Messages in this thread Patch in this message | | | Date | Wed, 23 Feb 2022 08:54:04 +0100 | From | Oleksij Rempel <> | Subject | Re: [PATCH net-next v1 1/1] net: dsa: microchip: ksz9477: implement MTU configuration |
| |
On Tue, Feb 22, 2022 at 04:52:17PM -0800, Jakub Kicinski wrote: > On Mon, 21 Feb 2022 09:43:28 +0100 Oleksij Rempel wrote: > > This chips supports two ways to configure max MTU size: > > - by setting SW_LEGAL_PACKET_DISABLE bit: if this bit is 0 allowed packed size > > will be between 64 and bytes 1518. If this bit is 1, it will accept > > packets up to 2000 bytes. > > - by setting SW_JUMBO_PACKET bit. If this bit is set, the chip will > > ignore SW_LEGAL_PACKET_DISABLE value and use REG_SW_MTU__2 register to > > configure MTU size. > > > > Current driver has disabled SW_JUMBO_PACKET bit and activates > > SW_LEGAL_PACKET_DISABLE. So the switch will pass all packets up to 2000 without > > any way to configure it. > > > > By providing port_change_mtu we are switch to SW_JUMBO_PACKET way and will > > be able to configure MTU up to ~9000. > > And it has no negative side affects to always have jumbo enabled? > Maybe the internal buffer will be carved up in a different way?
Hm I tested it with iperf3 on 4 of 7 ports on this switch without noticeable changes before and after this patch. My setup looks as following:
----` | /- iperf -s = port0 | \- iperf3 -c 172.17.0.11 -t 100 | | = port1 ... same as port0, ... -c 172.17.0.10 = port2 ... same as port0, ... -c 172.17.0.13 = port3 ... same as port0, ... -c 172.17.0.12
Each port was sending and receiving. Each instance reported 938 Mbits/sec
> > +static int ksz9477_change_mtu(struct dsa_switch *ds, int port, int mtu) > > +{ > > + struct ksz_device *dev = ds->priv; > > + u16 new_mtu, max_mtu = 0; > > + int i; > > + > > + new_mtu = mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN; > > + > > + if (dsa_is_cpu_port(ds, port)) > > + new_mtu += KSZ9477_INGRESS_TAG_LEN; > > + > > + /* Cache the per-port MTU setting */ > > + dev->ports[port].max_mtu = new_mtu; > > + > > + for (i = 0; i < dev->port_cnt; i++) { > > + if (dev->ports[i].max_mtu > max_mtu) > > + max_mtu = dev->ports[i].max_mtu; > > + } > > nit: > > for (...) > max_mtu = max(max_mtu, dev->ports[i].max_mtu) > > > @@ -41,6 +41,7 @@ struct ksz_port { > > > > struct ksz_port_mib mib; > > phy_interface_t interface; > > + unsigned int max_mtu; > > }; > > max_mtu already has two meanings in this patch, let's call this > max_frame or max_len etc, instead of adding a third meaning.
Ok, thx. Will update the patch.
Regards, Oleksij -- Pengutronix e.K. | | Steuerwalder Str. 21 | http://www.pengutronix.de/ | 31137 Hildesheim, Germany | Phone: +49-5121-206917-0 | Amtsgericht Hildesheim, HRA 2686 | Fax: +49-5121-206917-5555 |
| |