CVE-2025-38168: perf: arm-ni: Unregister PMUs on probe failure
In the Linux kernel, the following vulnerability has been resolved:
perf: arm-ni: Unregister PMUs on probe failure
When a resource allocation fails in one clock domain of an NI device,
we need to properly roll back all previously registered perf PMUs in
other clock domains of the same device.
Otherwise, it can lead to kernel panics.
Calling arm_ni_init+0x0/0xff8 [arm_ni] @ 2374
arm-ni ARMHCB70:00: Failed to request PMU region 0x1f3c13000
arm-ni ARMHCB70:00: probe with driver arm-ni failed with error -16
list_add corruption: next->prev should be prev (fffffd01e9698a18),
but was 0000000000000000. (next=ffff10001a0decc8).
pstate: 6340009 (nZCv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--)
pc : list_add_valid_or_report+0x7c/0xb8
lr : list_add_valid_or_report+0x7c/0xb8
Call trace:
__list_add_valid_or_report+0x7c/0xb8
perf_pmu_register+0x22c/0x3a0
arm_ni_probe+0x554/0x70c [arm_ni]
platform_probe+0x70/0xe8
really_probe+0xc6/0x4d8
driver_probe_device+0x48/0x170
__driver_attach+0x8e/0x1c0
bus_for_each_dev+0x64/0xf0
driver_add+0x138/0x260
bus_add_driver+0x68/0x138
__platform_driver_register+0x2c/0x40
arm_ni_init+0x14/0x2a [arm_ni]
do_init_module+0x36/0x298
---[ end trace 0000000000000000 ]---
Kernel panic - not syncing: Oops - BUG: Fatal exception
SMP: stopping secondary CPUs
Security readout for executives and security teams
Plain-English summary
A Linux ARM Network Interconnect performance-monitoring driver can leave monitoring components registered when device setup fails. A later probe can corrupt a kernel list and cause a system panic, taking the host offline. The supplied record rates this local vulnerability 7.8 High.
Executive priority
Prioritize remediation for compatible ARM infrastructure where an unexpected kernel panic could disrupt critical services. Other Linux hosts are unlikely to share this specific driver path. Because exploitation is not established and triggering conditions are hardware-specific, use targeted inventory and patch verification rather than treating every Linux system as equally exposed.
Technical view
In arm-ni, a resource-allocation failure in one clock domain did not unregister PMUs already registered for other domains. Subsequent registration can encounter corrupted list state and trigger a fatal kernel exception. The supplied evidence demonstrates a kernel panic; it does not establish practical confidentiality or integrity compromise.
Likely exposure
Exposure appears limited to Linux systems using the ARM NI perf driver on compatible hardware where device probing encounters a resource-allocation failure. The supplied affected-version metadata includes Linux 6.12, 6.12.34, 6.15.3, and 6.16, but its exact range semantics are unclear. Vendor kernel backports require separate verification.
Exploitation context
The CVSS vector describes local, low-complexity exploitation requiring low privileges and no user interaction. However, the bundle provides no public exploitation evidence, and the CVE is not listed as KEV. The documented trigger is a driver probe failure leading to kernel list corruption and panic.
Researcher notes
The failure is an incomplete probe-error rollback: PMUs registered before a later clock-domain allocation failure remain registered. The trace shows re-registration reaching list validation and panicking. The bundle does not identify a CWE, working exploit, distribution package mapping, or unambiguous affected range; researchers should avoid extrapolating beyond compatible ARM NI configurations.
Mitigation direction
Install a vendor-supported kernel containing the applicable ARM NI rollback fix.
Compare vendor kernel backports against the three referenced stable Linux commits.
Prioritize compatible ARM systems where the arm-ni driver is present or loaded.
Check Linux distribution or hardware-vendor guidance before selecting a fixed package.
Validation and detection
Inventory ARM systems and identify whether the arm-ni driver is available or loaded.
Record kernel versions, distribution build identifiers, and vendor backport status.
Review kernel logs for arm-ni probe failures, PMU registration errors, or list corruption.
Confirm the installed source or package includes an applicable referenced stable commit.
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Potential ATT&CK relevance
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
cve · low confidence lookup
CVE-2025-38168 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
1CVSS vectors
3Timeline events
0ADP providers
4Source links
CVSS vector scores
1 official score
We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.