LiveActive security incident?Get immediate response
CVE Record

CVE-2025-38424: perf: Fix sample vs do_exit()

In the Linux kernel, the following vulnerability has been resolved: perf: Fix sample vs do_exit() Baisheng Gao reported an ARM64 crash, which Mark decoded as being a synchronous external abort -- most likely due to trying to access MMIO in bad ways. The crash further shows perf trying to do a user stack sample while in exit_mmap()'s tlb_finish_mmu() -- i.e. while tearing down the address space it is trying to access. It turns out that we stop perf after we tear down the userspace mm; a receipie for disaster, since perf likes to access userspace for various reasons. Flip this order by moving up where we stop perf in do_exit(). Additionally, harden PERF_SAMPLE_CALLCHAIN and PERF_SAMPLE_STACK_USER to abort when the current task does not have an mm (exit_mm() makes sure to set current->mm = NULL; before commencing with the actual teardown). Such that CPU wide events don't trip on this same problem.

HighCVSS 7.8Not KEV-listedUpdated
Glexia's TakeAutomated analysishigh

Security readout for executives and security teams

Plain-English summary

A Linux perf timing flaw can sample a process’s user stack while its address space is being destroyed. The reported outcome was an ARM64 kernel crash. Because triggering requires local, low-privileged access, this is primarily a host stability and local security concern, not a remotely exploitable issue based on available evidence.

Executive priority

Treat as a high-priority kernel maintenance issue for shared or perf-enabled Linux systems. Patch through normal expedited change control, prioritizing exposed multi-user hosts. Emergency incident response is not supported solely by current evidence because active exploitation is unconfirmed and access is local.

Technical view

During do_exit(), perf was stopped after exit_mmap() began dismantling the userspace memory map. PERF_SAMPLE_CALLCHAIN or PERF_SAMPLE_STACK_USER could therefore access an invalid address space. The fix stops perf earlier and rejects these samples when current->mm is NULL, also protecting CPU-wide events.

Likely exposure

Exposure applies to affected Linux kernel builds using perf sampling, particularly user-stack or call-chain sampling during process exit. The supplied version data is ambiguous and should not be treated as a definitive package list; confirm status against each distribution’s kernel advisory and changelog.

Exploitation context

The CVSS vector describes a local, low-complexity issue requiring low privileges and no user interaction. CISA KEV status is false, and the supplied sources do not establish active exploitation or a public weaponized exploit. The documented evidence is an ARM64 crash; broader confidentiality or integrity impact is not demonstrated in the description.

Researcher notes

The source establishes an ordering defect and defensive checks, but does not document a reliable security exploit, affected configuration prerequisites, or demonstrated privilege escalation. Version records appear flattened or incomplete; use stable commit ancestry and distribution package status for authoritative exposure decisions.

Mitigation direction

  • Install a vendor-supported kernel containing the applicable stable fix.
  • Check distribution advisories for exact corrected package versions.
  • Prioritize multi-user, shared-compute, and perf-enabled systems.
  • If updates are delayed, obtain vendor-approved compensating guidance; none is specified in the supplied sources.

Validation and detection

  • Inventory kernel versions across Linux hosts and container nodes.
  • Compare installed packages with distribution advisories and changelogs.
  • Confirm the kernel includes the applicable referenced stable commit.
  • Review kernel logs for perf, exit_mmap, tlb_finish_mmu, or synchronous external abort crashes.
  • After updating, verify the new kernel is running following reboot.
Prepared
Confidence
medium
Sources
12

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-2025-38424 mapping review

Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.

Open ATT&CK lookup
Vulnerability profileCVE Program record
Severity
High
CVSS
7.8 (3.1)
Known Exploited
No
Published

Vector: CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Official CVE source material

CNA and ADP enrichment extracted from CVE v5

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
1ADP providers
11Source 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.

ScoreVersionSeverityVectorExploitImpactSource
7.8CVSS 3.1HighCVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H1.85.9Linux

Vulnerability scoring details

Base CVSS 3.1 score

7.8High
CVSS 3.1 vector shape for CVE-2025-38424Attack VectorAttack ComplexityPrivileges RequiredUser InteractionScopeConfidentiality ImpactIntegrity ImpactAvailability Impact

Vector: CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Attack Vector
NetworkAdjacentLocalPhysical
Attack Complexity
LowHigh
Privileges Required
NoneLowHigh
User Interaction
NoneRequired
Scope
ChangedUnchanged
Confidentiality Impact
HighLowNone
Integrity Impact
HighLowNone
Availability Impact
HighLowNone

Vulnerability timeline

Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.

  1. CVE reservedCVE Program

    The CVE ID was reserved by the assigning CNA.

  2. CVE publishedCVE Program

    The CVE record was published.

  3. CVE updatedCVE Program

    The CVE record metadata indicates this as the latest update time.

ADP provider summaries

CVECVE Program Container
Affected products

Products and packages named in the record

VendorProductVersion / packageStatus
LinuxLinuxc5ebcedb566ef17bda7b02686e0d658a7bb42ee7, c5ebcedb566ef17bda7b02686e0d658a7bb42ee7, c5ebcedb566ef17bda7b02686e0d658a7bb42ee7, c5ebcedb566ef17bda7b02686e0d658a7bb42ee7, c5ebcedb566ef17bda7b02686e0d658a7bb42ee7, c5ebcedb566ef17bda7b02686e0d658a7bb42ee7, c5ebcedb566ef17bda7b02686e0d658a7bb42ee7, c5ebcedb566ef17bda7b02686e0d658a7bb42ee7unaffected
LinuxLinux3.7, 0, 5.4.295, 5.10.239, 5.15.186, 6.1.142, 6.6.95, 6.12.35, 6.15.4, 6.16affected
Weakness

CWE details

No CWE listed

CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.