From: Jacob Shin <jacob.shin@amd.com>
To: Pekka Enberg <penberg@kernel.org>
Cc: Yinghai Lu <yinghai@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@elte.hu>,
"H. Peter Anvin" <hpa@zytor.com>, Tejun Heo <tj@kernel.org>,
<linux-kernel@vger.kernel.org>
Subject: Re: [PATCH -v3 14/14] x86, mm: Map ISA area with connected ram range at the same time
Date: Thu, 6 Sep 2012 09:13:14 -0500 [thread overview]
Message-ID: <20120906141305.GA10013@jshin-Toonie> (raw)
In-Reply-To: <alpine.LFD.2.02.1209061021440.2210@tux.localdomain>
On Thu, Sep 06, 2012 at 10:22:19AM +0300, Pekka Enberg wrote:
> On Wed, Sep 5, 2012 at 1:02 AM, Pekka Enberg <penberg@kernel.org> wrote:
> > > How significant is the speed gain? The "isa_done" flag makes code flow
> > > more difficult to follow.
>
> On Wed, 5 Sep 2012, Yinghai Lu wrote:
> > Not really much.
> >
> > when booting system:
> > memmap=16m$128m memmap=16m$512m memmap=16m$256m memmap=16m$768m memmap=16m$1024m
> >
> > with the patch
> > [ 0.000000] init_memory_mapping: [mem 0x00000000-0x07ffffff]
> > [ 0.000000] [mem 0x00000000-0x07ffffff] page 2M
> > [ 0.000000] init_memory_mapping: [mem 0x09000000-0x0fffffff]
> > [ 0.000000] [mem 0x09000000-0x0fffffff] page 2M
> > [ 0.000000] init_memory_mapping: [mem 0x11000000-0x1fffffff]
> > [ 0.000000] [mem 0x11000000-0x1fffffff] page 2M
> > [ 0.000000] init_memory_mapping: [mem 0x21000000-0x2fffffff]
> > [ 0.000000] [mem 0x21000000-0x2fffffff] page 2M
> > [ 0.000000] init_memory_mapping: [mem 0x31000000-0x3fffffff]
> > [ 0.000000] [mem 0x31000000-0x3fffffff] page 2M
> > [ 0.000000] init_memory_mapping: [mem 0x41000000-0x7fffdfff]
> > [ 0.000000] [mem 0x41000000-0x7fdfffff] page 2M
> > [ 0.000000] [mem 0x7fe00000-0x7fffdfff] page 4k
> >
> > otherwise will have
> >
> > [ 0.000000] init_memory_mapping: [mem 0x00000000-0x000fffff]
> > [ 0.000000] [mem 0x00000000-0x000fffff] page 4k
> > [ 0.000000] init_memory_mapping: [mem 0x00100000-0x07ffffff]
> > [ 0.000000] [mem 0x00100000-0x001fffff] page 4k
> > [ 0.000000] [mem 0x00200000-0x07ffffff] page 2M
> > [ 0.000000] init_memory_mapping: [mem 0x09000000-0x0fffffff]
> > [ 0.000000] [mem 0x09000000-0x0fffffff] page 2M
> > [ 0.000000] init_memory_mapping: [mem 0x11000000-0x1fffffff]
> > [ 0.000000] [mem 0x11000000-0x1fffffff] page 2M
> > [ 0.000000] init_memory_mapping: [mem 0x21000000-0x2fffffff]
> > [ 0.000000] [mem 0x21000000-0x2fffffff] page 2M
> > [ 0.000000] init_memory_mapping: [mem 0x31000000-0x3fffffff]
> > [ 0.000000] [mem 0x31000000-0x3fffffff] page 2M
> > [ 0.000000] init_memory_mapping: [mem 0x41000000-0x7fffdfff]
> > [ 0.000000] [mem 0x41000000-0x7fdfffff] page 2M
> > [ 0.000000] [mem 0x7fe00000-0x7fffdfff] page 4k
>
> OK. Is there any other reason than performance to do this?
May be minor, but ..
The first range [mem 0x00000000-0x07ffffff] is covered entirely by 2M
page tables, instead of some 4K + some 2M.
-Jacob
>
> Pekka
>
next prev parent reply other threads:[~2012-09-06 14:13 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-09-05 5:46 [PATCH -v3 00/14] x86, mm: init_memory_mapping cleanup Yinghai Lu
2012-09-05 5:46 ` [PATCH -v3 01/14] x86, mm: Add global page_size_mask Yinghai Lu
2012-09-05 5:46 ` [PATCH -v3 02/14] x86, mm: Split out split_mem_range Yinghai Lu
2012-09-05 5:46 ` [PATCH -v3 03/14] x86, mm: Moving init_memory_mapping calling Yinghai Lu
2012-09-05 5:46 ` [PATCH -v3 04/14] x86, mm: Revert back good_end setting for 64bit Yinghai Lu
2012-09-05 5:46 ` [PATCH -v3 05/14] x86, mm: Find early page table only one time Yinghai Lu
2012-09-05 5:46 ` [PATCH -v3 06/14] x86, mm: Separate out calculate_table_space_size() Yinghai Lu
2012-09-05 5:46 ` [PATCH -v3 07/14] x86, mm: Move down two calculate_table_space_size down Yinghai Lu
2012-09-05 5:46 ` [PATCH -v3 08/14] x86, mm: set memblock initial limit to 1M Yinghai Lu
2012-09-05 5:46 ` [PATCH -v3 09/14] x86: if kernel .text .data .bss are not marked as E820_RAM, complain and fix Yinghai Lu
2012-09-05 5:46 ` [PATCH -v3 10/14] x86: Fixup code testing if a pfn is direct mapped Yinghai Lu
2012-09-05 5:46 ` [PATCH -v3 11/14] x86: Only direct map addresses that are marked as E820_RAM Yinghai Lu
2012-09-05 5:46 ` [PATCH -v3 12/14] x86/mm: calculate_table_space_size based on memory ranges that are being mapped Yinghai Lu
2012-09-05 5:46 ` [PATCH -v3 13/14] x86, mm: Use func pointer to table size calculation and mapping Yinghai Lu
2012-09-05 8:02 ` Pekka Enberg
2012-09-05 5:46 ` [PATCH -v3 14/14] x86, mm: Map ISA area with connected ram range at the same time Yinghai Lu
2012-09-05 8:02 ` Pekka Enberg
2012-09-05 18:57 ` Yinghai Lu
2012-09-06 7:22 ` Pekka Enberg
2012-09-06 14:13 ` Jacob Shin [this message]
2012-09-05 20:08 ` [PATCH -v3 00/14] x86, mm: init_memory_mapping cleanup Jacob Shin
2012-09-13 15:00 ` Jacob Shin
2012-09-27 8:22 ` 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=20120906141305.GA10013@jshin-Toonie \
--to=jacob.shin@amd.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=penberg@kernel.org \
--cc=tglx@linutronix.de \
--cc=tj@kernel.org \
--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;
as well as URLs for NNTP newsgroup(s).