Intel XL710 broken link down detection?

[Steven Hartland]

Its been a couple of weeks now so wanted to check if you had any news on 
this Pieper?

Also for extra visibility I'm looking to bring ixl in stable/10 up to 
date with the MFC's commits present in HEAD, which are quite a way behind.

One commit requires big changes between HEAD and stable/10, due to it 
being a combination of RSS support (not going to MFC'ed) and some bug 
fixes, is up for review here:
https://reviews.freebsd.org/D4265

I'm looking to use this for a 10.x based DC rollout over the next few 
weeks, so if anyone can look at that it would be most appreciated.

     Regards
     Steve

On 12/11/2015 15:18, Pieper, Jeffrey E wrote:
> We already have a fix in place that will be committed for review shortly.
>
> Thanks,
> Jeff
>
> -----Original Message-----
> From: owner-freebsd-net at freebsd.org [mailto:owner-freebsd-net at freebsd.org] On Behalf Of Steven Hartland
> Sent: Thursday, November 12, 2015 1:52 AM
> To: Ryan Stone <rysto32 at gmail.com>
> Cc: Jack F Vogel <jfv at freebsd.org>; freebsd-net at freebsd.org
> Subject: Re: Intel XL710 broken link down detection?
>
> Yes this works but a better way IMO would be to invert the bits we want:
> https://people.freebsd.org/~smh/ixl_int_init.patch
>
> If there are no objections then I'll commit this later today.
>
> Also just fixed the debug sysctls from causing panics when compiled with
> INVARIANTS see:
> https://svnweb.freebsd.org/base?view=revision&revision=290708
>
>       Regards
>       Steve
>
> On 11/11/2015 16:31, Ryan Stone wrote:
>> On Wed, Nov 11, 2015 at 11:18 AM, Steven Hartland
>> <steven at multiplay.co.uk <mailto:steven at multiplay.co.uk>> wrote:
>>
>>      Comparing this to the Linux driver which does detect the link down
>>      I've discovered it actually polls the link status by default in
>>      its watchdog.
>>
>>      Disabling this with "ethtool --set-priv-flags eth1 LinkPolling
>>      off" and the Linux driver also fails to detect link down.
>>
>>      So this seems like a firmware or even hardware bug where it should
>>      be reporting down events and the Linux driver has been updated to
>>      workaround the problem?
>>
>>
>> No, apparently the Linux devs just didn't read the datasheet closely
>> enough (and presumably the FreeBSD driver copied the mistake).  There
>> is a mask of interrupt causes that works backwards from how one would
>> expect; you mask out events that you *don't* want rather than events
>> that you do want.  Both the Linux and FreeBSD drivers pass a mask of
>> events that they want interrupts for (the only reason why it appears
>> to work on link up is that the the AN Completed event fires when link
>> is up, as far as I can tell).  Try the following patch:
>>
>> https://people.freebsd.org/~rstone/patches/ixl_link_int.diff
>> <https://people.freebsd.org/%7Erstone/patches/ixl_link_int.diff>
>>
> _______________________________________________
> freebsd-net at freebsd.org mailing list
> https://lists.freebsd.org/mailman/listinfo/freebsd-net
> To unsubscribe, send any mail to "freebsd-net-unsubscribe at freebsd.org"