Re: [PATCH] Fix northbridge quirk to assign correct NUMA node

[Daniel J Blueman <daniel@numascale.com>]

On 03/22/2014 01:16 AM, Suravee Suthikulpanit wrote:
> On 3/20/2014 10:38 PM, Daniel J Blueman wrote:
>> On 21/03/2014 06:07, Bjorn Helgaas wrote:
>>> [+cc linux-pci, Myron, Suravee, Kim, Aravind]
>>>
>>> On Thu, Mar 13, 2014 at 5:43 AM, Daniel J Blueman
>>> <daniel@numascale.com> wrote:
>>>> For systems with multiple servers and routed fabric, all
>>>> northbridges get
>>>> assigned to the first server. Fix this by also using the node
>>>> reported from
>>>> the PCI bus. For single-fabric systems, the northbriges are on PCI
>>>> bus 0
>>>> by definition, which are on NUMA node 0 by definition, so this is
>>>> invarient
>>>> on most systems.
>>>>
>>>> Tested on fam10h and fam15h single and multi-fabric systems and
>>>> candidate
>>>> for stable.
>>
>>> I wish this had been cc'd to linux-pci.  We're talking about a related
>>> change by Suravee there.  In fact, we were hoping this quirk could be
>>> removed altogether.
>>
>> Noted.
>>
>>> I don't understand what this quirk is doing.  Normally we discover the
>>> NUMA node for a PCI host bridge via the ACPI _PXM method.  The way
>>> _PXM works is that every PCI device in the hierarchy below the bridge
>>> inherits the same node number as the host bridge.  I first thought
>>> this might be a workaround for a system that lacks _PXM, but I don't
>>> think that can be right, because you're only changing the node for a
>>> few devices, not the whole hierarchy.
>>  >
>>> So I suspect the problem is more complicated, and maybe _PXM is
>>> insufficient to describe the topology?  Are there subtrees that should
>>> have nodes different from the host bridge?
>>
>> Yes; see below.
>>
>>> I know this patch is already in v3.14-rc7, but I'd still like to
>>> understand it so we can do the right thing with Suravee's patch.
>>
>> The _PXM method associates each northbridge with the first NUMA node,
>> 0 in single-fabric systems, and eg 4 for the second server in a
>> multi-fabric system with 2 dual-module Opterons (with 2 NUMA nodes
>> internally) etc, since the northbridges appear in the
>> PCI tree, under the host bridge, not above it [1].
> Daniel,
>
> That lspci looks interesting, what is the value returned from
> pci_bus_to_node() on your system for each fabric?

pci_bus_to_node returns 0 for PCI domain 0000, 2 for PCI domain 0001, 4 
for PCI domain 0002 and so on.

Our processor fabric interconnect has HyperTransport NodeId 2 on each 
server (as they start from bus 0, device 0x18 of course):
0000:00:1a.0 Host bridge: Device 1b47:0601 (rev 02)
0000:00:1a.1 Host bridge: Device 1b47:0602 (rev 02)

Thanks,
   Daniel
-- 
Daniel J Blueman
Principal Software Engineer, Numascale