Messages in this thread | | | Subject | Re: io-uring: KASAN failure, presumably REQ_F_REISSUE issue | From | Nadav Amit <> | Date | Sat, 11 Sep 2021 21:43:18 -0700 |
| |
> On Sep 11, 2021, at 7:34 PM, Nadav Amit <nadav.amit@gmail.com> wrote: > > Hello Jens (& Pavel), > > I hope you are having a nice weekend. I ran into a KASAN failure in io-uring > which I think is not "my fault".
Small correction of myself (beside the subject): > > I believe the issue is related to the handling of REQ_F_REISSUE and > specifically to commit 230d50d448acb ("io_uring: move reissue into regular IO > path"). There seems to be a race between io_write()/io_read() > and __io_complete_rw()/kiocb_done(). > > __io_complete_rw() sets REQ_F_REIUSSE: > > if ((res == -EAGAIN || res == -EOPNOTSUPP) && > io_rw_should_reissue(req)) { > req->flags |= REQ_F_REISSUE; > return; > }
The race only appears to be with __io_complete_rw(), not kiocb_done().
| |