The race condition occurs between __perf_event_overflow() and perf_event_exit_event() when only preemption is disabled. The overflow handler may reference structures that have already been freed, such as BPF programs, which can result in memory corruption or a system crash. If an attacker can exploit the corruption, it could potentially elevate privileges. The weakness is a resource‑management error catalogued as CWE‑367.

All Linux kernel implementations prior to the commit that enforces IRQ disable in __perf_event_overflow() are affected. This includes any distribution kernel that has not yet incorporated the fix contained in the referenced commit. The vulnerability applies to any kernel with the perf subsystem and BPF support enabled.

The CVSS score of 7.8 indicates high severity, and the EPSS score is below 1 %, reflecting a low likelihood of exploitation. The vulnerability is not listed in the CISA KEV catalog. Exploitation would require a local or privileged attacker to trigger a perf event overflow that races with the context cleanup path. Because the issue can cause a system crash or potential privilege escalation, administrators should treat it as high risk even if exploitation probability is low.