[CVE-2026-68347][MODERATE REGULAR] iommu/amd: Fix IRQ unsafe locking in gdom allocation [ Upstream

[AL-KERNEL <alkernel@kernelcve.org>]

CVE: CVE-2026-68347
Priority: MODERATE REGULAR
AL-KERNEL base severity: MODERATE
KPANIC flag: NO
Patch: iommu/amd: Fix IRQ unsafe locking in gdom allocation [ Upstream
Commit: e0c78cdf35af3ada05f9309f4641e9f83c945dbd
Upstream patch: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=e0c78cdf35af3ada05f9309f4641e9f83c945dbd
Original CVE announcement: https://lore.kernel.org/linux-cve-announce/?q=CVE-2026-68347
Analysis date: Mon, 10 Aug 2026 19:28:24 -0400
ActionableScore: 3
ActionableScore lower bound: 2
Actionable bucket: Borderline Moderate / manual review recommended
Manual review required: YES

Summary:
AMD IOMMU nested-domain gdom allocation used IRQ-unsafe xarray locking in paths that can interact with hardirq-safe IOTLB flush handling, allowing a local virtualization or device-assignment control process to potentially trigger a host deadlock or lockup.

======================================================================
ABOUT THIS REPORT
======================================================================

The original Linux kernel CVE announcement for CVE-2026-68347 is available here:
https://lore.kernel.org/linux-cve-announce/?q=CVE-2026-68347

The original announcement does not normally provide a security severity
estimate, CVSS assessment, or enough information to determine whether the
reported kernel bug represents a practically relevant security issue.

This report was generated by AL-KERNEL, an AI-assisted Linux kernel
vulnerability analysis system developed by Alexander Larkin. It combines
an autonomous classifier with LLM-assisted technical analysis and a
separate ActionableScore mechanism.

The purpose of this report is to prioritize Linux kernel CVEs before
manual review, identify cases that require prompt investigation, and
support automatic closure of issues that are unlikely to have meaningful
security impact.

Published priority for this report: MODERATE REGULAR
Manual review required: YES

A detailed explanation of the methodology and priority rules is included
at the end of this message.

======================================================================
AL-KERNEL CLASSIFICATION RESULT
======================================================================

CVE-2026-68347	MODERATE	CHECK WITH IMPACT FROM ORIG NN LOW	Maybe valid. Check manually. Hints by AL-KERNEL: The best (paranoid) CVSS is 'AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H';CWE-667;*CWE-833;CWE-821;Other CVSS 'AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H';BEST CVSS score: '5.5';DESCR 'AMD IOMMU nested domain allocation can create a hardirq unsafe lock ordering problem because the gdom xarray lock is taken without irqsave while related IOTLB flush paths may be reached from hardirq safe contexts. A local user or service that can drive iommufd or a QEMU based nested IOMMU setup may trigger a host lockup or deadlock during nested domain allocation, invalidation, or free operations. For the CVSS the PR:L is used because reliable triggering requires local execution with access to the virtualization or device assignment control path, but it does not necessarily require full host root in delegated VM or service account deployments. The issue is not network reachable by itself and packet traffic is not the direct attack vector. Impact is denial of service only through host hang or lockup, with no concrete evidence of information disclosure, memory corruption, or privilege escalation.';YES REQUIRES MANUAL CHECK; ,and ActionableScore result is Borderline Moderate / manual review recommended (with actual score 3)  SKIP CVE-2026-68347 UNKNOWN SKIP The Fixes patch not applied yet, so unlikely that actual: 757d2b1fdf5b7d6eead5963a49b5780617987ab8 YES  NO NO unknown 	MAYBE	LOCK HARDWARE MEMORY  DECREASED_TO_MODERATE_REGULAR_FROM_MODERATE7_BASED_ON_GUESSCVSS_AND_CIANNH	-	-	checked

======================================================================
ACTIONABLESCORE ANALYSIS
======================================================================

ActionableScore=3
ActionableScoreLower=2

## 1. ActionableScore

* Conservative score: 2
* Paranoid score: 3
* Final recommended bucket: **Borderline Moderate / manual review recommended**::

## 2. Signal breakdown

Triggered signals:

* Reliable kernel crash / strong DoS: +1
  The lock ordering issue can plausibly lead to a host lockup or deadlock in AMD IOMMU nested-domain paths.

* Availability impact realistic: +1
  The affected path is host IOMMU code used by virtualization and device assignment. A deadlock here can affect the host, not only one guest process.

* Local low-privileged or delegated service trigger: +1 in paranoid score
  Typical triggering is through iommufd / QEMU / VFIO-like device-assignment control paths. This is not ordinary remote reachability, but in delegated VM-service deployments the triggering process may be less than full host root.

Negative / limiting signals:

* Hard or timing-dependent condition: -1 conservative
  The issue is an IRQ-safe vs IRQ-unsafe lock ordering problem. The real deadlock depends on interrupt timing and concurrent IOMMU flush/allocation/free activity.

* Rare / configuration-dependent subsystem: -1 conservative/paranoid
  The affected code is AMD IOMMU nested-domain handling, not a broad default kernel path.

Not awarded:

* No generic memory corruption bonus. The patch fixes locking mode and GFP context, not UAF, OOB write, double free, type confusion, or arbitrary write.
* No privilege escalation bonus. The supplied patch and call path support host DoS, not LPE.
* No confidentiality or integrity impact. There is no supported leak, overwrite, or policy-bypass primitive.
* No remote/network trigger. Network traffic is not the direct attack vector.

## 3. Reachability analysis

The likely trigger is local access to virtualization or device-assignment control paths, such as a QEMU process using iommufd with AMD IOMMU nested-domain support. In typical deployments this is not available to an arbitrary unprivileged user, but it may be reachable by a VM service account, containerized management process, or reduced-capability root process that is allowed to manage assigned devices.

Namespaces do not automatically make this unprivileged, but delegated device-management setups can lower practical privilege from full host root to PR:L-like service access. The path is not network reachable by itself. Realistic exploitation requires AMD IOMMU nested-domain support and concurrent IOMMU invalidation/free/allocation activity sufficient to expose the unsafe lock ordering.

Call-site confidence: high, because the provided trace and diff show the relevant iommufd ioctl path, AMD IOMMU nested allocation path, IOTLB flush path, and free path.

## 4. Severity interpretation

This behaves like a Moderate host DoS issue with manual-review relevance, not an Important-class memory corruption vulnerability. The evidence supports a lock-ordering deadlock or host lockup, but not UAF, object reuse, attacker-controlled overwrite, information disclosure, or privilege escalation.

The paranoid score is raised only to 3 because the affected subsystem is security-sensitive host virtualization / IOMMU infrastructure and may be reachable by delegated VM-management processes. It should not be treated as Strong Important based on the current patch evidence.

## 5. One-sentence report phrase

AMD IOMMU nested-domain gdom allocation used IRQ-unsafe xarray locking in paths that can interact with hardirq-safe IOTLB flush handling, allowing a local virtualization or device-assignment control process to potentially trigger a host deadlock or lockup.

## 6. Manual review recommendation

MANUAL CHECK RECOMMENDED

Reason: the issue is DoS-only from the supplied evidence, but it affects AMD IOMMU nested virtualization and iommufd-related host device-management paths, so product-specific exposure should be checked before auto-closing.

======================================================================
UPSTREAM PATCH SUMMARY
======================================================================

Patch: iommu/amd: Fix IRQ unsafe locking in gdom allocation [ Upstream
Commit: e0c78cdf35af3ada05f9309f4641e9f83c945dbd
Upstream URL: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=e0c78cdf35af3ada05f9309f4641e9f83c945dbd

Changed files:
  drivers/iommu/amd/nested.c

Diff excerpt:

Not included in this email. See the upstream URL for the full patch.

Full patch:
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=e0c78cdf35af3ada05f9309f4641e9f83c945dbd

======================================================================
DETAILED REPORT METHODOLOGY
======================================================================

The original Linux kernel CVE announcement for CVE-2026-68347 can be found here:
https://lore.kernel.org/linux-cve-announce/?q=CVE-2026-68347

The original CVE announcement normally does not include a security-level
estimate. In particular, it may not contain a CVSS assessment, an impact
level, or enough information to determine whether the reported bug is a
practically relevant security issue. One purpose of this parallel CVE list
is to provide that missing technical and prioritization information.

The original goal of the AL-KERNEL project was to prioritize Linux kernel
CVE analysis automatically before manual review. The system can also help
identify non-security issues that may be suitable for automatic closure.

This report was generated by AL-KERNEL, an AI-assisted Linux kernel
vulnerability analysis system developed by Alexander Larkin.

The first analysis stage combines an autonomous classifier with additional
LLM-based analysis. The autonomous classifier runs locally on a CPU and is
based on a backpropagation neural network. Together, these mechanisms
produce a technical vulnerability description, identify likely weakness
types, estimate CVSS severity, and provide input for ActionableScore.

Two CVSS estimates are retained because incomplete kernel vulnerability
information often permits more than one defensible interpretation:

  Conservative CVSS vector: AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
  The Best / paranoid CVSS vector: AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
  The Best / paranoid CVSS score: 5.5

The conservative vector represents a lower-impact interpretation.
The Best/paranoid vector intentionally represents a plausible upper-bound
interpretation and should not automatically be treated as demonstrated
real-world impact.

CVSS may also need to be adjusted for a particular Linux deployment,
because actual reachability, privileges, enabled kernel configuration,
hardware, namespaces, exposed device nodes, and other environmental
conditions can differ significantly between systems.

A separate ActionableScore mechanism evaluates practical remediation
urgency. Its analysis may include reachability, attack prerequisites,
subsystem exposure, memory-corruption characteristics, denial-of-service
reliability, and possible confidentiality, integrity, or
privilege-escalation impact.

  Conservative ActionableScore: 2
  Paranoid ActionableScore: 3

The final base severity is taken directly from the second tab-separated
field of the AL-KERNEL classification result. ActionableScore does not
replace or independently override that final AL-KERNEL decision, and
if ActionableScore adjusted impact level of ALKERNEL, then you would see
self-readable flags above like INCREASED_TO_HIGH_BASED_ON_ACTIONABLESCOREHIGHEREQTHAN7.

For an AL-KERNEL result of MODERATE, this report uses the following
additional presentation split:

  ActionableScore below 5   -> MODERATE REGULAR
  ActionableScore 5 or more -> MODERATE 7.0

The distinction between MODERATE REGULAR and MODERATE 7.0 makes it
possible to identify Moderate issues that should receive manual analysis
and fixes before lower-priority MODERATE REGULAR issues. In many cases,
MODERATE REGULAR fixes may wait for a later rebase or routine update.

There is one override in which MODERATE REGULAR becomes MODERATE 7.0
even when the ActionableScore is below 5. When the AL-KERNEL result
contains the KPANIC flag, a MODERATE result is always presented as
MODERATE 7.0. The KPANIC flag selected with few regexps without
usage of AI at all, so it helps to detect cases when Kernel Crash happens
and similar (to filter False-Negative results from the LLM usage).

KPANIC indicates that a reliable kernel crash, kernel panic, or similarly
serious kernel availability impact was identified by the classification
workflow.

AL-KERNEL base severity for this report: MODERATE
KPANIC detected for this report: NO
Published priority for this report (same as in Subject): MODERATE REGULAR

These results are intended to support engineering triage. They are
machine-generated estimates, and cases marked for manual review should
be validated by a human security engineer before final disposition.
For more info read docs linked from here: https://kernelcve.org/
(and you can submit you own patch there to generate such a report
for non-existant CVE-id yet).

Note that in many cases this AI tool selects higher severity, than
real is (means you can expect Importants instead of Moderate 7.0 or
Moderates 7.0 instead of regular Moderates). If you see such cases,
please use reply email interface to add additional manual analyses
info to this particular CVE.
And please, please, let me know when you see Lows instead of Importants
or Important instead of Low (because particular for such cases I
need to tune this AI tool to make it better for this one and next similar).
My contact email for such notifications is alexanjelausa@gmail.com (and both
send reply to CVE record itself too and see "reply" button below for howto reply).