[RFC][PATCH v14 5/7] sched: Add an initial sketch of the find_proxy_task() function

[John Stultz <jstultz@google.com>]

Add a find_proxy_task() function which doesn't do much.

When we select a blocked task to run, we will just deactivate it
and pick again. The exception being if it has become unblocked
after find_proxy_task() was called.

Greatly simplified from patch by:
  Peter Zijlstra (Intel) <peterz@infradead.org>
  Juri Lelli <juri.lelli@redhat.com>
  Valentin Schneider <valentin.schneider@arm.com>
  Connor O'Brien <connoro@google.com>

Cc: Joel Fernandes <joelaf@google.com>
Cc: Qais Yousef <qyousef@layalina.io>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Zimuzo Ezeozue <zezeozue@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Will Deacon <will@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Metin Kaya <Metin.Kaya@arm.com>
Cc: Xuewen Yan <xuewen.yan94@gmail.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: kernel-team@android.com
[jstultz: Split out from larger proxy patch and simplified
 for review and testing.]
Signed-off-by: John Stultz <jstultz@google.com>
---
v5:
* Split out from larger proxy patch
v7:
* Fixed unused function arguments, spelling nits, and tweaks for
  clarity, pointed out by Metin Kaya
* Fix build warning Reported-by: kernel test robot <lkp@intel.com>
  Closes: https://lore.kernel.org/oe-kbuild-all/202311081028.yDLmCWgr-lkp@intel.com/
v8:
* Fixed case where we might return a blocked task from find_proxy_task()
* Continued tweaks to handle avoiding returning blocked tasks
v9:
* Add zap_balance_callbacks helper to unwind balance_callbacks
  when we will re-call pick_next_task() again.
* Add extra comment suggested by Metin
* Typo fixes from Metin
* Moved adding proxy_resched_idle earlier in the series, as suggested
  by Metin
* Fix to call proxy_resched_idle() *prior* to deactivating next, to avoid
  crashes caused by stale references to next
* s/PROXY/SCHED_PROXY_EXEC/ as suggested by Metin
* Number of tweaks and cleanups suggested by Metin
* Simplify proxy_deactivate as suggested by Metin
v11:
* Tweaks for earlier simplification in try_to_deactivate_task
v13:
* Rename rename "next" to "donor" in find_proxy_task() for clarity
* Similarly use "donor" instead of next in proxy_deactivate
* Refactor/simplify proxy_resched_idle
* Moved up a needed fix from later in the series
---
 kernel/sched/core.c  | 129 ++++++++++++++++++++++++++++++++++++++++++-
 kernel/sched/rt.c    |  15 ++++-
 kernel/sched/sched.h |  10 +++-
 3 files changed, 148 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f8714050b6d0d..b492506d33415 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5052,6 +5052,34 @@ static void do_balance_callbacks(struct rq *rq, struct balance_callback *head)
 	}
 }
 
+/*
+ * Only called from __schedule context
+ *
+ * There are some cases where we are going to re-do the action
+ * that added the balance callbacks. We may not be in a state
+ * where we can run them, so just zap them so they can be
+ * properly re-added on the next time around. This is similar
+ * handling to running the callbacks, except we just don't call
+ * them.
+ */
+static void zap_balance_callbacks(struct rq *rq)
+{
+	struct balance_callback *next, *head;
+	bool found = false;
+
+	lockdep_assert_rq_held(rq);
+
+	head = rq->balance_callback;
+	while (head) {
+		if (head == &balance_push_callback)
+			found = true;
+		next = head->next;
+		head->next = NULL;
+		head = next;
+	}
+	rq->balance_callback = found ? &balance_push_callback : NULL;
+}
+
 static void balance_push(struct rq *rq);
 
 /*
@@ -6592,7 +6620,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  * Otherwise marks the task's __state as RUNNING
  */
 static bool try_to_block_task(struct rq *rq, struct task_struct *p,
-			      unsigned long task_state)
+			      unsigned long task_state, bool deactivate_cond)
 {
 	int flags = DEQUEUE_NOCLOCK;
 
@@ -6601,6 +6629,9 @@ static bool try_to_block_task(struct rq *rq, struct task_struct *p,
 		return false;
 	}
 
+	if (!deactivate_cond)
+		return false;
+
 	p->sched_contributes_to_load =
 		(task_state & TASK_UNINTERRUPTIBLE) &&
 		!(task_state & TASK_NOLOAD) &&
@@ -6624,6 +6655,88 @@ static bool try_to_block_task(struct rq *rq, struct task_struct *p,
 	return true;
 }
 
+#ifdef CONFIG_SCHED_PROXY_EXEC
+
+static inline struct task_struct *
+proxy_resched_idle(struct rq *rq)
+{
+	put_prev_task(rq, rq->donor);
+	rq_set_donor(rq, rq->idle);
+	set_next_task(rq, rq->idle);
+	set_tsk_need_resched(rq->idle);
+	return rq->idle;
+}
+
+static bool proxy_deactivate(struct rq *rq, struct task_struct *donor)
+{
+	unsigned long state = READ_ONCE(donor->__state);
+
+	/* Don't deactivate if the state has been changed to TASK_RUNNING */
+	if (state == TASK_RUNNING)
+		return false;
+	/*
+	 * Because we got donor from pick_next_task, it is *crucial*
+	 * that we call proxy_resched_idle before we deactivate it.
+	 * As once we deactivate donor, donor->on_rq is set to zero,
+	 * which allows ttwu to immediately try to wake the task on
+	 * another rq. So we cannot use *any* references to donor
+	 * after that point. So things like cfs_rq->curr or rq->donor
+	 * need to be changed from next *before* we deactivate.
+	 */
+	proxy_resched_idle(rq);
+	return try_to_block_task(rq, donor, state, true);
+}
+
+/*
+ * Initial simple proxy that just returns the task if it's waking
+ * or deactivates the blocked task so we can pick something that
+ * isn't blocked.
+ */
+static struct task_struct *
+find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
+{
+	struct task_struct *p = donor;
+	struct mutex *mutex;
+
+	mutex = p->blocked_on;
+	/* Something changed in the chain, so 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 != get_task_blocked_on(p)) {
+		/*
+		 * 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).
+		 */
+		goto out;
+	}
+	if (!proxy_deactivate(rq, donor))
+		/* XXX: This hack won't work when we get to migrations */
+		donor->blocked_on_state = BO_RUNNABLE;
+
+out:
+	raw_spin_unlock(&p->blocked_lock);
+	raw_spin_unlock(&mutex->wait_lock);
+	return NULL;
+}
+#else /* SCHED_PROXY_EXEC */
+static struct task_struct *
+find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
+{
+	WARN_ONCE(1, "This should never be called in the !SCHED_PROXY_EXEC case\n");
+	return donor;
+}
+#endif /* SCHED_PROXY_EXEC */
+
 /*
  * __schedule() is the main scheduler function.
  *
@@ -6732,12 +6845,22 @@ static void __sched notrace __schedule(int sched_mode)
 			goto picked;
 		}
 	} else if (!preempt && prev_state) {
-		block = try_to_block_task(rq, prev, prev_state);
+		block = try_to_block_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->donor, &rf);
 	rq_set_donor(rq, next);
+	if (unlikely(task_is_blocked(next))) {
+		next = find_proxy_task(rq, next, &rf);
+		if (!next) {
+			/* zap the balance_callbacks before picking again */
+			zap_balance_callbacks(rq);
+			goto pick_again;
+		}
+	}
 picked:
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index bd66a46b06aca..fa4d9bf76ad49 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1479,8 +1479,19 @@ 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_donor(rq, p))
+		return;
+	/*
+	 * Pinned tasks can't be pushed.
+	 */
+	if (p->nr_cpus_allowed == 1)
+		return;
+
+	enqueue_pushable_task(rq, p);
 }
 
 static bool dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 24eae02ddc7f6..f560d1d1a7a0c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2272,6 +2272,14 @@ static inline int task_current_donor(struct rq *rq, struct task_struct *p)
 	return rq->donor == p;
 }
 
+static inline bool task_is_blocked(struct task_struct *p)
+{
+	if (!sched_proxy_exec())
+		return false;
+
+	return !!p->blocked_on && p->blocked_on_state != BO_RUNNABLE;
+}
+
 static inline int task_on_cpu(struct rq *rq, struct task_struct *p)
 {
 #ifdef CONFIG_SMP
@@ -2481,7 +2489,7 @@ static inline void put_prev_set_next_task(struct rq *rq,
 					  struct task_struct *prev,
 					  struct task_struct *next)
 {
-	WARN_ON_ONCE(rq->curr != prev);
+	WARN_ON_ONCE(rq->donor != prev);
 
 	__put_prev_set_next_dl_server(rq, prev, next);
 
-- 
2.47.0.371.ga323438b13-goog