CVE-2025-40300
BaseFortify
Publication date: 2025-09-11
Last updated on: 2025-11-17
Assigner: kernel.org
Description
Description
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| linux | kernel | 5.10.244-1 |
| linux | kernel | 6.1.153-1 |
| qemu | qemu | * |
Helpful Resources
Exploitability
| CWE ID | Description |
|---|---|
| CWE-UNKNOWN |
Attack-Flow Graph
AI Powered Q&A
Can you explain this vulnerability to me?
This vulnerability, known as VMSCAPE, affects the Linux kernel's x86 architecture and involves insufficient branch predictor isolation between a guest virtual machine and a userspace hypervisor like QEMU. It allows a malicious guest to potentially exploit the branch predictor state shared with userspace, which can lead to information leakage or other side-channel attacks. The mitigation involves conditionally issuing an Indirect Branch Prediction Barrier (IBPB) after a VMexit and before returning to userspace to flush the branch predictors and reduce the risk of exploitation.
How can this vulnerability impact me? :
This vulnerability can impact users by allowing a malicious guest virtual machine to exploit the branch predictor state shared with userspace, potentially leading to information leakage or side-channel attacks against the userspace hypervisor or other userspace processes. Workloads that frequently switch between hypervisor and userspace may experience performance overhead due to the additional IBPB instructions used as mitigation.
What immediate steps should I take to mitigate this vulnerability?
To mitigate this vulnerability, ensure that your Linux kernel is updated to include the conditional IBPB (Indirect Branch Prediction Barrier) mitigation after VMexit before returning to userspace. This involves applying the patch that adds conditional IBPB flushing of branch predictors to protect userspace from poisoned branch predictors. Additionally, existing mitigations such as speculation control via prctl() at context switch time should be maintained. Since this mitigation may cause overhead for workloads frequently switching between hypervisor and userspace, monitor performance accordingly.