Re: [RFC/RFT PATCH 1/3] PCI: Introduce pci_bus_find_numa_node()

[Vadim Lomovtsev]

On Fri, May 12, 2017 at 10:18:46AM -0700, Vadim Lomovtsev wrote:
Hi Lorenzo,

> Hi Lorenzo
> 
> On Fri, May 12, 2017 at 04:50:40PM +0100, Lorenzo Pieralisi wrote:
> > Hi Vadim,
> > 
> > On Fri, May 12, 2017 at 05:44:05AM -0700, Vadim Lomovtsev wrote:
> > > Hi Lorenzo,
> > > 
> > > Are there any news related to these patches ?
> > 
> > Not really, I have not received any feedback but I was expecting some
> > to make progress here. Have you tested it ?
> >
> > Please let me know, thanks !
> 
> Not yet. Plan to test them after weekend and will get back to you.
>

Here is the results of testing you patches at dual-socketed board
with Cavium ThunderX SoC.

Each boot kernel boot with acpi=force argument.

1. The 4.12-rc1 couldn't find rootfs partition so can't be tested.
2.1  The 4.11 without your patch set 0 to numa node for pci device
  cat /sys/bus/pci/devices/*/numa_node
  got zeroes here for all devices
2.2 The 4.11 with your patches applied set -1 to numa_node for all pci devices
  same command provides "-1"

So looking at your patches..

At the patch 1/3 you implemented pci_bus_find_numa_node function:

+int pci_bus_find_numa_node(struct pci_bus *bus)
+{
+	return NUMA_NO_NODE;
+}

Then at the 2/3 patch it is called from pci_register_host_bridge:
@@ -770,6 +770,7 @@ int pci_register_host_bridge(struct pci_host_bridge *bridge)
[..]
+	set_dev_node(&bus->dev, pci_bus_find_numa_node(bus));

I suppose that is why I'm seeing those -1 in the numa_node field.

And at the patch 3/3 you implemented acpi_pci_bus_find_numa_node function
 +int acpi_pci_bus_find_numa_node(struct pci_bus *bus)
which implements actual work of getting numa node value,
but it seems that nodoby calls it, isn't it ?

Don't we need to update pci_bus_find_numa_node with proper calling
of acpi_pci_bus_find_numa_node() ?

> > 
> > Lorenzo
> 
> WBR,
> Vadim

WBR,
Vadim