Intel vulnerabilities discovered

[Head_on_a_Stick]

Yet more evidence that Intel are a bunch of clueless clowns: https://www.intel.com/content/www/us/en ... 00314.html

And Phoronix have noted a 58% performance hit for the Haswell generation when the patches are applied:

https://www.phoronix.com/scan.php?page= ... l-gen7-hit

FFS...

Security tracker: https://security-tracker.debian.org/tra ... 2019-14615

[neuraleskimo]

Yet more evidence that Intel are a bunch of clueless clowns: https://www.intel.com/content/www/us/en ... 00314.html

And Phoronix have noted a 58% performance hit for the Haswell generation when the patches are applied:

https://www.phoronix.com/scan.php?page= ... l-gen7-hit

Security tracker: https://security-tracker.debian.org/tra ... 2019-14615

I saw that. Disappointing is probably the best I can say. So far AMD has fared better, but what is your opinion of whether AMD is really doing better security or simply has other yet to be discovered bugs?

[Head_on_a_Stick]

what is your opinion of whether AMD is really doing better security or simply has other yet to be discovered bugs?

Well I'm no expert on the subject but the kernel developers seem to think AMD is a better option. From my (2nd generation) Ryzen laptop:

Code: Select all

empty@E485:~ $ grep -R . /sys/devices/system/cpu/vulnerabilities
/sys/devices/system/cpu/vulnerabilities/spectre_v2:Mitigation: Full AMD retpoline, IBPB: conditional, STIBP: disabled, RSB filling
/sys/devices/system/cpu/vulnerabilities/itlb_multihit:Not affected
/sys/devices/system/cpu/vulnerabilities/mds:Not affected
/sys/devices/system/cpu/vulnerabilities/l1tf:Not affected
/sys/devices/system/cpu/vulnerabilities/spec_store_bypass:Mitigation: Speculative Store Bypass disabled via prctl and seccomp
/sys/devices/system/cpu/vulnerabilities/tsx_async_abort:Not affected
/sys/devices/system/cpu/vulnerabilities/spectre_v1:Mitigation: usercopy/swapgs barriers and __user pointer sanitization
/sys/devices/system/cpu/vulnerabilities/meltdown:Not affected
empty@E485:~ $

An Intel system wouldn't have as many "not affected" results.

Probably still worth disabling SMT for security-critical systems though, even for AMD. That's what OpenBSD does.

[neuraleskimo]

Well I'm no expert on the subject...

Maybe, but I still put some stock on your opinions.

Probably still worth disabling SMT for security-critical systems though, even for AMD. That's what OpenBSD does.

Agreed and good point. Plus for math-heavy code, disabling SMT can (and usually will) increase throughput (which is why I disable SMT).

[CwF]

Code: Select all

~#  grep -R . /sys/devices/system/cpu/vulnerabilities
/sys/devices/system/cpu/vulnerabilities/spectre_v2:Mitigation: Full generic retpoline, STIBP: disabled, RSB filling
/sys/devices/system/cpu/vulnerabilities/mds:Vulnerable: Clear CPU buffers attempted, no microcode; SMT disabled
/sys/devices/system/cpu/vulnerabilities/l1tf:Mitigation: PTE Inversion; VMX: conditional cache flushes, SMT disabled
/sys/devices/system/cpu/vulnerabilities/spec_store_bypass:Vulnerable
/sys/devices/system/cpu/vulnerabilities/spectre_v1:Mitigation: usercopy/swapgs barriers and __user pointer sanitization
/sys/devices/system/cpu/vulnerabilities/meltdown:Mitigation: PTI

OMG! No worries. I'm more concerned with execution across numa zones, socket to socket latency and the like. I think I can rely on Intel's quote "elevated privilege local user".

[Head_on_a_Stick]

https://cacheoutattack.com/

If I made a new thread for each new vulnerability the forums would be full of them so I'll just start appending them here...

[CwF]

https://software.intel.com/security-sof ... n-sampling

[Head_on_a_Stick]

A vulnerability has been found in the ROM of the Intel Converged Security and Management Engine (CSME):

http://blog.ptsecurity.com/2020/03/inte ... trust.html

The problem is not only that it is impossible to fix firmware errors that are hard-coded in the Mask ROM of microprocessors and chipsets. The larger worry is that, because this vulnerability allows a compromise at the hardware level, it destroys the chain of trust for the platform as a whole.

CVE-2019-0090

^ That name of the CVE shows that Intel have known about this since last year...

Debian bug tracker: https://security-tracker.debian.org/tra ... -2019-0090

No mitigations yet.

[Hallvor]

Not good, but doesn't it require physical access?

[Head_on_a_Stick]

doesn't it require physical access?

That's right, yes.

[Head_on_a_Stick]

Load Value Injection

More side-channel madness from everybody's favourite crappy CPU manufacturer, yay!

https://software.intel.com/security-sof ... -injection

https://cve.mitre.org/cgi-bin/cvename.c ... -2020-0551

Intel users should brace themselves for a substantial and significant performance hit once the new mitigations (not fixes) are rolled out.

[Head_on_a_Stick]

V0LTpwn: Attacking x86 Processor Integrity from Software

The exploit leverages Intel's so-called software guard extensions (SGX) and undervolting to change the results of computations and so allow remote code execution.

CVE: https://nvd.nist.gov/vuln/detail/CVE-2019-11157

Intel's advisory: https://www.intel.com/content/www/us/en ... 00289.html

[LE_746F6D617A7A69]

I'm not an Intel/AMD fan - in fact, if it would be up to Me, I would forbid to use x86 opcodes at all - this architecture is flawed since the very beginning -> but, to be honest, the bugs mentioned here are nothing but bullshits -> the attacks are possible only if You have a Root privileges -> so You can do just *everything*, no matter if there are some CPU vulnerabilities or not..
Of course, such security holes are important to know, but with all the respect to You, HOAS, they are not going to be exploitable under normal conditions ...
(sorry, but I'm trying to be objective: both AMD and Intel sucks in the same way/on the same level... - and I've just bought the another Ryzen 3700X , knowing all of this... )

EDIT:
I've realised, that My last sentence can be considered as an advertisement - it's not -> Ryzens have their own problems, although it may seem not so obvious...

[Deb-fan]

Don't like Intel or Amd ? So basically you don't approve of systems with a cpu then? Lol ... Kidding but not like there are very many options. Long been very vocal about thinking the side channel issues are way over blown. Just in my view they are only more YAT's ... (Yet another threat's.) With plenty others of far greater concern to computer users. Especially for personal computers/users. In context of commercial/production tech(depending), would consider them more of a potential threat. In some Enterprise tech scenarios, mitigation would have to be mandatory.

Have also expressed an interest in pinning or rolling back microcode to avoid performance impacts brought by the mitigations or attempted fixes. Anyone doing such? Personally have been custom compiling kernels for several years, I compile out support for many of these side channel deals on my personal computers.

PS, most dire threat faced by computers everywhere, the USERS, pebcak incidents, ... It's a particularly hard threat to mitigate too.

[johnbeck7799]

Yet more evidence that Intel are a bunch of clueless clowns: https://www.intel.com/content/www/us/en ... 00314.html

And Phoronix have noted a 58% performance hit for the Haswell generation when the patches are applied:

https://cuteplushies.net/

FFS...

Security tracker: https://security-tracker.debian.org/tra ... 2019-14615

what is your opinion of whether AMD is really doing better security or simply has other yet to be discovered bugs?