netdev - Re: MT7530 bug, forward broadcast and unknown frames to the correct CPU port

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 for Android: free password hash cracker in your pocket

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

Message-ID: <ZE-VEuhiPygZYGPe@makrotopia.org>
Date:   Mon, 1 May 2023 11:31:46 +0100
From:   Daniel Golle <daniel@...rotopia.org>
To:     Vladimir Oltean <olteanv@...il.com>
Cc:     Arınç ÜNAL <arinc.unal@...nc9.com>,
        DENG Qingfang <dqfext@...il.com>,
        Greg Ungerer <gerg@...nel.org>,
        Richard van Schagen <richard@...terhints.com>,
        Richard van Schagen <vschagen@...com>,
        Frank Wunderlich <frank-w@...lic-files.de>,
        mithat.guner@...ont.com, erkin.bozoglu@...ont.com,
        bartel.eerdekens@...stell8.be, netdev <netdev@...r.kernel.org>
Subject: Re: MT7530 bug, forward broadcast and unknown frames to the correct
 CPU port

On Mon, May 01, 2023 at 01:09:30PM +0300, Vladimir Oltean wrote:
> On Sat, Apr 29, 2023 at 10:52:12PM +0300, Arınç ÜNAL wrote:
> > On 29.04.2023 21:56, Vladimir Oltean wrote:
> > > On Sat, Apr 29, 2023 at 09:39:41PM +0300, Arınç ÜNAL wrote:
> > > > Are you fine with the preferred port patch now that I mentioned port 6
> > > > would be preferred for MT7531BE since it's got 2.5G whilst port 5 has
> > > > got 1G? Would you like to submit it or leave it to me to send the diff
> > > > above and this?
> > > 
> > > No, please tell me: what real life difference would it make to a user
> > > who doesn't care to analyze which CPU port is used?
> > 
> > They would get 2.5 Gbps download/upload bandwidth in total to the CPU,
> > instead of 1 Gbps. 3 computers connected to 3 switch ports would each get
> > 833 Mbps download/upload speed to/from the CPU instead of 333 Mbps.
> 
> In theory, theory and practice are the same. In practice, they aren't.
> Are you able to obtain 833 Mbps concurrently over 3 user ports?

Probably the 2.5 GBit/s won't saturate, but I do manage to get more
than 1 Gbit/s total (using the hardware flow offloading capability to
NAT-route WAN<->LAN and simultanously have a WiFi client access a NAS
device which also connects to a LAN port. I use MT7915E+MT7975D mPCIe
module with BPi-R2)

Using PHY muxing to directly map the WAN port to GMAC2 is also an
option, but would be limiting the bandwidth for those users who just
want all 5 ports to be bridged. Hence I do agree with Arınç that the
best would be to use the TRGMII link on GMAC1 for the 4 WAN ports and
prefer using RGMII link on GMAC2 for the WAN port, but keep using DSA.