From: Eric Dumazet <eric.dumazet@gmail.com>
To: Stephen Hemminger <stephen@networkplumber.org>,
Solio Sarabia <solio.sarabia@intel.com>
Cc: David Ahern <dsahern@gmail.com>,
davem@davemloft.net, netdev@vger.kernel.org,
sthemmin@microsoft.com, shiny.sebastian@intel.com
Subject: Re: [PATCH RFC 2/2] veth: propagate bridge GSO to peer
Date: Thu, 30 Nov 2017 09:26:39 -0800 [thread overview]
Message-ID: <1512062799.19682.19.camel@gmail.com> (raw)
In-Reply-To: <20171130091021.658869b0@xeon-e3>
On Thu, 2017-11-30 at 09:10 -0800, Stephen Hemminger wrote:
>
>
> The problem goes back into the core GSO networking code.
> Something like this is needed.
>
> static inline bool netif_needs_gso(struct sk_buff *skb,
> const struct net_device *dev,
> netdev_features_t features)
> {
> return skb_is_gso(skb) &&
> (!skb_gso_ok(skb, features) ||
> unlikely(skb_shinfo(skb)->gso_segs > dev-
> >gso_max_segs) || << new
> unlikely(skb_shinfo(skb)->gso_size > dev-
> >gso_max_size) || << new
> unlikely((skb->ip_summed != CHECKSUM_PARTIAL) &&
> (skb->ip_summed != CHECKSUM_UNNECESSARY)));
> }
>
> What that will do is split up the monster GSO packets if they ever
> bleed
> across from one device to another through the twisty mazes of packet
> processing paths.
Since very few drivers have these gso_max_segs / gso_max_size, check
could be done in their ndo_features_check()
next prev parent reply other threads:[~2017-11-30 17:26 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-11-26 18:17 [PATCH RFC 0/2] veth, bridge, and GSO maximums Stephen Hemminger
2017-11-26 18:17 ` [PATCH RFC 1/2] br: add notifier for when bridge changes it " Stephen Hemminger
2017-11-26 18:17 ` [PATCH RFC 2/2] veth: propagate bridge GSO to peer Stephen Hemminger
2017-11-27 3:13 ` David Ahern
2017-11-27 7:07 ` Stephen Hemminger
2017-11-27 20:14 ` Solio Sarabia
2017-11-27 21:15 ` Stephen Hemminger
2017-11-28 1:42 ` Solio Sarabia
2017-11-28 2:02 ` David Ahern
2017-11-30 0:35 ` Solio Sarabia
2017-11-30 17:10 ` Stephen Hemminger
2017-11-30 17:26 ` Eric Dumazet [this message]
2017-11-30 17:36 ` Stephen Hemminger
2017-11-30 17:38 ` David Miller
2017-11-30 17:49 ` Stephen Hemminger
2017-11-30 17:59 ` Eric Dumazet
2017-11-30 18:08 ` Stephen Hemminger
2017-11-30 18:10 ` Eric Dumazet
2017-12-01 20:30 ` Stephen Hemminger
2017-11-30 15:47 ` [PATCH RFC 0/2] veth, bridge, and GSO maximums David Miller
2017-11-30 17:11 ` Stephen Hemminger
2017-11-30 20:50 ` Alexander Duyck
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=1512062799.19682.19.camel@gmail.com \
--to=eric.dumazet@gmail.com \
--cc=davem@davemloft.net \
--cc=dsahern@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=shiny.sebastian@intel.com \
--cc=solio.sarabia@intel.com \
--cc=stephen@networkplumber.org \
--cc=sthemmin@microsoft.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;
as well as URLs for NNTP newsgroup(s).