arm64/fpsimd: Discard stale CPU state when handling SME traps
In 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_
- Products
- Kernel
- Affected versions
- Not specified
- Fixed versions
- 6.1.142, 6.12.34, 6.15.3, 6.6.94
- CVEs
- CVE-2025-38170
- Confirmed fixed CVEs
- Not specified
- Updated in this feed
- 5 Nov 2026, 01:00 UTC · Revision 1
Source evidence
arm64/fpsimd: Discard stale CPU state when handling SME traps
core-osv · Original sourcePublished 3 Jul 2025, 08:36 UTC
In 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_
osv:CVE-2025-38170
Kernel
Fixed versions: 6.1.142, 6.6.94, 6.12.34, 6.15.3
Complete source record
{
"id": "5179b11c5ce8e51307c43337825f56f38fd8df6ef545d1771197b5774a97a9fe",
"url": "https://osv.dev/vulnerability/CVE-2025-38170",
"method": "structured",
"payload": {
"kind": "advisory",
"title": "arm64/fpsimd: Discard stale CPU state when handling SME traps",
"summary": "In 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_",
"evidence": "osv:CVE-2025-38170",
"products": [
{
"name": {
"value": "Kernel",
"evidence": "/affected/1/package/name"
},
"prerequisites": [],
"fixed_versions": [
{
"value": "6.1.142",
"evidence": "/affected/1/ranges"
},
{
"value": "6.6.94",
"evidence": "/affected/1/ranges"
},
{
"value": "6.12.34",
"evidence": "/affected/1/ranges"
},
{
"value": "6.15.3",
"evidence": "/affected/1/ranges"
}
],
"affected_versions": []
}
],
"severity": "unknown",
"structured": {
"id": "CVE-2025-38170",
"aliases": [
"CVE-2025-38170"
],
"affected": [
{
"ranges": [
{
"repo": "https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git",
"type": "GIT",
"events": [
{
"introduced": "8bd7f91c03d886f41d35f6108078d20be5a4a1bd"
},
{
"fixed": "de89368de3894a8db27caeb8fd902ba1c49f696a"
},
{
"fixed": "43be952e885476dafb74aa832c0847b2f4f650c6"
},
{
"fixed": "6103f9ba51a59afb5a0f32299c837377c5a5a693"
},
{
"fixed": "c4a4786d93e99517d6f10ed56b9ffba4ce88d3b3"
},
{
"fixed": "d3eaab3c70905c5467e5c4ea403053d67505adeb"
}
]
}
],
"database_specific": {
"source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2025-38170.json"
}
},
{
"ranges": [
{
"type": "ECOSYSTEM",
"events": [
{
"introduced": "5.19.0"
},
{
"fixed": "6.1.142"
}
]
},
{
"type": "ECOSYSTEM",
"events": [
{
"introduced": "6.2.0"
},
{
"fixed": "6.6.94"
}
]
},
{
"type": "ECOSYSTEM",
"events": [
{
"introduced": "6.7.0"
},
{
"fixed": "6.12.34"
}
]
},
{
"type": "ECOSYSTEM",
"events": [
{
"introduced": "6.13.0"
},
{
"fixed": "6.15.3"
}
]
}
],
"package": {
"name": "Kernel",
"ecosystem": "Linux"
},
"database_specific": {
"source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2025-38170.json"
}
}
],
"modified": "2026-10-28T02:30:41.558786341Z",
"provider": "osv",
"references": [
"https://git.kernel.org/stable/c/43be952e885476dafb74aa832c0847b2f4f650c6",
"https://git.kernel.org/stable/c/6103f9ba51a59afb5a0f32299c837377c5a5a693",
"https://git.kernel.org/stable/c/c4a4786d93e99517d6f10ed56b9ffba4ce88d3b3",
"https://git.kernel.org/stable/c/d3eaab3c70905c5467e5c4ea403053d67505adeb",
"https://git.kernel.org/stable/c/de89368de3894a8db27caeb8fd902ba1c49f696a",
"https://lists.debian.org/debian-lts-announce/2025/10/msg00008.html",
"https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/38xxx/CVE-2025-38170.json",
"https://nvd.nist.gov/vuln/detail/CVE-2025-38170",
"https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git"
],
"provider_metadata": {
"cna_assigner": "Linux",
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/38xxx/CVE-2025-38170.json"
}
},
"related_cves": [
{
"value": "CVE-2025-38170",
"evidence": "/id"
}
],
"security_relevant": true,
"severity_evidence": null
},
"source_id": "core-osv",
"document_id": 508837,
"published_at": "2025-07-03T08:36:09.012+00:00"
}