io-uring.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Stefan Metzmacher <metze@samba.org>
To: Victor Stewart <v@nametag.social>,
	io-uring <io-uring@vger.kernel.org>, Jens Axboe <axboe@kernel.dk>
Subject: Re: [RFC 0/1] whitelisting UDP GSO and GRO cmsgs
Date: Mon, 23 Nov 2020 17:13:30 +0100	[thread overview]
Message-ID: <4bb2cb8a-c3ef-bfa9-7b04-cb2cca32d3ee@samba.org> (raw)
In-Reply-To: <CAM1kxwi5m6i8hrtkw7nZYoziPTD-Wp03+fcsUwh3CuSc=81kUQ@mail.gmail.com>


[-- Attachment #1.1: Type: text/plain, Size: 1172 bytes --]

Hi Victor,

wouldn't it be enough to port the PROTO_CMSG_DATA_ONLY check to the sendmsg path?

UDP sockets should have PROTO_CMSG_DATA_ONLY set.

I guess that would fix your current problem.

Whitelisting more (or even all) would need more work, but can be done
later.

metze

Am 23.11.20 um 16:29 schrieb Victor Stewart:
> so currently all cmsg headers are disabled through sendmsg and recvmsg
> operations through io_uring because of
> https://www.exploit-db.com/exploits/47779
> 
> i think it's time we start whitelisting the good guys though? GSO and
> GRO are hugely important for QUIC servers, and together offer a higher
> throughput gain than io_uring alone (rate of data transit
> considering), thus io_uring is the lesser performance choice for QUIC
> servers at the moment.
> 
> RE http://vger.kernel.org/lpc_net2018_talks/willemdebruijn-lpc2018-udpgso-paper-DRAFT-1.pdf,
> GSO is about +~63% and GRO +~82%.
> 
> this patch closes that loophole.
> 
> Victor Stewart (1);
>    net/socket.c: add __sys_whitelisted_cmsghdrs()
> 
>    net/socket.c | 15 ++++++++++++---
>    1 file changed, 12 insertions(+), 3 deletions(-)
> 



[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

  reply	other threads:[~2020-11-23 16:13 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-23 15:29 [RFC 0/1] whitelisting UDP GSO and GRO cmsgs Victor Stewart
2020-11-23 16:13 ` Stefan Metzmacher [this message]
     [not found]   ` <CAM1kxwhUcXLKU=2hCVaBngOKRL_kgMX4ONy9kpzKW+ZBZraEYw@mail.gmail.com>
     [not found]     ` <5d71d36c-0bfb-a313-07e8-0e22f7331a7a@samba.org>
2020-11-28 19:03       ` Victor Stewart
2020-11-30 10:52         ` Stefan Metzmacher
2020-11-30 14:57           ` Soheil Hassas Yeganeh
2020-11-30 15:05             ` Stefan Metzmacher
2020-11-30 15:15               ` Soheil Hassas Yeganeh
2020-11-30 16:17                 ` Victor Stewart
2020-11-30 16:20                   ` Soheil Hassas Yeganeh

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=4bb2cb8a-c3ef-bfa9-7b04-cb2cca32d3ee@samba.org \
    --to=metze@samba.org \
    --cc=axboe@kernel.dk \
    --cc=io-uring@vger.kernel.org \
    --cc=v@nametag.social \
    /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).