kernel panic on Intel(R) Xeon(R) Gold 5418Y with CR0 Modification in Linux 6.8+

[CR0_panic]

Hello Intel Community,

I encountered a kernel panic on both a Linux VM running on an Intel Core i7-13700 (13th Gen) CPU and a Linux server running on an Intel(R) Xeon(R) Gold 5418Y server CPU.

The cause of the panic is a general protection fault, triggered by a C program that uses inline assembly to set the WP bit of the CR0 register to 0.

Example:

asm volatile("mov %0, %%cr0" : "+r"(cr0), "+m"(__force_order));

As noted in the title, this kernel panic occurs only in environments using the Intel Core i7-13700 (13th Gen) CPU and the Intel(R) Xeon(R) Gold 5418Y server CPU.

dmesg output:

general protection fault, maybe for address 0x80040033: 0000 [#1] PREEMPT SMP NOPTI

For reference, in the environment using the server-class CPU, the IBT flag is enabled in the CPU flags.

I would appreciate your guidance on the following points regarding this issue:

1. Is this behavior caused by a hardware issue or a software bug?

2. Has this issue already been resolved? If so, what is the solution or workaround?

3. If the issue has not been resolved, are there any immediate mitigation measures available?

4. If this is a hardware-related issue and remains unresolved, what are the future plans to address it?

Thank you for your support.

[Amina_Sadiya]

Hello CR0_panic,

Greetings from Intel!  

Thank you for contacting Intel. To proceed further with your query, I kindly request that you share the below details: 

1. Product details and system details on which processor is installed.

2. Please confirm if the processor was purchased separately or was it pre-installed on the system.

3. Please share the image of the processor ensuring that the markings are clearly visible.

Please feel free to respond to this email at your earliest convenience. 

Regards, 

Amina 

Intel Customer Support Technician 

[IntelSupport]

Hello CR0_panic,

Greetings for the day!

I hope this message finds you well.

We are following up to check if you were able to find the information we requested for. 

1. Product details and system details on which processor is installed.

2. Please confirm if the processor was purchased separately or was it pre-installed on the system.

3. Please share the image of the processor ensuring that the markings are clearly visible.

Also, please let us know the troubleshooting steps you have already performed to confirm that the issue is specific to the Intel® Core™ i7‑13700 (13th Gen) CPU and the Intel® Xeon® Gold 5418Y processor.

In particular, could you confirm the following:

1. Have you tested the same CPUs on a different system or motherboard, and does the issue persist there as well?
2. Have you tried running multiple operating system versions to check whether the general protection fault or kernel panic still occurs?

Kindly revert with the details, so that we can check further.

Thank you for using Intel products and services.

Regards,

Shankith K P

Intel Customer Support Technician

[CR0_panic]

Hello Customer Support Team,

I am currently checking on the information you requested.

Since the processors experiencing the issue are used at our customer sites, it is taking some time to collect the requested details.

I will leave a comment as soon as the information gathering is complete.

Thank you.

[IntelSupport]

Hello CR0_panic,

Thank you for writing back to us.

We will wait for an update from you.

Regards,

Shankith K P

​​​​​​​Intel Customer Support Technician

[IntelSupport]

Hello CR0_panic,

Greetings!

May we have an update on the requested details ?

We are still awaiting your response.

Regards,

Shankith K P

​​​​​​​Intel Customer Support Technician

[CR0_panic]

Hello Intel Customer Support Team,

I sincerely apologize for the long delay.

We have not yet received the information for items 1, 2, and 3 from our customer.

In the meantime, I would like to share the findings related to the additional questions you asked.

We were unable to test the servers using Xeon CPUs, as we do not have such systems internally.

However, since we do have desktops using the Intel Core i7-13700 CPU, we conducted tests across multiple desktop systems. As a result, the same issue was reproduced on most of those PCs.

In addition, we created Linux VM environments on desktops using the i7-13700 CPU and tested multiple OS versions. The kernel panic occurred only when using kernel versions 6.8 or later.

We will provide additional responses for items 1, 2, and 3 as soon as we hear back from our customer.

Thank you.

[Azhari_Intel]

Hello CR0_panic,

Good day to you!

Thank you for the update.

Please let us know once the information is available to be shared, and also please help to see below.

1. Regarding the result you mentioned kernel panic occurred only when using kernel version 6.8 or later, may we know is this the same when tested on environment with Intel(R) Xeon(R) Gold 5418Y?

2. In the Xeon CPUs environment, what hypervisor is being used?

3. Other than dmesg output message shared earlier, is there any additional details regarding the kernel panic?

4. May we know if there are any troubleshooting carried out on the Xeon CPUs system?

Looking forward to hearing back from you on this.

Best Regards,

Azhari_Intel

[IntelSupport]

Hello CR0_panic,

Good day!

We are still awaiting a response from you with the below details.

1. Regarding the result you mentioned kernel panic occurred only when using kernel version 6.8 or later, may we know is this the same when tested on environment with Intel(R) Xeon(R) Gold 5418Y?

2. In the Xeon CPUs environment, what hypervisor is being used?

3. Other than dmesg output message shared earlier, is there any additional details regarding the kernel panic?

4. May we know if there are any troubleshooting carried out on the Xeon CPUs system?

Looking forward to hearing back from you on this.

Regards,

Shankith K P

​​​​​​​Intel Customer Support Technician

[CR0_panic]

Hello Intel Community,

Please find our responses to your questions below:

1. In the Xeon(R) Gold 5418Y environment, the kernel panic has been confirmed only with kernel version 6.14. Earlier kernel versions have not been tested.
2. As this is a customer server environment, we cannot confirm with certainty, but we believe VMware ESXi may be in use.
3. We do not have any additional information beyond what has already been shared.
4. As a mitigation measure, the affected systems have been configured not to run the program that modifies the CR0 register.

Thank you.

[Sachinks]

Hello CR0_panic,

Greetings from Intel!

Thank you for your reply and thank you for the details.

In order to check this further, could you provide us the system model details in which this processor is installed?

Also, kindly let us know if this processor came along with the system or was it manually added later. Also, if possible, kindly share an image of the processor with the markings visible.

As we need the system details to check this further, we request you to provide us the above information so that we can proceed further with the troubleshooting.

Please don’t hesitate to contact us for any further assistance.

Thank you for using Intel products and services.

Best Regards,

Sachin KS

Intel Customer Support Technician

[Shankith]

Hello CR0_panic,

Greetings for the day!

I hope this message finds you well.

We are following up to check if you were able to find the information we requested for. 

Kindly revert with the details, so that we can continue assisting you in resolving this matter.

Thank you for using Intel products and services.

Regards,

Shankith K P

Intel Customer Support Technician

[CR0_panic]

Hello Intel Community,

I apologize for the delayed response.

We made every effort to request the required information from our technical support team so they could coordinate with the affected customer. However, due to this kernel panic issue, the customer has withdrawn the use of our product, and we are currently unable to re-establish communication with them.

As a result, it appears that we are unable to provide the additional information you requested.

Thank you for your understanding.

[Shankith]

Hello CR0_panic,

Thank you for getting back to us.

We understand the situation, and we appreciate the efforts you made to gather the requested information. However, without the necessary product and system details, it is difficult for us to fully understand the environment and provide further technical analysis or support on this issue.

Once you are able to obtain the required details, please feel free to initiate a new case, and we will be glad to assist you further.

As we are currently unable to proceed without the requested information, we will go ahead and close this thread.

If you need any additional support in the future, please start a new conversation, as this thread will no longer be monitored.

Regards,

Shankith K P

​​​​​​​Intel Customer Support Technician