[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <612eb79343225_6b872087a@john-XPS-13-9370.notmuch>
Date: Tue, 31 Aug 2021 16:13:23 -0700
From: John Fastabend <john.fastabend@...il.com>
To: Lorenzo Bianconi <lorenzo@...nel.org>, bpf@...r.kernel.org,
netdev@...r.kernel.org
Cc: lorenzo.bianconi@...hat.com, davem@...emloft.net, kuba@...nel.org,
ast@...nel.org, daniel@...earbox.net, shayagr@...zon.com,
john.fastabend@...il.com, dsahern@...nel.org, brouer@...hat.com,
echaudro@...hat.com, jasowang@...hat.com,
alexander.duyck@...il.com, saeed@...nel.org,
maciej.fijalkowski@...el.com, magnus.karlsson@...el.com,
tirthendu.sarkar@...el.com, toke@...hat.com
Subject: RE: [PATCH v12 bpf-next 01/18] net: skbuff: add size metadata to
skb_shared_info for xdp
Lorenzo Bianconi wrote:
> Introduce xdp_frags_tsize field in skb_shared_info data structure
> to store xdp_buff/xdp_frame truesize (xdp_frags_tsize will be used
> in xdp multi-buff support). In order to not increase skb_shared_info
> size we will use a hole due to skb_shared_info alignment.
> Introduce xdp_frags_size field in skb_shared_info data structure
> reusing gso_type field in order to store xdp_buff/xdp_frame paged size.
> xdp_frags_size will be used in xdp multi-buff support.
>
> Signed-off-by: Lorenzo Bianconi <lorenzo@...nel.org>
I assume we can use xdp_frags_tsize for anything else above XDP later?
Other than simple question looks OK to me.
Acked-by: John Fastabend <john.fastabend@...il.com>
> ---
> include/linux/skbuff.h | 6 +++++-
> 1 file changed, 5 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> index 6bdb0db3e825..1abeba7ef82e 100644
> --- a/include/linux/skbuff.h
> +++ b/include/linux/skbuff.h
> @@ -522,13 +522,17 @@ struct skb_shared_info {
> unsigned short gso_segs;
> struct sk_buff *frag_list;
> struct skb_shared_hwtstamps hwtstamps;
> - unsigned int gso_type;
> + union {
> + unsigned int gso_type;
> + unsigned int xdp_frags_size;
> + };
> u32 tskey;
>
> /*
> * Warning : all fields before dataref are cleared in __alloc_skb()
> */
> atomic_t dataref;
> + unsigned int xdp_frags_tsize;
>
> /* Intermediate layers must ensure that destructor_arg
> * remains valid until skb destructor */
> --
> 2.31.1
>
Powered by blists - more mailing lists