All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alexei Starovoitov <ast@plumgrid.com>
To: Eric Dumazet <eric.dumazet@gmail.com>, Florian Westphal <fw@strlen.de>
Cc: Daniel Borkmann <daniel@iogearbox.net>,
	davem@davemloft.net, jhs@mojatatu.com, netdev@vger.kernel.org
Subject: Re: [PATCH net-next v2] net: core: set and refine qdisc pkt len before tc_classify
Date: Wed, 13 May 2015 15:27:09 -0700	[thread overview]
Message-ID: <5553CFBD.1070204@plumgrid.com> (raw)
In-Reply-To: <1431553132.27831.22.camel@edumazet-glaptop2.roam.corp.google.com>

On 5/13/15 2:38 PM, Eric Dumazet wrote:
>
> One possibility would be to set it in GRO engine.
>
> But then we would have to set qdisc_skb_cb(skb)->pkt_len = skb->len for
> non GRO packets.
>
> Also note the DODGY thing might be not needed for ingress,
> and I am not sure we can currently deliver UDP aggregated packets.

yeah, current qdisc_pkt_len_init() is certainly TX oriented.
I'm not sure we can use tcp_hdrlen(skb) on RX which is called as
part of qdisc_pkt_len_init().
I think it's probably better to take Florian's V1 with:
qdisc_skb_cb(skb)->pkt_len = skb->len;
to fix immediate breakage of act police and then proceed further?
Like doing qdisc_skb_cb(skb)->pkt_len = skb->len inside GRO engine
is probably not possible, since cb is used by napi_gro_cb ?

  reply	other threads:[~2015-05-13 22:27 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-05-13 20:50 [PATCH net-next v2] net: core: set and refine qdisc pkt len before tc_classify Daniel Borkmann
2015-05-13 21:07 ` Alexei Starovoitov
2015-05-13 21:20 ` Eric Dumazet
2015-05-13 21:33   ` Florian Westphal
2015-05-13 21:38     ` Eric Dumazet
2015-05-13 22:27       ` Alexei Starovoitov [this message]
2015-05-13 22:43         ` Eric Dumazet
2015-05-13 21:36   ` Daniel Borkmann
2015-05-13 21:42   ` Eric Dumazet

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=5553CFBD.1070204@plumgrid.com \
    --to=ast@plumgrid.com \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=eric.dumazet@gmail.com \
    --cc=fw@strlen.de \
    --cc=jhs@mojatatu.com \
    --cc=netdev@vger.kernel.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.