From: Hannes Frederic Sowa <hannes@stressinduktion.org>
To: Tom Herbert <tom@herbertland.com>
Cc: Linux Kernel Network Developers <netdev@vger.kernel.org>,
Eric Dumazet <edumazet@google.com>,
Vladislav Yasevich <vyasevich@gmail.com>,
Benjamin Coddington <bcodding@redhat.com>
Subject: Re: [PATCH net v2 1/4] ipv4: no CHECKSUM_PARTIAL on MSG_MORE corked sockets
Date: Tue, 27 Oct 2015 17:34:04 +0100 [thread overview]
Message-ID: <1445963644.1412577.421660985.2D10CC9A@webmail.messagingengine.com> (raw)
In-Reply-To: <CALx6S36PRh1EmmydMAUhZVxyyAanNYBTRUzTN67=dHnbBTNOGQ@mail.gmail.com>
On Tue, Oct 27, 2015, at 17:04, Tom Herbert wrote:
> On Tue, Oct 27, 2015 at 8:02 AM, Hannes Frederic Sowa
> <hannes@stressinduktion.org> wrote:
> > We cannot reliable calculate packet size on MSG_MORE corked sockets
> > and thus cannot decide if they are going to be fragmented later on,
> > so better not use CHECKSUM_PARTIAL in the first place.
> >
> MSG_MORE should be independent of checksum offload. If packet is
> fragmented the fix in ip_output will ensure that skb_checksum_help is
> properly called.
The probability is that we are going to fragment if MSG_MORE is set,
because exceeding link mtu is quite probable, see e.g. NFS use case. Why
not simply use the csum functions during copy-in in that case? It makes
much more sense to me.
I don't see a reason to test for fragment length at all, then.
Bye,
Hannes
next prev parent reply other threads:[~2015-10-27 16:34 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-10-27 15:02 [PATCH net v2 0/4] net: clean up interactions of CHECKSUM_PARTIAL and fragmentation Hannes Frederic Sowa
2015-10-27 15:02 ` [PATCH net v2 1/4] ipv4: no CHECKSUM_PARTIAL on MSG_MORE corked sockets Hannes Frederic Sowa
2015-10-27 16:04 ` Tom Herbert
2015-10-27 16:34 ` Hannes Frederic Sowa [this message]
2015-10-27 16:41 ` Tom Herbert
2015-10-27 15:02 ` [PATCH net v2 2/4] ipv4: add defensive check for CHECKSUM_PARTIAL skbs in ip_fragment Hannes Frederic Sowa
2015-10-27 16:06 ` Tom Herbert
2015-10-27 18:30 ` Hannes Frederic Sowa
2015-10-27 18:46 ` Tom Herbert
2015-10-27 19:01 ` Sergei Shtylyov
2015-10-27 19:15 ` Hannes Frederic Sowa
2015-10-27 15:02 ` [PATCH net v2 3/4] ipv6: no CHECKSUM_PARTIAL on MSG_MORE corked sockets Hannes Frederic Sowa
2015-10-27 16:36 ` Tom Herbert
2015-10-27 16:44 ` Hannes Frederic Sowa
2015-10-27 17:32 ` Tom Herbert
2015-10-27 18:29 ` Hannes Frederic Sowa
2015-10-27 18:37 ` Tom Herbert
2015-10-27 19:19 ` Hannes Frederic Sowa
2015-10-27 21:42 ` Hannes Frederic Sowa
2015-10-27 22:03 ` Tom Herbert
2015-10-28 0:12 ` Hannes Frederic Sowa
2015-10-28 0:31 ` Tom Herbert
2015-10-27 15:02 ` [PATCH net v2 4/4] ipv6: add defensive check for CHECKSUM_PARTIAL skbs in ip_fragment Hannes Frederic Sowa
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=1445963644.1412577.421660985.2D10CC9A@webmail.messagingengine.com \
--to=hannes@stressinduktion.org \
--cc=bcodding@redhat.com \
--cc=edumazet@google.com \
--cc=netdev@vger.kernel.org \
--cc=tom@herbertland.com \
--cc=vyasevich@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).