On Fri, 2017-09-22 at 18:51 -0400, Willem de Bruijn wrote:
> Zerocopy skbs frags are copied when the skb is looped to a local sock.
> Commit 1080e512d44d ("net: orphan frags on receive") introduced calls
> to skb_orphan_frags to deliver_skb and __netif_receive_skb.
>
> With msg_zerocopy, these skbs can also exist in the tx path and thus
> loop from dev_queue_xmit_nit. This already calls deliver_skb in its
> loop. But it does not orphan before a separate pt_prev->func().
>
> Add the missing skb_orphan_frags_rx.
>
> Fixes: 1f8b977ab32d ("sock: enable MSG_ZEROCOPY")
> Signed-off-by: Willem de Bruijn <will...@google.com>
> ---
> net/core/dev.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/net/core/dev.c b/net/core/dev.c
> index 9a2254f9802f..3f5b26ff4f74 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -1948,7 +1948,7 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct
> net_device *dev)
> goto again;
> }
> out_unlock:
> - if (pt_prev)
> + if (pt_prev && !skb_orphan_frags_rx(skb2, GFP_ATOMIC))
> pt_prev->func(skb2, skb->dev, pt_prev, skb->dev);
Don't you need to kfree_skb(skb2) in case of failure ?
> rcu_read_unlock();
> }
