CVE-2026-90243

iommu/vt-d: Clear Present bit before tearing down copied context entry

Published Sep 17, 2026 CVSS 3.1 · 8.1 High EPSS < 1% KEV · Not listed
Description
In the Linux kernel, the following vulnerability has been resolved:

iommu/vt-d: Clear Present bit before tearing down copied context entry

copied_context_tear_down() zeroes the 128-bit context entry with
context_clear_entry() while the Present bit is still set, and only then
issues the context-cache and IOTLB invalidations. This leaves a window
in which hardware can fetch a torn entry, with some fields already zeroed
while Present is still set, leading to unpredictable behaviour or
spurious faults. While x86 provides strong write ordering, the compiler
may reorder the writes to the two 64-bit halves of the entry, and the
hardware fetch is not guaranteed to be atomic with respect to multiple
CPU writes.

There is no cacheline flush before the invalidation either, so on an
IOMMU without coherent access to the context table the zeroed entry may
not be visible to hardware at the point the invalidation is submitted.

Apply the same ownership handshake described in the VT-d spec, Section
6.5.3.3 ("Guidance to Software for Invalidations"): clear only the Present
bit, flush it out to the IOMMU, perform the invalidations, and only then
zero the remainder of the entry.

Analysis

AI-generated

Technical impact

A flaw in Linux kernel VT‑d handling causes a partially torn IOMMU context entry to remain marked present while its fields are being cleared, allowing the hardware to read an incomplete entry and produce unpredictable device behavior or spurious faults. The race arises because the kernel zeroes a 128‑bit context entry while the Present bit stays set and performs IOTLB invalidation without flushing, enabling the hardware to observe a half‑cleared entry in the context table. This race condition maps to CWE‑362 (Race Condition).

Affected Systems

Linux kernel – any version prior to the commit that enforces the proper sequence of clearing the Present bit, flushing the entry to the IOMMU, performing invalidations, and then zeroing the remaining fields. The affected builds are all distributions that ship the unpatched kernel and rely on VT‑d IOMMU support for device passthrough or isolation.

Risk and Exploitability

The CVSS score of 8.1 indicates high severity. The EPSS score is below 1 %, implying a low likelihood of exploitation at present, and the vulnerability is not listed in CISA’s KEV catalog. The likely attack vector is local with elevated privileges, as attacking the context teardown would require triggering a device unplug or driver unload, which requires local privileged access; this inference is based on the description. Nonetheless, the potential for hardware‑level faults justifies timely mitigation.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Apply the latest Linux kernel release that contains the VT‑d context tear‑down fix.
  • If an upgrade cannot be performed immediately, disable VT‑d/IOMMU support on the affected hosts to remove the fault path.
  • Review and update any in‑kernel modules or custom code that performs IOMMU context teardown to follow the new correct order, or remove them if they are unnecessary.

Generated by OpenCVE AI on September 20, 2026 at 01:05 UTC.

Tracking

Sign in to view the affected projects.

Advisories

Source ID Title
Debian DLA Debian DLA DLA-4817-1 linux-6.12 security update
Debian DSA Debian DSA DSA-6528-1 linux security update
Ubuntu USN Ubuntu USN USN-9019-1 Linux kernel (Azure) vulnerabilities
Ubuntu USN Ubuntu USN USN-9020-1 Linux kernel vulnerabilities
Ubuntu USN Ubuntu USN USN-9160-1 Linux kernel (Azure) vulnerabilities
History
Type Values Removed Values Added
Weaknesses CWE-362
Type Values Removed Values Added
Metrics cvssV3_1

{'score': 8.1, 'vector': 'CVSS:3.1/AV:L/AC:H/PR:N/UI:N/S:C/C:H/I:H/A:H'}

Type Values Removed Values Added
Description In the Linux kernel, the following vulnerability has been resolved: iommu/vt-d: Clear Present bit before tearing down copied context entry copied_context_tear_down() zeroes the 128-bit context entry with context_clear_entry() while the Present bit is still set, and only then issues the context-cache and IOTLB invalidations. This leaves a window in which hardware can fetch a torn entry, with some fields already zeroed while Present is still set, leading to unpredictable behaviour or spurious faults. While x86 provides strong write ordering, the compiler may reorder the writes to the two 64-bit halves of the entry, and the hardware fetch is not guaranteed to be atomic with respect to multiple CPU writes. There is no cacheline flush before the invalidation either, so on an IOMMU without coherent access to the context table the zeroed entry may not be visible to hardware at the point the invalidation is submitted. Apply the same ownership handshake described in the VT-d spec, Section 6.5.3.3 ("Guidance to Software for Invalidations"): clear only the Present bit, flush it out to the IOMMU, perform the invalidations, and only then zero the remainder of the entry.
Title iommu/vt-d: Clear Present bit before tearing down copied context entry
First Time appeared Linux
Linux linux Kernel
CPEs cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*
Vendors & Products Linux
Linux linux Kernel
References
Weaknesses
  • CWE-362

    Concurrent Execution using Shared Resource with Improper Synchronization ('Race Condition')

Sources

Status
PUBLISHED
Assigner
Linux
Published
Updated
Oct 19, 2026, 9:00 AM
Reserved
Sep 11, 2026, 7:38 PM
Status
Received
Published
Sep 17, 2026, 5:17 PM
Modified
Oct 19, 2026, 9:19 AM