[PATCH v5 14/19] sched: Add a very simple proxy() function

[John Stultz]

This adds a very simple proxy() function so if
we select a blocked task to run, we will deactivate it
and pick again. The exception being if it has become
unblocked after proxy() was called.

Greatly simplified from patch by:
  Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
  Juri Lelli <juri.lelli@xxxxxxxxxx>
  Valentin Schneider <valentin.schneider@xxxxxxx>
  Connor O'Brien <connoro@xxxxxxxxxx>

Cc: Joel Fernandes <joelaf@xxxxxxxxxx>
Cc: Qais Yousef <qyousef@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Valentin Schneider <vschneid@xxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Ben Segall <bsegall@xxxxxxxxxx>
Cc: Zimuzo Ezeozue <zezeozue@xxxxxxxxxx>
Cc: Youssef Esmat <youssefesmat@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Waiman Long <longman@xxxxxxxxxx>
Cc: Boqun Feng <boqun.feng@xxxxxxxxx>
Cc: "Paul E . McKenney" <paulmck@xxxxxxxxxx>
Cc: kernel-team@xxxxxxxxxxx
[jstultz: Split out from larger proxy patch and simplified
 for review and testing.]
Signed-off-by: John Stultz <jstultz@xxxxxxxxxx>
---
v5:
* Split out from larger proxy patch
---
 kernel/sched/core.c | 89 +++++++++++++++++++++++++++++++++++++++++++--
 kernel/sched/rt.c   | 19 +++++++++-
 2 files changed, 102 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 76a42f21dda7..72d0803c7d47 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6562,11 +6562,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 # define SM_MASK_PREEMPT	SM_PREEMPT
 #endif
 
-bool try_to_deactivate_task(struct rq *rq, struct task_struct *p, unsigned long state)
+bool try_to_deactivate_task(struct rq *rq, struct task_struct *p,
+			    unsigned long state, bool deactivate_cond)
 {
 	if (signal_pending_state(state, p)) {
 		WRITE_ONCE(p->__state, TASK_RUNNING);
-	} else {
+	} else if (deactivate_cond) {
 		p->sched_contributes_to_load =
 			(state & TASK_UNINTERRUPTIBLE) &&
 			!(state & TASK_NOLOAD) &&
@@ -6597,6 +6598,74 @@ bool try_to_deactivate_task(struct rq *rq, struct task_struct *p, unsigned long
 	return false;
 }
 
+#ifdef CONFIG_PROXY_EXEC
+/*
+ * Initial simple proxy that just returns the task if its waking
+ * or deactivates the blocked task so we can pick something that
+ * isn't blocked.
+ */
+static struct task_struct *
+proxy(struct rq *rq, struct task_struct *next, struct rq_flags *rf)
+{
+	struct task_struct *p = next;
+	struct mutex *mutex;
+	unsigned long state;
+
+	mutex = p->blocked_on;
+	/* Something changed in the chain, pick_again */
+	if (!mutex)
+		return NULL;
+	/*
+	 * By taking mutex->wait_lock we hold off concurrent mutex_unlock()
+	 * and ensure @owner sticks around.
+	 */
+	raw_spin_lock(&mutex->wait_lock);
+	raw_spin_lock(&p->blocked_lock);
+
+	/* Check again that p is blocked with blocked_lock held */
+	if (!task_is_blocked(p) || mutex != p->blocked_on) {
+		/*
+		 * Something changed in the blocked_on chain and
+		 * we don't know if only at this level. So, let's
+		 * just bail out completely and let __schedule
+		 * figure things out (pick_again loop).
+		 */
+		raw_spin_unlock(&p->blocked_lock);
+		raw_spin_unlock(&mutex->wait_lock);
+		return NULL;
+	}
+
+	state = READ_ONCE(p->__state);
+	/* Don't deactivate if the state has been changed to TASK_RUNNING */
+	if (!state) {
+		raw_spin_unlock(&p->blocked_lock);
+		raw_spin_unlock(&mutex->wait_lock);
+		return p;
+	}
+
+	try_to_deactivate_task(rq, next, state, true);
+
+	/*
+	 * If next is the selected task, then remove lingering
+	 * references to it from rq and sched_class structs after
+	 * dequeueing.
+	 */
+	put_prev_task(rq, next);
+	rq_set_selected(rq, rq->idle);
+	resched_curr(rq);
+	raw_spin_unlock(&p->blocked_lock);
+	raw_spin_unlock(&mutex->wait_lock);
+	return NULL;
+}
+#else /* PROXY_EXEC */
+static struct task_struct *
+proxy(struct rq *rq, struct task_struct *next, struct rq_flags *rf)
+{
+	BUG(); // This should never be called in the !PROXY case
+	return next;
+}
+#endif /* PROXY_EXEC */
+
 /*
  * __schedule() is the main scheduler function.
  *
@@ -6687,12 +6756,24 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 	 */
 	prev_state = READ_ONCE(prev->__state);
 	if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
-		try_to_deactivate_task(rq, prev, prev_state);
+		try_to_deactivate_task(rq, prev, prev_state,
+				       !task_is_blocked(prev));
 		switch_count = &prev->nvcsw;
 	}
 
-	next = pick_next_task(rq, prev, &rf);
+pick_again:
+	next = pick_next_task(rq, rq_selected(rq), &rf);
 	rq_set_selected(rq, next);
+	if (unlikely(task_is_blocked(next))) {
+		next = proxy(rq, next, &rf);
+		if (!next) {
+			rq_unpin_lock(rq, &rf);
+			__balance_callbacks(rq);
+			rq_repin_lock(rq, &rf);
+			goto pick_again;
+		}
+	}
+
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
 #ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 6d9036547c1d..cfbf3925e595 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1537,8 +1537,19 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 
 	enqueue_rt_entity(rt_se, flags);
 
-	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
-		enqueue_pushable_task(rq, p);
+	/*
+	 * Current can't be pushed away. Selected is tied to current,
+	 * so don't push it either.
+	 */
+	if (task_current(rq, p) || task_current_selected(rq, p))
+		return;
+	/*
+	 * Pinned tasks can't be pushed.
+	 */
+	if (p->nr_cpus_allowed == 1)
+		return;
+
+	enqueue_pushable_task(rq, p);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
@@ -1825,6 +1836,10 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 
 	update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 1);
 
+	/* Avoid marking selected as pushable */
+	if (task_current_selected(rq, p))
+		return;
+
 	/*
 	 * The previous task needs to be made eligible for pushing
 	 * if it is still active
-- 
2.42.0.rc1.204.g551eb34607-goog