linux-kernel - Re: [RFC][PATCH] IO-APIC blacklist

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Sat, 2 Jun 2007 13:32:23 -0700 (PDT)
From:	Tear <tarrqt@...oo.com>
To:	Linus Torvalds <torvalds@...ux-foundation.org>
Cc:	mingo@...hat.com, akpm@...ux-foundation.org,
	linux-kernel@...r.kernel.org
Subject: Re: [RFC][PATCH] IO-APIC blacklist

--- Linus Torvalds <torvalds@...ux-foundation.org> wrote:

> 
> 
> On Sat, 2 Jun 2007, Tear wrote:
> > 
> > I own a Dell OptiPlex GX240 which, when ACPI is disabled
> > but IO-APIC is enabled, shows very slow USB performance.
> > I thought that this could be related to IO-APIC and
> > tried to boot with "noapic" appended to the kernel
> > command line. This way the USB transfer speed returned
> > to normal values.
> 
> Well, it's almost certainly not the IO-APIC per se.
> 
> It's more likely to be some irq routing issue, where ACPI fixes up 
> something.  Do you have diffs of 'dmesg' with and without ACPI?
> 
> 		Linus

Mr. Torvalds,

I have tested my system with different kernel command lines
and have ruled out all of the four possibilities. Here's a
matrix which summarizes the situtation. My USB-enabled
digital camera's data transfer rate is as follows:

           | acpi=ht   | acpi=force
~~~~~~~~~~~+~~~~~~~~~~~+~~~~~~~~~~~~
 apic      | very slow | normal
~~~~~~~~~~~+~~~~~~~~~~~+~~~~~~~~~~~~
 noapic    | normal    | normal

"apic" means that an apic related option was NOT
appended to the kernel command line whereas "noapic"
means that "noapic" was appended to the kernel
command line. acpi=ht is the default since Dell
OptiPlex GX240 is in the ACPI blacklist.

By testing carefully, I have concluded that it is IO-APIC
which causes problems when acpi is =ht or =off. This is
why I wrote the IO-APIC blacklist patch.

I am attaching the dmesg output of all of the four cases.
If you would like a diff between any of the four cases,
I would be glad to send one. (The kernel command line
printed by the kernel should help in determining which
dmesg output is which - in addition to the names of
the attachments.)

Thank you for your attention.

Regards,
- Tear

      ____________________________________________________________________________________
Park yourself in front of a world of choices in alternative vehicles. Visit the Yahoo! Auto Green Center.
http://autos.yahoo.com/green_center/ 
View attachment "dmesg-acpi=force-apic.txt" of type "text/plain" (14258 bytes)

View attachment "dmesg-acpi=force-noapic.txt" of type "text/plain" (14590 bytes)

View attachment "dmesg-acpi=ht-apic.txt" of type "text/plain" (13498 bytes)

View attachment "dmesg-acpi=ht-noapic.txt" of type "text/plain" (13536 bytes)