Linux kernel task hang in AMDGPU dma-buf move notifications
Linux
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
| No fix yet |
| Linux Linux |
Linux
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
| No fix yet |
| Linux Linux |
6.17
|
In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu: check amdgpu_vm_ready() in dma-buf move notify
amdgpu_dma_buf_move_notify() touches the page tables without first calling amdgpu_vm_ready(). When a process is SIGKILLed, its VM entities are stopped. Teardown of an imported dma-buf then tries to clear PTEs by submitting to one of those stopped entities. That eventually hangs the task.
Commit aa5fc4362fac ("drm/amdgpu: fix task hang from failed job submission during process kill") added the stopped entity check in amdgpu_vm_ready() and used it in amdgpu_cs_vm_handling(). That did not cover a call in amdgpu_dma_buf_move_notify(), what was already mentioned in: https://lists.freedesktop.org/archives/amd-gfx/2025-October/133076.html
Tested by SIGKILLing a GPU workload holding imported dma-bufs. Without the patch "Trying to push to a killed entity" errors are logged, then a task hangs. With the patch there are no hung tasks. This was tested on a 6.18 kernel.
(cherry picked from commit bee5c9d7a34cb1b510ad3b4c18c30f9d38b0ab7d)
From the CVE record · Linux
The Linux kernel’s amdgpu dma-buf move notification can access page tables after a process’s VM entities have stopped. If a GPU workload holding imported dma-bufs is SIGKILLed, teardown can hang a task. The described trigger is local; the input does not specify authentication requirements.
Engineers running Linux kernels with amdgpu and workloads that import dma-bufs should check their kernels; the issue was tested on a 6.18 kernel without the patch.