netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Michał Mirosław" <mirqus@gmail.com>
To: David Miller <davem@davemloft.net>
Cc: daniel.lezcano@free.fr, eric.dumazet@gmail.com, kaber@trash.net,
	nightnord@gmail.com, netdev@vger.kernel.org
Subject: Re: [PATCH][v3] dev : fix mtu check when TSO is enabled
Date: Tue, 22 Mar 2011 01:05:46 +0100	[thread overview]
Message-ID: <AANLkTikhqMdLV4jObYNuFcxmwFMkuLKJ+d1xtjw83Jou@mail.gmail.com> (raw)
In-Reply-To: <20110314.165929.232913682.davem@davemloft.net>

2011/3/15 David Miller <davem@davemloft.net>:
> From: Daniel Lezcano <daniel.lezcano@free.fr>
> Date: Mon, 14 Mar 2011 21:39:50 +0100
>> +
>> +     /* if TSO is enabled, we don't care about the length as the packet
>> +      * could be forwarded without being segmented before
>> +      */
>> +     if (skb->dev && skb->dev->features & NETIF_F_TSO)
>> +             return true;
> I am trying to understand why you aren't simply checking also if this
> is a segmented frame?  Perhaps skb_is_gso() && device has NETIF_F_TSO
> set?

Is the check of netdev features even necessary? Devices without TSO
enabled the skbs are segmented before ndo_start_xmit() anyway.

With TSO there's a question if the receiving end of macvlan can handle
GRO/LRO packets?

BTW, checking only NETIF_F_TSO will break at least for IPv6 TSO
(NETIF_F_TSO6) or whatever else can be segmented in hardware.

Best Regards,
Michał Mirosław

      parent reply	other threads:[~2011-03-22  0:06 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-03-14 20:39 [PATCH][v3] dev : fix mtu check when TSO is enabled Daniel Lezcano
2011-03-14 23:59 ` David Miller
2011-03-15 13:57   ` Daniel Lezcano
2011-03-15 18:17     ` Stephen Hemminger
2011-03-16 13:56       ` Daniel Lezcano
2011-03-16 15:35         ` Stephen Hemminger
2011-03-16 16:19           ` Daniel Lezcano
2011-03-16 16:45             ` Stephen Hemminger
2011-03-21 22:58               ` Eric W. Biederman
2011-03-22  2:31                 ` Jesse Gross
2011-03-22  3:02                   ` Eric W. Biederman
2011-03-22  0:05   ` Michał Mirosław [this message]

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=AANLkTikhqMdLV4jObYNuFcxmwFMkuLKJ+d1xtjw83Jou@mail.gmail.com \
    --to=mirqus@gmail.com \
    --cc=daniel.lezcano@free.fr \
    --cc=davem@davemloft.net \
    --cc=eric.dumazet@gmail.com \
    --cc=kaber@trash.net \
    --cc=netdev@vger.kernel.org \
    --cc=nightnord@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;
as well as URLs for NNTP newsgroup(s).