Merge branch 'kvm-redo-enable-virt' into HEAD

Register KVM's cpuhp and syscore callbacks when enabling virtualization in
hardware, as the sole purpose of said callbacks is to disable and re-enable
virtualization as needed.

The primary motivation for this series is to simplify dealing with enabling
virtualization for Intel's TDX, which needs to enable virtualization
when kvm-intel.ko is loaded, i.e. long before the first VM is created.

That said, this is a nice cleanup on its own.  By registering the callbacks
on-demand, the callbacks themselves don't need to check kvm_usage_count,
because their very existence implies a non-zero count.

Patch 1 (re)adds a dedicated lock for kvm_usage_count.  This avoids a
lock ordering issue between cpus_read_lock() and kvm_lock.  The lock
ordering issue still exist in very rare cases, and will be fixed for
good by switching vm_list to an (S)RCU-protected list.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 134 insertions, 136 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index cb2b78e92910..5f9a66df7bfb 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -136,8 +136,8 @@ static int kvm_no_compat_open(struct inode *inode, struct file *file)
 #define KVM_COMPAT(c)	.compat_ioctl	= kvm_no_compat_ioctl,	\
 			.open		= kvm_no_compat_open
 #endif
-static int hardware_enable_all(void);
-static void hardware_disable_all(void);
+static int kvm_enable_virtualization(void);
+static void kvm_disable_virtualization(void);
 
 static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
 
@@ -1220,7 +1220,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (r)
 		goto out_err_no_arch_destroy_vm;
 
-	r = hardware_enable_all();
+	r = kvm_enable_virtualization();
 	if (r)
 		goto out_err_no_disable;
 
@@ -1263,7 +1263,7 @@ out_no_coalesced_mmio:
 		mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
 #endif
 out_err_no_mmu_notifier:
-	hardware_disable_all();
+	kvm_disable_virtualization();
 out_err_no_disable:
 	kvm_arch_destroy_vm(kvm);
 out_err_no_arch_destroy_vm:
@@ -1360,7 +1360,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 #endif
 	kvm_arch_free_vm(kvm);
 	preempt_notifier_dec();
-	hardware_disable_all();
+	kvm_disable_virtualization();
 	mmdrop(mm);
 }
 
@@ -5571,137 +5571,67 @@ static struct miscdevice kvm_dev = {
 };
 
 #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING
+static bool enable_virt_at_load = true;
+module_param(enable_virt_at_load, bool, 0444);
+
 __visible bool kvm_rebooting;
 EXPORT_SYMBOL_GPL(kvm_rebooting);
 
-static DEFINE_PER_CPU(bool, hardware_enabled);
+static DEFINE_PER_CPU(bool, virtualization_enabled);
+static DEFINE_MUTEX(kvm_usage_lock);
 static int kvm_usage_count;
 
-static int __hardware_enable_nolock(void)
+__weak void kvm_arch_enable_virtualization(void)
+{
+
+}
+
+__weak void kvm_arch_disable_virtualization(void)
 {
-	if (__this_cpu_read(hardware_enabled))
+
+}
+
+static int kvm_enable_virtualization_cpu(void)
+{
+	if (__this_cpu_read(virtualization_enabled))
 		return 0;
 
-	if (kvm_arch_hardware_enable()) {
+	if (kvm_arch_enable_virtualization_cpu()) {
 		pr_info("kvm: enabling virtualization on CPU%d failed\n",
 			raw_smp_processor_id());
 		return -EIO;
 	}
 
-	__this_cpu_write(hardware_enabled, true);
+	__this_cpu_write(virtualization_enabled, true);
 	return 0;
 }
 
-static void hardware_enable_nolock(void *failed)
-{
-	if (__hardware_enable_nolock())
-		atomic_inc(failed);
-}
-
 static int kvm_online_cpu(unsigned int cpu)
 {
-	int ret = 0;
-
 	/*
 	 * Abort the CPU online process if hardware virtualization cannot
 	 * be enabled. Otherwise running VMs would encounter unrecoverable
 	 * errors when scheduled to this CPU.
 	 */
-	mutex_lock(&kvm_lock);
-	if (kvm_usage_count)
-		ret = __hardware_enable_nolock();
-	mutex_unlock(&kvm_lock);
-	return ret;
+	return kvm_enable_virtualization_cpu();
 }
 
-static void hardware_disable_nolock(void *junk)
+static void kvm_disable_virtualization_cpu(void *ign)
 {
-	/*
-	 * Note, hardware_disable_all_nolock() tells all online CPUs to disable
-	 * hardware, not just CPUs that successfully enabled hardware!
-	 */
-	if (!__this_cpu_read(hardware_enabled))
+	if (!__this_cpu_read(virtualization_enabled))
 		return;
 
-	kvm_arch_hardware_disable();
+	kvm_arch_disable_virtualization_cpu();
 
-	__this_cpu_write(hardware_enabled, false);
+	__this_cpu_write(virtualization_enabled, false);
 }
 
 static int kvm_offline_cpu(unsigned int cpu)
 {
-	mutex_lock(&kvm_lock);
-	if (kvm_usage_count)
-		hardware_disable_nolock(NULL);
-	mutex_unlock(&kvm_lock);
+	kvm_disable_virtualization_cpu(NULL);
 	return 0;
 }
 
-static void hardware_disable_all_nolock(void)
-{
-	BUG_ON(!kvm_usage_count);
-
-	kvm_usage_count--;
-	if (!kvm_usage_count)
-		on_each_cpu(hardware_disable_nolock, NULL, 1);
-}
-
-static void hardware_disable_all(void)
-{
-	cpus_read_lock();
-	mutex_lock(&kvm_lock);
-	hardware_disable_all_nolock();
-	mutex_unlock(&kvm_lock);
-	cpus_read_unlock();
-}
-
-static int hardware_enable_all(void)
-{
-	atomic_t failed = ATOMIC_INIT(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()
-	 * is called, and so on_each_cpu() between them includes the CPU that
-	 * is being onlined.  As a result, hardware_enable_nolock() may get
-	 * invoked before kvm_online_cpu(), which also enables hardware if the
-	 * usage count is non-zero.  Disable CPU hotplug to avoid attempting to
-	 * enable hardware multiple times.
-	 */
-	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);
-
-		if (atomic_read(&failed)) {
-			hardware_disable_all_nolock();
-			r = -EBUSY;
-		}
-	}
-
-	mutex_unlock(&kvm_lock);
-	cpus_read_unlock();
-
-	return r;
-}
-
 static void kvm_shutdown(void)
 {
 	/*
@@ -5717,34 +5647,32 @@ static void kvm_shutdown(void)
 	 */
 	pr_info("kvm: exiting hardware virtualization\n");
 	kvm_rebooting = true;
-	on_each_cpu(hardware_disable_nolock, NULL, 1);
+	on_each_cpu(kvm_disable_virtualization_cpu, NULL, 1);
 }
 
 static int kvm_suspend(void)
 {
 	/*
 	 * Secondary CPUs and CPU hotplug are disabled across the suspend/resume
-	 * callbacks, i.e. no need to acquire kvm_lock to ensure the usage count
-	 * is stable.  Assert that kvm_lock is not held to ensure the system
-	 * isn't suspended while KVM is enabling hardware.  Hardware enabling
-	 * can be preempted, but the task cannot be frozen until it has dropped
-	 * all locks (userspace tasks are frozen via a fake signal).
+	 * callbacks, i.e. no need to acquire kvm_usage_lock to ensure the usage
+	 * count is stable.  Assert that kvm_usage_lock is not held to ensure
+	 * the system isn't suspended while KVM is enabling hardware.  Hardware
+	 * enabling can be preempted, but the task cannot be frozen until it has
+	 * dropped all locks (userspace tasks are frozen via a fake signal).
 	 */
-	lockdep_assert_not_held(&kvm_lock);
+	lockdep_assert_not_held(&kvm_usage_lock);
 	lockdep_assert_irqs_disabled();
 
-	if (kvm_usage_count)
-		hardware_disable_nolock(NULL);
+	kvm_disable_virtualization_cpu(NULL);
 	return 0;
 }
 
 static void kvm_resume(void)
 {
-	lockdep_assert_not_held(&kvm_lock);
+	lockdep_assert_not_held(&kvm_usage_lock);
 	lockdep_assert_irqs_disabled();
 
-	if (kvm_usage_count)
-		WARN_ON_ONCE(__hardware_enable_nolock());
+	WARN_ON_ONCE(kvm_enable_virtualization_cpu());
 }
 
 static struct syscore_ops kvm_syscore_ops = {
@@ -5752,13 +5680,95 @@ static struct syscore_ops kvm_syscore_ops = {
 	.resume = kvm_resume,
 	.shutdown = kvm_shutdown,
 };
+
+static int kvm_enable_virtualization(void)
+{
+	int r;
+
+	guard(mutex)(&kvm_usage_lock);
+
+	if (kvm_usage_count++)
+		return 0;
+
+	kvm_arch_enable_virtualization();
+
+	r = cpuhp_setup_state(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online",
+			      kvm_online_cpu, kvm_offline_cpu);
+	if (r)
+		goto err_cpuhp;
+
+	register_syscore_ops(&kvm_syscore_ops);
+
+	/*
+	 * Undo virtualization enabling and bail if the system is going down.
+	 * If userspace initiated a forced reboot, e.g. reboot -f, then it's
+	 * possible for an in-flight operation to enable virtualization after
+	 * syscore_shutdown() is called, i.e. without kvm_shutdown() being
+	 * invoked.  Note, this relies on system_state being set _before_
+	 * kvm_shutdown(), e.g. to ensure either kvm_shutdown() is invoked
+	 * or this CPU observes the impending shutdown.  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) {
+		r = -EBUSY;
+		goto err_rebooting;
+	}
+
+	return 0;
+
+err_rebooting:
+	unregister_syscore_ops(&kvm_syscore_ops);
+	cpuhp_remove_state(CPUHP_AP_KVM_ONLINE);
+err_cpuhp:
+	kvm_arch_disable_virtualization();
+	--kvm_usage_count;
+	return r;
+}
+
+static void kvm_disable_virtualization(void)
+{
+	guard(mutex)(&kvm_usage_lock);
+
+	if (--kvm_usage_count)
+		return;
+
+	unregister_syscore_ops(&kvm_syscore_ops);
+	cpuhp_remove_state(CPUHP_AP_KVM_ONLINE);
+	kvm_arch_disable_virtualization();
+}
+
+static int kvm_init_virtualization(void)
+{
+	if (enable_virt_at_load)
+		return kvm_enable_virtualization();
+
+	return 0;
+}
+
+static void kvm_uninit_virtualization(void)
+{
+	if (enable_virt_at_load)
+		kvm_disable_virtualization();
+}
 #else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */
-static int hardware_enable_all(void)
+static int kvm_enable_virtualization(void)
+{
+	return 0;
+}
+
+static int kvm_init_virtualization(void)
 {
 	return 0;
 }
 
-static void hardware_disable_all(void)
+static void kvm_disable_virtualization(void)
+{
+
+}
+
+static void kvm_uninit_virtualization(void)
 {
 
 }
@@ -6460,15 +6470,6 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 	int r;
 	int cpu;
 
-#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING
-	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online",
-				      kvm_online_cpu, kvm_offline_cpu);
-	if (r)
-		return r;
-
-	register_syscore_ops(&kvm_syscore_ops);
-#endif
-
 	/* A kmem cache lets us meet the alignment requirements of fx_save. */
 	if (!vcpu_align)
 		vcpu_align = __alignof__(struct kvm_vcpu);
@@ -6479,10 +6480,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 					   offsetofend(struct kvm_vcpu, stats_id)
 					   - offsetof(struct kvm_vcpu, arch),
 					   NULL);
-	if (!kvm_vcpu_cache) {
-		r = -ENOMEM;
-		goto err_vcpu_cache;
-	}
+	if (!kvm_vcpu_cache)
+		return -ENOMEM;
 
 	for_each_possible_cpu(cpu) {
 		if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu),
@@ -6516,6 +6515,10 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 
 	kvm_gmem_init(module);
 
+	r = kvm_init_virtualization();
+	if (r)
+		goto err_virt;
+
 	/*
 	 * Registration _must_ be the very last thing done, as this exposes
 	 * /dev/kvm to userspace, i.e. all infrastructure must be setup!
@@ -6529,6 +6532,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 	return 0;
 
 err_register:
+	kvm_uninit_virtualization();
+err_virt:
 	kvm_vfio_ops_exit();
 err_vfio:
 	kvm_async_pf_deinit();
@@ -6539,11 +6544,6 @@ err_cpu_kick_mask:
 	for_each_possible_cpu(cpu)
 		free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
 	kmem_cache_destroy(kvm_vcpu_cache);
-err_vcpu_cache:
-#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING
-	unregister_syscore_ops(&kvm_syscore_ops);
-	cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE);
-#endif
 	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_init);
@@ -6559,16 +6559,14 @@ void kvm_exit(void)
 	 */
 	misc_deregister(&kvm_dev);
 
+	kvm_uninit_virtualization();
+
 	debugfs_remove_recursive(kvm_debugfs_dir);
 	for_each_possible_cpu(cpu)
 		free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
 	kmem_cache_destroy(kvm_vcpu_cache);
 	kvm_vfio_ops_exit();
 	kvm_async_pf_deinit();
-#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING
-	unregister_syscore_ops(&kvm_syscore_ops);
-	cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE);
-#endif
 	kvm_irqfd_exit();
 }
 EXPORT_SYMBOL_GPL(kvm_exit);