netdev - RE: rawip: delayed and mis-sequenced transmits

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <fd92e34c41b94cd1ac9bfcadd4a94ee6@AcuMS.aculab.com>
Date:   Thu, 7 Jul 2022 08:02:05 +0000
From:   David Laight <David.Laight@...LAB.COM>
To:     'Jakub Kicinski' <kuba@...nel.org>
CC:     "netdev@...r.kernel.org" <netdev@...r.kernel.org>
Subject: RE: rawip: delayed and mis-sequenced transmits

From: Jakub Kicinski
> Sent: 07 July 2022 02:54
> 
> On Wed, 6 Jul 2022 15:54:18 +0000 David Laight wrote:
> > Anyone any ideas before I start digging through the kernel code?
> 
> If the qdisc is pfifo_fast and kernel is old there could be races.
> But I don't think that's likely given you probably run something
> recent and next packet tx would usually flush the stuck packet.
> In any case - switching qdisc could be a useful test, also bpftrace
> is your friend for catching patckets with long sojourn time.

Yes, I forgot to mention the system is running a 5.18-rc6 kernel.
(I've already got some diagnostics in the receive path.)

I'd expect bugs in the qdisc layer to (mostly) keep packets
in order.
In this case I'm sending several packets at 20ms intervals that
overtake the 'stuck' packet.
So it really must be on a per socket queue.
Also the 'stuck' packet is sent after the packet that unblocks it.

I'm not sure normal tracing will help.
I'm seeing one mis-sequence every couple of million packets.
I can add code to the ethernet tx code to call ftrace_stop()
when the delayed packet gets sent.
(I've got the same check in the rx path to detect lost packets.)
That should show where it came from and probably why it got queued.

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)