mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Will Deacon <will.deacon@arm.com>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Avi Kivity <avi@redhat.com>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
	Ingo Molnar <mingo@elte.hu>,
	"acme@ghostprotocols.net" <acme@ghostprotocols.net>,
	Jason Wessel <jason.wessel@windriver.com>
Subject: Re: [PATCH 1/3] perf: add context field to perf_event
Date: Thu, 21 Jul 2011 16:32:38 +0100	[thread overview]
Message-ID: <20110721153238.GC8446@e102144-lin.cambridge.arm.com> (raw)
In-Reply-To: <1310463060.14978.17.camel@twins>

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


  parent reply	other threads:[~2011-07-21 15:32 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-06-29 15:42 [PATCH 0/3] Preparatory perf patches for KVM PMU support Avi Kivity
2011-06-29 15:42 ` [PATCH 1/3] perf: add context field to perf_event Avi Kivity
2011-06-29 16:08   ` Frederic Weisbecker
2011-06-29 16:25     ` Avi Kivity
2011-06-29 16:27     ` Will Deacon
2011-07-04 13:58       ` Frederic Weisbecker
2011-07-04 14:10         ` Avi Kivity
2011-07-04 14:36           ` Frederic Weisbecker
2011-07-11 21:07             ` Will Deacon
2011-07-12  7:20               ` Avi Kivity
2011-07-12  8:38                 ` Peter Zijlstra
2011-07-12  9:08                   ` Avi Kivity
2011-07-12  9:14                     ` Peter Zijlstra
2011-07-12  9:16                       ` Avi Kivity
2011-07-12  9:18                         ` Peter Zijlstra
2011-07-12  9:27                           ` Avi Kivity
2011-07-12  9:31                             ` Peter Zijlstra
2011-07-12  9:36                               ` Avi Kivity
2011-07-12  9:42                                 ` Will Deacon
2011-07-12  9:41                               ` Joerg Roedel
2011-07-12  9:44                                 ` Avi Kivity
2011-07-12  9:48                                   ` Joerg Roedel
2011-07-12  9:55                                     ` Avi Kivity
2011-07-12 10:03                                       ` Joerg Roedel
2011-07-12 10:07                                         ` Avi Kivity
2011-07-12 10:24                                           ` Joerg Roedel
2011-07-12 10:36                                             ` Avi Kivity
2011-07-21 15:32                               ` Will Deacon [this message]
2011-07-21 15:36                                 ` Avi Kivity
2011-07-21 15:46                                   ` Will Deacon
2011-07-21 15:59                                     ` Avi Kivity
2011-07-21 16:37                                       ` Will Deacon
2011-07-05 14:30         ` Will Deacon
2011-07-05 14:34           ` Frederic Weisbecker
2011-07-01 15:24   ` [tip:perf/core] perf: Add " tip-bot for Avi Kivity
2011-06-29 15:42 ` [PATCH 2/3] x86, perf: add constraints for architectural PMU v1 Avi Kivity
2011-07-01 15:24   ` [tip:perf/core] x86, perf: Add constraints for architectural PMU tip-bot for Avi Kivity
2011-06-29 15:42 ` [PATCH 3/3] perf: export perf_event_refresh() to modules Avi Kivity
2011-07-01 15:25   ` [tip:perf/core] " tip-bot for Avi Kivity

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20110721153238.GC8446@e102144-lin.cambridge.arm.com \
    --to=will.deacon@arm.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@ghostprotocols.net \
    --cc=avi@redhat.com \
    --cc=fweisbec@gmail.com \
    --cc=jason.wessel@windriver.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®