io_uring/poll: correctly handle io_poll_add() return value on update

When the core of io_uring was updated to handle completions
consistently and with fixed return codes, the POLL_REMOVE opcode
with updates got slightly broken. If a POLL_ADD is pending and
then POLL_REMOVE is used to update the events of that request, if that
update causes the POLL_ADD to now trigger, then that completion is lost
and a CQE is never posted.

Additionally, ensure that if an update does cause an existing POLL_ADD
to complete, that the completion value isn't always overwritten with
-ECANCELED. For that case, whatever io_poll_add() set the value to
should just be retained.

Cc: stable@vger.kernel.org
Fixes: 97b388d ("io_uring: handle completions in the core")
Reported-by: syzbot+641eec6b7af1f62f2b99@syzkaller.appspotmail.com
Tested-by: syzbot+641eec6b7af1f62f2b99@syzkaller.appspotmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: axboe

io_uring/poll.c

@@ -937,12 +937,17 @@ int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags)
 
 		ret2 = io_poll_add(preq, issue_flags & ~IO_URING_F_UNLOCKED);
 		/* successfully updated, don't complete poll request */
-		if (!ret2 || ret2 == -EIOCBQUEUED)
+		if (ret2 == IOU_ISSUE_SKIP_COMPLETE)
 			goto out;
+		/* request completed as part of the update, complete it */
+		else if (ret2 == IOU_COMPLETE)
+			goto complete;
 	}
 
-	req_set_fail(preq);
 	io_req_set_res(preq, -ECANCELED, 0);
+complete:
+	if (preq->cqe.res < 0)
+		req_set_fail(preq);
 	preq->io_task_work.func = io_req_task_complete;
 	io_req_task_work_add(preq);
 out: