drm/amdgpu: force complete the KIQ ring fences on reset
Linux
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
|
Linux
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
|
≥ 65781c78ad74e4260fbec92c0ecc05738044e177 · < fd65d1742992361fc2201ecb4e43411e6e417fcb| No fix yet |
| Linux Linux |
|
|
In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu: force complete the KIQ ring fences on reset
Like the MES scheduler ring, the KIQ ring sets no_scheduler = true and uses a polling fence, so it is skipped by the force-completion loop in amdgpu_device_pre_asic_reset(). Its hw fence value lives in wb (GTT) memory and survives a MODE1 reset while fence_drv.sync_seq keeps advancing, so after a reset the first KIQ submission can poll forever on a seq that is never written back.
Force complete the KIQ ring fences too so their hw fence is realigned to sync_seq.
From the CVE record · Linux
In the Linux kernel's amdgpu driver, KIQ ring fences are not force-completed during a reset. After a MODE1 reset, the first KIQ submission can poll forever because its hardware fence value is out of sync. The input does not describe an attacker path, authentication requirement, or user interaction.
Engineers running Linux kernels with the amdgpu driver should check their vendor's affected-version information; no versions are listed here.