netfilter-devel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: Cong Wang <xiyou.wangcong@gmail.com>,
	Eric Dumazet <eric.dumazet@gmail.com>
Cc: Flavio Leitner <fbl@redhat.com>,
	Linux Kernel Network Developers <netdev@vger.kernel.org>,
	Paolo Abeni <pabeni@redhat.com>,
	David Miller <davem@davemloft.net>,
	Florian Westphal <fw@strlen.de>,
	NetFilter <netfilter-devel@vger.kernel.org>
Subject: Re: [PATCH net-next] net: preserve sock reference when scrubbing the skb.
Date: Wed, 27 Jun 2018 12:33:19 -0700	[thread overview]
Message-ID: <096ada36-8e05-c330-e5b3-3f6fcc77aea2@gmail.com> (raw)
In-Reply-To: <CAM_iQpUnyVHPb96TTNeNo0Ydu9D9s4HqVMwr-YX822euSPXngw@mail.gmail.com>



On 06/27/2018 11:59 AM, Cong Wang wrote:

> 
> IIRC, this skb_orphan() was introduced much earlier than TSQ, probably
> from the beginning of veth.

Sigh

SO_SNDBUF was invented years ago before veth.

You focus on TSQ while it is only one of the many things that are broken.

> 
> Leaving the stack should be effectively equivalent to leaving the host,
> from the view of network isolation.
> 


Having a UDP socket being able to burn a cpu and fill a qdisc is a major bug.

Bu default (blocking send() syscalls) the following loop should
block the thread if socket sk_wmem_alloc hits sk_sndbuf, this is
the beauty of backpressure.

while (1)
    send(fd, ...);  

With skb_orphan(), sk_wmem_alloc will stay around 0, so the loop will burn a cpu
and fill a qdisc, eventually breaking "network isolation", since other sockets
might be unable to send a single packet.

If you have a concrete case where the skb_orphan() is needed, then you will have
to add a parameter to let the admin opt-in for this.

  reply	other threads:[~2018-06-27 19:33 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-06-25 15:56 [PATCH net-next] net: preserve sock reference when scrubbing the skb Flavio Leitner
2018-06-26  4:15 ` Cong Wang
2018-06-26  6:41   ` Eric Dumazet
2018-06-26 12:38     ` Flavio Leitner
2018-06-26 13:06       ` Eric Dumazet
2018-06-26 13:32         ` Flavio Leitner
2018-06-26 21:48     ` Cong Wang
2018-06-26 22:03       ` Flavio Leitner
2018-06-26 22:47         ` Cong Wang
2018-06-26 23:33           ` Flavio Leitner
2018-06-27  0:29             ` Cong Wang
2018-06-27  0:39               ` Flavio Leitner
2018-06-27  1:28                 ` Cong Wang
2018-06-27 12:31                   ` Flavio Leitner
2018-06-27 19:06                     ` Cong Wang
2018-06-27 20:19                       ` Flavio Leitner
2018-06-28 21:51                         ` Cong Wang
2018-06-27  2:32               ` Eric Dumazet
2018-06-26 23:53           ` Eric Dumazet
2018-06-27  0:44             ` Cong Wang
2018-06-27  2:35               ` Eric Dumazet
2018-06-27 18:59                 ` Cong Wang
2018-06-27 19:33                   ` Eric Dumazet [this message]
2018-06-27 19:55                     ` Cong Wang
2018-06-28 23:18 ` Cong Wang

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=096ada36-8e05-c330-e5b3-3f6fcc77aea2@gmail.com \
    --to=eric.dumazet@gmail.com \
    --cc=davem@davemloft.net \
    --cc=fbl@redhat.com \
    --cc=fw@strlen.de \
    --cc=netdev@vger.kernel.org \
    --cc=netfilter-devel@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=xiyou.wangcong@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).