Linux Kernel AMDGPU Device Removal Hang Vulnerability

A vulnerability in the Linux kernel's AMDGPU graphics driver can cause a hang and a call trace warning when removing an AMDGPU device on GPUs with Reliability, Availability, and Serviceability (RAS) enabled. This issue occurs because the driver improperly manages the device's shutdown process, leading to a memory wipe that disrupts normal operations.

Impact

The vulnerability causes a hang in the system, disrupting normal operations and potentially leading to a denial of service.

Reproduction

The vulnerability can be reproduced by removing an AMDGPU device on a system with RAS enabled. This action will trigger a call trace warning and cause the system to hang, indicating a disruption in normal operations.