hardware virtualization during a
reboot instead of using the dedicated reboot_notifier so that KVM disables
virtualization _after_ system_state has been updated.  This will allow
fixing a race in KVM's handling of a forced reboot where KVM can end up
enabling hardware virtualization between kernel_restart_prepare() and
machine_restart().

Rename KVM's hook to match the syscore op to avoid any possible confusion
from wiring up a "reboot" helper to a "shutdown" hook (neither "shutdown
nor "reboot" is completely accurate as the hook handles both).

Opportunistically rewrite kvm_shutdown()'s comment to make it less VMX
specific, and to explain why kvm_rebooting exists.

Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: James Morse <james.morse@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Zenghui Yu <yuzenghui@huawei.com>
Cc: kvmarm@lists.linux.dev
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Atish Patra <atishp@atishpatra.org>
Cc: kvm-riscv@lists.infradead.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Message-Id: <20230512233127.804012-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 11 insertions, 15 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index cb5c13eee193..2079d6065795 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -5213,26 +5213,24 @@ static int hardware_enable_all(void)
 	return r;
 }
 
-static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
-		      void *v)
+static void kvm_shutdown(void)
 {
 	/*
-	 * Some (well, at least mine) BIOSes hang on reboot if
-	 * in vmx root mode.
-	 *
-	 * And Intel TXT required VMX off for all cpu when system shutdown.
+	 * Disable hardware virtualization and set kvm_rebooting to indicate
+	 * that KVM has asynchronously disabled hardware virtualization, i.e.
+	 * that relevant errors and exceptions aren't entirely unexpected.
+	 * Some flavors of hardware virtualization need to be disabled before
+	 * transferring control to firmware (to perform shutdown/reboot), e.g.
+	 * on x86, virtualization can block INIT interrupts, which are used by
+	 * firmware to pull APs back under firmware control.  Note, this path
+	 * is used for both shutdown and reboot scenarios, i.e. neither name is
+	 * 100% comprehensive.
 	 */
 	pr_info("kvm: exiting hardware virtualization\n");
 	kvm_rebooting = true;
 	on_each_cpu(hardware_disable_nolock, NULL, 1);
-	return NOTIFY_OK;
 }
 
-static struct notifier_block kvm_reboot_notifier = {
-	.notifier_call = kvm_reboot,
-	.priority = 0,
-};
-
 static int kvm_suspend(void)
 {
 	/*
@@ -5263,6 +5261,7 @@ static void kvm_resume(void)
 static struct syscore_ops kvm_syscore_ops = {
 	.suspend = kvm_suspend,
 	.resume = kvm_resume,
+	.shutdown = kvm_shutdown,
 };
 #else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */
 static int hardware_enable_all(void)
@@ -5967,7 +5966,6 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 	if (r)
 		return r;
 
-	register_reboot_notifier(&kvm_reboot_notifier);
 	register_syscore_ops(&kvm_syscore_ops);
 #endif
 
@@ -6039,7 +6037,6 @@ err_cpu_kick_mask:
 err_vcpu_cache:
 #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING
 	unregister_syscore_ops(&kvm_syscore_ops);
-	unregister_reboot_notifier(&kvm_reboot_notifier);
 	cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE);
 #endif
 	return r;
@@ -6065,7 +6062,6 @@ void kvm_exit(void)
 	kvm_async_pf_deinit();
 #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING
 	unregister_syscore_ops(&kvm_syscore_ops);
-	unregister_reboot_notifier(&kvm_reboot_notifier);
 	cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE);
 #endif
 	kvm_irqfd_exit();