From: David Laight <david.laight.linux@gmail.com>
To: Wang Zhan <wang.zhan@smartx.com>
Cc: netdev@vger.kernel.org, davem@davemloft.net, edumazet@google.com,
kuba@kernel.org, pabeni@redhat.com, horms@kernel.org,
keyong.sun@smartx.com, Ilya Maximets <i.maximets@ovn.org>,
Aaron Conole <aconole@redhat.com>,
Eelco Chaudron <echaudro@redhat.com>,
dev@openvswitch.org, Andrew Lunn <andrew+netdev@lunn.ch>,
Jason Wang <jasowangio@gmail.com>,
Willem de Bruijn <willemdebruijn.kernel@gmail.com>,
Neal Cardwell <ncardwell@google.com>,
Kuniyuki Iwashima <kuniyu@google.com>,
Alice Mikityanska <alice@isovalent.com>
Subject: Re: [PATCH net-next v2 2/4] net: gso: support bounded TCP segmentation
Date: Thu, 24 Sep 2026 11:53:12 +0100 [thread overview]
Message-ID: <20260924115312.505d89fa@pumpkin> (raw)
In-Reply-To: <20260918084651.3022878-3-wang.zhan@smartx.com>
On Fri, 18 Sep 2026 16:46:49 +0800
Wang Zhan <wang.zhan@smartx.com> wrote:
> The bounded resegmentation added by the next patch splits an oversized TCP
> GSO skb into several GSO skbs which fit the device limits. That needs the
> GSO engine to group several MSS segments into one output skb, so let
> callers bound the number of MSS segments each output skb carries and pass
> the bound through the existing __skb_gso_segment() entry point. Ordinary
> callers use zero for no limit.
>
> skb_segment() only groups several MSS into one output skb when the device
> advertises NETIF_F_GSO_PARTIAL, or when the skb has a frag_list which can
> be split into uniform pieces, and falls back to one segment per skb
> otherwise. A caller which passes a bound asks for that grouping
> regardless, so the frag_list check is skipped when max_segs is set. Every
> other caller keeps it, and the bounded path is only used for skbs which do
> not carry a frag_list.
>
> The output stays a GSO skb: gso_size is the original MSS and gso_segs is
> the number of MSS it holds, so a downstream device can still perform
> ordinary TSO. Store the bound in the existing skb_gso_cb scratch context,
> alongside the call-local data_offset and mac_offset fields, so that the
> segmentation methods keep their signature. A zero max_segs value means
> that no bound is active; it is not a persistent skb flag. Clear the value
> when each output skb copies the input header so the temporary limit is not
> propagated to the next GSO call.
>
...
> @@ -86,7 +87,8 @@ static bool skb_needs_check(const struct sk_buff *skb, bool tx_path)
> * Segmentation preserves SKB_GSO_CB_OFFSET bytes of previous skb cb.
> */
> struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
> - netdev_features_t features, bool tx_path)
> + netdev_features_t features, bool tx_path,
> + unsigned int max_segs)
> {
> struct sk_buff *segs;
>
> @@ -117,6 +119,7 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
>
> SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb);
> SKB_GSO_CB(skb)->encap_level = 0;
> + SKB_GSO_CB(skb)->max_segs = min_t(unsigned int, max_segs, U16_MAX);
Why min_t() ??
David
next prev parent reply other threads:[~2026-09-24 10:53 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-18 8:46 [PATCH net-next v2 0/4] net: resegment oversized TCP GSO skbs Wang Zhan
2026-09-18 8:46 ` [PATCH net-next v2 1/4] net: core: factor out the GSO device limit check Wang Zhan
2026-09-18 8:46 ` [PATCH net-next v2 2/4] net: gso: support bounded TCP segmentation Wang Zhan
2026-09-19 15:35 ` Willem de Bruijn
2026-09-20 13:12 ` Wang Zhan
2026-09-21 20:36 ` Willem de Bruijn
2026-09-23 9:45 ` Wang Zhan
2026-09-23 16:42 ` Willem de Bruijn
2026-09-24 9:03 ` Wang Zhan
2026-09-21 21:07 ` Willem de Bruijn
2026-09-23 10:38 ` Wang Zhan
2026-09-23 16:44 ` Willem de Bruijn
2026-09-24 9:27 ` Wang Zhan
2026-09-21 20:50 ` netdev-bot+sashiko
2026-09-23 16:50 ` Willem de Bruijn
2026-09-24 9:09 ` Wang Zhan
2026-09-24 10:53 ` David Laight [this message]
2026-09-24 12:15 ` Wang Zhan
2026-09-24 14:09 ` Paolo Abeni
2026-09-25 7:45 ` Wang Zhan
2026-09-18 8:46 ` [PATCH net-next v2 3/4] net: core: resegment oversized TCP GSO skbs Wang Zhan
2026-09-19 15:37 ` Willem de Bruijn
2026-09-20 13:31 ` Wang Zhan
2026-09-24 14:02 ` Paolo Abeni
2026-09-21 20:50 ` netdev-bot+sashiko
2026-09-18 8:46 ` [PATCH net-next v2 4/4] net: net_test: add tests for bounded GSO segmentation Wang Zhan
2026-09-21 20:50 ` netdev-bot+sashiko
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260924115312.505d89fa@pumpkin \
--to=david.laight.linux@gmail.com \
--cc=aconole@redhat.com \
--cc=alice@isovalent.com \
--cc=andrew+netdev@lunn.ch \
--cc=davem@davemloft.net \
--cc=dev@openvswitch.org \
--cc=echaudro@redhat.com \
--cc=edumazet@google.com \
--cc=horms@kernel.org \
--cc=i.maximets@ovn.org \
--cc=jasowangio@gmail.com \
--cc=keyong.sun@smartx.com \
--cc=kuba@kernel.org \
--cc=kuniyu@google.com \
--cc=ncardwell@google.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=wang.zhan@smartx.com \
--cc=willemdebruijn.kernel@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox