Re: EEH error in doing DMA with PEX 8619

[Benjamin Herrenschmidt <benh@au1.ibm.com>]

On Tue, 2017-04-11 at 18:39 -0700, IanJiang wrote:
> On Tue, Apr 11, 2017 at 5:37 PM, Benjamin Herrenschmidt [via
> linuxppc]
> <ml-node+s10917n121182h95@n7.nabble.com> wrote:
> 
> > Another possibility would be if the requests from the PLX have a 
> > different initiator ID on the bus than the device you are setting
> > up 
> > the DMA for. 
> 
> Is there a way to check out the initiator ID in the driver? I'd like
> to make sure of this.

If you are running bare metal (ie, not under any hypervisor, aka
"powernv" platform), the EEH error log will contain a register dump. If
you paste that to us, we might be able to decode it, it will tell us
more data about the cause of the failure, including possibly the
initiator of the failing transaction.

The initiator ID (aka RID, aka bus/device/fn) of the DMA packets must
match the ones of the struct pci_dev you are using to establish the
mapping.

Cheers,
Ben.

> 
> --
> View this message in context: http://linuxppc.10917.n7.nabble.com/EEH
> -error-in-doing-DMA-with-PEX-8619-tp121121p121224.html
> Sent from the linuxppc-dev mailing list archive at Nabble.com.