netdev - Re: can: expected receive behavior broken

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 for Android: free password hash cracker in your pocket

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

Message-ID: <4C514BAE.4070201@hartkopp.net>
Date:	Thu, 29 Jul 2010 11:36:46 +0200
From:	Oliver Hartkopp <socketcan@...tkopp.net>
To:	Matthias Fuchs <matthias.fuchs@....eu>
CC:	Wolfgang Grandegger <wg@...ndegger.com>,
	Linux Netdev List <netdev@...r.kernel.org>,
	Socketcan-core@...ts.berlios.de
Subject: Re: can: expected receive behavior broken

On 28.07.2010 10:23, Matthias Fuchs wrote:
> plx_pci/sja1000 + esd_usb2
> 

Hi Matthias,

i added a test program to the SVN that checks whether the CAN_RAW_LOOPBACK and
CAN_RAW_RECV_OWN_MSGS socket options work properly (in can.ko and can-raw-ko
and vcan.ko).

So far i was only able to test it on vcan0, as i'm on a business trip and
don't have a real CAN hardware with me.

I'll enhance it to force the CAN netdev to be given on the commandline.

Regarding your request, i was able to see the bad behaviour in the latest
net-next-2.6. You need to make

    modprobe vcan echo=1

before creating vcan devices to test the loopback on driver level!

Invoking tst-rcv-own-msgs produces this output, which is far away from the
correct (wanted) output seen in the commit message below.

sockopt default
 s : 0
 t : 0
 timeout
sockopt - -
 timeout
sockopt - R
 timeout
sockopt L -
 s : 3
 t : 3
 timeout
sockopt L R
 s : 4
 t : 4
 timeout
done.

I'll check that with the latest linux-2.6 (after rebooting :-)

Thanks for the hint! I'll run the tst-rcv-own-msgs test tool on the upcoming
net-next-2.6's and also put it into LTP later on.

Regards,
Oliver

--- snip! ---

Added:
   trunk/test/tst-rcv-own-msgs.c
Modified:
   trunk/test/Makefile
Log:
Added test programm to check the correct functionality of
CAN_RAW_LOOPBACK and CAN_RAW_RECV_OWN_MSGS socket options.

It needs a vcan0 virtual CAN network interface and should produce an output
like this, when invoked:

sockopt default
 t : 0
 timeout
sockopt - -
 timeout
sockopt - R
 timeout
sockopt L -
 t : 3
 timeout
sockopt L R
 s : 4
 t : 4
 timeout
done.

> 
> On Wednesday 28 July 2010 10:17, Wolfgang Grandegger wrote:
>> On 07/28/2010 09:56 AM, Matthias Fuchs wrote:
>>> Hi,
>>>
>>> I just noticed that the receive behavior of CAN sockets is broken
>>> in current net-next-2.6.
>>> I wrote some simple code that receives messages and echos them back to
>>> the bus. When I now trigger one single message on the bus, I get
>>> this message received and echoed back in an endless loop.
>>>
>>> I do not touch the sockopts CAN_RAW_LOOPBACK or CAN_RAW_RECV_OWN_MSGS in my code.
>>> Only (!) setting CAN_RAW_LOOPBACK to 0 helps at the moment. But this behavior
>>> actually has nothing to do with LOOPBACK but more with RECV_OWN_MSGS.
>>
>> Sounds wired! What driver are you using?
>>
>> Wolfgang.
>>
>>
>>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html