Intel processor security flaw requires OS kernel level fix

[kalniel]

OK so want to know how a pre-westmere i7 950 behaves with an 850 evo SSD?

Games: Not a spot of difference.
SSD benchmarks: random reads and writes are down 8-20% (seq figures varied too much to be used reliably).

Samsung magician
pre:
sq read: 3712 MB/s
sq write: 3485
rn read: 86k IOPS
rn write: 51k IOPS
post:
sq read: 3359 MB/s
sq write: 3212
rn read: 78k IOPS
rn write: 47k IOPS

Crystal disk mark:
pre
sq read 2163 MB/s
sq write 4476
rn 512K read 2200
rn 512K write 4036
rn 4k read 421.5
rn 4k write 243.6
rn 4k qd32 read 409.7
rn 4k qd32 write 230.1
post
sq read 3047 MB/s
sq write 4342
rn 512K read 2885
rn 512K write 3905
rn 4k read 336.6
rn 4k write 206.6
rn 4k qd32 read 324.2.7
rn 4k qd32 write 197.8

Firestrike normal:
pre
10479
g:13319
p:9553
combined: 4272
post
10481
g:13320
p:9582
combined: 4266

ROTTR:
pre
overall 78.85 fps
post
overall 79.61 fps

[DanceswithUnix]

Out of order execution was first featured in Pentium Pro, and subsequently the Pentium II and its successors.

AMD K5 was OoO, but I think I threw mine out in the last house move so can't test if it was vulnerable
Not sure how much speculation there was in that old chip though, which sounds more important here.

[Strawb77]

It probably explains why the intel ceo sold 11 million in shares just last month....https://www.nystocknews.com/2017/12/...poration-intc/

mm- looks like he did know about it..

http://uk.businessinsider.com/intel-ceo-krzanich-sold-shares-after-company-was-informed-of-chip-flaw-2018-1

[watercooled]

CD's take on this, FWIW: https://semiaccurate.com/2018/01/04/...s-marketshare/

[outwar6010]

There's a Youtube video giving some before & after benchmarks following the emergency Windows patch:



Edit!

As they mention in the video, they don't look at server loads in their assessment, but I think that won't be too much of a concern for most people on this Forum...

People are expecting bigger differences in the full fix.

[outwar6010]

https://security-center.intel.com/ad...nguageid=en-fr

Intel have released a list of affected processors

Intel® Core™ i3 processor (45nm and 32nm)
Intel® Core™ i5 processor (45nm and 32nm)
Intel® Core™ i7 processor (45nm and 32nm)
Intel® Core™ M processor family (45nm and 32nm)
2nd generation Intel® Core™ processors
3rd generation Intel® Core™ processors
4th generation Intel® Core™ processors
5th generation Intel® Core™ processors
6th generation Intel® Core™ processors
7th generation Intel® Core™ processors
8th generation Intel® Core™ processors
Intel® Core™ X-series Processor Family for Intel® X99 platforms
Intel® Core™ X-series Processor Family for Intel® X299 platforms
Intel® Xeon® processor 3400 series
Intel® Xeon® processor 3600 series
Intel® Xeon® processor 5500 series
Intel® Xeon® processor 5600 series
Intel® Xeon® processor 6500 series
Intel® Xeon® processor 7500 series
Intel® Xeon® Processor E3 Family
Intel® Xeon® Processor E3 v2 Family
Intel® Xeon® Processor E3 v3 Family
Intel® Xeon® Processor E3 v4 Family
Intel® Xeon® Processor E3 v5 Family
Intel® Xeon® Processor E3 v6 Family
Intel® Xeon® Processor E5 Family
Intel® Xeon® Processor E5 v2 Family
Intel® Xeon® Processor E5 v3 Family
Intel® Xeon® Processor E5 v4 Family
Intel® Xeon® Processor E7 Family
Intel® Xeon® Processor E7 v2 Family
Intel® Xeon® Processor E7 v3 Family
Intel® Xeon® Processor E7 v4 Family
Intel® Xeon® Processor Scalable Family
Intel® Xeon Phi™ Processor 3200, 5200, 7200 Series
Intel® Atom™ Processor C Series
Intel® Atom™ Processor E Series
Intel® Atom™ Processor A Series
Intel® Atom™ Processor x3 Series
Intel® Atom™ Processor Z Series
Intel® Celeron® Processor J Series
Intel® Celeron® Processor N Series
Intel® Pentium® Processor J Series
Intel® Pentium® Processor N Series

[adidan]

Great it looks like my piece o'junk netbook is fine.

Maybe i'll dig it out of the drawer, not sure its performance could get worse though

[Corky34]

People are expecting bigger differences in the full fix.

I guess they're expecting the difference in the wrong direction, the performance impact, what little there is for the majority of workloads, is only going to become less, not more, as further mitigation techniques are rolled out, the most basic fix (afaik) simply flushes the processors local memory whenever a context switch happens so there's a delay as the memory is repopulated, that delay is (afaik) already being mitigated via various techniques so any performance impacts that we're currently seeing will only decrease overtime.

[watercooled]

I guess they're expecting the difference in the wrong direction, the performance impact, what little there is for the majority of workloads, is only going to become less, not more, as further mitigation techniques are rolled out, the most basic fix (afaik) simply flushes the processors local memory whenever a context switch happens so there's a delay as the memory is repopulated, that delay is (afaik) already being mitigated via various techniques so any performance impacts that we're currently seeing will only decrease overtime.

That was my understanding of it too. It already is a 'full fix' and one which hasn't had time to be well-optimised for performance.

[watercooled]

Now that some benchmarks are appearing, does anyone know for sure whether MS pushed the update to AMD systems (and unaffected Intel systems like Gen 1 Atom)?

[adidan]

No idea but I would imagine it's easier to roll out to all. W7 had it in a monthly roundup anyway so i'm not sure how it would not go to every machine.

[watercooled]

The update covering it would, but it being enabled is simply a case of detecting the CPU and setting a registry flag, just like how it's possible to manually disable it after the update.

[satrow]

Now that some benchmarks are appearing, does anyone know for sure whether MS pushed the update to AMD systems (and unaffected Intel systems like Gen 1 Atom)?

Some W7 PCs, all on AMD, have rebooted to 0xC4 BSODs after the Monthly Rollup KB 4056894.

[watercooled]

What antivirus are you using? Apparently some are incompatible with this patch.

[satrow]

I'm not using any but neither am I running any AMDs.

Here are some reports, though it looks like MS have dropped pushing that patch.

[MrJim]

Just seen a further video by Hardware Unboxed which looks at BIOS updates from Asus relating to the security flaws. Not good news for SSD performance:



Seems that Asus are quick off the mark with BIOS updates for their current motherboards. I'm quite worried that their older motherboards will be left without BIOS level updates - I have a five year old Asus P8Z77-V motherboard, and I can't see Asus providing a BIOS update for that.