1 files changed, 37 insertions, 22 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index cb5c13eee193..479802a892d4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3962,18 +3962,19 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	}
 
 	vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus);
-	r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT);
-	BUG_ON(r == -EBUSY);
+	r = xa_reserve(&kvm->vcpu_array, vcpu->vcpu_idx, GFP_KERNEL_ACCOUNT);
 	if (r)
 		goto unlock_vcpu_destroy;
 
 	/* Now it's all set up, let userspace reach it */
 	kvm_get_kvm(kvm);
 	r = create_vcpu_fd(vcpu);
-	if (r < 0) {
-		xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx);
-		kvm_put_kvm_no_destroy(kvm);
-		goto unlock_vcpu_destroy;
+	if (r < 0)
+		goto kvm_put_xa_release;
+
+	if (KVM_BUG_ON(!!xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) {
+		r = -EINVAL;
+		goto kvm_put_xa_release;
 	}
 
 	/*
@@ -3988,6 +3989,9 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	kvm_create_vcpu_debugfs(vcpu);
 	return r;
 
+kvm_put_xa_release:
+	kvm_put_kvm_no_destroy(kvm);
+	xa_release(&kvm->vcpu_array, vcpu->vcpu_idx);
 unlock_vcpu_destroy:
 	mutex_unlock(&kvm->lock);
 	kvm_dirty_ring_free(&vcpu->dirty_ring);
@@ -5184,7 +5188,20 @@ static void hardware_disable_all(void)
 static int hardware_enable_all(void)
 {
 	atomic_t failed = ATOMIC_INIT(0);
-	int r = 0;
+	int r;
+
+	/*
+	 * Do not enable hardware virtualization if the system is going down.
+	 * If userspace initiated a forced reboot, e.g. reboot -f, then it's
+	 * possible for an in-flight KVM_CREATE_VM to trigger hardware enabling
+	 * after kvm_reboot() is called.  Note, this relies on system_state
+	 * being set _before_ kvm_reboot(), which is why KVM uses a syscore ops
+	 * hook instead of registering a dedicated reboot notifier (the latter
+	 * runs before system_state is updated).
+	 */
+	if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF ||
+	    system_state == SYSTEM_RESTART)
+		return -EBUSY;
 
 	/*
 	 * When onlining a CPU, cpu_online_mask is set before kvm_online_cpu()
@@ -5197,6 +5214,8 @@ static int hardware_enable_all(void)
 	cpus_read_lock();
 	mutex_lock(&kvm_lock);
 
+	r = 0;
+
 	kvm_usage_count++;
 	if (kvm_usage_count == 1) {
 		on_each_cpu(hardware_enable_nolock, &failed, 1);
@@ -5213,26 +5232,24 @@ 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 +5280,7 @@ 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 +5985,6 @@ 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 +6056,6 @@ 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 +6081,6 @@ 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();