GHSA-WCFV-P978-69XF
Vulnerability from github – Published: 2026-08-15 06:32 – Updated: 2026-08-19 18:32In the Linux kernel, the following vulnerability has been resolved:
perf/x86/amd/brs: Fix kernel address leakage
A user-only branch stack can contain branches that originate from the kernel. As a result, kernel addresses are exposed to user space even when PERF_SAMPLE_BRANCH_USER is requested. On AMD processors supporting X86_FEATURE_BRS (Zen 3 only), perf can still report entries such as SYSRET/interrupt returns for which the branch-from addresses are in the kernel.
E.g.
$ perf record -j any,u -c 4000 -e branch-brs -o - -- \ perf bench syscall basic --loop 1000 | \ perf script -i - -F brstack|tr ' ' '\n'| \ grep -E '0x[89a-f][0-9a-f]{15}'
... 0xffffffff810001c4/0x72e2e32955eb/-/-/-/0//- 0xffffffff810001c4/0x72e2d94a9821/-/-/-/0//- 0xffffffff810001c4/0x72e2d94ffa1b/-/-/-/0//- ...
BRS provides no hardware branch filtering, so privilege level filtering is performed entirely in software. However, amd_brs_match_plm() only validates the branch-to address against the requested privilege levels. For branches from the kernel to user space, the branch-from address is left unchecked and is leaked. Extend the software filter to also validate the branch-from address, so that any branch record whose branch-from address is in the kernel is dropped when PERF_SAMPLE_BRANCH_USER is requested.
{
"affected": [],
"aliases": [
"CVE-2026-72237"
],
"database_specific": {
"cwe_ids": [],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-08-15T06:21:50Z",
"severity": null
},
"details": "In the Linux kernel, the following vulnerability has been resolved:\n\nperf/x86/amd/brs: Fix kernel address leakage\n\nA user-only branch stack can contain branches that originate from\nthe kernel. As a result, kernel addresses are exposed to user space\neven when PERF_SAMPLE_BRANCH_USER is requested. On AMD processors\nsupporting X86_FEATURE_BRS (Zen 3 only), perf can still report entries\nsuch as SYSRET/interrupt returns for which the branch-from addresses\nare in the kernel.\n\nE.g.\n\n $ perf record -j any,u -c 4000 -e branch-brs -o - -- \\\n perf bench syscall basic --loop 1000 | \\\n perf script -i - -F brstack|tr \u0027 \u0027 \u0027\\n\u0027| \\\n grep -E \u00270x[89a-f][0-9a-f]{15}\u0027\n\n ...\n 0xffffffff810001c4/0x72e2e32955eb/-/-/-/0//-\n 0xffffffff810001c4/0x72e2d94a9821/-/-/-/0//-\n 0xffffffff810001c4/0x72e2d94ffa1b/-/-/-/0//-\n ...\n\nBRS provides no hardware branch filtering, so privilege level\nfiltering is performed entirely in software. However, amd_brs_match_plm()\nonly validates the branch-to address against the requested privilege\nlevels. For branches from the kernel to user space, the branch-from\naddress is left unchecked and is leaked. Extend the software filter to\nalso validate the branch-from address, so that any branch record whose\nbranch-from address is in the kernel is dropped when\nPERF_SAMPLE_BRANCH_USER is requested.",
"id": "GHSA-wcfv-p978-69xf",
"modified": "2026-08-19T18:32:27Z",
"published": "2026-08-15T06:32:16Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-72237"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/046f6244da9b68e463a849b21446b9424e531491"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/2e706be56f418718bb3ae66c0aa94f9b61150e6d"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/47915e855fb38b42133e31ba917d99565f862154"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/4f949bc3913a6e3ce3b8574ac6ed1da8ec7a5ad1"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/90843d00dbc61220b66408ea0d8775cae9e51f70"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/ac44b4a3d6137489f8fa2e794b12e849c6b22eaa"
}
],
"schema_version": "1.4.0",
"severity": []
}
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.