ghsa-wm2r-7vm2-cpg9
Vulnerability from github
In the Linux kernel, the following vulnerability has been resolved:
KVM: x86/pmu: Disable support for adaptive PEBS
Drop support for virtualizing adaptive PEBS, as KVM's implementation is architecturally broken without an obvious/easy path forward, and because exposing adaptive PEBS can leak host LBRs to the guest, i.e. can leak host kernel addresses to the guest.
Bug #1 is that KVM doesn't account for the upper 32 bits of IA32_FIXED_CTR_CTRL when (re)programming fixed counters, e.g fixed_ctrl_field() drops the upper bits, reprogram_fixed_counters() stores local variables as u8s and truncates the upper bits too, etc.
Bug #2 is that, because KVM always sets precise_ip to a non-zero value for PEBS events, perf will always generate an adaptive record, even if the guest requested a basic record. Note, KVM will also enable adaptive PEBS in individual counter, even if adaptive PEBS isn't exposed to the guest, but this is benign as MSR_PEBS_DATA_CFG is guaranteed to be zero, i.e. the guest will only ever see Basic records.
Bug #3 is in perf. intel_pmu_disable_fixed() doesn't clear the upper bits either, i.e. leaves ICL_FIXED_0_ADAPTIVE set, and intel_pmu_enable_fixed() effectively doesn't clear ICL_FIXED_0_ADAPTIVE either. I.e. perf always enables ADAPTIVE counters, regardless of what KVM requests.
Bug #4 is that adaptive PEBS might effectively bypass event filters set by the host, as "Updated Memory Access Info Group" records information that might be disallowed by userspace via KVM_SET_PMU_EVENT_FILTER.
Bug #5 is that KVM doesn't ensure LBR MSRs hold guest values (or at least zeros) when entering a vCPU with adaptive PEBS, which allows the guest to read host LBRs, i.e. host RIPs/addresses, by enabling "LBR Entries" records.
Disable adaptive PEBS support as an immediate fix due to the severity of the LBR leak in particular, and because fixing all of the bugs will be non-trivial, e.g. not suitable for backporting to stable kernels.
Note! This will break live migration, but trying to make KVM play nice with live migration would be quite complicated, wouldn't be guaranteed to work (i.e. KVM might still kill/confuse the guest), and it's not clear that there are any publicly available VMMs that support adaptive PEBS, let alone live migrate VMs that support adaptive PEBS, e.g. QEMU doesn't support PEBS in any capacity.
{
"affected": [],
"aliases": [
"CVE-2024-26992"
],
"database_specific": {
"cwe_ids": [],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2024-05-01T06:15:16Z",
"severity": null
},
"details": "In the Linux kernel, the following vulnerability has been resolved:\n\nKVM: x86/pmu: Disable support for adaptive PEBS\n\nDrop support for virtualizing adaptive PEBS, as KVM\u0027s implementation is\narchitecturally broken without an obvious/easy path forward, and because\nexposing adaptive PEBS can leak host LBRs to the guest, i.e. can leak\nhost kernel addresses to the guest.\n\nBug #1 is that KVM doesn\u0027t account for the upper 32 bits of\nIA32_FIXED_CTR_CTRL when (re)programming fixed counters, e.g\nfixed_ctrl_field() drops the upper bits, reprogram_fixed_counters()\nstores local variables as u8s and truncates the upper bits too, etc.\n\nBug #2 is that, because KVM _always_ sets precise_ip to a non-zero value\nfor PEBS events, perf will _always_ generate an adaptive record, even if\nthe guest requested a basic record. Note, KVM will also enable adaptive\nPEBS in individual *counter*, even if adaptive PEBS isn\u0027t exposed to the\nguest, but this is benign as MSR_PEBS_DATA_CFG is guaranteed to be zero,\ni.e. the guest will only ever see Basic records.\n\nBug #3 is in perf. intel_pmu_disable_fixed() doesn\u0027t clear the upper\nbits either, i.e. leaves ICL_FIXED_0_ADAPTIVE set, and\nintel_pmu_enable_fixed() effectively doesn\u0027t clear ICL_FIXED_0_ADAPTIVE\neither. I.e. perf _always_ enables ADAPTIVE counters, regardless of what\nKVM requests.\n\nBug #4 is that adaptive PEBS *might* effectively bypass event filters set\nby the host, as \"Updated Memory Access Info Group\" records information\nthat might be disallowed by userspace via KVM_SET_PMU_EVENT_FILTER.\n\nBug #5 is that KVM doesn\u0027t ensure LBR MSRs hold guest values (or at least\nzeros) when entering a vCPU with adaptive PEBS, which allows the guest\nto read host LBRs, i.e. host RIPs/addresses, by enabling \"LBR Entries\"\nrecords.\n\nDisable adaptive PEBS support as an immediate fix due to the severity of\nthe LBR leak in particular, and because fixing all of the bugs will be\nnon-trivial, e.g. not suitable for backporting to stable kernels.\n\nNote! This will break live migration, but trying to make KVM play nice\nwith live migration would be quite complicated, wouldn\u0027t be guaranteed to\nwork (i.e. KVM might still kill/confuse the guest), and it\u0027s not clear\nthat there are any publicly available VMMs that support adaptive PEBS,\nlet alone live migrate VMs that support adaptive PEBS, e.g. QEMU doesn\u0027t\nsupport PEBS in any capacity.",
"id": "GHSA-wm2r-7vm2-cpg9",
"modified": "2024-05-03T03:30:46Z",
"published": "2024-05-01T06:31:43Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2024-26992"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/037e48ceccf163899374b601afb6ae8d0bf1d2ac"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/0fb74c00d140a66128afc0003785dcc57e69d312"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/7a7650b3ac23e5fc8c990f00e94f787dc84e3175"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/9e985cbf2942a1bb8fcef9adc2a17d90fd7ca8ee"
},
{
"type": "WEB",
"url": "https://lists.fedoraproject.org/archives/list/package-announce@lists.fedoraproject.org/message/4EZ6PJW7VOZ224TD7N4JZNU6KV32ZJ53"
},
{
"type": "WEB",
"url": "https://lists.fedoraproject.org/archives/list/package-announce@lists.fedoraproject.org/message/DAMSOZXJEPUOXW33WZYWCVAY7Z5S7OOY"
},
{
"type": "WEB",
"url": "https://lists.fedoraproject.org/archives/list/package-announce@lists.fedoraproject.org/message/GCBZZEC7L7KTWWAS2NLJK6SO3IZIL4WW"
}
],
"schema_version": "1.4.0",
"severity": []
}
- Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
- Confirmed: The vulnerability is confirmed from an analyst perspective.
- Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
- Patched: This vulnerability was successfully patched by the user reporting the sighting.
- Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
- Not confirmed: The user expresses doubt about the veracity of the vulnerability.
- Not patched: This vulnerability was not successfully patched by the user reporting the sighting.