Posted on 03/19/2009 9:45:32 AM PDT by ShadowAce
This is the scariest, stealthiest, and most dangerous exploit I've seen come around since the legendary Blue Pill! No, I'm not just trying to sensationalize this or spread fear, uncertainty and doubt. This is serious and represents a massive new security threat for us all.
Security Researchers Joanna Rutkowska and Loic Duflot are planning to release a research paper + exploit code for a new SMM (System Management Mode) exploit that installs via an Intel® CPU caching vulnerability. Joanna, of blue pill fame, reported this on her blog
Joanna cleared it up for me that they are not releasing a SMM rootkit but rather a exploit. It will be up to some other folks to tie this in with a SMM rootkit like this one perhaps.
"Thursday, March 19th, 1600 UTC, we will publish a paper (+ exploits) on exploiting Intel® CPU cache mechanisms. The attack allows for privilege escalation from Ring 0 to the SMM on many recent motherboards with Intel CPUs. Rafal implemented a working exploit with code execution in SMM in a matter of just a few hours."
The heart-stopping thing about this particular exploit is that it hides itself in the SMM space. To put that into perspective, SMM is more privileged than a hypervisor is and it's not controllable by any Operating System. By design, the operating system cannot override or disable System Management Interupt (SMI) calls. In practice, the only way for you to know what is running in SMM space is to physically disassemble the firmware of your computer. So, given that an SMI takes precedence over any OS call, the OS cannot control or read SMM, and the only way to read SMM is to disassemble the system makes an SMM rootkit incredibly stealthy! It is very much like the blue pill attack (the PC is living in the matrix which is under your complete control) except that SMM attacks are at an even deeper hardware level of abstraction than a hypervisor exploit! SMM has been around in Intel chips since 386 processors so if you'd like further education or history lesson here is a good article.
Now remember that what Joanna and Loic will be releasing is a brand new, never before disclosed Intel caching hack that allows them to gain access to SMM space and run their new exploit. If you then use this exploit to run a SMM rootkit that has the ability to call home to its creator to get new code or deposit its findings your really gonna have a powerful hack. No software you can run on your operating system would be able to detect this type of exploit once you are powned.
So why would they release the exploit code to the public you ask. Aren't security researchers supposed to play by the rules and refrain from disclosure? Well here's the thing, both the CPU caching vulnerabilities and the SMM vulnerabilities already have been reported to intel. In fact, according to Joanna "the first mention of the possible attack using caching for compromising SMM has been discussed in certain documents authored as early as the end of 2005 (!) by nobody else than... Intel's own employees." Both Joanna and Loic also officially reported this and other related bugs to Intel. Loic did so back in October 2008. (correction
: the previous tracking number I just deleted in the article is for a different bug that Joanna also discovered and is currently not patched by Intel yet.) Bottom line is that Intel has known about this vulnerability and others for years and it can be argued they haven't done due diligence to fix them yet. When this happens, security researchers have little choice but to release their finding publicly, the assumption being that if they have known about it for years then for sure someone with less than legal intentions is already exploiting it. Here is how Joanna puts it,
"If there is a bug somewhere and if it stays unpatched for enough time, it is almost guaranteed that various people will (re)discover and exploit it, sooner or later. So, don't blame researchers that they find and publish information about bugs — they actually do a favor to our society."
Is your PC currently powned by some hacker ninja using a SMM rootkit? How would you tell? You can't tell!!!!! MUWHAHA!
I just hope Intel fixes these vulnerabilities fast.
Keep checking this site on Thursday, the paper and code will be published here. Good article on previous theoretical SMM exploits can be found here.
Well, I guess I’m glad I’ve got AMD.
Is it a permanent write, or does the hack clear when you cold boot?
Ditto.
>Well, I guess I’m glad I’ve got AMD.
Yep.
Is there any memory within the chip itself?
They have no business posting this. They should send the hack to Intel. To do anything else is akin to a breach of national security.
Me too, at least at home. :-)
They have no business posting this. They should send the hack to Intel. To do anything else is akin to a breach of national security.
both the CPU caching vulnerabilities and the SMM vulnerabilities already have been reported to intel. In fact, according to Joanna "the first mention of the possible attack using caching for compromising SMM has been discussed in certain documents authored as early as the end of 2005 (!) by nobody else than... Intel's own employees."
"If there is a bug somewhere and if it stays unpatched..." and if someone could somehow rewrite firmware from unpriviledged user application, and if, after all that, someone could somehow "call home" (critical for any exploit to be useful, and has to be executed, again, using the unpriviledged user level, which will be intercepted by even primitive firewalls) ...
I'd say the chances for exploiting this in an undetecteble rootkit are pretty "remote". Not that vigilance is not warranted, but releasing the exploits will help others, besides Intel, to find a rootkit detection and/or fix on a callback level.
Well done, Joanna!
It’s a good thing. Those of us that are trying to defend the enterprise don’t have time to go poking into every nook and cranny in systems looking for holes that can be attacked. Joanna and other researchers’ data is vital to defending systems from attack. The data provided can be used to design detection and prevention strategies aimed at thwarting potential attacks.
Or would that be the nature of the attack -- a bogus "Intel CPU patch" that gets into the regular OS updates (whether Windows or Mac)?
A detector shouldn’t be impossible. Running SMM code causes the CPU state saved and restored, flushes the cache and can mess with program timekeeping. Such operations are not common, so a constant recurrence of them would be an indicator you’ve been rooted.
Beyond that, you need specialized hardware to really see what’s going on. Our resident FPGA programmer (sorry, can’t remember which FReeper you are) could shed more light on that.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.