Re: [PATCH] rbd: optimize barrier usage for Rmw atomic bitops

[Ilya Dryomov]

On Wed, Jan 29, 2020 at 7:23 PM Davidlohr Bueso <dave@xxxxxxxxxxxx> wrote:
>
> For both set and clear_bit, we can avoid the unnecessary barrier
> on non LL/SC architectures, such as x86. Instead, use the
> smp_mb__{before,after}_atomic() calls.
>
> Signed-off-by: Davidlohr Bueso <dbueso@xxxxxxx>
> ---
>  drivers/block/rbd.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
> index 2b184563cd32..7bc79b2b8f65 100644
> --- a/drivers/block/rbd.c
> +++ b/drivers/block/rbd.c
> @@ -1371,13 +1371,13 @@ static void rbd_osd_submit(struct ceph_osd_request *osd_req)
>  static void img_request_layered_set(struct rbd_img_request *img_request)
>  {
>         set_bit(IMG_REQ_LAYERED, &img_request->flags);
> -       smp_mb();
> +       smp_mb__after_atomic();
>  }
>
>  static void img_request_layered_clear(struct rbd_img_request *img_request)
>  {
>         clear_bit(IMG_REQ_LAYERED, &img_request->flags);
> -       smp_mb();
> +       smp_mb__after_atomic();
>  }
>
>  static bool img_request_layered_test(struct rbd_img_request *img_request)

Hi Davidlohr,

I don't think these barriers are needed at all.  I'll remove them.

Thanks,

                Ilya