public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Joerg Platte <jplatte@naasa.net>
To: Arjan van de Ven <arjan@infradead.org>
Cc: linux-kernel@vger.kernel.org
Subject: Re: Userspace process may be able to DoS kernel
Date: Sat, 11 Nov 2006 14:15:31 +0100	[thread overview]
Message-ID: <200611111415.32459.jplatte@naasa.net> (raw)
In-Reply-To: <1163248773.3293.20.camel@laptopd505.fenrus.org>

Am Samstag, 11. November 2006 13:39 schrieb Arjan van de Ven:

> this isn't per se acpi related: This is reading the PM timer from your
> chipset. The PMTimer is a clock on your chipset that the kernel can use
> to read a stable incrementing clock to find out what time it is right
> now, usually as part of userspace asking the kernel what time it is via
> the gettimeofday() system call. ACPI is just the component that does the
> actual (slow) hardware access... eg the messenger.

OK.

> Normally systems have better/faster clocks than the pmtimer, but there
> are circumstances where those can't be used.
>
> 1) HPET. The HPET is a lot faster than pmtimer, and very reliable. Most
> of the systems sold in the last 3 years have an hpet, but unfortunately,
> many bioses turn this off by default. If your BOOS has a "Multimedia
> timer" setting, make sure it's set to "On".

My computer is 3,5 years old (one of the first centrino notebooks). Maybe it 
does not have a HPET timer. I can't find HPET somewhere in the kernel.log 
file and no option in the BIOS. But it is enabled in my kernel config.

> 2) TSC. This is a super fast method of finding how much time has passed,
> since it's inside the CPU. However there are many reasons why this
> method may be unreliable, for example certain powermanagement features
> on laptops cause this clock to stop when idle (not useful), or to vary
> in frequency (also not useful if you want to find out what time it is).
> Also on AMD Opteron SMP systems or extreme Intel big honking NUMA
> systems, this timer is not synchronized between the various processors
> and that breaks the current time keeping in Linux, and so Linux doesn't
> use it in that case.

I'm using frequency scaling. Maybe that's a reason for not using TSC in each 
case.

> So my advice is
> 1) Check the bios to see if you have the HPET enabled. If not, enable
> it.
> 2) Check the kernel config to see if you have HPET enabled there, if not
> enable it.
> 3) Check dmesg to see if there's a reason the kernel doesn't use TSC;
> there is probably nothing you can do but at least you know why :)

The kernel semm to use TSC. I can't find another message stating that TSC has 
been disabled.

localhost kernel: Time: tsc clocksource has been installed.

There seem to be some clock drift. Each time when starting skype everything 
works perfect for a couple of hours. Then, skype behaves strange by causing 
this high system load. 

regards,
Jörg

      reply	other threads:[~2006-11-11 13:15 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-10-11 16:54 Userspace process may be able to DoS kernel Günther Starnberger
2006-10-12  6:02 ` Joerg Platte
2006-10-12  6:49   ` Willy Tarreau
2006-10-12 10:54     ` Joerg Platte
2006-10-12 11:30   ` Pekka Enberg
2006-10-12 11:41     ` Joerg Platte
2006-10-12 11:57       ` Pekka Enberg
2006-10-12 20:11         ` Joerg Platte
2006-10-12 20:25           ` Günther Starnberger
2006-10-13 13:24             ` Joerg Platte
2006-10-12 15:51 ` Lee Revell
2006-10-12 16:55   ` Günther Starnberger
2006-10-12 17:05     ` Lee Revell
2006-10-12 20:30   ` Günther Starnberger
2006-10-12 20:37     ` Lee Revell
2006-10-12 15:56 ` Lee Revell
2006-10-12 16:10   ` Jan Engelhardt
2006-10-12 16:19     ` Lee Revell
2006-10-12 22:02       ` Jan Engelhardt
     [not found] ` <200611100803.03958.lists@naasa.net>
     [not found]   ` <20061109231958.f18cd1ef.akpm@osdl.org>
2006-11-11 12:29     ` Joerg Platte
2006-11-11 12:39       ` Arjan van de Ven
2006-11-11 13:15         ` Joerg Platte [this message]

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=200611111415.32459.jplatte@naasa.net \
    --to=jplatte@naasa.net \
    --cc=arjan@infradead.org \
    --cc=linux-kernel@vger.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