Recent Topics
Lubricant Additives - A Practical Guide
by wemay. 09/24/18 01:39 PM
Fram Ultra--Any Real Competition?
by IndyFan. 09/24/18 12:59 PM
Used generator price.
by Eddie. 09/24/18 11:55 AM
More energy concerns about Bitcoin
by OVERKILL. 09/24/18 10:01 AM
Soot loading from DI engines - Size of particles
by StevieC. 09/24/18 09:58 AM
New TV bad picture some channels
by raaizin. 09/24/18 09:35 AM
Crown Victoria HVAC repair
by emmett442. 09/24/18 08:44 AM
2007 Toyota Camry LE Alternator
by maverickfhs. 09/24/18 08:28 AM
AutoSense drying not drying
by Ifixyawata. 09/24/18 08:23 AM
Time for a new Generator... Wisdom desired!
by webfors. 09/24/18 06:36 AM
flat roof weight bearing support
by henni. 09/24/18 06:29 AM
ADD A MARBLE - Make Life Easier
by MasterSolenoid. 09/24/18 06:17 AM
Mobile 1 ESP @ Dowler Karn St. Thomas Ont
by RogerBacon. 09/24/18 05:40 AM
Mobile 1 ESP @ Dowler Karn St. Thomas Ont.
by RogerBacon. 09/24/18 05:37 AM
Newest Members
albert001, LG_Electronics, TCam, OzFrog, Kursk
66062 Registered Users
Who's Online Now
88 registered members (2010Civic, advocate, aquariuscsm, Astro14, ad244, 6 invisible), 1,867 guests, and 35 spiders.
Key: Admin, Global Mod, Mod
Forum Statistics
Forums67
Topics290,944
Posts4,852,974
Members66,062
Most Online3,590
Jan 24th, 2017
Donate to BITOG
Previous Thread
Next Thread
Print Thread
Hop To
Page 1 of 4 1 2 3 4
Intel processor bug #4622759
01/03/18 02:33 PM
01/03/18 02:33 PM
Joined: Jun 2003
Posts: 5,921
Illinois
SHOZ Offline OP
SHOZ  Offline OP
Joined: Jun 2003
Posts: 5,921
Illinois
Says any Intel processors made in the last decade is vulnerable.

Python Sweetness

The mysterious case of the Linux Page Table Isolation patches The mysterious case of the Linux Page Table Isolation patches

[Various errors and updates are addressed in Quiet in the peanut gallery]

tl;dr: there is presently an embargoed security bug impacting apparently all contemporary CPU architectures that implement virtual memory, requiring hardware changes to fully resolve. Urgent development of a software mitigation is being done in the open and recently landed in the Linux kernel, and a similar mitigation began appearing in NT kernels in November. In the worst case the software fix causes huge slowdowns in typical workloads. There are hints the attack impacts common virtualization environments including Amazon EC2 and Google Compute Engine, and additional hints the exact attack may involve a new variant of Rowhammer.



2008 Hyundai Accent 1.6L 5 sp manual hatchback
2010 Hyundai Genesis Coupe Track 2L Turbo 6sp manual
Re: Intel processor bug [Re: SHOZ] #4622806
01/03/18 03:18 PM
01/03/18 03:18 PM
Joined: Apr 2008
Posts: 37,186
Ontario, Canada
OVERKILL Offline
OVERKILL  Offline
Joined: Apr 2008
Posts: 37,186
Ontario, Canada
I see the updated errata states "may not affect AMD CPU's". I guess we wait for further clarification?


2018 RAM 1500 Big Horn EcoDiesel
2016 Grand Cherokee SRT
Re: Intel processor bug [Re: OVERKILL] #4622816
01/03/18 03:29 PM
01/03/18 03:29 PM
Joined: Mar 2004
Posts: 20,758
Upstate NY
Donald Offline
Donald  Offline
Joined: Mar 2004
Posts: 20,758
Upstate NY
Originally Posted By: OVERKILL
I see the updated errata states "may not affect AMD CPU's". I guess we wait for further clarification?


But will they put these checks in software and check processor or just do the checks regardless.


2015 Subaru Forester 2.5 engine/CVT
2015 Ford F250 w/Powerstroke
2016 Subaru Crosstrek CVT (wife's)
Re: Intel processor bug [Re: SHOZ] #4622844
01/03/18 03:55 PM
01/03/18 03:55 PM
Joined: Apr 2008
Posts: 37,186
Ontario, Canada
OVERKILL Offline
OVERKILL  Offline
Joined: Apr 2008
Posts: 37,186
Ontario, Canada
For more detail on the software-side of things, specifically how it is being addressed in Linux, there's a nice thread on the Kernel Developers Mailing list found here . A gentleman from AMD chimes in in another thread indicating that AMD processors aren't susceptible to this bug and asks for their processors to be omitted from the patch. One of the dev's responds indicating that omission may not be a good idea, as not being affected by this bug doesn't mean that future exploits that are similar in nature will except AMD CPU's. Be interesting to see what that officially evolves into.

The biggest issue aside from the vulnerability itself seems to be the performance impact of the patches shrug

Will be interesting to see what, if anything, Intel has to say on the matter.


2018 RAM 1500 Big Horn EcoDiesel
2016 Grand Cherokee SRT
Re: Intel processor bug [Re: SHOZ] #4622855
01/03/18 04:10 PM
01/03/18 04:10 PM
Joined: Sep 2011
Posts: 3,322
Somewhere
itguy08 Offline
itguy08  Offline
Joined: Sep 2011
Posts: 3,322
Somewhere
AMD is on the record as saying their CPUs are not vulnerable.

Intel is in damage control mode:
https://www.barrons.com/articles/intel-r...&yptr=yahoo

Hopefully this will reduce their clout tremendously.

Re: Intel processor bug [Re: SHOZ] #4622860
01/03/18 04:16 PM
01/03/18 04:16 PM
Joined: Mar 2013
Posts: 4,784
The Midwest
skyactiv Offline
skyactiv  Offline
Joined: Mar 2013
Posts: 4,784
The Midwest
I had an old Compaq desktop with an AMD Sempron processor that ran 32 bit Linux distros much faster/better than my Gateway gaming desktop that had an Intel Q6600 CPU. Windows was much faster on the Intel chip however.


Wife: 15' Audi A4 quattro 6 speed manual
Me: 13' VW GTI 3 door 6 speed manual
Re: Intel processor bug [Re: SHOZ] #4622866
01/03/18 04:23 PM
01/03/18 04:23 PM
Joined: Sep 2011
Posts: 3,322
Somewhere
itguy08 Offline
itguy08  Offline
Joined: Sep 2011
Posts: 3,322
Somewhere
The latest AMD Stuff is freakin' awesome. Built a Ryzen 7 1700 system and it flies. Load up a few VM's and it doesn't know they are there.

EPYC is using less power and killing it in high performance workloads and in datacener type stuff.

Re: Intel processor bug [Re: SHOZ] #4622901
01/03/18 04:58 PM
01/03/18 04:58 PM
Joined: Apr 2017
Posts: 429
Utah, USA
28oz Offline
28oz  Offline
Joined: Apr 2017
Posts: 429
Utah, USA
Haven't built an Intel based system in probably 15 years. Everything has been AMD. For the price/performance ratio, it's hard to beat AMD.


-----------------
1990 Nissan 300zx - Castrol Edge Euro 0W-40
2004 Nissan Quest - Pennzoil Platinum Euro 0W-40
2003 Ford Excursion 7.3 PSD - Mobil 1 TDT 5w-40
Re: Intel processor bug [Re: SHOZ] #4622951
01/03/18 06:01 PM
01/03/18 06:01 PM
Joined: Aug 2008
Posts: 3,168
USA
Reddy45 Offline
Reddy45  Offline
Joined: Aug 2008
Posts: 3,168
USA
I'm a big Intel fan but it wouldn't hurt for any opportunity to either level out the competition between the 2 majors, or to get a 3rd or 4th company in the mix. I HATE duopoly situations.

Re: Intel processor bug [Re: Reddy45] #4622956
01/03/18 06:09 PM
01/03/18 06:09 PM
Joined: Apr 2008
Posts: 37,186
Ontario, Canada
OVERKILL Offline
OVERKILL  Offline
Joined: Apr 2008
Posts: 37,186
Ontario, Canada
Originally Posted By: Reddy45
I'm a big Intel fan but it wouldn't hurt for any opportunity to either level out the competition between the 2 majors, or to get a 3rd or 4th company in the mix. I HATE duopoly situations.


There used to be Cyrix, LOL!


2018 RAM 1500 Big Horn EcoDiesel
2016 Grand Cherokee SRT
Re: Intel processor bug [Re: itguy08] #4622958
01/03/18 06:11 PM
01/03/18 06:11 PM
Joined: Apr 2008
Posts: 37,186
Ontario, Canada
OVERKILL Offline
OVERKILL  Offline
Joined: Apr 2008
Posts: 37,186
Ontario, Canada
Originally Posted By: itguy08
AMD is on the record as saying their CPUs are not vulnerable.

Intel is in damage control mode:
https://www.barrons.com/articles/intel-r...&yptr=yahoo

Hopefully this will reduce their clout tremendously.


Yes, I mentioned that above. One of the guys from AMD chimes in about it in the Kernel dev mailing list.

I'll quote him here for the sake of clarity:

Originally Posted By: Tom Lendacky

AMD processors are not subject to the types of attacks that the kernel
page table isolation feature protects against. The AMD microarchitecture
does not allow memory references, including speculative references, that
access higher privileged data when running in a lesser privileged mode
when that access would result in a page fault.

Disable page table isolation by default on AMD processors by not setting
the X86_BUG_CPU_INSECURE feature, which controls whether X86_FEATURE_PTI
is set.

Signed-off-by: Tom Lendacky <[email protected]>


From HERE.


2018 RAM 1500 Big Horn EcoDiesel
2016 Grand Cherokee SRT
Re: Intel processor bug [Re: SHOZ] #4622966
01/03/18 06:19 PM
01/03/18 06:19 PM
Joined: Mar 2016
Posts: 1,351
toronto
PeterPolyol Offline
PeterPolyol  Offline
Joined: Mar 2016
Posts: 1,351
toronto
Why am I not surprised about a fundamental hardware level security 'defect' from Intel specifically? :eyesroll:

Re: Intel processor bug [Re: PeterPolyol] #4622981
01/03/18 06:34 PM
01/03/18 06:34 PM
Joined: Apr 2008
Posts: 37,186
Ontario, Canada
OVERKILL Offline
OVERKILL  Offline
Joined: Apr 2008
Posts: 37,186
Ontario, Canada
Originally Posted By: PeterPolyol
Why am I not surprised about a fundamental hardware level security 'defect' from Intel specifically? :eyesroll:


It may also affect ARM. I'm waiting for further details to emerge before I cast judgement on Intel.


2018 RAM 1500 Big Horn EcoDiesel
2016 Grand Cherokee SRT
Re: Intel processor bug [Re: OVERKILL] #4622982
01/03/18 06:34 PM
01/03/18 06:34 PM
Joined: Mar 2009
Posts: 2,625
Cedarbrae, Ontario
xxch4osxx Offline
xxch4osxx  Offline
Joined: Mar 2009
Posts: 2,625
Cedarbrae, Ontario
Originally Posted By: OVERKILL
Originally Posted By: Reddy45
I'm a big Intel fan but it wouldn't hurt for any opportunity to either level out the competition between the 2 majors, or to get a 3rd or 4th company in the mix. I HATE duopoly situations.


There used to be Cyrix, LOL!
I had a 486DX2-80 Cyrix processor in one of my computers from back in the day. My buddies Intel 486DX2-66 was a faster system playing the same games. I'm an AMD user these days though.


2015 RAM SXT Crew Cab 5.7 with 6 speed tranny.

2008 Mazda 3 GS Sport Hatchback 5sp MT (Girlfriend's car)

Re: Intel processor bug [Re: OVERKILL] #4622986
01/03/18 06:38 PM
01/03/18 06:38 PM
Joined: Aug 2008
Posts: 3,168
USA
Reddy45 Offline
Reddy45  Offline
Joined: Aug 2008
Posts: 3,168
USA
Originally Posted By: OVERKILL
Originally Posted By: Reddy45
I'm a big Intel fan but it wouldn't hurt for any opportunity to either level out the competition between the 2 majors, or to get a 3rd or 4th company in the mix. I HATE duopoly situations.


There used to be Cyrix, LOL!



The very first PC our family bought back in the day had a Cyrix processor. Crazy to think how far we have come.

Page 1 of 4 1 2 3 4

BOB IS THE OIL GUY® Powered by UBB.threads™