CVE-2026-68237

published 10 Aug 2026 · updated 17 Aug 2026

drm/amdgpu/userq: fix indefinite fence wait during GPU reset

5.0MediumEPSS 0%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. Fixed in Kernel 3085ae8695e025b39d208f288c6265edc75abbe8 and Kernel 5d75ec2e5f1736c2f10c7d6f4565bf1bf29f29a7.

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)

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
LinuxKernel=6.19, >=290f46cf5726509f55fac4c7abe9b9d311aa5a3a <3085ae8695e025b39d208f288c6265edc75abbe8, >=290f46cf5726509f55fac4c7abe9b9d311aa5a3a <5d75ec2e5f1736c2f10c7d6f4565bf1bf29f29a73085ae8695e025b39d208f288c6265edc75abbe8, 5d75ec2e5f1736c2f10c7d6f4565bf1bf29f29a7

Timeline

Every event on this vulnerability

Related

Other vulnerabilities in Kernel, strongest first

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-68237 severity on Zeptric[![CVE-2026-68237](https://zeptric.io/badge/cve/CVE-2026-68237.svg)](https://zeptric.io/cve/CVE-2026-68237)