On Tue, Jul 12, 2011 at 10:31:00AM +0100, Peter Zijlstra wrote:
> On Tue, 2011-07-12 at 12:27 +0300, Avi Kivity wrote:
> > On 07/12/2011 12:18 PM, Peter Zijlstra wrote:
> > > >
> > > >  The guarantee is that the task was sleeping just before the function is
> > > >  called.  Of course it's woken up to run the function.
> > > >
> > > >  The idea is that you run the function in a known safe point to avoid
> > > >  extra synchronization.
> > > >
> > >
> > > I'd much rather we didn't wake the task and let it sleep, that's usually
> > > a very safe place for tasks to be. All you'd need is a guarantee it
> > > won't be woken up while you're doing your thing.
> > 
> > But it means that 'current' is not set to the right value.  If the 
> > function depends on it, then it will misbehave.  And in fact 
> > preempt_notifier_register(), which is the function we want to call here, 
> > does depend on current.
> > 
> > Of course we need to find more users for this, but I have a feeling this 
> > will be generally useful.  The alternative is to keep adding bits to 
> > thread_info::flags.
> 
> Using TIF_bits sounds like a much better solution for this, wakeups are
> really rather expensive and its best to avoid extra if at all possible.

The problem with using a TIF bit to tell a task that it needs to perform
some preempt_notifier registrations is that you end up with something that
looks a lot like preempt notifiers! You also don't escape the concurrent
read/write to thelist of pending registrations.

One thing I tried was simply using an RCU protected hlist for the preempt
notifiers so that we don't have to worry about atomicity when reading the
notifiers in finish_task_switch. It's a bit odd, since we know we only ever
have a single reader, but I've included it below anyway.

If anybody has any better ideas, I'm all ears.

Will


diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 2e681d9..2e21ffe 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -132,6 +132,11 @@ struct preempt_notifier {
 void preempt_notifier_register(struct preempt_notifier *notifier);
 void preempt_notifier_unregister(struct preempt_notifier *notifier);
 
+void preempt_notifier_register_task(struct preempt_notifier *notifier,
+                                   struct task_struct *tsk);
+void preempt_notifier_unregister_task(struct preempt_notifier *notifier,
+                                     struct task_struct *tsk);
+
 static inline void preempt_notifier_init(struct preempt_notifier *notifier,
                                     struct preempt_ops *ops)
 {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 496770a..5530d91 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1233,6 +1233,7 @@ struct task_struct {
 #ifdef CONFIG_PREEMPT_NOTIFIERS
        /* list of struct preempt_notifier: */
        struct hlist_head preempt_notifiers;
+       struct mutex preempt_notifiers_mutex;
 #endif
 
        /*
diff --git a/kernel/sched.c b/kernel/sched.c
index 9769c75..d3c46ca 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2784,6 +2784,7 @@ static void __sched_fork(struct task_struct *p)
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
        INIT_HLIST_HEAD(&p->preempt_notifiers);
+       mutex_init(&p->preempt_notifiers_mutex);
 #endif
 }
 
@@ -2901,13 +2902,31 @@ void wake_up_new_task(struct task_struct *p)
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 
+void preempt_notifier_register_task(struct preempt_notifier *notifier,
+                                   struct task_struct *tsk)
+{
+       mutex_lock(&tsk->preempt_notifiers_mutex);
+       hlist_add_head_rcu(&notifier->link, &tsk->preempt_notifiers);
+       mutex_unlock(&tsk->preempt_notifiers_mutex);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_register_task);
+
+void preempt_notifier_unregister_task(struct preempt_notifier *notifier,
+                                     struct task_struct *tsk)
+{
+       mutex_lock(&tsk->preempt_notifiers_mutex);
+       hlist_del_rcu(&notifier->link);
+       mutex_unlock(&tsk->preempt_notifiers_mutex);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_unregister_task);
+
 /**
  * preempt_notifier_register - tell me when current is being preempted & 
rescheduled
  * @notifier: notifier struct to register
  */
 void preempt_notifier_register(struct preempt_notifier *notifier)
 {
-       hlist_add_head(&notifier->link, &current->preempt_notifiers);
+       preempt_notifier_register_task(notifier, current);
 }
 EXPORT_SYMBOL_GPL(preempt_notifier_register);
 
@@ -2919,7 +2938,7 @@ EXPORT_SYMBOL_GPL(preempt_notifier_register);
  */
 void preempt_notifier_unregister(struct preempt_notifier *notifier)
 {
-       hlist_del(&notifier->link);
+       preempt_notifier_unregister_task(notifier, current);
 }
 EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
 
@@ -2928,8 +2947,12 @@ static void fire_sched_in_preempt_notifiers(struct 
task_struct *curr)
        struct preempt_notifier *notifier;
        struct hlist_node *node;
 
-       hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
+       rcu_read_lock();
+
+       hlist_for_each_entry_rcu(notifier, node, &curr->preempt_notifiers, link)
                notifier->ops->sched_in(notifier, raw_smp_processor_id());
+
+       rcu_read_unlock();
 }
 
 static void
@@ -2939,8 +2962,12 @@ fire_sched_out_preempt_notifiers(struct task_struct 
*curr,
        struct preempt_notifier *notifier;
        struct hlist_node *node;
 
-       hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
+       rcu_read_lock();
+
+       hlist_for_each_entry_rcu(notifier, node, &curr->preempt_notifiers, link)
                notifier->ops->sched_out(notifier, next);
+
+       rcu_read_unlock();
 }
 
 #else /* !CONFIG_PREEMPT_NOTIFIERS */
@@ -7979,6 +8006,7 @@ void __init sched_init(void)
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
        INIT_HLIST_HEAD(&init_task.preempt_notifiers);
+       mutex_init(&init_task.preempt_notifiers_mutex);
 #endif
 
 #ifdef CONFIG_SMP

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to