public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Nishanth Aravamudan <nacc@us.ibm.com>
To: Sean Bruno <sean.bruno@dsl-only.net>
Cc: karim@opersys.com, ak@suse.de, LKML <linux-kernel@vger.kernel.org>
Subject: Re: The system works (2.6.14-rc2): functional k8n-dl
Date: Fri, 23 Sep 2005 10:37:43 -0700	[thread overview]
Message-ID: <20050923173743.GJ5910@us.ibm.com> (raw)
In-Reply-To: <1127496135.25701.22.camel@oscar>

On 23.09.2005 [10:22:15 -0700], Sean Bruno wrote:
> On Fri, 2005-09-23 at 10:20 -0700, Nishanth Aravamudan wrote:
> > On 23.09.2005 [10:08:16 -0700], Sean Bruno wrote:
> > > On Thu, 2005-09-22 at 17:29 -0400, Karim Yaghmour wrote:
> > > > Nish,
> > > > 
> > > > OK, I can confirm that with version 1006 of the BIOS it works flawlessly
> > > > with Linux. I was able to install full FC4 and boot without a problem
> > > > even with the SATA disk plugged to the nVidia controller (reading the
> > > > archives you will see that the nVidia SATA controller is something I
> > > > was simply unable to get working.) I didn't need to recompile anything.
> > > > The kernel that came with FC4 worked just fine.
> > > I can also confirm these findings.  However, I still have to boot the
> > > kernel with iommu=memaper=3 in order to get the system to work
> > > properly.  
> > 
> > You have 6GB of RAM, right? That must be the difference, as I only have
> > 2 GB (and the IOMMU is used when you have more than 3 GB according to
> > menuconfig?).
> > 
> Yes 6GB of ram.

Odd, any ideas of why that is? What happens when you don't pass the
param? (sorry, haven't followed all the k8n-dl threads :)

A couple of points. Noticed that param is not documented in
Documentation/kernel-parameters.txt; care to make up a patch? Also,
after your message, I did a quick grep through my dmesg and see the
following:

[    0.000000] Checking aperture...
[    0.000000] CPU 0: aperture @ 4000000 size 32 MB
[    0.000000] Aperture from northbridge cpu 0 too small (32 MB)
[    0.000000] No AGP bridge found
[    0.000000] Your BIOS doesn't leave a aperture memory hole
[    0.000000] Please enable the IOMMU option in the BIOS setup
[    0.000000] This costs you 64 MB of RAM
[    0.000000] Mapping aperture over 65536 KB of RAM @ 4000000

Is the aperture memory hole necessary even without AGP? Does the ASUS
BIOS provide a means to change the aperture size (I didn't see one when
I looked, but I could easily have missed it).

[   45.703183] PCI: Using ACPI for IRQ routing
[   45.703194] PCI: If a device doesn't work, try "pci=routeirq".  If it helps, post a report
[   45.703286] PCI-DMA: Disabling AGP.
[   45.703295] PCI-DMA: More than 4GB of RAM and no IOMMU
[   45.703296] PCI-DMA: 32bit PCI IO may malfunction.<6>PCI-DMA: Disabling IOMMU.

I am not sure why the kernel thinks I have more than 4GB of RAM, when I
have 2 GB. Seems like a bug? Looks like that "Disabling IOMMU" printk is
b0rked...and why does it disable it if I don't have one?  (according to
2 messages before that one?) Andi, do you have any input on this?

/proc/meminfo:

MemTotal:      1989424 kB
MemFree:         32896 kB
Buffers:        276924 kB
Cached:        1013852 kB
SwapCached:          0 kB
Active:        1085736 kB
Inactive:       510788 kB
HighTotal:           0 kB
HighFree:            0 kB
LowTotal:      1989424 kB
LowFree:         32896 kB
SwapTotal:           0 kB
SwapFree:            0 kB
Dirty:              24 kB
Writeback:           0 kB
Mapped:         355348 kB
Slab:           340204 kB
CommitLimit:    994712 kB
Committed_AS:   432912 kB
PageTables:       6792 kB
VmallocTotal: 34359738367 kB
VmallocUsed:    262572 kB
VmallocChunk: 34359475707 kB
HugePages_Total:     0
HugePages_Free:      0
Hugepagesize:     2048 kB

Thanks,
Nish

  reply	other threads:[~2005-09-23 17:37 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-09-22 15:52 The system works (2.6.14-rc2): functional k8n-dl Nishanth Aravamudan
2005-09-22 17:20 ` Karim Yaghmour
2005-09-22 19:19 ` Bill Davidsen
2005-09-23 17:15   ` Nishanth Aravamudan
2005-09-23 17:43     ` Bill Davidsen
2005-09-23 17:55       ` Nishanth Aravamudan
2005-09-24 17:30         ` Bill Davidsen
2005-09-22 21:29 ` Karim Yaghmour
2005-09-23 17:08   ` Sean Bruno
2005-09-23 17:20     ` Nishanth Aravamudan
2005-09-23 17:22       ` Sean Bruno
2005-09-23 17:37         ` Nishanth Aravamudan [this message]
2005-09-23 17:16   ` Nishanth Aravamudan
2005-09-23 18:22     ` Karim Yaghmour
2005-09-23 18:16       ` Nishanth Aravamudan
2005-09-23 20:38       ` Karim Yaghmour

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=20050923173743.GJ5910@us.ibm.com \
    --to=nacc@us.ibm.com \
    --cc=ak@suse.de \
    --cc=karim@opersys.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=sean.bruno@dsl-only.net \
    /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