GHSA-PWC7-RCQ3-J2VW
Vulnerability from github – Published: 2025-07-03 09:30 – Updated: 2025-12-18 21:31In the Linux kernel, the following vulnerability has been resolved:
arm64/fpsimd: Discard stale CPU state when handling SME traps
The logic for handling SME traps manipulates saved FPSIMD/SVE/SME state incorrectly, and a race with preemption can result in a task having TIF_SME set and TIF_FOREIGN_FPSTATE clear even though the live CPU state is stale (e.g. with SME traps enabled). This can result in warnings from do_sme_acc() where SME traps are not expected while TIF_SME is set:
| / With TIF_SME userspace shouldn't generate any traps / | if (test_and_set_thread_flag(TIF_SME)) | WARN_ON(1);
This is very similar to the SVE issue we fixed in commit:
751ecf6afd6568ad ("arm64/sve: Discard stale CPU state when handling SVE traps")
The race can occur when the SME trap handler is preempted before and after manipulating the saved FPSIMD/SVE/SME state, starting and ending on the same CPU, e.g.
| void do_sme_acc(unsigned long esr, struct pt_regs regs) | { | // Trap on CPU 0 with TIF_SME clear, SME traps enabled | // task->fpsimd_cpu is 0. | // per_cpu_ptr(&fpsimd_last_state, 0) is task. | | ... | | // Preempted; migrated from CPU 0 to CPU 1. | // TIF_FOREIGN_FPSTATE is set. | | get_cpu_fpsimd_context(); | | / With TIF_SME userspace shouldn't generate any traps */ | if (test_and_set_thread_flag(TIF_SME)) | WARN_ON(1); | | if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { | unsigned long vq_minus_one = | sve_vq_from_vl(task_get_sme_vl(current)) - 1; | sme_set_vq(vq_minus_one); | | fpsimd_bind_task_to_cpu(); | } | | put_cpu_fpsimd_context(); | | // Preempted; migrated from CPU 1 to CPU 0. | // task->fpsimd_cpu is still 0 | // If per_cpu_ptr(&fpsimd_last_state, 0) is still task then: | // - Stale HW state is reused (with SME traps enabled) | // - TIF_FOREIGN_FPSTATE is cleared | // - A return to userspace skips HW state restore | }
Fix the case where the state is not live and TIF_FOREIGN_FPSTATE is set by calling fpsimd_flush_task_state() to detach from the saved CPU state. This ensures that a subsequent context switch will not reuse the stale CPU state, and will instead set TIF_FOREIGN_FPSTATE, forcing the new state to be reloaded from memory prior to a return to userspace.
Note: this was originallly posted as [1].
[ Rutland: rewrite commit message ]
{
"affected": [],
"aliases": [
"CVE-2025-38170"
],
"database_specific": {
"cwe_ids": [],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2025-07-03T09:15:32Z",
"severity": "MODERATE"
},
"details": "In the Linux kernel, the following vulnerability has been resolved:\n\narm64/fpsimd: Discard stale CPU state when handling SME traps\n\nThe logic for handling SME traps manipulates saved FPSIMD/SVE/SME state\nincorrectly, and a race with preemption can result in a task having\nTIF_SME set and TIF_FOREIGN_FPSTATE clear even though the live CPU state\nis stale (e.g. with SME traps enabled). This can result in warnings from\ndo_sme_acc() where SME traps are not expected while TIF_SME is set:\n\n| /* With TIF_SME userspace shouldn\u0027t generate any traps */\n| if (test_and_set_thread_flag(TIF_SME))\n| WARN_ON(1);\n\nThis is very similar to the SVE issue we fixed in commit:\n\n 751ecf6afd6568ad (\"arm64/sve: Discard stale CPU state when handling SVE traps\")\n\nThe race can occur when the SME trap handler is preempted before and\nafter manipulating the saved FPSIMD/SVE/SME state, starting and ending on\nthe same CPU, e.g.\n\n| void do_sme_acc(unsigned long esr, struct pt_regs *regs)\n| {\n| // Trap on CPU 0 with TIF_SME clear, SME traps enabled\n| // task-\u003efpsimd_cpu is 0.\n| // per_cpu_ptr(\u0026fpsimd_last_state, 0) is task.\n|\n| ...\n|\n| // Preempted; migrated from CPU 0 to CPU 1.\n| // TIF_FOREIGN_FPSTATE is set.\n|\n| get_cpu_fpsimd_context();\n|\n| /* With TIF_SME userspace shouldn\u0027t generate any traps */\n| if (test_and_set_thread_flag(TIF_SME))\n| WARN_ON(1);\n|\n| if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {\n| unsigned long vq_minus_one =\n| sve_vq_from_vl(task_get_sme_vl(current)) - 1;\n| sme_set_vq(vq_minus_one);\n|\n| fpsimd_bind_task_to_cpu();\n| }\n|\n| put_cpu_fpsimd_context();\n|\n| // Preempted; migrated from CPU 1 to CPU 0.\n| // task-\u003efpsimd_cpu is still 0\n| // If per_cpu_ptr(\u0026fpsimd_last_state, 0) is still task then:\n| // - Stale HW state is reused (with SME traps enabled)\n| // - TIF_FOREIGN_FPSTATE is cleared\n| // - A return to userspace skips HW state restore\n| }\n\nFix the case where the state is not live and TIF_FOREIGN_FPSTATE is set\nby calling fpsimd_flush_task_state() to detach from the saved CPU\nstate. This ensures that a subsequent context switch will not reuse the\nstale CPU state, and will instead set TIF_FOREIGN_FPSTATE, forcing the\nnew state to be reloaded from memory prior to a return to userspace.\n\nNote: this was originallly posted as [1].\n\n[ Rutland: rewrite commit message ]",
"id": "GHSA-pwc7-rcq3-j2vw",
"modified": "2025-12-18T21:31:33Z",
"published": "2025-07-03T09:30:35Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2025-38170"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/43be952e885476dafb74aa832c0847b2f4f650c6"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/6103f9ba51a59afb5a0f32299c837377c5a5a693"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/c4a4786d93e99517d6f10ed56b9ffba4ce88d3b3"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/d3eaab3c70905c5467e5c4ea403053d67505adeb"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/de89368de3894a8db27caeb8fd902ba1c49f696a"
},
{
"type": "WEB",
"url": "https://lists.debian.org/debian-lts-announce/2025/10/msg00008.html"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
"type": "CVSS_V3"
}
]
}
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.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.