Messages in this thread | | | Date | Tue, 22 Feb 2022 16:52:17 -0800 | From | Jakub Kicinski <> | Subject | Re: [PATCH net-next v1 1/1] net: dsa: microchip: ksz9477: implement MTU configuration |
| |
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?
> +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.
| |