Jens Axboe <axboe@xxxxxxxxx> writes:
> The way the logic is setup in io_uring_enter() means that you can't wake
> up the SQ poller thread while at the same time waiting (or polling) for
> completions afterwards. There's no reason for that to be the case.
>
> Reported-by: Lewis Baker <lbaker@xxxxxx>
> Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
Reviewed-by: Jeff Moyer <jmoyer@xxxxxxxxxx>
>
> --
>
> diff --git a/fs/io_uring.c b/fs/io_uring.c
> index 4bc3ee4ea81f..3c8859d417eb 100644
> --- a/fs/io_uring.c
> +++ b/fs/io_uring.c
> @@ -3356,15 +3356,12 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
> * Just return the requested submit count, and wake the thread if
> * we were asked to.
> */
> + ret = 0;
> if (ctx->flags & IORING_SETUP_SQPOLL) {
> if (flags & IORING_ENTER_SQ_WAKEUP)
> wake_up(&ctx->sqo_wait);
> submitted = to_submit;
> - goto out_ctx;
> - }
> -
> - ret = 0;
> - if (to_submit) {
> + } else if (to_submit) {
> bool block_for_last = false;
>
> to_submit = min(to_submit, ctx->sq_entries);
> @@ -3394,7 +3391,6 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
> }
> }
>
> -out_ctx:
> io_ring_drop_ctx_refs(ctx, 1);
> out_fput:
> fdput(f);
