[CVE-2026-64289][MODERATE REGULAR] iommufd: Set upper bounds on cache invalidation entry_num and entry_len

[CVE-2026-64289][MODERATE REGULAR] iommufd: Set upper bounds on cache invalidation entry_num and entry_len

[AL-KERNEL]

CVE: CVE-2026-64289
Priority: MODERATE REGULAR
AL-KERNEL base severity: MODERATE
KPANIC flag: NO
Patch: iommufd: Set upper bounds on cache invalidation entry_num and entry_len
Commit: d2bd041e0efaf7d81789779b135279d18b33d6d5
Upstream patch: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=d2bd041e0efaf7d81789779b135279d18b33d6d5
Original CVE announcement: https://lore.kernel.org/linux-cve-announce/?q=CVE-2026-64289
Analysis date: Sat, 25 Jul 2026 13:03:16 -0400
ActionableScore: 3
ActionableScore lower bound: 2
Actionable bucket: Ordinary Moderate / auto-close candidate unless iommufd is exposed to untrusted tenants
Manual review required: NO

Summary:
`iommufd_hwpt_invalidate allowed user controlled entry_num and entry_len values to drive excessive zero scanning or backend invalidation loops, allowing a local process with access to the iommufd HWPT invalidation interface to cause CPU pinning or soft lockup DoS.`

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

The original Linux kernel CVE announcement for CVE-2026-64289 is available here:
https://lore.kernel.org/linux-cve-announce/?q=CVE-2026-64289

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: NO

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

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

CVE-2026-64289	MODERATE	CHECK WITH IMPACT FROM ORIG NN MODERATE	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-400;CWE-834;*CWE-20;BEST CVSS score: '5.5';DESCR 'iommufd_hwpt_invalidate accepted user controlled entry_num and entry_len values with only very large upper bounds, allowing a local process to force long uninterruptible work in the kernel. A very large entry_len can make copy_struct_from_user scan excessive zeroed user memory, while a very large entry_num can drive backend invalidation loops that copy entries and flush caches repeatedly. For the CVSS the PR:L is selected because the attacker needs a local process with access to the iommufd HWPT invalidation interface, but full administrator privileges are not necessarily required in delegated VFIO or virtualization setups. The issue is not network reachable and is triggered through a local ioctl rather than packet traffic. Impact is denial of service due to CPU soft lockup or prolonged CPU pinning. No confidentiality or integrity impact is assigned because the patch shows bounded CPU consumption and input validation, not a memory corruption primitive.';NO MANUAL CHECK; ,and ActionableScore result is Ordinary Moderate / auto-close candidate unless iommufd is exposed to untrusted tenants (with actual score 3)	YES	DEADLOCK SIMPLEFIX HARDWARE MEMORY  DECREASED_TO_MODERATE_REGULAR_FROM_MODERATE7_BASED_ON_GUESSCVSS_AND_CIANNH	YES	NO	checked

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

ActionableScore=3
ActionableScoreLower=2

## 1. ActionableScore

* Conservative score: 2
* Paranoid score: 3
* Final recommended bucket: **Ordinary Moderate / auto-close candidate unless iommufd is exposed to untrusted tenants**::

## 2. Signal breakdown

Conservative signals:

* Local unprivileged or delegated local trigger: +1. The issue is reachable through a local iommufd ioctl by a process that can access the relevant HWPT invalidation object. This may be non-root in delegated VFIO or virtualization setups.
* Reliable kernel crash / strong DoS: +1. Large `entry_len` can force long zero scanning in `copy_struct_from_user()`, and large `entry_num` can drive long backend invalidation loops without reschedule.
* Rare or configuration-dependent path: -1. Practical triggering depends on iommufd, HWPT invalidation, and commonly VFIO or nested IOMMU usage rather than a broad default syscall path.
* Availability impact realistic: +1. Counted conservatively only through the strong DoS signal, not double-counted in the lower score.

Paranoid delta:

* Availability impact realistic: +1. In the higher interpretation, CPU pinning and soft-lockup watchdog behavior on non-preemptible kernels can be treated as system-wide availability impact.

Not applied:

* No memory corruption signal. The patch bounds loop and scan lengths and does not show UAF, OOB write, double free, type confusion, stale pointer reuse, or arbitrary write.
* No confidentiality or integrity impact.
* No remote or network reachability.
* No privilege escalation plausibility.

## 3. Reachability analysis

A local process must be able to issue `IOMMU_HWPT_INVALIDATE` through iommufd against an appropriate HWPT object. This is not a packet-processing or network-reachable path. In typical systems, access depends on VFIO, virtualization, device assignment, or delegated device-management configuration. Full host-root is not inherently required in all deployments, because iommufd/VFIO objects may be delegated to a VM manager or tenant process, but an ordinary unprivileged shell normally will not have this interface available without prior setup.

Namespaces and containers matter only if the host deliberately delegates the relevant device or iommufd access into that environment. If the product exposes iommufd only to trusted root-managed virtualization services, practical risk is lower.

## 4. Severity interpretation

This behaves like an ordinary Moderate local DoS issue, with an actionable note only for multi-tenant virtualization environments where untrusted users can reach iommufd invalidation ioctls. The demonstrated primitive is CPU pinning and soft lockup due to unbounded user-controlled loop or scan length. There is no supported evidence of memory corruption, privilege escalation, information disclosure, or persistent storage corruption.

## 5. One-sentence report phrase

`iommufd_hwpt_invalidate allowed user controlled entry_num and entry_len values to drive excessive zero scanning or backend invalidation loops, allowing a local process with access to the iommufd HWPT invalidation interface to cause CPU pinning or soft lockup DoS.`

## 6. Manual review recommendation

NO MANUAL CHECK NEEDED

Reason: this is a bounded resource-exhaustion / CPU-DoS validation fix without memory corruption, network reachability, confidentiality impact, integrity impact, or privilege escalation evidence. Manual review is only recommended if the target product exposes iommufd/VFIO HWPT operations to untrusted tenants.

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

Patch: iommufd: Set upper bounds on cache invalidation entry_num and entry_len
Commit: d2bd041e0efaf7d81789779b135279d18b33d6d5
Upstream URL: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=d2bd041e0efaf7d81789779b135279d18b33d6d5

Commit description:

iommufd_hwpt_invalidate() takes a user-controlled entry_num and entry_len,
each bounded only by U32_MAX. An entry_len beyond the kernel's struct size
makes the copy helper verify the extra bytes are zero, scanning that excess
in one uninterruptible pass; a multi-gigabyte value over zeroed user memory
trips the soft-lockup watchdog.

A large entry_num is the other half, driving the backend invalidation loop
with no reschedule. The VT-d nested handler, for one, copies each entry and
flushes caches per iteration, pinning the CPU on a non-preemptible kernel.

Cap both in the ioctl. entry_len is held under PAGE_SIZE, above any request
struct, and entry_num under 1 << 19, the order of a hardware invalidation
queue and well beyond any real batch, bounding the per-call loop length.

Fixes: 8c6eaba ("iommufd: Add IOMMU_HWPT_INVALIDATE")
Link: https://patch.msgid.link/r/447fa93663f7526eb361719e83fa8b649464483d.1780521606.git.nicolinc@nvidia.com
Cc: stable@vger.kernel.org
Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Changed files:
  drivers/iommu/iommufd/hw_pagetable.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=d2bd041e0efaf7d81789779b135279d18b33d6d5

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

The original Linux kernel CVE announcement for CVE-2026-64289 can be found here:
https://lore.kernel.org/linux-cve-announce/?q=CVE-2026-64289

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: Not available
  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).