sched, preempt_notifier: separate notifier registration from static_key inc/dec

Commit 1cde2930e154 ("sched/preempt: Add static_key() to preempt_notifiers")
had two problems.  First, the preempt-notifier API needs to sleep with the
addition of the static_key, we do however need to hold off preemption
while modifying the preempt notifier list, otherwise a preemption could
observe an inconsistent list state.  KVM correctly registers and
unregisters preempt notifiers with preemption disabled, so the sleep
caused dmesg splats.

Second, KVM registers and unregisters preemption notifiers very often
(in vcpu_load/vcpu_put).  With a single uniprocessor guest the static key
would move between 0 and 1 continuously, hitting the slow path on every
userspace exit.

To fix this, wrap the static_key inc/dec in a new API, and call it from
KVM.

Fixes: 1cde2930e154 ("sched/preempt: Add static_key() to preempt_notifiers")
Reported-by: Pontus Fuchs <pontus.fuchs@gmail.com>
Reported-by: Takashi Iwai <tiwai@suse.de>
Tested-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

3 files changed, 20 insertions, 2 deletions

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 0f1534acaf60..84991f185173 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -293,6 +293,8 @@ struct preempt_notifier {
 	struct preempt_ops *ops;
 };
 
+void preempt_notifier_inc(void);
+void preempt_notifier_dec(void);
 void preempt_notifier_register(struct preempt_notifier *notifier);
 void preempt_notifier_unregister(struct preempt_notifier *notifier);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b803e1b8ab0c..552710ab19e0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2320,13 +2320,27 @@ void wake_up_new_task(struct task_struct *p)
 
 static struct static_key preempt_notifier_key = STATIC_KEY_INIT_FALSE;
 
+void preempt_notifier_inc(void)
+{
+	static_key_slow_inc(&preempt_notifier_key);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_inc);
+
+void preempt_notifier_dec(void)
+{
+	static_key_slow_dec(&preempt_notifier_key);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_dec);
+
 /**
  * preempt_notifier_register - tell me when current is being preempted & rescheduled
  * @notifier: notifier struct to register
  */
 void preempt_notifier_register(struct preempt_notifier *notifier)
 {
-	static_key_slow_inc(&preempt_notifier_key);
+	if (!static_key_false(&preempt_notifier_key))
+		WARN(1, "registering preempt_notifier while notifiers disabled\n");
+
 	hlist_add_head(&notifier->link, &current->preempt_notifiers);
 }
 EXPORT_SYMBOL_GPL(preempt_notifier_register);
@@ -2340,7 +2354,6 @@ EXPORT_SYMBOL_GPL(preempt_notifier_register);
 void preempt_notifier_unregister(struct preempt_notifier *notifier)
 {
 	hlist_del(&notifier->link);
-	static_key_slow_dec(&preempt_notifier_key);
 }
 EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 848af90b8091..8b8a44453670 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -553,6 +553,8 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	list_add(&kvm->vm_list, &vm_list);
 	spin_unlock(&kvm_lock);
 
+	preempt_notifier_inc();
+
 	return kvm;
 
 out_err:
@@ -620,6 +622,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	cleanup_srcu_struct(&kvm->irq_srcu);
 	cleanup_srcu_struct(&kvm->srcu);
 	kvm_arch_free_vm(kvm);
+	preempt_notifier_dec();
 	hardware_disable_all();
 	mmdrop(mm);
 }