io_uring: fix UAF due to missing POLLFREE handling

Fixes a problem described in 50252e4
("aio: fix use-after-free due to missing POLLFREE handling")
and copies the approach used there.

In short, we have to forcibly eject a poll entry when we meet POLLFREE.
We can't rely on io_poll_get_ownership() as can't wait for potentially
running tw handlers, so we use the fact that wqs are RCU freed. See
Eric's patch and comments for more details.

Reported-by: Eric Biggers <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Reported-and-tested-by: [email protected]
Fixes: 221c5eb ("io_uring: add support for IORING_OP_POLL")
Signed-off-by: Pavel Begunkov <[email protected]>
Link: https://lore.kernel.org/r/4ed56b6f548f7ea337603a82315750449412748a.1642161259.git.asml.silence@gmail.com
[axboe: drop non-functional change from patch]
Signed-off-by: Jens Axboe <[email protected]>

Author: isilence

fs/io_uring.c

@@ -5462,23 +5462,41 @@ static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events,
 
 static inline void io_poll_remove_entry(struct io_poll_iocb *poll)
 {
-	struct wait_queue_head *head = poll->head;
+	struct wait_queue_head *head = smp_load_acquire(&poll->head);
 
-	spin_lock_irq(&head->lock);
-	list_del_init(&poll->wait.entry);
-	poll->head = NULL;
-	spin_unlock_irq(&head->lock);
+	if (head) {
+		spin_lock_irq(&head->lock);
+		list_del_init(&poll->wait.entry);
+		poll->head = NULL;
+		spin_unlock_irq(&head->lock);
+	}
 }
 
 static void io_poll_remove_entries(struct io_kiocb *req)
 {
 	struct io_poll_iocb *poll = io_poll_get_single(req);
 	struct io_poll_iocb *poll_double = io_poll_get_double(req);
 
-	if (poll->head)
-		io_poll_remove_entry(poll);
-	if (poll_double && poll_double->head)
+	/*
+	 * While we hold the waitqueue lock and the waitqueue is nonempty,
+	 * wake_up_pollfree() will wait for us.  However, taking the waitqueue
+	 * lock in the first place can race with the waitqueue being freed.
+	 *
+	 * We solve this as eventpoll does: by taking advantage of the fact that
+	 * all users of wake_up_pollfree() will RCU-delay the actual free.  If
+	 * we enter rcu_read_lock() and see that the pointer to the queue is
+	 * non-NULL, we can then lock it without the memory being freed out from
+	 * under us.
+	 *
+	 * Keep holding rcu_read_lock() as long as we hold the queue lock, in
+	 * case the caller deletes the entry from the queue, leaving it empty.
+	 * In that case, only RCU prevents the queue memory from being freed.
+	 */
+	rcu_read_lock();
+	io_poll_remove_entry(poll);
+	if (poll_double)
 		io_poll_remove_entry(poll_double);
+	rcu_read_unlock();
 }
 
 /*
@@ -5618,6 +5636,30 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 						 wait);
 	__poll_t mask = key_to_poll(key);
 
+	if (unlikely(mask & POLLFREE)) {
+		io_poll_mark_cancelled(req);
+		/* we have to kick tw in case it's not already */
+		io_poll_execute(req, 0);
+
+		/*
+		 * If the waitqueue is being freed early but someone is already
+		 * holds ownership over it, we have to tear down the request as
+		 * best we can. That means immediately removing the request from
+		 * its waitqueue and preventing all further accesses to the
+		 * waitqueue via the request.
+		 */
+		list_del_init(&poll->wait.entry);
+
+		/*
+		 * Careful: this *must* be the last step, since as soon
+		 * as req->head is NULL'ed out, the request can be
+		 * completed and freed, since aio_poll_complete_work()
+		 * will no longer need to take the waitqueue lock.
+		 */
+		smp_store_release(&poll->head, NULL);
+		return 1;
+	}
+
 	/* for instances that support it check for an event match first */
 	if (mask && !(mask & poll->events))
 		return 0;