Re: [PATCH v5 00/14] ACPI NUMA support for ARM64

From: Hanjun Guo
Date: Tue Apr 26 2016 - 09:03:57 EST


On 2016/4/26 20:15, Will Deacon wrote:
On Tue, Apr 26, 2016 at 01:31:07PM +0800, Hanjun Guo wrote:
On 2016/4/26 0:47, David Daney wrote:
On 04/25/2016 04:13 AM, Will Deacon wrote:
On Tue, Apr 19, 2016 at 06:40:25PM -0700, David Daney wrote:
From: David Daney <david.daney@xxxxxxxxxx>

Based on v16 of device-tree NUMA patch set for arm64 [1],this patch
set introduce the ACPI based configuration to provide NUMA
information.

ACPI 5.1 already introduced NUMA support for ARM64, which can get the
NUMA domain information from SRAT and SLIT table, so parse those two
tables to get mappings from cpu/mem to numa node configuration and
system locality.

Whilst I've queued the main NUMA series for arm64, I'd really like to
see more movement on the generic header file cleanups that you posted
separately:

http://lkml.kernel.org/r/1456358528-24213-1-git-send-email-ddaney.cavm@xxxxxxxxx


FWIW: Those patches should still apply. I am carrying them in my
development trees, and have not changed them in any way.

What's your plan for getting them merged?

This patch set touches lots of ACPI related file in arch/x86,
arch/ia64, and drivers/acpi/ (also arch/arm64), I think it can be
merged via ACPI tree by Rafael with your ack to ARM64 code, does
it make sense?


Given that this ACPI series already requires some significant cross-arch
interaction (which is actually good!), perhaps extending the clean-up
patches to encompass some of the ACPI bits might make sense, and we can
get that queued as a pre-requisite.

The cleanup patches you mention above are really independent of the ACPI
things. I have applied them both before and after the ACPI patches, and
both seem to work. With a quick perusal of the ACPI patches nothing
jumps out at me as being a candidate for inclusion in the header file
cleanup series.

I agree. My patch set is ACPI related enablement, cleanups and
consolidations, it would be good to merge as a single patch set
as it's self-contained.

Up to you. I just thought you might want to avoid having two sets of
cross-arch changes and the associated merging headaches that go with
that.

Good point, as I suggested above, it can go with ACPI tree if it's ok
to you and Rafael. The problem we have now is that dt based core NUMA
support for ARM64 is queued in your tree, that would be the headache.

Thanks
Hanjun