From: Pascal Mazon <pascal.mazon@6wind.com>
To: Ferruh Yigit <ferruh.yigit@intel.com>
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH] net/tap: add Rx/Tx checksum offload support
Date: Tue, 23 May 2017 08:51:43 +0200 [thread overview]
Message-ID: <20170523085143.73bb3f50@paques.dev.6wind.com> (raw)
In-Reply-To: <6acb1c97-0c27-da98-5c4f-292b0f87e29a@intel.com>
Hi Ferruh,
I'm not sure it would actually be so useful for other vPMDs.
Virtio and vmxnet3 for instance have their own mechanisms for handling
offloading.
Software offload is especially relevant for tap as packets may come from
anywhere (from another process, from a remote netdevice), and the
application would be interested in knowing how good the packet is.
At first, I'd rather keep the code as-is in tap, which is generic enough
to be easily moved later when actual need arise.
Best regards,
Pascal
On Mon, 22 May 2017 13:24:41 +0100
Ferruh Yigit <ferruh.yigit@intel.com> wrote:
> Hi Pascal,
>
> On 5/22/2017 12:20 PM, Pascal Mazon wrote:
> > This patch adds basic offloading support, widely expected in a PMD.
> >
> > Verify IPv4 and UDP/TCP checksums upon packet reception, and set
> > ol_flags accordingly.
> >
> > On Tx, set IPv4 and UDP/TCP checksums when required, considering
> > ol_flags.
>
> These are not specific to tap and can be used by any virtual PMD, right?
>
> What do you think moving implementation into more generic location (I
> don't know where right now) and use from there, and other PMDs also can
> benefit from these?
>
> Thanks,
> ferruh
>
> >
> > Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
>
> <...>
>
next prev parent reply other threads:[~2017-05-23 6:51 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-05-22 11:20 Pascal Mazon
2017-05-22 12:24 ` Ferruh Yigit
2017-05-23 6:51 ` Pascal Mazon [this message]
2017-05-26 9:23 ` Ferruh Yigit
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=20170523085143.73bb3f50@paques.dev.6wind.com \
--to=pascal.mazon@6wind.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@intel.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).