ublk: fix handling recovery & reissue in ublk_abort_queue()

Commit 8284066946e6 ("ublk: grab request reference when the request is handled
by userspace") doesn't grab request reference in case of recovery reissue.
Then the request can be requeued & re-dispatch & failed when canceling
uring command.

If it is one zc request, the request can be freed before io_uring
returns the zc buffer back, then cause kernel panic:

[  126.773061] BUG: kernel NULL pointer dereference, address: 00000000000000c8
[  126.773657] #PF: supervisor read access in kernel mode
[  126.774052] #PF: error_code(0x0000) - not-present page
[  126.774455] PGD 0 P4D 0
[  126.774698] Oops: Oops: 0000 [#1] SMP NOPTI
[  126.775034] CPU: 13 UID: 0 PID: 1612 Comm: kworker/u64:55 Not tainted 6.14.0_blk+ #182 PREEMPT(full)
[  126.775676] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-1.fc39 04/01/2014
[  126.776275] Workqueue: iou_exit io_ring_exit_work
[  126.776651] RIP: 0010:ublk_io_release+0x14/0x130 [ublk_drv]

Fixes it by always grabbing request reference for aborting the request.

Reported-by: Caleb Sander Mateos <csander@purestorage.com>
Closes: https://lore.kernel.org/linux-block/CADUfDZodKfOGUeWrnAxcZiLT+puaZX8jDHoj_sfHZCOZwhzz6A@mail.gmail.com/
Fixes: 8284066946e6 ("ublk: grab request reference when the request is handled by userspace")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250409011444.2142010-2-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 2fd05c1bd30b03343cb6f357f8c08dd92ff47af9..41bed67508f2600b7136d7ca71b267ad68c695fb 100644 (file)
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -1140,6 +1140,25 @@ static void ublk_complete_rq(struct kref *ref)
        __ublk_complete_rq(req);
 }
 
+static void ublk_do_fail_rq(struct request *req)
+{
+       struct ublk_queue *ubq = req->mq_hctx->driver_data;
+
+       if (ublk_nosrv_should_reissue_outstanding(ubq->dev))
+               blk_mq_requeue_request(req, false);
+       else
+               __ublk_complete_rq(req);
+}
+
+static void ublk_fail_rq_fn(struct kref *ref)
+{
+       struct ublk_rq_data *data = container_of(ref, struct ublk_rq_data,
+                       ref);
+       struct request *req = blk_mq_rq_from_pdu(data);
+
+       ublk_do_fail_rq(req);
+}
+
 /*
  * Since ublk_rq_task_work_cb always fails requests immediately during
  * exiting, __ublk_fail_req() is only called from abort context during
@@ -1153,10 +1172,13 @@ static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io,
 {
        WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE);
 
-       if (ublk_nosrv_should_reissue_outstanding(ubq->dev))
-               blk_mq_requeue_request(req, false);
-       else
-               ublk_put_req_ref(ubq, req);
+       if (ublk_need_req_ref(ubq)) {
+               struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
+
+               kref_put(&data->ref, ublk_fail_rq_fn);
+       } else {
+               ublk_do_fail_rq(req);
+       }
 }
 
 static void ubq_complete_io_cmd(struct ublk_io *io, int res,