On Wed, 24 Sep 2014, Yijing Wang wrote:
On 2014/9/25 7:30, Bjorn Helgaas wrote:
On Wed, Sep 24, 2014 at 4:41 PM, Keith Busch <keith.busch@xxxxxxxxx> wrote:
Just poking this thread to make sure it's not dead. :)
I tested Yijing's proposal and it is successful on our Intel server
platforms; hoping either this or something that derives similar behavior
will be applied so we can remove bus tuning kernel parameters.
Tested-by: Keith Busch <keith.busch@xxxxxxxxx>
Oops, thanks for poking me, because this was indeed dead.
My main objection was to testing "is_hotplug_bridge". That doesn't
seem right, because this issue really isn't specific to hotplug. I
didn't see a resolution of that, but let me know if I missed it.
Why I introduced "is_hotplug_bridge" is to avoid to touch the MPS which is not
in hotplug case when pcie_bus_config == PCIE_BUS_TUNE_OFF.
It's so sad that PCIe spec doesn't give a detailed guide to configure MPS.
I'd like to refactor current MPS framework, but now there are still some puzzles
to me. I need to have a deeper understanding of pcie mps. I read Jon's mps patch
log from git, I found he turn off all this MPS config, because some issues were found
in some platforms, but no platforms detailed info and no bugzilla records.
Just my opinion, I thought the hotplug check was a good idea: it addresses
a known issue, and does not mess with current unknowns. Outside a hotplug
scenario, I think we expect platform f/w to handle MPS settings and the
kernel can stay out of the way because of the unknown platform issues. If
it is hotplug, having the kernel set device's MPS to match the parent
couldn't make things worse off than doing nothing, right?
On the side, I'll see if I can ping some comrades on PCI-SIG to propose
an ECN to clarify configuring MPS. They usually ignore me though, so no
promises. :)
--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
