CVE-2026-99148: Linux kernel · drm/amdgpu: keep the eviction fence until the last handle is closed
Affects Linux kernelSource GCVE Database
Not known to be exploited.
Data as of 29 Oct 2026, 22:35 UTC
Rated by Threat Radar · CVSS not yet scored by NVD
Thin evidence
One scorer or noneExploitation evidence
Disclosed: evidence found.
CVE published 28 Oct 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 29 Oct 2026.
What to do
Affected software
| Product | Affected | Fixed in |
|---|---|---|
Ubuntu 26.10linuxpkg:deb/ubuntu/linux?arch=source&distro=stonkingOther threats | Affected
| Fixed in– |
Ubuntu 26.10linux-awspkg:deb/ubuntu/linux-aws?arch=source&distro=stonkingOther threats | Affected
| Fixed in– |
Ubuntu 26.10linux-azurepkg:deb/ubuntu/linux-azure?arch=source&distro=stonkingOther threats | Affected
| Fixed in– |
Ubuntu 26.10linux-azure-fdepkg:deb/ubuntu/linux-azure-fde?arch=source&distro=stonkingOther threats | Affected
| Fixed in– |
Ubuntu 26.10linux-gcppkg:deb/ubuntu/linux-gcp?arch=source&distro=stonkingOther threats | Affected
| Fixed in– |
Ubuntu 26.10linux-oraclepkg:deb/ubuntu/linux-oracle?arch=source&distro=stonkingOther threats | Affected
| Fixed in– |
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
Description
In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: keep the eviction fence until the last handle is closed amdgpu_gem_object_close() detaches the user queue eviction fence from the BO before it checks bo_va->ref_count, so closing any handle of a BO removes the fence, even when the file still has another handle to the BO and the bo_va with its GPU mappings stays. The BO can then be evicted without suspending the user queues of the file, which keep accessing it through mappings that are only marked for update. Seen on navi31 with a SDMA user queue: a BO opened twice in the same file (GEM_FLINK + GEM_OPEN) loses its eviction fence when the second handle is closed (traced attach/detach of the fence): attach bo=ffff8c78a6c84c00 GEM_CLOSE handle=7 detach bo=ffff8c78a6c84c00 while handle 6 and the mapping are still in use. Only detach the fence when the last reference to the bo_va goes away, matching amdgpu_gem_object_open(), which attaches it only when the bo_va is created. With this the fence stays until the file is closed. (cherry picked from commit 8387982f03d4026b7dc11b0b5e3118298eee4d6a)
References
- ubuntu.com/security/CVE-2026-99148 (opens in a new tab)
- cve.org/CVERecord?id=CVE-2026-99148 (opens in a new tab)
- git.kernel.org/stable/c/3c44cbcec5eb370713bbd2c315ed7c34d8ccec2b (opens in a new tab)
- git.kernel.org/stable/c/dce8f7f03a47b1744dccf506268f9229b67fab47 (opens in a new tab)
- git.kernel.org/stable/c/6467c4cc83b94850bfea614e9f98276edf9a7c3f (opens in a new tab)