Re: futex local DoS on most architectures

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
From: Mikael Pettersson
Date: Monday, February 11, 2008 - 6:56 am

Adrian Bunk writes:
 > The issue described in [1] is still present and unfixed (and even the 
 > fix there wasn't complete since it didn't cover SMP).
 > 
 > Thanks to Riku Voipio for noting that it is still unfixed.
 > 
 > cu
 > Adrian
 > 
 > [1] http://lkml.org/lkml/2007/8/1/474

I think calling it a local DoS may make people take it
less seriously.

The problem is not related to attacks or malice.
It's NORMAL futex usage on the affected architectures
that's broken and will throw the kernel into a loop.

/Mikael
--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
futex local DoS on most architectures, Adrian Bunk, (Mon Feb 11, 6:07 am)
Re: futex local DoS on most architectures, Mikael Pettersson, (Mon Feb 11, 6:56 am)
Re: futex local DoS on most architectures, Thomas Gleixner, (Mon Feb 11, 6:59 am)
Re: futex local DoS on most architectures, Lennert Buytenhek, (Mon Feb 11, 7:16 am)
Re: futex local DoS on most architectures, Riku Voipio, (Tue Feb 12, 5:50 am)
Re: futex local DoS on most architectures, Andrew Morton, (Thu Feb 14, 2:46 pm)
Re: futex local DoS on most architectures, Thomas Gleixner, (Thu Feb 14, 6:19 pm)
[PATCH 1/2] futex: fix init order, Thomas Gleixner, (Thu Feb 14, 6:23 pm)