[PATCH v2] sched/core: Dequeue waking proxy donors before reset

[Andrea Righi <arighi@nvidia.com>]

proxy_needs_return() resets an active donor while holding blocked_lock.
proxy_reset_donor() invokes scheduling-class callbacks, adding an
unnecessary raw-spinlock nesting. It also presents the waking donor to
put_prev_task() as still runnable immediately before block_task()
removes it from the runqueue.

Split block_task() so the waking donor can first be dequeued from its
scheduling class. Release blocked_lock, dequeue the donor while its
generic on_rq state still prevents migration, replace all donor
references, and only then complete the generic runqueue removal. This
follows the normal sleep ordering and avoids transiently re-enqueuing
the waking donor.

This is a preparatory change to support proxy execution with sched_ext.

Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
Changes in v2:
 - Simplify the proxy_needs_return() control flow (Tejun Heo)

 kernel/sched/core.c | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e1b597e6bf413..a77c042c3f7f4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2253,7 +2253,8 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 	dequeue_task(rq, p, flags);
 }
 
-static void block_task(struct rq *rq, struct task_struct *p, unsigned long task_state)
+static bool dequeue_block_task(struct rq *rq, struct task_struct *p,
+			       unsigned long task_state)
 {
 	int flags = DEQUEUE_NOCLOCK;
 
@@ -2274,9 +2275,15 @@ static void block_task(struct rq *rq, struct task_struct *p, unsigned long task_
 	 *
 	 * Where __schedule() and ttwu() have matching control dependencies.
 	 *
-	 * After this, schedule() must not care about p->state any more.
+	 * Once the caller invokes __block_task(), schedule() must not care about
+	 * p->state any more.
 	 */
-	if (dequeue_task(rq, p, DEQUEUE_SLEEP | flags))
+	return dequeue_task(rq, p, DEQUEUE_SLEEP | flags);
+}
+
+static void block_task(struct rq *rq, struct task_struct *p, unsigned long task_state)
+{
+	if (dequeue_block_task(rq, p, task_state))
 		__block_task(rq, p);
 }
 
@@ -3775,6 +3782,9 @@ static inline void proxy_reset_donor(struct rq *rq)
  */
 static inline bool proxy_needs_return(struct rq *rq, struct task_struct *p)
 {
+	bool reset_donor = false;
+	bool dequeued;
+
 	/*
 	 * Typically per __set_task_cpu(), task_cpu(p) == p->wake_cpu.
 	 *
@@ -3798,11 +3808,17 @@ static inline bool proxy_needs_return(struct rq *rq, struct task_struct *p)
 		if (task_current(rq, p))
 			return false;
 
-		/* If we're return migrating the rq->donor, switch it out for idle */
-		if (task_current_donor(rq, p))
-			proxy_reset_donor(rq);
+		reset_donor = task_current_donor(rq, p);
 	}
-	block_task(rq, p, TASK_WAKING);
+
+	dequeued = dequeue_block_task(rq, p, TASK_WAKING);
+
+	/* Keep on_rq set until all donor references have been replaced. */
+	if (reset_donor)
+		proxy_reset_donor(rq);
+
+	if (dequeued)
+		__block_task(rq, p);
 	return true;
 }
 #else /* !CONFIG_SCHED_PROXY_EXEC */
-- 
2.55.0