[CVE-2026-97928][LOW] drm/amdgpu: skip the VMID 0 flush for VRAM

[CVE-2026-97928][LOW] drm/amdgpu: skip the VMID 0 flush for VRAM

[AL-KERNEL]

CVE: CVE-2026-97928
Priority: LOW
AL-KERNEL base severity: LOW
KPANIC flag: NO
Patch: drm/amdgpu: skip the VMID 0 flush for VRAM
Commit: 241d7450cf75969cea450eb3e740cb9682f69c2f
Upstream patch: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=241d7450cf75969cea450eb3e740cb9682f69c2f
Original CVE announcement: https://lore.kernel.org/linux-cve-announce/?q=CVE-2026-97928
Analysis date: Fri, 25 Sep 2026 20:26:31 -0400
ActionableScore: 2
ActionableScore lower bound: unknown
Actionable bucket: Ordinary Moderate
Manual review required: NO

Summary:
No one-sentence report phrase was found.

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

The original Linux kernel CVE announcement for CVE-2026-97928 is available here:
https://lore.kernel.org/linux-cve-announce/?q=CVE-2026-97928

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: LOW
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-2026-97928	LOW	https://www.kernelcve.org/list/?q=CVE-2026-97928 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-670;CWE-404;CWE-754;Other CVSS 'AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L';BEST CVSS score: '5.5';DESCR 'An unnecessary VMID 0 flush can occur when amdgpu clears or copies local VRAM through a direct MC address even though no GART window was programmed. On affected GFX11 hardware such as Navi33, the spurious SDMA flush can wedge the engine and disrupt GPU workloads. A local process may reach the affected path by allocating and releasing VRAM when Clear-on-release is enabled. For the CVSS the PR:L value is used because access to a DRM render node and an ordinary local GPU workload may be sufficient, without requiring full administrative privileges. The issue is not network reachable. The confirmed impact is denial of service affecting the GPU engine. A persistent wedge or failed recovery may produce high availability impact, but there is no demonstrated UAF, out of bounds access, arbitrary write, or VRAM information disclosure primitive.';NO MANUAL CHECK; ,and ActionableScore result is Ordinary Moderate (with actual score 2)  SKIP CVE-2026-97928 UNKNOWN SKIP No affected files built, so skip this CVE NO  - - unknown 	MAYBE	OOB INIT SIMPLEFIX HARDWARE MEMORY  DECREASED_TO_MODERATE_REGULAR_FROM_MODERATE7_BASED_ON_GUESSCVSS_AND_CIANNH DECREASED_TO_LOW_FROM_MODERATE_BASED_ON_ACTIONABLESCORELESSTHAN3	-	-	checked

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

ActionableScore=2
PrimitiveClass=CLASS_C
RealUAF=NO
HostAdminRequired=NO
NamespaceScopedPrivilege=NO
ImportantCandidate=NO
ManualReview=NO
AutoDowngradeAllowed=YES

1. ActionableScore

* Raw conservative score: 2
* Conservative score: 2
* Raw paranoid score: 2
* Paranoid score: 2
* No floor or cap was applied.
* Final recommended bucket: **Ordinary Moderate**::

2. Signal breakdown

Positive signals:

* +1 Local unprivileged trigger. A process with access to the DRM render node can allocate and release VRAM objects and thereby reach the clear-on-release path without DRM master or host-administrator privileges when the feature is enabled.
* +1 Availability impact. The unnecessary VMID 0 flush can wedge the SDMA engine and disrupt workloads using the affected GPU.

Negative signals:

* No negative points were applied. GFX11 and Navi33 are hardware-specific, but they are not shown to be rare or physical-only hardware.
* No timing penalty was applied because this is a deterministic logic error rather than a race.

Material non-awarded signals:

* Reliable kernel crash or host-wide strong DoS was not awarded. The established consequence is an SDMA engine wedge, not a kernel panic or confirmed host-wide failure.
* Extra Availability was not awarded. Persistent disruption or failed GPU recovery is not independently established beyond the same engine wedge.
* No UAF, OOB access, overwrite, stale object, refcount error, or other memory-corruption primitive is demonstrated.
* Controlled reclaim, arbitrary read/write, information disclosure, and privilege escalation are not demonstrated.
* Remote reachability is not established.
* Broad/default exposure was not awarded because the vulnerable path depends on affected GFX11 hardware and VRAM Clear-on-release being active.
* No confidentiality or integrity signal was awarded merely because a failed wipe operation is involved. The supplied evidence does not establish that uncleared VRAM becomes observable by another process.

3. Reachability analysis

The immediate trigger is local GPU activity involving allocation and release of VRAM through an accessible DRM render node. An ordinary graphics application does not normally require DRM master, compositor authority, display-control privileges, or host administration merely to create and release buffer objects.

VRAM Clear-on-release must be enabled for the vulnerable clear path to run. This may involve prior administrator-controlled module or deployment configuration, but once enabled, the attacker performing the trigger need not be the administrator. No namespace capability is involved, and a user namespace does not independently provide access to the physical GPU render node.

The problem is tied to affected GFX11 hardware such as Navi33. It is not a race and does not require a narrow timing window. No network trigger is present.

4. Primitive and severity interpretation

The exact primitive is an invalid and unnecessary VMID 0 TLB flush issued after direct VRAM addressing where no GART window was programmed. On affected hardware, this operation can wedge the SDMA engine.

This is neither fixed stale storage nor an active structured-object UAF. No object is shown to outlive its valid lifetime, and no repeated release or refcount mutation exists. The issue is therefore CLASS_C device-state and denial-of-service behavior.

The demonstrated consequence is loss of GPU or SDMA availability. A persistent GPU wedge requiring reset is a plausible operational consequence, but host-wide failure, memory corruption, VRAM disclosure, and privilege escalation are not established. ImportantCandidate is NO because there is no unresolved corruption or security-boundary primitive. AutoDowngradeAllowed is YES because the evidence supports a device-local DoS without meaningful exploitation leverage beyond the wedge.

5. One-sentence report phrase

An unnecessary VMID 0 flush during direct VRAM clear or copy operations can wedge the SDMA engine on affected GFX11 GPUs, causing a local device-level denial of service without an established memory-corruption or privilege-escalation primitive.

6. Manual review recommendation

NO MANUAL CHECK NEEDED

The issue is a hardware-specific GPU engine wedge with no demonstrated UAF, memory corruption, information disclosure, authorization bypass, or host-wide crash.

7. Call-site confidence

Call-site confidence: high

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

Patch: drm/amdgpu: skip the VMID 0 flush for VRAM
Commit: 241d7450cf75969cea450eb3e740cb9682f69c2f
Upstream URL: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=241d7450cf75969cea450eb3e740cb9682f69c2f

Commit description:

Clear-on-release only runs on VRAM, which amdgpu_ttm_map_buffer() reaches
via its direct MC address without programming a GART window, yet the wipe
still forces a VMID 0 flush. On GFX11 (e.g. Navi33) that spurious SDMA
flush can wedge the engine; only flush when a GART window is actually used.

v2: Let amdgpu_ttm_map_buffer() return whether the VMID 0 flush is needed,
    and drive the clear and copy paths from that. (Christian)
v3: Make the vm_needs_flush output parameter mandatory instead of
    allowing NULL. (Christian)

Fixes: a68c7ea ("drm/amdgpu: Enable clear page functionality")
Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/5413
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit a306e406e570b74318ff7d80e5b07b540ca1d3a9)
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Changed files:
  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.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=241d7450cf75969cea450eb3e740cb9682f69c2f

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

The original Linux kernel CVE announcement for CVE-2026-97928 can be found here:
https://lore.kernel.org/linux-cve-announce/?q=CVE-2026-97928

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:L/PR:L/UI:N/S:U/C:N/I:N/A:L
  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: unknown
  Paranoid ActionableScore: 2

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: LOW
KPANIC detected for this report: NO
Published priority for this report (same as in Subject): LOW

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).