Posted on 01/03/2018 1:55:39 PM PST by Red Badger
Highly unlikely.
More like BK, the current CEO tried to ignore it.
The guy is from the Fab and only knows process issues (similar to Craig Barrett)
Not a clue about employees, customers and or quality.
All about the bottom line.
Getting BK fired would be the first good thing that has happened at Intel since he took over.
Corporate servers can’t afford the delay to fix, or the slowness if fixed. Watch them switch to AMD and IBM Power servers quickly. Buy AMD and IBM stock?
Nothing to see. It’s just the NSA opening up your backdoor.
Ping...
Back in the 80’s I had an IBM XT clone that had a ‘Turbo Boost’ button on the front.
I think all it did was turn on a light..................
Pfffttt...this is nothing compared to Apple slowing mobile devices with aging batteries a tiny bit to avoid sudden unexpected system shutdowns then offering nearly free battery replacements on your four year old phone.
Let’s keep some perspective here, people.
My experience with H1Bs is that they don't have any ethic for excellence. Their ethic is based on "good enough" or "slip one by". It is an ethos ingrained in them since childhood.
They take pride in their ability to "get over" and slide through life. Unless someone is looking over their shoulders, you can bet the task with be accomplished will minimal thought and care.
Until I see more info I’m skeptical. This could be nothing more than a timing delay when attempting to access certain kernel memory locations. The fact that there is no demonstrable exploit code makes me think it is just theoretical.
ditto and ditto
Now that it is ‘known’ there will be those who will exploit it................
From the Register article:
It appears, from what AMD software engineer Tom Lendacky was suggesting above, that Intel's CPUs speculatively execute code potentially without performing security checks. It seems it may be possible to craft software in such a way that the processor starts executing an instruction that would normally be blocked such as reading kernel memory from user mode and completes that instruction before the privilege level check occurs.That would allow ring-3-level user code to read ring-0-level kernel data. And that is not good.
Ah
The 0bama chip
It has already been demonstrated that small chunks of Ring 0 memory can be returned to user mode code.
AMD running Linux here, yay
“It has already been demonstrated that small chunks of Ring 0 memory can be returned to user mode code.”
Sure, but can you fetch a bigger, more meaningful chunk of kernel memory? Sure, if you increment the same small thing thousands of times over and over.
I thought you need physical access to the machine to exploit this.
more detailed technical information:
https://www.theregister.co.uk/2018/01/02/intel_cpu_design_flaw/
This is a BFD, WFT, are you kidding me moment.
Software “fix” will slow down every Intel PC by 17%-23%
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.