futex: Pass in task to futex_queue()

futex_queue() -> __futex_queue() uses 'current' as the task to store in
the struct futex_q->task field. This is fine for synchronous usage of
the futex infrastructure, but it's not always correct when used by
io_uring where the task doing the initial futex_queue() might not be
available later on. This doesn't lead to any issues currently, as the
io_uring side doesn't support PI futexes, but it does leave a
potentially dangling pointer which is never a good idea.

Have futex_queue() take a task_struct argument, and have the regular
callers pass in 'current' for that. Meanwhile io_uring can just pass in
NULL, as the task should never be used off that path. In theory
req->tctx->task could be used here, but there's no point populating it
with a task field that will never be used anyway.

Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/22484a23-542c-4003-b721-400688a0d055@kernel.dk

io_uring/futex.c

@@ -338,7 +338,7 @@ int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags)
 		hlist_add_head(&req->hash_node, &ctx->futex_list);
 		io_ring_submit_unlock(ctx, issue_flags);
 
-		futex_queue(&ifd->q, hb);
+		futex_queue(&ifd->q, hb, NULL);
 		return IOU_ISSUE_SKIP_COMPLETE;
 	}
 

kernel/futex/core.c

@@ -532,7 +532,8 @@ void futex_q_unlock(struct futex_hash_bucket *hb)
 	futex_hb_waiters_dec(hb);
 }
 
-void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb)
+void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
+		   struct task_struct *task)
 {
 	int prio;
 
@@ -548,7 +549,7 @@ void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb)
 
 	plist_node_init(&q->list, prio);
 	plist_add(&q->list, &hb->chain);
-	q->task = current;
+	q->task = task;
 }
 
 /**

kernel/futex/futex.h

@@ -285,13 +285,15 @@ static inline int futex_get_value_locked(u32 *dest, u32 __user *from)
 }
 
 extern void __futex_unqueue(struct futex_q *q);
-extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb);
+extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
+				struct task_struct *task);
 extern int futex_unqueue(struct futex_q *q);
 
 /**
  * futex_queue() - Enqueue the futex_q on the futex_hash_bucket
  * @q:	The futex_q to enqueue
  * @hb:	The destination hash bucket
+ * @task: Task queueing this futex
  *
  * The hb->lock must be held by the caller, and is released here. A call to
  * futex_queue() is typically paired with exactly one call to futex_unqueue().  The
@@ -299,11 +301,14 @@ extern int futex_unqueue(struct futex_q *q);
  * or nothing if the unqueue is done as part of the wake process and the unqueue
  * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
  * an example).
+ *
+ * Note that @task may be NULL, for async usage of futexes.
  */
-static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb)
+static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
+			       struct task_struct *task)
 	__releases(&hb->lock)
 {
-	__futex_queue(q, hb);
+	__futex_queue(q, hb, task);
 	spin_unlock(&hb->lock);
 }
 

kernel/futex/pi.c

@@ -982,7 +982,7 @@ retry_private:
 	/*
 	 * Only actually queue now that the atomic ops are done:
 	 */
-	__futex_queue(&q, hb);
+	__futex_queue(&q, hb, current);
 
 	if (trylock) {
 		ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex);

kernel/futex/waitwake.c

@@ -350,7 +350,7 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q,
 	 * access to the hash list and forcing another memory barrier.
 	 */
 	set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
-	futex_queue(q, hb);
+	futex_queue(q, hb, current);
 
 	/* Arm the timer */
 	if (timeout)
@@ -461,7 +461,7 @@ retry:
 			 * next futex. Queue each futex at this moment so hb can
 			 * be unlocked.
 			 */
-			futex_queue(q, hb);
+			futex_queue(q, hb, current);
 			continue;
 		}