netdev - Re: [PATCH net-next 7/8] ixgbe: add pause frame stats

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <20200914092053.5e0fd9f4@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com>
Date:   Mon, 14 Sep 2020 09:20:53 -0700
From:   Jakub Kicinski <kuba@...nel.org>
To:     Ido Schimmel <idosch@...sch.org>
Cc:     Alexander Duyck <alexander.duyck@...il.com>,
        David Miller <davem@...emloft.net>,
        Netdev <netdev@...r.kernel.org>,
        Michal Kubecek <mkubecek@...e.cz>,
        Michael Chan <michael.chan@...adcom.com>, tariqt@...dia.com,
        saeedm@...dia.com, Andrew Lunn <andrew@...n.ch>
Subject: Re: [PATCH net-next 7/8] ixgbe: add pause frame stats

On Sun, 13 Sep 2020 12:14:14 +0300 Ido Schimmel wrote:
> On Fri, Sep 11, 2020 at 03:13:43PM -0700, Jakub Kicinski wrote:
> > On Fri, 11 Sep 2020 14:12:50 -0700 Alexander Duyck wrote:  
> > > On Fri, Sep 11, 2020 at 12:53 PM Jakub Kicinski <kuba@...nel.org> wrote:  
> > > > @@ -3546,6 +3556,7 @@ static const struct ethtool_ops ixgbe_ethtool_ops = {
> > > >         .set_eeprom             = ixgbe_set_eeprom,
> > > >         .get_ringparam          = ixgbe_get_ringparam,
> > > >         .set_ringparam          = ixgbe_set_ringparam,
> > > > +       .get_pause_stats        = ixgbe_get_pause_stats,
> > > >         .get_pauseparam         = ixgbe_get_pauseparam,
> > > >         .set_pauseparam         = ixgbe_set_pauseparam,
> > > >         .get_msglevel           = ixgbe_get_msglevel,    
> > > 
> > > So the count for this is simpler in igb than it is for ixgbe. I'm
> > > assuming you want just standard link flow control frames. If so then
> > > this patch is correct. Otherwise if you are wanting to capture
> > > priority flow control data then those are a seperate array of stats
> > > prefixed with a "p" instead of an "l". Otherwise this looks fine to
> > > me.  
> > 
> > That's my interpretation, although I haven't found any place the
> > standard would address this directly. Non-PFC pause has a different
> > opcode, so I'm reasonably certain this makes sense.
> > 
> > BTW I'm not entirely clear on what "global PFC pause" is either.
> > 
> > Maybe someone can clarify? Mellanox folks?  
> 
> I checked IEEE 802.1Qaz and could not find anything relevant. My only
> guess is that it might be a PFC frame with all the priorities set.
> 
> Where did you see it?

I think I saw it in MLX5 and I thought it's something
implementation-specific. But then I noticed 802.1-2018 
has a ieee8021PfcGlobalReqdGroup group.