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
Attachment:
signature.asc
Description: PGP signature
