Re: [PATCH v26 10/10] sched: Handle blocked-waiter migration (and return migration)

[Peter Zijlstra]

On Thu, Apr 02, 2026 at 04:43:02PM +0200, Peter Zijlstra wrote:
> 
> So with that other issue cured, I'm back to staring at this thing....
> 
> On Tue, Mar 24, 2026 at 07:13:25PM +0000, John Stultz wrote:
> > +static bool proxy_deactivate(struct rq *rq, struct task_struct *donor)
> >  {
> >  	unsigned long state = READ_ONCE(donor->__state);
> >  
> > @@ -6598,17 +6610,140 @@ static bool __proxy_deactivate(struct rq *rq, struct task_struct *donor)
> >  	return try_to_block_task(rq, donor, &state, true);
> >  }
> >  
> 
> > @@ -6741,7 +6900,17 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
> >  	/* Handle actions we need to do outside of the guard() scope */
> >  	switch (action) {
> >  	case DEACTIVATE_DONOR:
> > -		return proxy_deactivate(rq, donor);
> > +		if (proxy_deactivate(rq, donor))
> > +			return NULL;
> > +		/* If deactivate fails, force return */
> > +		p = donor;
> > +		fallthrough;
> 
> I was going to reply to Prateek's email and was going over the whole
> ttwu path because of that, and that got me looking at this.
> 
> What happens here if donor is migrated; the current CPU no longer valid
> and we fail proxy_deactivate() because of a pending signal?

Something like so?

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2160,7 +2160,7 @@ void deactivate_task(struct rq *rq, stru
 	dequeue_task(rq, p, flags);
 }
 
-static void block_task(struct rq *rq, struct task_struct *p, int flags)
+static void _block_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (dequeue_task(rq, p, DEQUEUE_SLEEP | flags))
 		__block_task(rq, p);
@@ -6503,6 +6503,31 @@ pick_next_task(struct rq *rq, struct tas
 #define SM_PREEMPT		1
 #define SM_RTLOCK_WAIT		2
 
+static bool block_task(struct rq *rq, struct task_struct *p, unsigned long task_state)
+{
+	int flags = DEQUEUE_NOCLOCK;
+
+	p->sched_contributes_to_load =
+		(task_state & TASK_UNINTERRUPTIBLE) &&
+		!(task_state & TASK_NOLOAD) &&
+		!(task_state & TASK_FROZEN);
+
+	if (unlikely(is_special_task_state(task_state)))
+		flags |= DEQUEUE_SPECIAL;
+
+	/*
+	 * __schedule()			ttwu()
+	 *   prev_state = prev->state;    if (p->on_rq && ...)
+	 *   if (prev_state)		    goto out;
+	 *     p->on_rq = 0;		  smp_acquire__after_ctrl_dep();
+	 *				  p->state = TASK_WAKING
+	 *
+	 * Where __schedule() and ttwu() have matching control dependencies.
+	 *
+	 * After this, schedule() must not care about p->state any more.
+	 */
+	_block_task(rq, p, flags);
+}
 /*
  * Helper function for __schedule()
  *
@@ -6515,7 +6540,6 @@ static bool try_to_block_task(struct rq
 			      unsigned long *task_state_p, bool should_block)
 {
 	unsigned long task_state = *task_state_p;
-	int flags = DEQUEUE_NOCLOCK;
 
 	if (signal_pending_state(task_state, p)) {
 		WRITE_ONCE(p->__state, TASK_RUNNING);
@@ -6535,26 +6559,7 @@ static bool try_to_block_task(struct rq
 	if (!should_block)
 		return false;
 
-	p->sched_contributes_to_load =
-		(task_state & TASK_UNINTERRUPTIBLE) &&
-		!(task_state & TASK_NOLOAD) &&
-		!(task_state & TASK_FROZEN);
-
-	if (unlikely(is_special_task_state(task_state)))
-		flags |= DEQUEUE_SPECIAL;
-
-	/*
-	 * __schedule()			ttwu()
-	 *   prev_state = prev->state;    if (p->on_rq && ...)
-	 *   if (prev_state)		    goto out;
-	 *     p->on_rq = 0;		  smp_acquire__after_ctrl_dep();
-	 *				  p->state = TASK_WAKING
-	 *
-	 * Where __schedule() and ttwu() have matching control dependencies.
-	 *
-	 * After this, schedule() must not care about p->state any more.
-	 */
-	block_task(rq, p, flags);
+	block_task(rq, p, task_state);
 	return true;
 }
 
@@ -6599,7 +6604,8 @@ static bool proxy_deactivate(struct rq *
 	 * need to be changed from next *before* we deactivate.
 	 */
 	proxy_resched_idle(rq);
-	return try_to_block_task(rq, donor, &state, true);
+	block_task(rq, donor, state);
+	return true;
 }
 
 static inline void proxy_release_rq_lock(struct rq *rq, struct rq_flags *rf)