DPDK patches and discussions
 help / color / mirror / Atom feed
From: Elad Nachman <eladv6@gmail.com>
To: Stephen Hemminger <stephen@networkplumber.org>
Cc: Igor Ryzhov <iryzhov@nfware.com>,
	Ferruh Yigit <ferruh.yigit@intel.com>, dev <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH 2/2] kni: fix rtnl deadlocks and race conditions v4
Date: Fri, 26 Feb 2021 19:43:39 +0200
Message-ID: <CACXF7qk=Jozo9ahfmjX5yNdBvFBNeaEKCpCCq5KoyZVuyknbjA@mail.gmail.com> (raw)
In-Reply-To: <20210226074817.7e9e0a71@hermes.local>

The way the kernel handles its locks and lists for the dev close many
path, there is no way you can go around this with rtnl unlocked :

There is a race condition in __dev_close_many() processing the
close_list while the application terminates.
It looks like if two vEth devices are terminating,
and one releases the rtnl lock, the other takes it,
updating the close_list in an unstable state,
causing the close_list to become a circular linked list,
hence list_for_each_entry() will endlessly loop inside
__dev_close_many() .

And I don't expect David Miller will bend the kernel networking for DPDK or KNI.

But - Stephen - if you can personally convince David to accept a
kernel patch which will separate the close_list locking mechanism to a
separate (RCU?) lock, then I can introduce first a patch to the kernel
which will add a lock for the close_list, this way rtnl can be
unlocked for the if down case.

After that kernel patch, your original patch + relocation of the sync
mutex locking will do the job .

Otherwise, rtnl has to be kept locked all of the way for the if down
case in order to prevent corruption causing a circular linked list out
of the close_list, causing a hang in the kernel.

Currently, the rtnl lock is the only thing keeping the close_list from

If you doubt rtnl cannot be unlocked for dev close path, you can
consult David for his opinion, as I think it is critical to understand
what the kernel can or cannot do, or expects to be done before we can
unlock its locks as we wish inside rte_kni.ko .

Otherwise, if we are still in disagreement on how to patch this set of
problems, I think the responsible way around it is to completely
remove kni from the main dpdk tree and move it to dpdk-kmods

I know BSD style open-source does not carry legal responsibility from
the developers, but I think when a bunch of developers know a piece of
code is highly buggy, they should not leave it for countless new users
to bounce their head desperately against, if they cannot agree on a
correct way to solve the bunch of problems, of which I think we all
agree exist (we just do not agree on the proper solution or patch)...

That's my two cents,


On Fri, Feb 26, 2021 at 5:49 PM Stephen Hemminger
<stephen@networkplumber.org> wrote:
> On Fri, 26 Feb 2021 00:01:01 +0300
> Igor Ryzhov <iryzhov@nfware.com> wrote:
> > Hi Elad,
> >
> > Thanks for the patch, but this is still NACK from me.
> >
> > The only real advantage of KNI over other exceptional-path techniques
> > like virtio-user is the ability to configure DPDK-managed interfaces
> > directly
> > from the kernel using well-known utils like iproute2. A very important part
> > of this is getting responses from the DPDK app and knowing the actual
> > result of command execution.
> > If you're making async requests to the application and you don't know
> > the result, then what's the point of using KNI at all?
> >
> > Igor
> Do you have a better proposal that keeps the request result but does not
> call userspace with lock held.
> PS: I also have strong dislike of KNI, as designed it would have been rejected
> by Linux kernel developers.  A better solution would be userspace version of
> something like devlink devices. But doing control operations by proxy is
> a locking nightmare.

  reply	other threads:[~2021-02-26 17:43 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-26 14:46 [dpdk-dev] [PATCH] kni: fix rtnl deadlocks and race conditions Elad Nachman
2021-02-19 18:41 ` Ferruh Yigit
2021-02-21  8:03   ` Elad Nachman
2021-02-22 15:58     ` Ferruh Yigit
2021-02-23 12:05 ` [dpdk-dev] [PATCH V2] kni: fix rtnl deadlocks and race conditions v2 Elad Nachman
2021-02-23 12:53   ` Ferruh Yigit
2021-02-23 13:44 ` [dpdk-dev] [PATCH 1/2] kni: fix rtnl deadlocks and race conditions v3 Elad Nachman
2021-02-23 13:45 ` [dpdk-dev] [PATCH 2/2] " Elad Nachman
2021-02-24 12:49   ` Igor Ryzhov
2021-02-24 13:33     ` Elad Nachman
2021-02-24 14:04       ` Igor Ryzhov
2021-02-24 14:06         ` Elad Nachman
2021-02-24 14:41           ` Igor Ryzhov
2021-02-24 14:56             ` Elad Nachman
2021-02-24 15:18               ` Igor Ryzhov
     [not found]                 ` <CACXF7qkhkzFc-=v=iiBzh2V7rLjk1U34VUfPbNrnYJND_0TKHQ@mail.gmail.com>
2021-02-24 16:31                   ` Igor Ryzhov
2021-02-24 15:54     ` Stephen Hemminger
2021-02-25 14:32 ` [dpdk-dev] [PATCH 1/2] kni: fix kernel deadlock when using mlx devices Elad Nachman
2021-02-25 14:32   ` [dpdk-dev] [PATCH 2/2] kni: fix rtnl deadlocks and race conditions v4 Elad Nachman
2021-02-25 21:01     ` Igor Ryzhov
2021-02-26 15:48       ` Stephen Hemminger
2021-02-26 17:43         ` Elad Nachman [this message]
2021-03-01  8:10           ` Igor Ryzhov
2021-03-01 16:38             ` Stephen Hemminger
2021-03-15 16:58               ` Ferruh Yigit
2021-03-01 20:27             ` Dan Gora
2021-03-01 21:26               ` Dan Gora
2021-03-02 16:44                 ` Elad Nachman
2021-03-15 17:17     ` Ferruh Yigit
2021-03-16 18:35       ` Elad Nachman
2021-03-16 18:42         ` Ferruh Yigit
2021-03-15 17:17   ` [dpdk-dev] [PATCH 1/2] kni: fix kernel deadlock when using mlx devices Ferruh Yigit
2021-03-29 14:36 ` [dpdk-dev] [PATCH v5 1/3] kni: refactor user request processing Ferruh Yigit
2021-03-29 14:36   ` [dpdk-dev] [PATCH v5 2/3] kni: support async user request Ferruh Yigit
2021-03-29 14:36   ` [dpdk-dev] [PATCH v5 3/3] kni: fix kernel deadlock when using mlx devices Ferruh Yigit
2021-04-09 14:56     ` [dpdk-dev] [dpdk-stable] " Ferruh Yigit
2021-04-12 14:35       ` Elad Nachman
2021-04-20 23:07         ` Thomas Monjalon
2021-04-23  8:41           ` Igor Ryzhov
2021-04-23  8:59             ` Ferruh Yigit
2021-04-23 12:43               ` Igor Ryzhov
2021-04-23 12:58                 ` Igor Ryzhov

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:

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CACXF7qk=Jozo9ahfmjX5yNdBvFBNeaEKCpCCq5KoyZVuyknbjA@mail.gmail.com' \
    --to=eladv6@gmail.com \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@intel.com \
    --cc=iryzhov@nfware.com \
    --cc=stephen@networkplumber.org \


* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

DPDK patches and discussions

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://inbox.dpdk.org/dev/0 dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 dev dev/ https://inbox.dpdk.org/dev \
	public-inbox-index dev

Example config snippet for mirrors.
Newsgroup available over NNTP:

AGPL code for this site: git clone https://public-inbox.org/public-inbox.git