Merge tag 'locking_urgent_for_v6.8_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking fix from Borislav Petkov:

 - Prevent an inconsistent futex operation leading to stale state
   exposure

* tag 'locking_urgent_for_v6.8_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  futex: Prevent the reuse of stale pi_state

Author: torvalds

kernel/futex/core.c

@@ -627,12 +627,21 @@ int futex_unqueue(struct futex_q *q)
 }
 
 /*
- * PI futexes can not be requeued and must remove themselves from the
- * hash bucket. The hash bucket lock (i.e. lock_ptr) is held.
+ * PI futexes can not be requeued and must remove themselves from the hash
+ * bucket. The hash bucket lock (i.e. lock_ptr) is held.
  */
 void futex_unqueue_pi(struct futex_q *q)
 {
-	__futex_unqueue(q);
+	/*
+	 * If the lock was not acquired (due to timeout or signal) then the
+	 * rt_waiter is removed before futex_q is. If this is observed by
+	 * an unlocker after dropping the rtmutex wait lock and before
+	 * acquiring the hash bucket lock, then the unlocker dequeues the
+	 * futex_q from the hash bucket list to guarantee consistent state
+	 * vs. userspace. Therefore the dequeue here must be conditional.
+	 */
+	if (!plist_node_empty(&q->list))
+		__futex_unqueue(q);
 
 	BUG_ON(!q->pi_state);
 	put_pi_state(q->pi_state);

kernel/futex/pi.c

@@ -1135,6 +1135,7 @@ int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 
 	hb = futex_hash(&key);
 	spin_lock(&hb->lock);
+retry_hb:
 
 	/*
 	 * Check waiters first. We do not trust user space values at
@@ -1177,12 +1178,17 @@ int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 		/*
 		 * Futex vs rt_mutex waiter state -- if there are no rt_mutex
 		 * waiters even though futex thinks there are, then the waiter
-		 * is leaving and the uncontended path is safe to take.
+		 * is leaving. The entry needs to be removed from the list so a
+		 * new futex_lock_pi() is not using this stale PI-state while
+		 * the futex is available in user space again.
+		 * There can be more than one task on its way out so it needs
+		 * to retry.
 		 */
 		rt_waiter = rt_mutex_top_waiter(&pi_state->pi_mutex);
 		if (!rt_waiter) {
+			__futex_unqueue(top_waiter);
 			raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-			goto do_uncontended;
+			goto retry_hb;
 		}
 
 		get_pi_state(pi_state);
@@ -1217,7 +1223,6 @@ int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 		return ret;
 	}
 
-do_uncontended:
 	/*
 	 * We have no kernel internal state, i.e. no waiters in the
 	 * kernel. Waiters which are about to queue themselves are stuck