Massive security hole in CPU's incoming?Official Meltdown/Spectre Discussion Thread

[moinmoin]

Intel also had a shared memory exploit for their iGPUs. I'm not surprised AMD had the same problem.

Still disappointing. AMD on the same level as Intel? No way!

Good on AMD reacting this swiftly and already rolling out the fix. More info by the finder: https://medium.com/@dannyodler/attacking-the-golden-ring-on-amd-mini-pc-b7bfb217b437

 

[amd6502]

These vulnerabilities seem to be never ending for Intel over the last several years. The latest ones (from the article above) have been dubbed "CrossTalk".

Here are some very broad complaints from Jobs' mob:

https://fudzilla.com/news/pc-hardware/51076-apple-was-hacked-off-with-intel

Moving to to the acorn platform, especially with big wide cores, won't eliminate Spectre vulnerabilities. It will probably mostly be security by obscurity for them.

 

[Gideon]

A gift that keeps on giving ...

Researchers Make More Discoveries Around L1TF/Foreshadow - It's Not Good - Phoronix

www.phoronix.com

 

[nicalandia]

A gift that keeps on giving ...

Researchers Make More Discoveries Around L1TF/Foreshadow - It's Not Good - Phoronix

www.phoronix.com

Intel is the Gift That Keeps on Giving...…...……. I am glad that I switch to Amd…. Wait I have never owned an Intel CPU

 

[nicalandia]

Is this the same Vulnerability or another one?

Exclusive: Intel CPU Vulnerability Can Be Used to Kill CPUs and Crash Systems

Exclusive: Intel CPU Vulnerability Can Be Used to Kill CPUs and Crash Systems

Technology Vision

adoredtv.com

Intel is on a Roll, almost as if they do this on purpose

 

[DrMrLordX]

If a script kiddee got their hands on a tool to push signed drivers enabling a +.5v uptick on Intel systems, they could harass people by killing their entire PC. When I was younger, and back when there weren't yet any Federal laws against DoS/DDoS, I used Winnuke to knock out Win95 systems as a prank a few times. Don't think I would kill an entire PC, but I knew the kinds of people who might do that . . .

 

[VirtualLarry]

Given the severity and lack of current fix for that last mentioned vuln., I'm changing my limited warranty period for my Intel-based gaming PCs to 30 days, and not stocking any more Intel-based rigs.

What kind of timespan (generation-wise) are we talking about? 4th-gen through current? Or only 6th-gen through current? 4th-gen had FIVR, IIRC, and changing the "mobo CPU voltage" only varied the voltage input to the FIVR. So, possibly, 4th-Gen systems are immune? Just a thought, might be incorrect.

 

[maddie]

Intel is the Gift That Keeps on Giving...…...……. I am glad that I switch to Amd…. Wait I have never owned an Intel CPU

Looks like all vendors might be at risk.

 

[amd6502]

Looks like all vendors might be at risk.

These are just follow up studies from Graz university. It's so broad it covers about all modern processors (eg POWER, acorn risc, x86). However imho these are far fetched proofs of concept that are going to be hard to exploit.

A solution would be further sandbox the most likely vectors which are running withing browser; that is, malicious javascript scripts as well as webassembly. Hence browsers have the first duty to reduce the risk.

The main thing is that a lot of CPU time is needed to get a likely hit.

So browsers could timeout a javascript or webassembly program after a set amount (user specified) of cpu time and then decrease thread priority or niceness to the absolute minimum, and move (or let OS move) these to either a low power core with no to little out of order execution and less L2 privileges, or an emulated core with similar properties.

 

[amd6502]

More from Graz University Side channel attack using power stats

 

[moinmoin]

Direct link to the website: https://platypusattack.com/

Should be noted that this is not a new attack (monitoring power usage to extract data has been done before), what's new is that Intel's RAPL power monitoring interface is being used for that purpose. Also they looked only at Intel (again) whereas AMD also supports RAPL and very likely is also affected unless they already thought of that attack vector before (not unthinkable, its finer grained boost algorithm in Zen 2 and 3 may well be able to hide power usage differences of instructions as is).

 

[DrMrLordX]

Looks like Platypus was patched?

 

[moinmoin]

Looks like Platypus was patched?

Yes, by Intel anyway: https://www.intel.com/content/www/us/en/security-center/advisory/intel-sa-00389.html

 

[DrMrLordX]

Just when you thought it was safe!

Working Windows and Linux Spectre exploits found on VirusTotal

Working exploits targeting Linux and Windows systems not patched against a three-year-old vulnerability dubbed Spectre were found by security researcher Julien Voisin on VirusTotal.

www.bleepingcomputer.com

It looks less like an actual infected file and more like part of a pen testing toolkit. Still.

 

[Stuka87]

Just when you thought it was safe!

Working Windows and Linux Spectre exploits found on VirusTotal

Working exploits targeting Linux and Windows systems not patched against a three-year-old vulnerability dubbed Spectre were found by security researcher Julien Voisin on VirusTotal.

www.bleepingcomputer.com

It looks less like an actual infected file and more like part of a pen testing toolkit. Still.

If there is a toolkit with a working exploit, it wont be long until malware has them, assuming there isnt already malware with it.

 

[VirtualLarry]

So, this working Spectre exploit, means that three-plus-year-old Intel platforms, now truely are "unsafe at any speed", unless they've been BIOS-patched?

 

[cortexa99]

So, this working Spectre exploit, means that three-plus-year-old Intel platforms, now truely are "unsafe at any speed", unless they've been BIOS-patched?

Very likely, these exploits are fully utilized by hackers and not only Intel but also AMD, ARM were affected, and according to some tests under Windows Intel lost most performance after bios/software mitigation fix, Linux might be another story but I guess situation would be similar to Windows.
After this find by Virustotal, I personally might give up the consideration of second-hand rig from Intel which were before Cometlake......

 

[beginner99]

So, this working Spectre exploit, means that three-plus-year-old Intel platforms, now truely are "unsafe at any speed", unless they've been BIOS-patched?

Fun times ahead. Do you think corporate ITs mass-patch laptop bioses? Hint: they don't.

 

[DrMrLordX]

If there is a toolkit with a working exploit, it wont be long until malware has them, assuming there isnt already malware with it.

Yup! Only a matter of time. One should assume state actors and some independent hacking groups already have these capabilities for targeted attacks.

So, this working Spectre exploit, means that three-plus-year-old Intel platforms, now truely are "unsafe at any speed", unless they've been BIOS-patched?

Yyyyyup

All those Skylake-SP shops that haven't updated already and are running with mitigations disabled for performance reasons should be sweating right about now.

 

[coercitiv]

Oh dear, even the ring inter-connect isn't safe anymore.

 

[DrMrLordX]

Oh dear, even the ring inter-connect isn't safe anymore.

That's truly arcane. Intel seems to think that "best practices" can prevent the exploit from ever being an issue. Hmm! Sounds like it's something they can't patch out on their ring-based CPUs.

 

[moinmoin]

How long until Intel's mesh interconnect is also found to be unsafe? This is ridiculous. I guess Intel "innovations" need to be considered unsafe until proven otherwise.

 

[Fanatical Meat]

How much of a threat is this ring vulnerability to a typical user?

 

[DrMrLordX]

How long until Intel's mesh interconnect is also found to be unsafe?

The mesh shouldn't suffer from bus contention issues, I wouldn't think.

How much of a threat is this ring vulnerability to a typical user?

Unknown. Ring-based CPUs are exclusively outside of the workstation/server sector, so if anyone bothers to produce an exploit, it'll be targeted at corporate users and/or home users. Based on Spectre, it should be 2-3 years before any exploits show up in the wild.

 

[cortexa99]

I'm not engineer and don't know how critical this Ring vulnerability is, but it sounds like it only affect Intel because of Ring. Is it fixable via bios update? Don't tell me this would lead to some other bit of performance lost......