• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

Zenbleeed: AMD Zen 2 vulnerability

Seems a new security bug has appeared for all Zen2 CPUs:

Tavis Ormandy, a researcher with Google Information Security, posted today about a new vulnerability he independently found in AMD's Zen 2 processors. The 'Zenbleed' vulnerability spans the entire Zen 2 product stack, including AMD's EPYC data center processors and the Ryzen 3000 CPUs, allowing the theft of protected information from the CPU, such as encryption keys and user logins. The attack does not require physical access to the computer or server and can even be executed via javascript on a webpage.

Ormandy says that AMD has issued a firmware fix for affected systems, and although signs of new firmwares with undefined changes did emerge for Linux today, we are unsure if they have the patches. AMD tells us that it will post an advisory about Zenbleed today, but it hasn't yet commented on the status of the patches. We also don't know if the firmware patches have a performance impact, but we will update this article as we learn more.

[Update 9:15am PT: AMD told us that patches to prevent Zenbleed are available for its EPYC Rome processors, but hasn't said if they are available for the impacted consumer Ryzen CPUs. AMD also hasn't given an ETA for patches for Ryzen chips or responded to our questions about potential performance impacts from the Zenbleed patches. We're still working to learn more.]

The Zenbleed vulnerability is filed as CVE-2023-20593 and allows data exfiltration (theft) at a rate of 30kb per core, per second, thus providing adequate throughput to steal sensitive information flowing through the processor. This attack works across all software running on the processor, including virtual machines, sandboxes, containers, and processes. The ability for this attack to read data across virtual machines is particularly threatening for cloud service providers and those who use cloud instances.

The attack can be accomplished via unprivileged arbitrary code execution. Ormandy has posted a security research repository and code for the exploit. The attack works by manipulating the register files to force a mispredicted command, as described below:

"The bug works like this, first of all you need to trigger something called the XMM Register Merge Optimization2, followed by a register rename and a mispredicted vzeroupper. This all has to happen within a precise window to work.

We now know that basic operations like strlen, memcpy and strcmp will use the vector registers - so we can effectively spy on those operations happening anywhere on the system! It doesn’t matter if they’re happening in other virtual machines, sandboxes, containers, processes, whatever!

This works because the register file is shared by everything on the same physical core. In fact, two hyperthreads even share the same physical register file,"
says Ormandy.

Ormandy says the bug can be patched through a software approach for multiple operating systems (e.g., Windows -"you can set the chicken bit DE_CFG[9]"), but this might result in a performance penalty. Ormandy says it is highly recommended to get the microcode update, but we don't have the details of firmware availability yet.

According to Ormandy, all Zen 2 CPUs are impacted, including the EPYC Rome processors:

  • AMD Ryzen 3000 Series Processors
  • AMD Ryzen PRO 3000 Series Processors
  • AMD Ryzen Threadripper 3000 Series Processors
  • AMD Ryzen 4000 Series Processors with Radeon Graphics
  • AMD Ryzen PRO 4000 Series Processors
  • AMD Ryzen 5000 Series Processors with Radeon Graphics
  • AMD Ryzen 7020 Series Processors with Radeon Graphics
  • AMD EPYC “Rome” Processors
 
Last edited:
I don't suppoose anyone knows if there is an update for Windows with a mitigation or CPU microcode update? I can see Linux has both mitigation in the kernel and new microcode, BSD has mitigation, but no mention of Windows anywhere. BIOS updates are not as convenient (if available at all).

Read both threads, but enjoyed this the best.

You win.
Thanks! I put entire minutes into making my posts the most entertaining on the 'net.
 
I don't suppoose anyone knows if there is an update for Windows with a mitigation or CPU microcode update? I can see Linux has both mitigation in the kernel and new microcode, BSD has mitigation, but no mention of Windows anywhere. BIOS updates are not as convenient (if available at all).


Thanks! I put entire minutes into making my posts the most entertaining on the 'net.
Keep VM’s to whole cores and pairs of threads. This will mitigate most issues. As for a Windows patch only god knows.

Keep up the good work.
 
Reports so far saying its around 18% hit in performance
Oof. When it was Intel (Spectre, Meltdown) the Internet and these forums were howling about it and calling them every name under the sun. Many were threatening to return CPUs for no longer hitting the performance they were sold at! I haven't seen that with AMD, despite it being almost the same type of vuln and a similar performance impact. To be clear, I like AMD anyway (Threadripper 3960X and 5500U's here) - I'm not digging at them, the contrast just jumped out at me. Hopefully they mitigate it in silicon in the next gen or two and manage to claw back the performance.
 
Last edited:
Just had a look at ASUS bios page and nothing been released since 20th June for the TRX40-E

ROG STRIX TRX40-E GAMING BIOS 1802
 
Jul 18th last from Gigabyte for my mobo, no mention of any chicken_bits though. Any notions of vendors addressing this yet?
 
Back
Top Bottom