[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87h7v2nwmw.fsf@kurt>
Date: Tue, 23 Jun 2020 08:07:03 +0200
From: Kurt Kanzenbach <kurt@...utronix.de>
To: Andrew Lunn <andrew@...n.ch>
Cc: Vivien Didelot <vivien.didelot@...il.com>,
Florian Fainelli <f.fainelli@...il.com>,
"David S. Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>, netdev@...r.kernel.org,
Rob Herring <robh+dt@...nel.org>, devicetree@...r.kernel.org,
Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
Richard Cochran <richardcochran@...il.com>,
Kamil Alkhouri <kamil.alkhouri@...offenburg.de>,
ilias.apalodimas@...aro.org
Subject: Re: [RFC PATCH 6/9] net: dsa: hellcreek: Add debugging mechanisms
On Mon Jun 22 2020, Andrew Lunn wrote:
> On Mon, Jun 22, 2020 at 02:32:28PM +0200, Kurt Kanzenbach wrote:
>> On Fri Jun 19 2020, Andrew Lunn wrote:
>> >> > Are trace registers counters?
>> >>
>> >> No. The trace registers provide bits for error conditions and if packets
>> >> have been dropped e.g. because of full queues or FCS errors, and so on.
>> >
>> > Is there some documentation somewhere? A better understanding of what
>> > they can do might help figure out the correct API.
>>
>> No, not that I'm aware of.
>>
>> Actually there are a few more debugging mechanisms and features which
>> should be exposed somehow. Here's the list:
>>
>> * Trace registers for the error conditions. This feature needs to be
>> configured for which ports should be traced
>> * Memory registers for indicating how many free page and meta pointers
>> are available (read-only)
>> * Limit registers for configuring:
>> * Maximum memory limit per port
>> * Reserved memory for critical traffic
>> * Background traffic rate
>> * Maximum queue depth
>> * Re-prioritization of packets based on the ether type (not mac address)
>> * Packet logging (-> retrieval of packet time stamps) based on port, traffic class and direction
>> * Queue tracking
>>
>> What API would be useful for these mechanisms?
>
> Hi Kurt
>
> You should take a look at devlink. Many of these fit devlink
> resources. Use that where it fits. But you might end up with an out of
> tree debugfs patch for your own debugging work. We have something
> similar of mv88e6xxx.
I see. Maybe I'll keep the debug stuff out of tree for now and will come
back to it later.
Thanks,
Kurt
Download attachment "signature.asc" of type "application/pgp-signature" (833 bytes)
Powered by blists - more mailing lists