Look up another CVE · open CVE-2026-80670 in the interactive tracker
CVE-2026-80670
perf tools: Use perf_env__get_cpu_topology() in machine__resolve()
Published 2026-08-28 (2 months ago) by the Linux kernel CNA. Subsystem tools/perf. Debian urgency: not yet assigned.
What to do, per Debian release
Debian's own status for CVE-2026-80670 in every release this site tracks, and what each one means in practice. Every status below is the one the Debian Security Team publishes for this CVE. source
| Release | Status | Version | What this means |
|---|---|---|---|
| Debian 12bookworm | vulnerable | 6.1.190-1 | No fix published anywhere yet, neither in Debian nor upstream for the series bookworm tracks. Watch the Debian tracker page for this CVE. Advisories for bookworm have historically landed a median of 23 days after publication. |
| Debian 13trixie | vulnerable | 6.12.113-1 | No fix published anywhere yet, neither in Debian nor upstream for the series trixie tracks. Watch the Debian tracker page for this CVE. Advisories for trixie have historically landed a median of 11 days after publication. |
| Debian 14forky | fixed | 7.1.5-1 | Update the kernel and reboot. Fixed in 7.1.5-1. A running kernel keeps the old code until the machine restarts. |
| Debian unstablesid | fixed | 7.1.5-1 | Update the kernel and reboot. Fixed in 7.1.5-1. A running kernel keeps the old code until the machine restarts. |
The vulnerability
What the bug is
machine__resolve() accesses env->cpu[al->cpu].socket_id after checking al->cpu >= 0 and env->cpu != NULL, but without validating al->cpu against env->nr_cpus_avail. Since al->cpu comes from the untrusted perf.data sample, a crafted file with a large CPU index causes an out-of-bounds heap read. Use perf_env__get_cpu_topology() which validates both NULL and bounds. Also bounds-check al->cpu before the cast to struct perf_cpu (int16_t): without this, values like 65536 silently truncate to 0, bypassing the accessor's internal check and returning CPU 0's topology.
Where it lives
The fix touches these files. If the subsystem is one you do not use, the practical exposure is lower, though the package is still the vulnerable one.
tools/perf/util/event.c
- What this is
- PERFORMANCE EVENTS SUBSYSTEMMAINTAINERS section matched on tools/perf/ · linux-perf-users@vger.kernel.org · Supported
Show whether Debian builds this, per release
Not established. This site could not find the build rule for the affected file in the kernel trees Debian ships, so it has no answer about whether Debian compiles this code. Read that as unknown, never as absent.
- bookworm, trixie, forky, sid?
- ?
- not established - no Makefile entry for the affected file
Where a release above reads "not established", no build rule for the affected file was found in that release's kernel tree. That is a gap in this lookup, not a finding that the code is absent.
From the configuration Debian publishes for every kernel flavour it builds. It covers only the architectures Debian ships a linux-config package for, and nothing about a kernel you built yourself. Debian's own status above stays authoritative about the source package.MAINTAINERS
Signals
- Published
- 2026-08-28 (2 months ago)source
- CVSS
- 9.1 critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:Hsource recompute it - Attack vector
- network (AV:N)source
- EPSS
- 0.67%, higher than 51.1% of all CVEssource
- CISA KEV
- not listedthe KEV catalogue
- Debian urgency
- not yet assignedsource
- Subsystem
- tools/perf
Upstream fixes
The versions the CNA records as introducing and fixing this, and the commit for each. source
| Introduced | Fixed in | Commit |
|---|---|---|
| 4.4 | 6.18.40 | b9e8406651dc |
| 4.4 | 7.1.5 | eb266a14c16a |
| 4.4 | 7.2 | 5484b43a0ec8 |
Why the CNA scored it this way
Quoted from the kernel CNA's own scoring file, word for word. A highlighted metric carries the most severe value CVSS v3.1 defines for it, which is what pushes the score up. source
- AV:NAttack vector, network
- machine__resolve() is reached when perf tools parse untrusted perf.data samples via perf report/script/mem/kvm/diff and related builtins; recordings are routinely ingested over the network through stdin pipes (perf -i -) or automated CI/profiling services that analyze uploaded artifacts, giving a remote attacker a network path to supply the malicious CPU index.
- AC:LAttack complexity, low
- The attacker fully controls sample.cpu in the crafted perf.data PERF_RECORD_SAMPLE payload; once perf opens the file or pipe, a single sample with cpu >= nr_cpus_avail deterministically triggers the out-of-bounds read without races, timing, or uncontrollable memory layout.
- PR:NPrivileges required, none
- Processing malicious perf.data requires no Linux capabilities or init-namespace root; any remote party who can supply a recording to a profiling pipeline, bug-report workflow, or piped perf session can trigger the bug on the analyzing host without local account privileges on that system.
- UI:NUser interaction, none
- No interactive victim action beyond normal automated ingestion of perf recordings is required; an attacker can deliver a crafted file to CI bots, shared profiling servers, or piped analysis sessions that invoke perf non-interactively, without the analyst manually opening attachments.
- S:UScope, unchanged
- The flaw is confined to the userspace perf tool process parsing the recording; impact does not cross VM, IOMMU, or container/kernel security boundaries and remains within the same security authority as the perf analyzer process.
- C:HConfidentiality impact, high
- The bug is an attacker-controlled out-of-bounds heap read through env->cpu[al->cpu].socket_id with no upper bound on the index relative to the allocated topology array, enabling disclosure of adjacent heap contents (metadata, pointers, strings) from the perf process address space.
- I:NIntegrity impact, none
- The vulnerability performs only an out-of-bounds read of topology fields into al->socket; it does not write memory, corrupt heap metadata, or provide a direct arbitrary-write or code-execution primitive in the vulnerable code path.
- A:HAvailability impact, high
- An out-of-bounds heap read with a large crafted CPU index commonly causes an immediate SIGSEGV or abort of the perf analysis process, denying availability of profiling, CI performance triage, and incident-response workflows that depend on perf report/script completing successfully.