Skip to main content

Severity by source

NVD PRIMARY
2.0 LOW
CVSS:4.0/AV:L/AC:H/AT:P/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
vuln.today AI
2.5 LOW

Local access (AV:L) and race condition timing dependency (AC:H) with low privileges (PR:L); only partial availability impact (A:L) with no confidentiality or integrity effects.

3.1 AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:L
4.0 AV:L/AC:H/AT:P/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N

Primary rating from NVD.

CVSS VectorNVD

Attack Vector
Local
Attack Complexity
High
Privileges Required
Low
User Interaction
None
Scope
X

Lifecycle Timeline

2
Analysis Generated
Jul 23, 2026 - 18:09 vuln.today
CVE Published
May 15, 2026 - 02:59 nvd
UNKNOWN (no severity yet)

DescriptionCVE.org

A race condition in the MxGPU-Virtualization driver’s ioctl path caused by concurrent unsynchronized access to the global variable amdgv_cmd in an unlocked ioctl handler could be exploited by an attacker to trigger a heap-based buffer overflow, potentially resulting in denial-of-service within the vulnerable system context.

AnalysisAI

Heap-based buffer overflow in AMD's MxGPU-Virtualization (GIM) driver affects a range of AMD Instinct and Radeon PRO datacenter GPUs, allowing a local low-privileged attacker to trigger denial-of-service by exploiting a race condition on the global variable amdgv_cmd in an unsynchronized ioctl handler. AMD has issued Security Bulletin AMD-SB-6027 confirming the issue and releasing GIM Driver 8.4 for affected Instinct-series products; no public exploit code exists and the vulnerability is not listed in CISA KEV. With EPSS at 0.01% (2nd percentile) and CVSS 4.0 score of 2.0, this represents a very low real-world exploitation priority despite the heap overflow classification.

Technical ContextAI

The vulnerability resides in the MxGPU-Virtualization driver (GIM - GPU IOV Module), AMD's kernel-level driver enabling GPU SR-IOV virtualization on enterprise and HPC hardware. The root cause is CWE-367 (Time-of-Check Time-of-Use Race Condition): the ioctl handler accesses the global variable amdgv_cmd without holding an appropriate lock, allowing two or more concurrent threads to simultaneously modify or read the variable during dispatch, leading to a heap-based buffer overflow in the ioctl path. Affected CPEs span AMD Instinct MI210, MI250, MI300A, MI300X, MI308X, MI325X, and AMD Radeon PRO V620 and V710 - all datacenter-class GPUs typically deployed in virtualized cloud or HPC environments. The CVSS 4.0 vector (AV:L/AC:H/AT:P/PR:L) accurately reflects that exploitation is local, requires a timing-sensitive race, and has a prerequisite attack condition (AT:P), consistent with a multi-threaded attacker scenario on the same host.

RemediationAI

For AMD Instinct MI210, MI250, MI300A, MI300X, MI308X, and MI325X deployments, upgrade the GIM (GPU IOV Module) driver to version 8.4 or later, as confirmed in AMD Security Bulletin AMD-SB-6027 (https://www.amd.com/en/resources/product-security/bulletin/AMD-SB-6027.html). For AMD Radeon PRO V620 and V710, no general-release patch version has been confirmed - administrators should contact their AMD Customer Engineering representative directly for remediation guidance. As a compensating control where patching is not immediately possible, restricting ioctl access to the MxGPU virtualization device to trusted processes or limiting concurrent ioctl submissions via Linux kernel namespace or cgroup controls can reduce exploitation opportunity, though these controls may affect virtualization performance. Given the low EPSS and local-only attack vector, patching can be scheduled during normal maintenance windows rather than treated as an emergency.

Share

CVE-2025-52532 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy