On 2018-04-16 20:16, Sinan Kaya wrote:
On 4/15/2018 11:17 PM, Bjorn Helgaas wrote:
From reliability perspective, it makes sense. DPC handles NONFATAL
by bringing down the link. If error happened behind a switch and root
is handling DPC, we are impacting a lot of devices operation because of
It doesn't seem right to me that we handle both ERR_NONFATAL and
ERR_FATAL events differently if we happen to have DPC support in a
Maybe we should consider triggering DPC only on ERR_FATAL? That would
keep DPC out of the ERR_NONFATAL cases.
Keith, do you have any preference on this direction?
For ERR_FATAL, maybe we should bite the bullet and use
remove/re-enumerate for AER as well as for DPC. That would be painful
for higher-level software, but if we're willing to accept that pain
for new systems that support DPC, maybe life would be better overall
if it worked the same way on systems without DPC?
Sure, we can go to this route as well.
ok so finally this is what is being proposed and so far Bjorn, Sinan and
myself agreed on following:
I need to move the stop and re-enumerate code into the AER path instead
of patch #6 for both DPC_FATAL and AER_FATAL error types.
Also, I should turn off DPC NON_FATAL error detection.
Keith, please confirm if you are okay with above proposal.