All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jakub Kicinski <kubakici@wp.pl>
To: Or Gerlitz <gerlitz.or@gmail.com>
Cc: Simon Horman <simon.horman@netronome.com>,
	David Miller <davem@davemloft.net>,
	Linux Netdev List <netdev@vger.kernel.org>,
	oss-drivers@netronome.com
Subject: Re: [PATCH net-next 00/12] nfp: add flower app with representors
Date: Thu, 22 Jun 2017 22:50:14 -0700	[thread overview]
Message-ID: <20170622225014.59d673c6@cakuba.netronome.com> (raw)
In-Reply-To: <CAJ3xEMhyOiQX_jTpD5zWKY0oNkBoU1jyG3SMTpA091O8TbrjLA@mail.gmail.com>

On Thu, 22 Jun 2017 17:28:25 +0300, Or Gerlitz wrote:
> On Wed, Jun 21, 2017 at 12:42 PM, Jakub Kicinski <kubakici@wp.pl> wrote:
> 
> > Let me try to describe it a bit more instead.  Sorry but I'm not great
> > at ASCII art at this level of complexity and while having to stay
> > within 80 chars ;)
> >
> > Driver communicates with the Management FW via a mailbox.
> >
> > Driver loads, it gets the Application FW from disk.  It pushes the
> > entire FW to the mailbox and tells the Management FW to load it.  At
> > this point the PCIe datapath is loaded and driver discovers what
> > other communication channels are available.
> >
> > Driver checks which FW is loaded and finds appropriate nfp_app callbacks
> > for that FW.  If the nfp_app requires control message channel it will
> > map the control message queue/vNIC.  Driver spawn netdevs for
> > data vNICs.  Flower nfp_app may upon init spawn physical port
> > representors (single NFP chip supports tens of ports so they are not
> > all guaranteed a full vNIC in many designs).  Whenever representor is
> > spawned Application FW is notified with a control message.
> >
> > When user enables SR-IOV nfp_app sriov callback will be invoked and
> > flower nfp_app will respond by spawning VF reprs.  First version of the
> > Flower APP targets only the switchdev mode.  We plan to add legacy mode
> > and automatically pre-populate the rules if there is user interest.
> > Although I personally hope that people interested in legacy SR-IOV will
> > use our simpler CoreNIC app FW...  Flower APP will initially come up in
> > switchdev mode, no rules installed, all traffic will simply end up at
> > representors.  
> 
> This is much clearer now, thanks for explaining that over. Will be happy
> if you can elaborate a bit on the automatic tables pre-population for
> legacy mode emulation, sounds interesting.

Oh, I just meant that if someone wants to switch between legacy and
switchdev mode without changing the app FW - driver could hide the
representors and populate MAC/VLAN forwarding rules to get the same
behaviour as "legacy" cards have.

      reply	other threads:[~2017-06-23  5:50 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-06-20  5:51 [PATCH net-next 00/12] nfp: add flower app with representors Simon Horman
2017-06-20  5:51 ` [PATCH net-next 01/12] net: store port/representator id in metadata_dst Simon Horman
2017-06-20  5:51 ` [PATCH net-next 02/12] nfp: devlink add support for getting eswitch mode Simon Horman
2017-06-20  5:51 ` [PATCH net-next 03/12] nfp: move physical port init into a helper Simon Horman
2017-06-20  5:51 ` [PATCH net-next 04/12] nfp: map mac_stats and vf_cfg BARs Simon Horman
2017-06-20  5:51 ` [PATCH net-next 05/12] nfp: general representor implementation Simon Horman
2017-06-20  5:51 ` [PATCH net-next 06/12] nfp: add stats and xmit helpers for representors Simon Horman
2017-06-20 17:15   ` kbuild test robot
2017-06-20 20:48     ` Simon Horman
2017-06-20  5:51 ` [PATCH net-next 07/12] nfp: app callbacks for SRIOV Simon Horman
2017-06-20  5:51 ` [PATCH net-next 08/12] nfp: provide nfp_port to of nfp_net_get_mac_addr() Simon Horman
2017-06-20  5:51 ` [PATCH net-next 09/12] nfp: add support for tx/rx with metadata portid Simon Horman
2017-06-20  5:51 ` [PATCH net-next 10/12] nfp: add support for control messages for flower app Simon Horman
2017-06-20  5:51 ` [PATCH net-next 11/12] nfp: add " Simon Horman
2017-06-20  5:51 ` [PATCH net-next 12/12] nfp: add VF and PF representors to " Simon Horman
2017-06-20 16:13 ` [PATCH net-next 00/12] nfp: add flower app with representors Or Gerlitz
2017-06-20 19:19   ` Simon Horman
2017-06-20 19:24   ` [oss-drivers] " Jakub Kicinski
2017-06-21  9:00     ` Or Gerlitz
2017-06-21  9:32       ` Simon Horman
2017-06-22 14:39         ` Or Gerlitz
2017-06-22 19:09           ` Simon Horman
2017-06-21  9:42       ` Jakub Kicinski
2017-06-22 14:28         ` Or Gerlitz
2017-06-23  5:50           ` Jakub Kicinski [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170622225014.59d673c6@cakuba.netronome.com \
    --to=kubakici@wp.pl \
    --cc=davem@davemloft.net \
    --cc=gerlitz.or@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=oss-drivers@netronome.com \
    --cc=simon.horman@netronome.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.