CVE-2026-68237

A flaw was found in the Linux kernel's drm/amdgpu/userq component. During a GPU reset, the pre_reset function only force-completes fences for mapped queues. If a queue is in another state, its last fence remains pending and never signals after the reset. This can cause the eviction/suspend worker and process teardown to wait indefinitely, leading to a system hang and a Denial of Service.

Moderate: A flaw in the amdgpu kernel driver can cause a system to hang indefinitely during a GPU reset operation. This issue affects Red Hat In-Vehicle OS and specific versions of Red Hat Enterprise Linux, potentially leading to system unresponsiveness.

The CVSS score(s) listed for this vulnerability do not reflect the associated product's status, and are included for informational purposes to better understand the severity of this vulnerability.

To mitigate this issue, prevent the amdgpu module from being loaded. See https://access.redhat.com/solutions/41278 for instructions.