On 07/17/2010 07:01 PM, Manuel Lauss wrote:
> Servus Wolfgang,
>
> On Sat, Jul 17, 2010 at 4:38 PM, Wolfgang Grandegger <wg@grandegger.com>
> wrote:
>> From: Wolfgang Grandegger <wg@denx.de>
>>
>> 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.
|