The vulnerability arises in the AMDGPU driver for RDNA4 (GFX12) GPUs where zero‑size GDS, GWS, or OA memory regions are incorrectly initialized. The init code unconditionally creates a TTM range manager for each resource, even when its size is zero. This triggers an assertion that crashes the kernel during module loading, resulting in a kernel panic. The weakness corresponds to improper handling of zero‑size resource ranges (CWE-1284) and includes an unspecified additional CWE (NVD-CWE-noinfo).

All Linux kernel builds that ship an unpatched AMDGPU driver on RDNA4 hardware, such as Radeon RX 9070 XT and similar GPUs. The exact kernel version range is not specified, but any kernel that has the unrevised amdgpu_ttm_init_on_chip implementation before the commit that introduced the early return is vulnerable. Users of newer kernel releases that contain the patch are not affected.

Because the defect is triggered by loading or initializing the amdgpu driver module, the attack requires local privilege to load the module or to boot into a kernel that executes it. The vulnerability has a CVSS score of 5.5, indicating medium severity, and is alleviated in kernel builds that include the early-return fix. The EPSS score of < 1% indicates a very low exploitation probability, and the vulnerability is not listed in the CISA KEV catalog, implying limited exploitation risk at present. Nevertheless, failure to patch leaves a system vulnerable to intentional denial of service by any attacker who can load the AMDGPU module.