On 07/17/2010 07:01 PM, Manuel Lauss wrote: > Servus Wolfgang, > > On Sat, Jul 17, 2010 at 4:38 PM, Wolfgang Grandegger <wg@xxxxxxxxxxxxxx> wrote: >> From: Wolfgang Grandegger <wg@xxxxxxx> >> >> Currently, the eth devices are probed in the inverse order, first >> au1xxx_eth1_device and then au1xxx_eth0_device. On the GPR board, >> this makes trouble: >> >> # ifconfig|grep HWaddr >> eth0 Link encap:Ethernet HWaddr 00:50:C2:0C:30:01 >> eth1 Link encap:Ethernet HWaddr 66:22:01:80:38:10 >> >> A bogous ethernet hwaddr is assigned to the first device and >> au1xxx_eth0_device is mapped to eth1, which even does not work >> properly. With this patch, the problems are gone: >> >> # ifconfig|grep HWaddr >> eth0 Link encap:Ethernet HWaddr 66:22:11:32:38:10 >> eth1 Link encap:Ethernet HWaddr 66:22:11:32:38:11 > > Interesting. I don't disagree with the patch; what do you think about > passing MAC address via platform_data? I don't particularly like > how the driver is trying to get a MAC address using the prom interface. Well, I don't think it's a good idea. Each board should have a different mac address and it's nomally stored somewhere in the boards non-volatile storage during board bringup. > I'll try to cook something up. But not via platform data, please. Or have I missed something. With the flat device tree (as used for PowerPC) the situation is different because the boot-loader can fixup the MAC address before booting Linux. Wolfgang.
