Re: [PATCH 0/1] mv643xx_eth: Disable TSO by default

[Ezequiel Garcia <ezequiel.garcia@free-electrons.com>]

[-- Attachment #1: Type: text/plain, Size: 1716 bytes --]

On 11/01/2014 02:37 PM, Eric Dumazet wrote:
> On Sat, 2014-11-01 at 10:26 -0700, Eric Dumazet wrote:
>> On Sat, 2014-11-01 at 12:30 -0300, Ezequiel Garcia wrote:
>>> Several users ([1], [2]) have been reporting data corruption with TSO on
>>> Kirkwood platforms (i.e. using the mv643xx_eth driver).
>>>
>>> Until we manage to find what's causing this, this simple patch will make
>>> the TSO path disabled by default. This patch should be queued for stable,
>>> fixing the TSO feature introduced in v3.16.
>>>
>>> The corruption itself is very easy to reproduce: checking md5sum on a mounted
>>> NFS directory gives a different result each time. Same tests using the mvneta
>>> driver (Armada 370/38x/XP SoC) pass with no issues.
>>>
>>> Frankly, I'm a bit puzzled about this, and so any ideas or debugging hints
>>> are well received.
>>
>> lack of barriers maybe ?
>>

Yup, that was my initial thought as well...

>> It seems you might need to populate all TX descriptors but delay the
>> first, like doing the populate in descending order.
>>
>> If you take a look at txq_submit_skb(), you'll see the final
>> desc->cmd_sts = cmd_sts (line 959) is done _after_ frags were cooked by
>> txq_submit_frag_skb()
>>
>> You should kick the nick only when all TX descriptors are ready and
>> committed to memory.
>>
> 
> Untested patch would be :
> 

Yeah, it makes sense. I'm still seeing the corruption after applying
your patch.

However, maybe we are onto something. I'll see about taking a closer
look and give this some more thought.

Thanks for the hint!
-- 
Ezequiel García, Free Electrons
Embedded Linux, Kernel and Android Engineering
http://free-electrons.com


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 819 bytes --]