Re: [RFC -v2 PATCH 2/3] sched: add yield_to function

[Mike Galbraith <mgalbraith@suse.de>]

On Mon, 2010-12-20 at 10:40 -0500, Rik van Riel wrote:
> On 12/17/2010 02:15 AM, Mike Galbraith wrote:
> 
> > BTW, with this vruntime donation thingy, what prevents a task from
> > forking off accomplices who do nothing but wait for a wakeup and
> > yield_to(exploit)?
> >
> > Even swapping vruntimes in the same cfs_rq is dangerous as hell, because
> > one party is going backward.
> 
> I just realized the answer to this question.
> 
> We only give cpu time to tasks that are runnable, but not
> currently running.  That ensures one task cannot block others
> from running by having time yielded to it constantly.

Hm.  Don't think that will 100% sure prevent clock stoppage, because the
running task doesn't necessarily advance min_vruntime.

What about something like the below instead?  It compiles, but may eat
your first born child.

sched: implement fair class yield_to(task) using cfs_rq->next as a selection hint.

<CHANGELOG>

Not-signed-off-by: Mike Galbraith <efault@gmx.de>
---
 include/linux/sched.h |    1 
 kernel/sched.c        |   47 +++++++++++++++++++++++++++++++++++++++++
 kernel/sched_fair.c   |   56 ++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 104 insertions(+)

Index: linux-2.6/include/linux/sched.h
===================================================================
--- linux-2.6.orig/include/linux/sched.h
+++ linux-2.6/include/linux/sched.h
@@ -1056,6 +1056,7 @@ struct sched_class {
 	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*yield_task) (struct rq *rq);
+	int (*yield_to_task) (struct task_struct *p, int preempt);
 
 	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
 
Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -5325,6 +5325,53 @@ void __sched yield(void)
 }
 EXPORT_SYMBOL(yield);
 
+/**
+ * yield_to - yield the current processor to another thread in
+ * your thread group, or accelerate that thread toward the
+ * processor it's on.
+ *
+ * It's the caller's job to ensure that the target task struct
+ * can't go away on us before we can do any checks.
+ */
+void __sched yield_to(struct task_struct *p, int preempt)
+{
+	struct task_struct *curr = current;
+	struct rq *rq, *p_rq;
+	unsigned long flags;
+	int yield = 0;
+
+	local_irq_save(flags);
+	rq = this_rq();
+
+again:
+	p_rq = task_rq(p);
+	double_rq_lock(rq, p_rq);
+	while (task_rq(p) != p_rq) {
+		double_rq_unlock(rq, p_rq);
+		goto again;
+	}
+
+	if (task_running(p_rq, p) || p->state || !p->se.on_rq ||
+			!same_thread_group(p, curr) ||
+			!curr->sched_class->yield_to_task ||
+			curr->sched_class != p->sched_class) {
+		goto out;
+	}
+
+	yield = curr->sched_class->yield_to_task(p, preempt);
+
+out:
+	double_rq_unlock(rq, p_rq);
+	local_irq_restore(flags);
+
+	if (yield) {
+		set_current_state(TASK_RUNNING);
+		schedule();
+	}
+}
+EXPORT_SYMBOL(yield_to);
+
+
 /*
  * This task is about to go to sleep on IO. Increment rq->nr_iowait so
  * that process accounting knows that this is a task in IO wait state.
Index: linux-2.6/kernel/sched_fair.c
===================================================================
--- linux-2.6.orig/kernel/sched_fair.c
+++ linux-2.6/kernel/sched_fair.c
@@ -1320,6 +1320,61 @@ static void yield_task_fair(struct rq *r
 }
 
 #ifdef CONFIG_SMP
+static void pull_task(struct rq *src_rq, struct task_struct *p,
+		      struct rq *this_rq, int this_cpu);
+#endif
+
+static int yield_to_task_fair(struct task_struct *p, int preempt)
+{
+	struct sched_entity *se = &current->se;
+	struct sched_entity *pse = &p->se;
+	struct sched_entity *curr = &(task_rq(p)->curr)->se;
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	struct cfs_rq *p_cfs_rq = cfs_rq_of(pse);
+	int yield = this_rq() == task_rq(p);
+	int want_preempt = preempt;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	if (cfs_rq->tg != p_cfs_rq->tg)
+		return 0;
+
+	/* Preemption only allowed within the same task group. */
+	if (preempt && cfs_rq->tg != cfs_rq_of(curr)->tg)
+		preempt = 0;
+#endif
+	/* Preemption only allowed within the same thread group. */
+	if (preempt && !same_thread_group(current, task_of(p_cfs_rq->curr)))
+		preempt = 0;
+
+#ifdef CONFIG_SMP
+	/*
+	 * If this yield is important enough to want to preempt instead
+	 * of only dropping a ->next hint, we're alone, and the target
+	 * is not alone, pull the target to this cpu.
+	 */
+	if (want_preempt && !yield && cfs_rq->nr_running == 1 &&
+			cpumask_test_cpu(smp_processor_id(), &p->cpus_allowed)) {
+		pull_task(task_rq(p), p, this_rq(), smp_processor_id());
+		p_cfs_rq = cfs_rq_of(pse);
+		yield = 1;
+	}
+#endif
+
+	if (yield)
+		clear_buddies(cfs_rq, se);
+	else if (preempt)
+		clear_buddies(p_cfs_rq, curr);
+
+	/* Tell the scheduler that we'd really like pse to run next. */
+	p_cfs_rq->next = pse;
+
+	if (!yield && preempt)
+		resched_task(task_of(p_cfs_rq->curr));
+
+	return yield;
+}
+
+#ifdef CONFIG_SMP
 
 static void task_waking_fair(struct rq *rq, struct task_struct *p)
 {
@@ -4126,6 +4181,7 @@ static const struct sched_class fair_sch
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
+	.yield_to_task		= yield_to_task_fair,
 
 	.check_preempt_curr	= check_preempt_wakeup,