On Wed, May 31, 2023 at 12:16:13PM +0200, Magnus Karlsson wrote:
> On Mon, 29 May 2023 at 17:57, Maciej Fijalkowski
> <maciej.fijalkowski@xxxxxxxxx> wrote:
> >
> > Introduce new xdp_feature NETDEV_XDP_ACT_NDO_ZC_SG that will be used to
> > find out if user space that wants to do ZC multi-buffer will be able to
> > do so against underlying ZC driver.
> >
> > Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@xxxxxxxxx>
> > ---
> > include/uapi/linux/netdev.h | 4 ++--
> > net/xdp/xsk_buff_pool.c | 6 ++++++
> > 2 files changed, 8 insertions(+), 2 deletions(-)
> >
> > diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
> > index 639524b59930..bfca07224f7b 100644
> > --- a/include/uapi/linux/netdev.h
> > +++ b/include/uapi/linux/netdev.h
> > @@ -33,8 +33,8 @@ enum netdev_xdp_act {
> > NETDEV_XDP_ACT_HW_OFFLOAD = 16,
> > NETDEV_XDP_ACT_RX_SG = 32,
> > NETDEV_XDP_ACT_NDO_XMIT_SG = 64,
> > -
> > - NETDEV_XDP_ACT_MASK = 127,
> > + NETDEV_XDP_ACT_NDO_ZC_SG = 128,
>
> Since this flag has nothing to do with an NDO, I would prefer the
> simpler NETDEV_XDP_ACT_ZC_SG. What do you think?
+1, brain fart with that "NDO" on my side.
>
> > + NETDEV_XDP_ACT_MASK = 255,
> > };
> >
> > enum {
> > diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
> > index 0a9f8ea68de3..43cca5fa90cf 100644
> > --- a/net/xdp/xsk_buff_pool.c
> > +++ b/net/xdp/xsk_buff_pool.c
> > @@ -189,6 +189,12 @@ int xp_assign_dev(struct xsk_buff_pool *pool,
> > goto err_unreg_pool;
> > }
> >
> > + if (!(netdev->xdp_features & NETDEV_XDP_ACT_NDO_ZC_SG) &&
> > + flags & XDP_USE_SG) {
> > + err = -EOPNOTSUPP;
> > + goto err_unreg_pool;
> > + }
> > +
> > bpf.command = XDP_SETUP_XSK_POOL;
> > bpf.xsk.pool = pool;
> > bpf.xsk.queue_id = queue_id;
> > --
> > 2.35.3
> >
> >
>
