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.
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.
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.
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.