Jump to content

My take on Intel refuse to patch the bug.

2 hours ago, DeadlyTitan said:

Well am sure it can be. I am an application developer and when something can be fixed via OS level patch then am sure as hell that it can be fixed with a microcode update. 

Application software development is a totally different game than system software development.

 

EDIT: I'm reading up on the KAISER whitepaper that was released. Something they mentioned is that x86 processors have a single TLB register that's shared between the high and low memory space, which OS developers tend to use for kernel and user space respectively. ARM has two TLB registers, one for each half and they believe because of this, ARM is not susceptible to the same attack.

 

This is a hardware issue. Microcode updates cannot fix this.

 

Quote
On modern Intel x86-64 processors, the top-level translation table is the page map level 4 (PML4). Its physical address is stored in the CR3 register of the CPU. The PML4 divides the 48-bit virtual address space into 512 PML4 entries, each covering a memory region of 512 GB. Each subsequent level sub-divides one block of the upper layer into 512 smaller regions until 4 kB pages are mapped using page tables (PTs) on the last level. The CPU has multiple levels of caches for address translation table entries, the so-called TLBs. They speed up address translation and privilege checks. The kernel address space is typically a defined region in the virtual address space, e.g., the upper half of the address space.
 
Similar translation tables exist on modern ARM (Cortex-A) processors too, with small differences in size and property bits. One significant difference to x86-64 is that ARM CPUs have two registers to store physical addresses of translation tables (TTBR0 and TTBR1). Typically, one is used to map the user address space (lower half) whereas the other is used to map the kernel address space (upper half). Gruss et al. [6] speculated that this might be one of the reasons why the attack does not work on ARM processors.

 

Edited by M.Yurizaki
Link to comment
Share on other sites

Link to post
Share on other sites

15 minutes ago, johnukguy said:

Though it's still retailing at just under $300 if you ever decided to sell the CPU. 

Yeah, got it for 130cad/100usd with a nice mini and waterblock, it'll be going into a gift workstation pc soon.

Want to custom loop?  Ask me more if you are curious

 

Link to comment
Share on other sites

Link to post
Share on other sites

1 minute ago, Damascus said:

Yeah, got it for 130cad/100usd with a nice mini and waterblock, it'll be going into a gift workstation pc soon.

That's actually a pretty sweet deal. Where do you find deals like that in Canada? 

Link to comment
Share on other sites

Link to post
Share on other sites

Becuase of the nature of this HARDWARE issue, the kernal behavior needed to be changed to address it, not firmware.

Come Bloody Angel

Break off your chains

And look what I've found in the dirt.

 

Pale battered body

Seems she was struggling

Something is wrong with this world.

 

Fierce Bloody Angel

The blood is on your hands

Why did you come to this world?

 

Everybody turns to dust.

 

Everybody turns to dust.

 

The blood is on your hands.

 

The blood is on your hands!

 

Pyo.

Link to comment
Share on other sites

Link to post
Share on other sites

2 hours ago, Droidbot said:

Mostly I/O and Memory based tasks. 

 

IO is by far where it hits the hardest. 

So for users using eGPUs with Thunderbolt 3 docks, that would drastically hinder performance.

Main Gaming PC (new): HP Omen 30L || i9 10850K || RTX 3070 || 512GB WD Blue NVME || 2TB HDD, 4TB HDD, 8TB HDD ||  750W P2 ||  16GB HyperX Black DDR4

Main Gaming PC (old, still own) : Intel Core i7 7700K @5.0Ghz || GPU: GTX 1080 Seahawk EK X || Motherboard: Maximus VIII Impact || Case: Fractal Design Define Nano S || RAM : 32GB Corsair Vengeance LPX 

Cooling: EK XRES D5 100mm || Alphacool ST30 280mm w/ Vardars || Alphacool ST30 240mm w/ Vardars || Swiftech 3/8 x 1/2'' Lok-Seal Compressions || Swiftech EVGA Hydrocopper Block || Primochill Advanced LRT Orange || Distilled Water

Folding@Home Rig: 2x X5690s @4.6Ghz || GPUs: 2x Radeon HD 7990 || Motherboard: EVGA SR-2 || Case: Corsair 900D || RAM: 48GB Corsair Dominator GT 2000Mhz CL9

Ethereum Mining Rig: Pentium G4400 || Gigabyte Z170X-UD5 TH || 2x GTX 1060s (Samsung & Hynix) 1x GTX 1070 (Micron), 2x RX480s BIOS modded (Samsung), 1x R9 290X 8GB, 1x GTX 1660 Super = ~ 195 Mh/s

Peripherals: 3x U2412M (5760x1200), 1x U3011 (2560x1600) || Logitech G710 (Cherry Blues) || Logitech G600 || Brainwavz HM5 with @Gofspar Mod 

Laptop: Dell XPS 15 || "Infinity Edge" 4K IPS Screen || i7 7700HQ || GTX 1050 || 16GB 2400Mhz RAM 

 

Link to comment
Share on other sites

Link to post
Share on other sites

2 minutes ago, arnavvr said:

So for users using eGPUs with Thunderbolt 3 docks, that would drastically hinder performance.

No, I'm talking about IO as in storage. Unless that's not what you meant. It's 5:30AM. Help. 

idk

Link to comment
Share on other sites

Link to post
Share on other sites

Just now, Droidbot said:

No, I'm talking about IO as in storage. Unless that's not what you meant. It's 5:30AM. Help. 

Wouldn't the Thunderbolt bus also be considered I/O? 

Main Gaming PC (new): HP Omen 30L || i9 10850K || RTX 3070 || 512GB WD Blue NVME || 2TB HDD, 4TB HDD, 8TB HDD ||  750W P2 ||  16GB HyperX Black DDR4

Main Gaming PC (old, still own) : Intel Core i7 7700K @5.0Ghz || GPU: GTX 1080 Seahawk EK X || Motherboard: Maximus VIII Impact || Case: Fractal Design Define Nano S || RAM : 32GB Corsair Vengeance LPX 

Cooling: EK XRES D5 100mm || Alphacool ST30 280mm w/ Vardars || Alphacool ST30 240mm w/ Vardars || Swiftech 3/8 x 1/2'' Lok-Seal Compressions || Swiftech EVGA Hydrocopper Block || Primochill Advanced LRT Orange || Distilled Water

Folding@Home Rig: 2x X5690s @4.6Ghz || GPUs: 2x Radeon HD 7990 || Motherboard: EVGA SR-2 || Case: Corsair 900D || RAM: 48GB Corsair Dominator GT 2000Mhz CL9

Ethereum Mining Rig: Pentium G4400 || Gigabyte Z170X-UD5 TH || 2x GTX 1060s (Samsung & Hynix) 1x GTX 1070 (Micron), 2x RX480s BIOS modded (Samsung), 1x R9 290X 8GB, 1x GTX 1660 Super = ~ 195 Mh/s

Peripherals: 3x U2412M (5760x1200), 1x U3011 (2560x1600) || Logitech G710 (Cherry Blues) || Logitech G600 || Brainwavz HM5 with @Gofspar Mod 

Laptop: Dell XPS 15 || "Infinity Edge" 4K IPS Screen || i7 7700HQ || GTX 1050 || 16GB 2400Mhz RAM 

 

Link to comment
Share on other sites

Link to post
Share on other sites

1 minute ago, arnavvr said:

Wouldn't the Thunderbolt bus also be considered I/O? 

Theoretically on some machines if the kernel patch makes more overhead for PCI-E NVMe devices during IO transactions it could impact TB3 if it's connected to the PCH. 

 

That's it, really. Otherwise it's just connected to the PCI-E CPU lanes. 

idk

Link to comment
Share on other sites

Link to post
Share on other sites

50 minutes ago, johnukguy said:

That's actually a pretty sweet deal. Where do you find deals like that in Canada? 

Kijiji :) I was just browsing around and it seems that in Toronto and Ottawa that's a pretty common price.

 

Mobos a p55 ftw sli and the block is an lga 775 dietek one

Want to custom loop?  Ask me more if you are curious

 

Link to comment
Share on other sites

Link to post
Share on other sites

1 minute ago, Damascus said:

Kijiji :) I was just browsing around and it seems that in Toronto and Ottawa that's a pretty common price.

 

Mobos a p55 ftw sli and the block is an lga 775 dietek one

Aha! Now this is very handy. Thank you.

Link to comment
Share on other sites

Link to post
Share on other sites

What exact processors are affected, is this goes back to even  Sandy Bridge EP?

Link to comment
Share on other sites

Link to post
Share on other sites

GAH! I don't wanna update my OS again! Sierra gave my late 2012 mbp so much performance (I wasn't expecting it after incremental slow-downs from previous updates)... faster response times and quicker loading and everything! Felt like a new system almost. I fear it will be back to the old sluggishness once I update. It is always such a gamble which is why I stopped caring about updates. Now I will be forced and that sucks!>:(>:(>:(

Folding stats

Vigilo Confido

 

Link to comment
Share on other sites

Link to post
Share on other sites

29 minutes ago, glubox said:

What exact processors are affected, is this goes back to even  Sandy Bridge EP?

It goes back to Pentium Pro that's 1995 that's a whole different century!

Link to comment
Share on other sites

Link to post
Share on other sites

I suggest everyone owning any intel hardware to sell ti fast on good price, before everyone learn the true. Later with the money we bye new chips without a bug.

Link to comment
Share on other sites

Link to post
Share on other sites

8 minutes ago, glubox said:

I suggest everyone owning any intel hardware to sell ti it fast on at good price, before everyone learn(s)? the true truth. Later with the money we bye buy new chips without a bug.

I'm a terrible human, forgive me master. 

Link to comment
Share on other sites

Link to post
Share on other sites

@Astrotek sorry for the poor language, I was in fury, write quickly, and last not native English language. But I personally just posted my very expensive personal (loved) workstation to our local equivalent to craigslist for sale. (Actually I will not approve any offer until I benchmark the performance hit).  

Link to comment
Share on other sites

Link to post
Share on other sites

12 minutes ago, glubox said:

@Astrotek sorry for the poor language, I was in fury, write quickly, and last not native English language. But I personally just posted my very expensive personal (loved) workstation to our local equivalent to craigslist for sale. (Actually I will not approve any offer until I benchmark the performance hit).  

You've got nothing to apologize for. I'm a little bored at work and pointed some of it at you. 

Link to comment
Share on other sites

Link to post
Share on other sites

2 hours ago, glubox said:

What exact processors are affected, is this goes back to even  Sandy Bridge EP?

Yes :(

 

EDIT ; sorry, didn't even see I wasn't on the last page ! xD

 

Edited by wkdpaul

If you need help with your forum account, please use the Forum Support form !

Link to comment
Share on other sites

Link to post
Share on other sites

2 hours ago, glubox said:

I suggest everyone owning any intel hardware to sell ti fast on good price, before everyone learn the true. Later with the money we bye new chips without a bug.

Wait, so it IS a hardware issue? And has intel been doing this since 1995? Do I really need to sell my CPU or can I just wait for a fix and live with the bad performance?

Link to comment
Share on other sites

Link to post
Share on other sites

7 hours ago, Droidbot said:

Screenshot_2018-01-03-13-16-06-951_com.emogoth.android.phone_mimi.png.d8db68ddf9920ef92e3424cc7d2ddf04.png

 

this is from /g/ and it sums it up pre well

OH BOY I'M SURE GLAD LINUS IS BACKPORTING THIS TO STABLE KERNELS OVER CHRISTMAS WITHOUT EVEN BEING ANGRY!

8700k @5.0GHz | Maximus X Hero | RAM 32GB @3200MHz CL14 | 1080 TI | SSD 250GB + 2x500GB Raid 0 | Monitor 1440p 165Hz ISP

Link to comment
Share on other sites

Link to post
Share on other sites

17 hours ago, DeadlyTitan said:

Well am sure it can be. I am an application developer and when something can be fixed via OS level patch then am sure as hell that it can be fixed with a microcode update. 

A BIOS level patch is very possible, however the logistics of it creating a bios update for 10 year old, outdated motherboards in which there are thousands of different models, and having the motherboard manufacturers rolling out BIOS level updates on hardware that has not been supported for years, then getting the headache of the average person to do them, is impossible. Thus the 'easy' way to do this is via OS Software updates and also much simpler, I'm not sure on this aspect but Rolling out OS software updates on supported OS's like windows 10, and leaving the XP/Vista/Windows7 people to die due to the lack of OS support is most likely. so patching the latest supported OS's is much much more simple and logistically sound. 

 

Thats my perspective.

 

Also from what i've seen on reports, the effect on gaming is zero. 

Link to comment
Share on other sites

Link to post
Share on other sites

If this exploit requires redesigns of the kernel for all major operating systems, would that same redesign also hinder performance on systems that wouldn't be affected by the exploit in the first place. For example when Microsoft  pushes out their update it will that kernel memory seperation affect AMD systems as well? Or will the fix detect what platform/vendor it is on?

~ Luc Luc

Link to comment
Share on other sites

Link to post
Share on other sites

It depends entirely on how MS implement it. Linux devs I think have accepted the change to the Kernel so that it doesn't hinder AMDs CPUs. 

 

Basically it's up to the OS provider.

Link to comment
Share on other sites

Link to post
Share on other sites

I've heard that AMD are contacting OS Devs and asking them not to, whether or not MS has agreed I can't be sure.

HEADS UP, THIS ACCOUNT IS INACTIVE NOW

I'm keeping everything else the way it was for anyone who might check out my answers in future, but I won't be using LTT.

 

 

 

 

Don't forget to quote me when replying to me!

Please explain your question fully, so I can answer it fully.

PSU Tier List Cooler Tier List SSD Tier List  My Specs Below!

Spoiler

My PC:

CPU: Ryzen 5 1600 @ 3.2GHz

Cooler: Stock Wraith Spire

RAM: G.Skill Trident Z RGB 3000mHz 16GB DDR4 (2x8GB) RGB

Motherboard: Asus ROG Strix X370-F Gaming ATX

SSD: Crucial MX500 500GB 2.5"

HDD: Western Digital Blue 1TB 7200rpm

GPU: Asus ROG Strix OC GTX 1060 6GB

Case: Cooler Master H500P

PSU: Corsair RM650i 650W 80+ Gold Fully Modular

OS: Windows 10 Home 64-bit

Fans: 4x Cooler Master Masterfan Pro 120 Air Balance

Spoiler

Potato Laptop (Samsung Series 5 Ultrabook, 2013):

CPU: Intel Ivy Bridge i5 3337U @ 1.8GHz

RAM: 8GB DDR3 2133mhz SODIMM (1x4GB Samsung, 1x4GB Kingston)

SSD: Kingston 24GB SSD (originally for caching)

HDD: HGST 500GB 5400rpm

GPU: Intel HD 4000 Graphics

OS: Windows 10 Home 64-bit

 

Link to comment
Share on other sites

Link to post
Share on other sites

AMD processors also have similar design flaws that needs the Patch, the difference is that Intel has it worse.

 

Intel kernel flaw opens door for both Meltdown and Spectre exploits while AMD chips only opens door for the Spectre exploit, either ways both needs fixing:

 

https://meltdownattack.com/

Personal Desktop":

CPU: Intel Core i7 10700K @5ghz |~| Cooling: bq! Dark Rock Pro 4 |~| MOBO: Gigabyte Z490UD ATX|~| RAM: 16gb DDR4 3333mhzCL16 G.Skill Trident Z |~| GPU: RX 6900XT Sapphire Nitro+ |~| PSU: Corsair TX650M 80Plus Gold |~| Boot:  SSD WD Green M.2 2280 240GB |~| Storage: 1x3TB HDD 7200rpm Seagate Barracuda + SanDisk Ultra 3D 1TB |~| Case: Fractal Design Meshify C Mini |~| Display: Toshiba UL7A 4K/60hz |~| OS: Windows 10 Pro.

Luna, the temporary Desktop:

CPU: AMD R9 7950XT  |~| Cooling: bq! Dark Rock 4 Pro |~| MOBO: Gigabyte Aorus Master |~| RAM: 32G Kingston HyperX |~| GPU: AMD Radeon RX 7900XTX (Reference) |~| PSU: Corsair HX1000 80+ Platinum |~| Windows Boot Drive: 2x 512GB (1TB total) Plextor SATA SSD (RAID0 volume) |~| Linux Boot Drive: 500GB Kingston A2000 |~| Storage: 4TB WD Black HDD |~| Case: Cooler Master Silencio S600 |~| Display 1 (leftmost): Eizo (unknown model) 1920x1080 IPS @ 60Hz|~| Display 2 (center): BenQ ZOWIE XL2540 1920x1080 TN @ 240Hz |~| Display 3 (rightmost): Wacom Cintiq Pro 24 3840x2160 IPS @ 60Hz 10-bit |~| OS: Windows 10 Pro (games / art) + Linux (distro: NixOS; programming and daily driver)
Link to comment
Share on other sites

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now


×