[PATCH v19 6/8] sched: Add an initial sketch of the find_proxy_task() function

[John Stultz]

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.

This allows us to validate keeping blocked tasks on the runqueue
and later deactivating them is working ok, stressing the failure
cases for when a proxy isn't found.

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>

Tested-by: K Prateek Nayak <kprateek.nayak@xxxxxxx>
[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
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@xxxxxxxxx>
  Closes: https://lore.kernel.org/oe-kbuild-all/202311081028.yDLmCWgr-lkp@xxxxxxxxx/
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
v15:
* Tweaked some comments to better explain the initial sketch of
  find_proxy_task(), suggested by Qais
* Build fixes for !CONFIG_SMP
* Slight rework for blocked_on_state being added later in the
  series.
* Move the zap_balance_callbacks to later in the patch series
v16:
* Move the enqueue_task_rt() out to later in the series, as
  suggested by K Prateek Nayak
* Fixup whitespace error pointed out by K Prateek Nayak
* Use put_prev_set_next_task as suggested by K Prateek Nayak
* Try to rework find_proxy_task() locking to use guard and
  proxy_deactivate_task() in the way Peter suggested.
v17:
* Slightly simplified variable names per suggestion from
  Juri Lelli
* Minor comment and commit message tweaks suggested by Peter
v19:
* Rename try_to_block_task() arguments and add additional
  comments suggested by Peter

Cc: Joel Fernandes <joelagnelf@xxxxxxxxxx>
Cc: Qais Yousef <qyousef@xxxxxxxxxxx>
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: Mel Gorman <mgorman@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Waiman Long <longman@xxxxxxxxxx>
Cc: Boqun Feng <boqun.feng@xxxxxxxxx>
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxx>
Cc: Metin Kaya <Metin.Kaya@xxxxxxx>
Cc: Xuewen Yan <xuewen.yan94@xxxxxxxxx>
Cc: K Prateek Nayak <kprateek.nayak@xxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Cc: Suleiman Souhlal <suleiman@xxxxxxxxxx>
Cc: kuyo chang <kuyo.chang@xxxxxxxxxxxx>
Cc: hupu <hupu.gm@xxxxxxxxx>
Cc: kernel-team@xxxxxxxxxxx
---
 kernel/sched/core.c  | 117 +++++++++++++++++++++++++++++++++++++++++--
 kernel/sched/sched.h |  10 +++-
 2 files changed, 121 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 45daa0e5b27d3..917043f815335 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6615,11 +6615,13 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 /*
  * Helper function for __schedule()
  *
- * If a task does not have signals pending, deactivate it
- * Otherwise marks the task's __state as RUNNING
+ * Tries to deactivate the task, unless the should_block arg
+ * is false or if a signal is pending. In the case a signal
+ * is pending, marks the task's __state as RUNNING (and clear
+ * blocked_on).
  */
 static bool try_to_block_task(struct rq *rq, struct task_struct *p,
-			      unsigned long *task_state_p)
+			      unsigned long *task_state_p, bool should_block)
 {
 	unsigned long task_state = *task_state_p;
 	int flags = DEQUEUE_NOCLOCK;
@@ -6630,6 +6632,16 @@ static bool try_to_block_task(struct rq *rq, struct task_struct *p,
 		return false;
 	}
 
+	/*
+	 * We check should_block after signal_pending because we
+	 * will want to wake the task in that case. But if
+	 * should_block is false, its likely due to the task being
+	 * blocked on a mutex, and we want to keep it on the runqueue
+	 * to be selectable for proxy-execution.
+	 */
+	if (!should_block)
+		return false;
+
 	p->sched_contributes_to_load =
 		(task_state & TASK_UNINTERRUPTIBLE) &&
 		!(task_state & TASK_NOLOAD) &&
@@ -6653,6 +6665,88 @@ static bool try_to_block_task(struct rq *rq, struct task_struct *p,
 	return true;
 }
 
+#ifdef CONFIG_SCHED_PROXY_EXEC
+static inline void proxy_resched_idle(struct rq *rq)
+{
+	put_prev_set_next_task(rq, rq->donor, rq->idle);
+	rq_set_donor(rq, rq->idle);
+	set_tsk_need_resched(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);
+}
+
+static struct task_struct *proxy_deactivate(struct rq *rq, struct task_struct *donor)
+{
+	if (!__proxy_deactivate(rq, donor)) {
+		/*
+		 * XXX: For now, if deactivation failed, set donor
+		 * as unblocked, as we aren't doing proxy-migrations
+		 * yet (more logic will be needed then).
+		 */
+		donor->blocked_on = NULL;
+	}
+	return NULL;
+}
+
+/*
+ * Initial simple sketch that just deactivates the blocked task
+ * chosen by pick_next_task() so we can then 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 mutex *mutex;
+
+	mutex = donor->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.
+	 */
+	guard(raw_spinlock)(&mutex->wait_lock);
+
+	/* Check again that donor is blocked with blocked_lock held */
+	if (!task_is_blocked(donor) || mutex != __get_task_blocked_on(donor)) {
+		/*
+		 * 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).
+		 */
+		return NULL; /* do pick_next_task() again */
+	}
+	return proxy_deactivate(rq, donor);
+}
+#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.
  *
@@ -6765,12 +6859,25 @@ static void __sched notrace __schedule(int sched_mode)
 			goto picked;
 		}
 	} else if (!preempt && prev_state) {
-		try_to_block_task(rq, prev, &prev_state);
+		/*
+		 * We pass task_is_blocked() as the should_block arg
+		 * in order to keep mutex-blocked tasks on the runqueue
+		 * for slection with proxy-exec (without proxy-exec
+		 * task_is_blocked() will always be false).
+		 */
+		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)
+			goto pick_again;
+	}
 picked:
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6b61e0c7f6e78..590a44c0215fb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2290,6 +2290,14 @@ 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;
+}
+
 static inline int task_on_cpu(struct rq *rq, struct task_struct *p)
 {
 #ifdef CONFIG_SMP
@@ -2499,7 +2507,7 @@ 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);
 
-- 
2.50.0.727.gbf7dc18ff4-goog