diff mbox

[tip/core/rcu,01/28] rcu: Simplify curing of load woes

Message ID 1307561407-13809-1-git-send-email-paulmck@linux.vnet.ibm.com
State Accepted
Commit 9a432736904d386cda28b987b38ba14dae960ecc
Headers show

Commit Message

Paul E. McKenney June 8, 2011, 7:29 p.m. UTC 
Make the functions creating the kthreads wake them up.  Leverage the
fact that the per-node and boost kthreads can run anywhere, thus
dispensing with the need to wake them up once the incoming CPU has
gone fully online.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutree.c        |   65 +++++++++++++++-------------------------------
 kernel/rcutree_plugin.h |   11 +-------
 2 files changed, 22 insertions(+), 54 deletions(-)

Comments

Paul E. McKenney June 10, 2011, 7:53 p.m. UTC | #1 
On Fri, Jun 10, 2011 at 04:18:32PM +0200, Peter Zijlstra wrote:
> On Wed, 2011-06-08 at 12:29 -0700, Paul E. McKenney wrote:
> > Make the functions creating the kthreads wake them up.  Leverage the
> > fact that the per-node and boost kthreads can run anywhere, thus
> > dispensing with the need to wake them up once the incoming CPU has
> > gone fully online.
> 
> Indeed, I failed to notice the node and boost threads weren't bound.

Hey, you did the big fix, so I cannot complain about doing a little
cleanup!  ;-)

> > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> > ---
> >  kernel/rcutree.c        |   65 +++++++++++++++-------------------------------
> >  kernel/rcutree_plugin.h |   11 +-------
> >  2 files changed, 22 insertions(+), 54 deletions(-)
> > 
> > diff --git a/kernel/rcutree.c b/kernel/rcutree.c
> > index 4cc6a94..36e79d2 100644
> > --- a/kernel/rcutree.c
> > +++ b/kernel/rcutree.c
> > @@ -1634,6 +1634,20 @@ static int rcu_cpu_kthread(void *arg)
> >   * to manipulate rcu_cpu_kthread_task.  There might be another CPU
> >   * attempting to access it during boot, but the locking in kthread_bind()
> >   * will enforce sufficient ordering.
> > + *
> > + * Please note that we cannot simply refuse to wake up the per-CPU
> > + * kthread because kthreads are created in TASK_UNINTERRUPTIBLE state,
> > + * which can result in softlockup complaints if the task ends up being
> > + * idle for more than a couple of minutes.
> > + *
> > + * However, please note also that we cannot bind the per-CPU kthread to its
> > + * CPU until that CPU is fully online.  We also cannot wait until the
> > + * CPU is fully online before we create its per-CPU kthread, as this would
> > + * deadlock the system when CPU notifiers tried waiting for grace
> > + * periods.  So we bind the per-CPU kthread to its CPU only if the CPU
> > + * is online.  If its CPU is not yet fully online, then the code in
> > + * rcu_cpu_kthread() will wait until it is fully online, and then do
> > + * the binding.
> >   */
> >  static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
> >  {
> > @@ -1646,12 +1660,14 @@ static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
> >         t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu);
> >         if (IS_ERR(t))
> >                 return PTR_ERR(t);
> > -       kthread_bind(t, cpu);
> > +       if (cpu_online(cpu))
> > +               kthread_bind(t, cpu);
> >         per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
> >         WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
> > -       per_cpu(rcu_cpu_kthread_task, cpu) = t;
> >         sp.sched_priority = RCU_KTHREAD_PRIO;
> >         sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
> > +       per_cpu(rcu_cpu_kthread_task, cpu) = t;
> > +       wake_up_process(t); /* Get to TASK_INTERRUPTIBLE quickly. */
> >         return 0;
> >  } 
> 
> I'm not quite seeing how this is working though, I cannot find any code
> in rcu_cpu_kthread() that sets the thread affinity (not a hunk in this
> patch that adds it).

This happens in rcu_cpu_kthread_should_stop(), which is called from
rcu_cpu_kthread() before it does any real work.

Here it is:

static int rcu_cpu_kthread_should_stop(int cpu)
{
	while (cpu_is_offline(cpu) ||
	       !cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)) ||
	       smp_processor_id() != cpu) {
		if (kthread_should_stop())
			return 1;
		per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
		per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id();
		local_bh_enable();
		schedule_timeout_uninterruptible(1);
		if (!cpumask_equal(&current->cpus_allowed, cpumask_of(cpu)))
			set_cpus_allowed_ptr(current, cpumask_of(cpu));
		local_bh_disable();
	}
	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
	return 0;
}

Thoughts?

							Thanx, Paul
diff mbox

Patch

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 4cc6a94..36e79d2 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1634,6 +1634,20 @@  static int rcu_cpu_kthread(void *arg)
  * to manipulate rcu_cpu_kthread_task.  There might be another CPU
  * attempting to access it during boot, but the locking in kthread_bind()
  * will enforce sufficient ordering.
+ *
+ * Please note that we cannot simply refuse to wake up the per-CPU
+ * kthread because kthreads are created in TASK_UNINTERRUPTIBLE state,
+ * which can result in softlockup complaints if the task ends up being
+ * idle for more than a couple of minutes.
+ *
+ * However, please note also that we cannot bind the per-CPU kthread to its
+ * CPU until that CPU is fully online.  We also cannot wait until the
+ * CPU is fully online before we create its per-CPU kthread, as this would
+ * deadlock the system when CPU notifiers tried waiting for grace
+ * periods.  So we bind the per-CPU kthread to its CPU only if the CPU
+ * is online.  If its CPU is not yet fully online, then the code in
+ * rcu_cpu_kthread() will wait until it is fully online, and then do
+ * the binding.
  */
 static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
 {
@@ -1646,12 +1660,14 @@  static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
 	t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu);
 	if (IS_ERR(t))
 		return PTR_ERR(t);
-	kthread_bind(t, cpu);
+	if (cpu_online(cpu))
+		kthread_bind(t, cpu);
 	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
 	WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
-	per_cpu(rcu_cpu_kthread_task, cpu) = t;
 	sp.sched_priority = RCU_KTHREAD_PRIO;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+	per_cpu(rcu_cpu_kthread_task, cpu) = t;
+	wake_up_process(t); /* Get to TASK_INTERRUPTIBLE quickly. */
 	return 0;
 }
 
@@ -1758,12 +1774,11 @@  static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		sp.sched_priority = 99;
 		sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+		wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
 	}
 	return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index);
 }
 
-static void rcu_wake_one_boost_kthread(struct rcu_node *rnp);
-
 /*
  * Spawn all kthreads -- called as soon as the scheduler is running.
  */
@@ -1771,30 +1786,18 @@  static int __init rcu_spawn_kthreads(void)
 {
 	int cpu;
 	struct rcu_node *rnp;
-	struct task_struct *t;
 
 	rcu_kthreads_spawnable = 1;
 	for_each_possible_cpu(cpu) {
 		per_cpu(rcu_cpu_has_work, cpu) = 0;
-		if (cpu_online(cpu)) {
+		if (cpu_online(cpu))
 			(void)rcu_spawn_one_cpu_kthread(cpu);
-			t = per_cpu(rcu_cpu_kthread_task, cpu);
-			if (t)
-				wake_up_process(t);
-		}
 	}
 	rnp = rcu_get_root(rcu_state);
 	(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
-	if (rnp->node_kthread_task)
-		wake_up_process(rnp->node_kthread_task);
 	if (NUM_RCU_NODES > 1) {
-		rcu_for_each_leaf_node(rcu_state, rnp) {
+		rcu_for_each_leaf_node(rcu_state, rnp)
 			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
-			t = rnp->node_kthread_task;
-			if (t)
-				wake_up_process(t);
-			rcu_wake_one_boost_kthread(rnp);
-		}
 	}
 	return 0;
 }
@@ -2220,31 +2223,6 @@  static void __cpuinit rcu_prepare_kthreads(int cpu)
 }
 
 /*
- * kthread_create() creates threads in TASK_UNINTERRUPTIBLE state,
- * but the RCU threads are woken on demand, and if demand is low this
- * could be a while triggering the hung task watchdog.
- *
- * In order to avoid this, poke all tasks once the CPU is fully
- * up and running.
- */
-static void __cpuinit rcu_online_kthreads(int cpu)
-{
-	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
-	struct rcu_node *rnp = rdp->mynode;
-	struct task_struct *t;
-
-	t = per_cpu(rcu_cpu_kthread_task, cpu);
-	if (t)
-		wake_up_process(t);
-
-	t = rnp->node_kthread_task;
-	if (t)
-		wake_up_process(t);
-
-	rcu_wake_one_boost_kthread(rnp);
-}
-
-/*
  * Handle CPU online/offline notification events.
  */
 static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
@@ -2261,7 +2239,6 @@  static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
 		rcu_prepare_kthreads(cpu);
 		break;
 	case CPU_ONLINE:
-		rcu_online_kthreads(cpu);
 	case CPU_DOWN_FAILED:
 		rcu_node_kthread_setaffinity(rnp, -1);
 		rcu_cpu_kthread_setrt(cpu, 1);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index c8bff30..ea2e2fb 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1299,15 +1299,10 @@  static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	sp.sched_priority = RCU_KTHREAD_PRIO;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
+	wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
 	return 0;
 }
 
-static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp)
-{
-	if (rnp->boost_kthread_task)
-		wake_up_process(rnp->boost_kthread_task);
-}
-
 #else /* #ifdef CONFIG_RCU_BOOST */
 
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
@@ -1331,10 +1326,6 @@  static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	return 0;
 }
 
-static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp)
-{
-}
-
 #endif /* #else #ifdef CONFIG_RCU_BOOST */
 
 #ifndef CONFIG_SMP