syzbot managed to trigger the following race:

   T1                               T2

 futex_wait_requeue_pi()
   futex_do_wait()
     schedule()
                               futex_requeue()
                                 futex_proxy_trylock_atomic()
                                   futex_requeue_pi_prepare()
                                   requeue_pi_wake_futex()
                                     futex_requeue_pi_complete()
                                      /* preempt */

         * timeout/ signal wakes T1 *

   futex_requeue_pi_wakeup_sync() // Q_REQUEUE_PI_LOCKED
   futex_hash_put()
  // back to userland, on stack futex_q is garbage

                                      /* back */
                                     wake_up_state(q->task, TASK_NORMAL);

In this scenario futex_wait_requeue_pi() is able to leave without using
futex_q::lock_ptr for synchronization.
This can be prevented by reading futex_q::task before updating the
futex_q::requeue_state. A reference on the task_struct is not needed
because requeue_pi_wake_futex() is invoked with a spinlock_t held which
implies a RCU read section. Even if T1 terminates immediately after, the
task_struct will remain valid during T2's wake_up_state().
A READ_ONCE on futex_q::task before futex_requeue_pi_complete() is
enough because it ensures that the variable is read before the state is
updated.

Read futex_q::task before the updating the requeue state, use it for the
following wakeup.

Fixes: 07d91ef510fb1 ("futex: Prevent requeue_pi() lock nesting issue on RT")
Reported-by: syzbot+034246a838a10d181e78@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/68b75989.050a0220.3db4df.01dd.GAE@google.com/
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 kernel/futex/requeue.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c
index c716a66f86929..d818b4d47f1ba 100644
--- a/kernel/futex/requeue.c
+++ b/kernel/futex/requeue.c
@@ -230,8 +230,9 @@ static inline
 void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
 			   struct futex_hash_bucket *hb)
 {
-	q->key = *key;
+	struct task_struct *task;
 
+	q->key = *key;
 	__futex_unqueue(q);
 
 	WARN_ON(!q->rt_waiter);
@@ -243,10 +244,11 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
 	futex_hash_get(hb);
 	q->drop_hb_ref = true;
 	q->lock_ptr = &hb->lock;
+	task = READ_ONCE(q->task);
 
 	/* Signal locked state to the waiter */
 	futex_requeue_pi_complete(q, 1);
-	wake_up_state(q->task, TASK_NORMAL);
+	wake_up_state(task, TASK_NORMAL);
 }
 
 /**
-- 
2.51.0

On 2025-09-10 12:42:45 [+0200], To Thomas Gleixner wrote:
> --- a/kernel/futex/requeue.c
> +++ b/kernel/futex/requeue.c
> @@ -243,10 +244,11 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
>  	futex_hash_get(hb);
>  	q->drop_hb_ref = true;
>  	q->lock_ptr = &hb->lock;
> +	task = READ_ONCE(q->task);
>  
>  	/* Signal locked state to the waiter */
>  	futex_requeue_pi_complete(q, 1);

once understood, adding an mdelay(500) here greatly improves the chances
to trigger.
futex_requeue_pi_complete() uses atomic_try_cmpxchg() which has full
ordering. This means that the q->drop_hb_ref assignment earlier is
visible to the other thread after that cmpxchg, correct? 

> -	wake_up_state(q->task, TASK_NORMAL);
> +	wake_up_state(task, TASK_NORMAL);
>  }

Sebastian