io_uring: fix an issue when IOSQE_IO_LINK is inserted into defer list

This patch may fix two issues:

First, when IOSQE_IO_DRAIN set, the next IOs need to be inserted into
defer list to delay execution, but link io will be actively scheduled to
run by calling io_queue_sqe.

Second, when multiple LINK_IOs are inserted together with defer_list,
the LINK_IO is no longer keep order.

   |-------------|
   |   LINK_IO   |      ----> insert to defer_list  -----------
   |-------------|                                            |
   |   LINK_IO   |      ----> insert to defer_list  ----------|
   |-------------|                                            |
   |   LINK_IO   |      ----> insert to defer_list  ----------|
   |-------------|                                            |
   |   NORMAL_IO |      ----> insert to defer_list  ----------|
   |-------------|                                            |
                                                              |
                              queue_work at same time   <-----|

Fixes: 9e645e1105c ("io_uring: add support for sqe links")
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/fs/io_uring.c b/fs/io_uring.c
index aa25b5bbd4aee2b62d0e071b5650428113a34bda..24bbe3cb7ad45e72b1cfca18c3084795d0be6a8c 100644 (file)
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2023,6 +2023,15 @@ static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 {
        int ret;
 
+       ret = io_req_defer(ctx, req, s->sqe);
+       if (ret) {
+               if (ret != -EIOCBQUEUED) {
+                       io_free_req(req);
+                       io_cqring_add_event(ctx, s->sqe->user_data, ret);
+               }
+               return 0;
+       }
+
        ret = __io_submit_sqe(ctx, req, s, true);
        if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
                struct io_uring_sqe *sqe_copy;
@@ -2095,13 +2104,6 @@ err:
                return;
        }
 
-       ret = io_req_defer(ctx, req, s->sqe);
-       if (ret) {
-               if (ret != -EIOCBQUEUED)
-                       goto err_req;
-               return;
-       }
-
        /*
         * If we already have a head request, queue this one for async
         * submittal once the head completes. If we don't have a head but