diff options
| author | Pavel Begunkov <asml.silence@gmail.com> | 2020-07-06 17:59:29 +0300 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2020-07-06 09:06:20 -0600 |
| commit | 3aadc23e6054353ca056bf14e87250c79efbd7ed (patch) | |
| tree | 78402f4b738e24c646cf9f2f9b8dc66aabc78f30 /fs/io_uring.c | |
| parent | 8b3656af2a37dc538d21e144a5a94bacae05e9f1 (diff) | |
| download | lwn-3aadc23e6054353ca056bf14e87250c79efbd7ed.tar.gz lwn-3aadc23e6054353ca056bf14e87250c79efbd7ed.zip | |
io_uring: don't delay iopoll'ed req completion
->iopoll() may have completed current request, but instead of reaping
it, io_do_iopoll() just continues with the next request in the list.
As a result it can leave just polled and completed request in the list
up until next syscall. Even outer loop in io_iopoll_getevents() doesn't
help the situation.
E.g. poll_list: req0 -> req1
If req0->iopoll() completed both requests, and @min<=1,
then @req0 will be left behind.
Check whether a req was completed after ->iopoll().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'fs/io_uring.c')
| -rw-r--r-- | fs/io_uring.c | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/fs/io_uring.c b/fs/io_uring.c index 9464f9470bbc..60f1a81c6c35 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2015,6 +2015,10 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, if (ret < 0) break; + /* iopoll may have completed current req */ + if (READ_ONCE(req->iopoll_completed)) + list_move_tail(&req->list, &done); + if (ret && spin) spin = false; ret = 0; |