On Tue, Jun 25, 2013 at 09:55:15PM +1000, Benjamin Herrenschmidt wrote:
>On Tue, 2013-06-25 at 18:00 +0800, Gavin Shan wrote:
>> + /*
>> + * When the PHB is fenced or dead, it's pointless to collect
>> + * the data from PCI config space because it should return
>> + * 0xFF's. For ER, we still retrieve the data from the PCI
>> + * config space.
>> + */
>> + if (eeh_probe_mode_dev() &&
>> + (pe->type & EEH_PE_PHB) &&
>> + (pe->state & (EEH_PE_ISOLATED | EEH_PE_PHB_DEAD)))
>> + valid_cfg_log = false;
>> +
>
>I'm still unsure about that one. EEH_PE_ISOLATED could be the result
>of a normal ER of PE#0 (which can happen for various reasons other
>than a fence) in which case the config space is available and
>interesting.
>
It's something like the followings. For ER on PE#0, we will have
PE with type of EEH_PE_BUS marked as isolated, instead of the
one with EEH_PE_PHB.
[ EEH_PE_PHB] <---> [ EEH_PE_PHB] <---> [ EEH_PE_PHB]
|
[ EEH_PE_BUS ] PE#0
|
-------------------------
| |
[ EEH_PE_BUS ] PE#1 [ EEH_PE_BUS] PE#2
>I would either not bother and collect the FF's, or make this specific
>to fence and only fence.
>
I'd like to keep it specific to fenced PHB and it's already be that :-)
Thanks,
Gavin
_______________________________________________
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
