CVE-2026-68237 drm/amdgpu/userq: fix indefinite fence wait during GPU reset
A local attacker can cause a system hang by triggering a GPU reset while a user queue is in a specific state, leading to a denial of service.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Local or same network only
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-68237?
CVE-2026-68237 is a denial of service vulnerability in Linux, published on 10 Aug 2026. It can only be exploited from the same machine or local network, with no action from the victim.
Official description
In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu/userq: fix indefinite fence wait during GPU reset
pre_reset only force-completes fences of MAPPED queues. A queue in any other state (e.g. mid-eviction) keeps its last_fence pending; after a GPU reset that fence never signals, so the eviction/suspend worker and process teardown (amdgpu_evf_mgr_flush_suspend) wait on it forever and wedge the machine:
INFO: task kworker/6:28 blocked for more than 120 seconds. Workqueue: events amdgpu_eviction_fence_suspend_worker [amdgpu] Call Trace: dma_fence_wait_timeout+0x7e/0x130 amdgpu_userq_evict+0x67/0x140 [amdgpu] amdgpu_eviction_fence_suspend_worker+0xd8/0x160 [amdgpu] process_scheduled_works+0xa6/0x420
Force-complete every queue's fence regardless of state. The unmap and mark-hung step stays gated on MAPPED, since unmapping a queue that is not mapped is invalid.
(cherry picked from commit 9102b39fa924dcc3dc75a3137bfa9633c40b88c0)
Which versions are affected by CVE-2026-68237?
How do I fix CVE-2026-68237?
Apply the vendor's patch.
Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.
Is CVE-2026-68237 being exploited?
There is no known exploitation of CVE-2026-68237 in the wild and no public exploit code.
Sources
Also known as DEBIAN-CVE-2026-68237, GHSA-p526-pm6j-fr73, UBUNTU-CVE-2026-68237.