mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: Yinghai Lu <yinghai@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@elte.hu>,
	"H. Peter Anvin" <hpa@zytor.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Thomas Renninger <trenn@suse.de>,
	Tang Chen <tangchen@cn.fujitsu.com>,
	linux-kernel@vger.kernel.org, Pekka Enberg <penberg@kernel.org>,
	Jacob Shin <jacob.shin@amd.com>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Subject: Re: [PATCH 14/14] x86, mm: Put pagetable on local node ram
Date: Thu, 7 Mar 2013 23:01:30 -0800	[thread overview]
Message-ID: <20130308070130.GM14556@mtj.dyndns.org> (raw)
In-Reply-To: <1362718720-27048-15-git-send-email-yinghai@kernel.org>

On Thu, Mar 07, 2013 at 08:58:40PM -0800, Yinghai Lu wrote:
> If node with ram is hotplugable, local node mem for page table and vmemmap
> should be on that node ram.
> 
> This patch is some kind of refreshment of
> | commit 1411e0ec3123ae4c4ead6bfc9fe3ee5a3ae5c327
> | Date:   Mon Dec 27 16:48:17 2010 -0800
> |
> |    x86-64, numa: Put pgtable to local node memory
> That was reverted before.
> 
> We have reason to reintroduce it to make memory hotplug work.
> 
> Split calling of init_mem_mapping into early_initmem_info
> for nodes after we get numa info there.
> 
> First node will be low range.
> Need to rework alloc_low_pages to alloc page table in following order:
> 	BRK, local node, low range
> 
> Still only load_cr3 one time, otherwise we would break xen 64bit again.

Hmmm... can you please split this patch further?  init_mem_mapping()
change can be separated, no?  Also, comments are disturbingly missing.
How are other people reading the code supposed to know what it's
trying to achieve why and how?  Hmmm... we're also likely to end up
with smaller mapping for misaligned NUMA configurations (I think my
test machine is like that).  Is it guaranteed that the top level ends
up in the first node?  It really needs documentation.

Thanks.

-- 
tejun

  reply	other threads:[~2013-03-08  7:01 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-03-08  4:58 [PATCH 00/14] x86, ACPI, numa: Parse numa info early Yinghai Lu
2013-03-08  4:58 ` [PATCH 01/14] x86, ACPI, mm: Kill max_low_pfn_mapped Yinghai Lu
2013-03-08  5:10   ` Tejun Heo
2013-03-08  5:22     ` Yinghai Lu
2013-03-08  5:25       ` Tejun Heo
2013-03-08  5:27         ` Yinghai Lu
2013-03-08  5:28           ` Tejun Heo
2013-03-08  6:09             ` H. Peter Anvin
2013-03-11 22:50               ` Daniel Vetter
2013-03-11 23:09                 ` Chris Wilson
2013-03-12  1:51                 ` H. Peter Anvin
2013-03-08  4:58 ` [PATCH 02/14] x86, ACPI: Split find/copy from acpi_initrd_override Yinghai Lu
2013-03-08  5:33   ` Tejun Heo
2013-03-08  6:47     ` Yinghai Lu
2013-03-08  4:58 ` [PATCH 03/14] x86, ACPI: store override acpi tables phys addr Yinghai Lu
2013-03-08  5:36   ` Tejun Heo
2013-03-08  6:49     ` Yinghai Lu
2013-03-08  7:08       ` Tejun Heo
2013-03-08  4:58 ` [PATCH 04/14] x86, ACPI: make acpi override finding work with 32bit flat mode Yinghai Lu
2013-03-08  5:50   ` Tejun Heo
2013-03-08  6:57     ` Yinghai Lu
2013-03-08  7:06       ` Tejun Heo
2013-03-08  7:25         ` Yinghai Lu
2013-03-08  7:28           ` Tejun Heo
2013-03-08  7:16       ` Andrew Morton
2013-03-08 21:25       ` Thomas Gleixner
2013-03-08  4:58 ` [PATCH 05/14] x86, ACPI: Find acpi tables in initrd early at head_32.S/head64.c Yinghai Lu
2013-03-08  5:57   ` Tejun Heo
2013-03-08  7:02     ` Yinghai Lu
2013-03-08  7:07       ` Tejun Heo
2013-03-08  4:58 ` [PATCH 06/14] x86, mm, numa: Move successful path handling code later Yinghai Lu
2013-03-08  6:04   ` Tejun Heo
2013-03-08  7:03     ` Yinghai Lu
2013-03-08  4:58 ` [PATCH 07/14] x86, mm, numa: call numa_meminfo_cover_memory() early Yinghai Lu
2013-03-08  4:58 ` [PATCH 08/14] x86, mm, numa: use numa_meminfo to check node_map_pfn alignment Yinghai Lu
2013-03-08  6:26   ` Tejun Heo
2013-03-08  7:05     ` Yinghai Lu
2013-03-08  4:58 ` [PATCH 09/14] x86, mm, numa: set memblock nid later Yinghai Lu
2013-03-08  6:28   ` Tejun Heo
2013-03-08  7:11     ` Yinghai Lu
2013-03-08  4:58 ` [PATCH 10/14] x86, mm, numa: Move emulation handling down Yinghai Lu
2013-03-08  6:42   ` Tejun Heo
2013-03-08  7:13     ` Yinghai Lu
2013-03-08  4:58 ` [PATCH 11/14] x86, acpi, numa: split SLIT handling out Yinghai Lu
2013-03-08  6:46   ` Tejun Heo
2013-03-08  7:18     ` Yinghai Lu
2013-03-08  7:19       ` Tejun Heo
2013-03-08  7:33         ` Yinghai Lu
2013-03-08  4:58 ` [PATCH 12/14] x86, mm, numa: Add early_initmem_init() stub Yinghai Lu
2013-03-08  4:58 ` [PATCH 13/14] x86, mm: Parse numa info early Yinghai Lu
2013-03-08  4:58 ` [PATCH 14/14] x86, mm: Put pagetable on local node ram Yinghai Lu
2013-03-08  7:01   ` Tejun Heo [this message]
2013-03-08  7:44     ` Yinghai Lu
2013-03-08  8:20   ` Tang Chen
2013-03-08 17:25     ` Yinghai Lu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20130308070130.GM14556@mtj.dyndns.org \
    --to=tj@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=hpa@zytor.com \
    --cc=jacob.shin@amd.com \
    --cc=konrad.wilk@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=penberg@kernel.org \
    --cc=tangchen@cn.fujitsu.com \
    --cc=tglx@linutronix.de \
    --cc=trenn@suse.de \
    --cc=yinghai@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®