GHSA-QV9G-M2J2-JRGJ
Vulnerability from github – Published: 2026-09-11 21:31 – Updated: 2026-09-14 15:32In the Linux kernel, the following vulnerability has been resolved:
s390/cpum_cf: Handle CPU hotplug via prepare/dead callbacks
The command 'perf stat -e cycles -- ' crashes the kernel when CPUs are hotplug added during that run.
Root cause is the allocation of struct cpu_cf_events at first event initialization. The allocation is dynamic and the first event that has task context creates such a structure for each online CPU. This is not sufficient. CPUs may be offline during event creation and can be set online during the perf run time. For example commands
# echo 0 > /sys/devices/system/cpu/cpu1/online # perf stat -e cycles -i -- stress-ng -t10s --matrix X # sleep 1 # echo 1 > /sys/devices/system/cpu/cpu1/online
create an event for CPUs 0,2-X. Since the events are created with task-context, the scheduler will eventually schedule the program on CPU1. This CPU has not created and initialized any per CPU event infrastructure as that CPU was not online at the time of the perf invocation. Thus when the scheduler runs stress-ng on CPU1, the function cpumf_pmu_add() refers to a NULL pointer:
struct cpu_cf_events *cpuhw = this_cpu_cfhw();
This function call is invoked after the task stress-ng has been made runnable on CPU1. And this_cpu_cfhw() returns NULL.
The result is a panic: Unable to handle kernel pointer dereference in virtual kernel address space Failing address: 0000000000000000 TEID: 0000000000000483 .... Krnl PSW : 0404d00180000000 000003ef8291fd0c (cpumf_pmu_add+0x3c/0x80) .... Call Trace: [<000003ef8291fd0c>] cpumf_pmu_add+0x3c/0x80 [<000003ef82bb5e3e>] event_sched_in+0xae/0x190 [<000003ef82bb60d6>] merge_sched_in+0x1b6/0x390 [<000003ef82bb65b8>] visit_groups_merge.constprop.0.isra.0+0x308/0x5b0 [<000003ef82bb689a>] pmu_groups_sched_in+0x3a/0x50 [<000003ef82bb6a30>] ctx_sched_in+0x180/0x260 [<000003ef82bb780c>] perf_event_context_sched_in+0x11c/0x2d0 [<000003ef82bb79ee>] __perf_event_task_sched_in+0x2e/0xc0 [<000003ef82994834>] finish_task_switch.isra.0+0x1a4/0x250 .... Last Breaking-Event-Address: [<000003ef8291f1d8>] this_cpu_cfhw+0x38/0x40
The issue arises only in per-task context when the CPUMF facility is used and the scheduler picks a random CPU for such a process to run on. The scheduler enables the CPUMF infrastructure via PMU callback functions pmu::add() and pmu::del().
Introduce a CPU hotplug prepare/dead callback pair which creates and removes the per CPU counter data while the CPU is offline. Count the users which track every CPU (cpu == -1), that is perf_event_open() events with task context and /dev/hwctr device sessions, in the new counter cpu_cf_root::tskcnt, protected by pmc_reserve_mutex. This ensures the infrastructure is available when new CPU is selected to run the per-task context process.
In cpum_cf_free_root() and cpum_cf_free_cpu() ensure the reference pointer to data structures is set to NULL before the data is freed to prevent interrupt handlers to access stale data.
[gor@linux.ibm.com: change commit message]
{
"affected": [],
"aliases": [
"CVE-2026-89460"
],
"database_specific": {
"cwe_ids": [],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-09-11T20:19:26Z",
"severity": null
},
"details": "In the Linux kernel, the following vulnerability has been resolved:\n\ns390/cpum_cf: Handle CPU hotplug via prepare/dead callbacks\n\nThe command \u0027perf stat -e cycles -- \u003ccommand\u003e\u0027 crashes the kernel\nwhen CPUs are hotplug added during that run.\n\nRoot cause is the allocation of struct cpu_cf_events at first\nevent initialization. The allocation is dynamic and the first\nevent that has task context creates such a structure for\neach online CPU. This is not sufficient. CPUs may be offline\nduring event creation and can be set online during the\nperf run time. For example commands\n\n # echo 0 \u003e /sys/devices/system/cpu/cpu1/online\n # perf stat -e cycles -i -- stress-ng -t10s --matrix X\n # sleep 1\n # echo 1 \u003e /sys/devices/system/cpu/cpu1/online\n\ncreate an event for CPUs 0,2-X. Since the events are created with\ntask-context, the scheduler will eventually schedule the program\non CPU1. This CPU has not created and initialized any per\nCPU event infrastructure as that CPU was not online at the time\nof the perf invocation. Thus when the scheduler runs stress-ng\non CPU1, the function cpumf_pmu_add() refers to a NULL pointer:\n\n struct cpu_cf_events *cpuhw = this_cpu_cfhw();\n\nThis function call is invoked after the task stress-ng has been\nmade runnable on CPU1. And this_cpu_cfhw() returns NULL.\n\nThe result is a panic:\nUnable to handle kernel pointer dereference in virtual kernel address space\nFailing address: 0000000000000000 TEID: 0000000000000483\n....\nKrnl PSW : 0404d00180000000 000003ef8291fd0c (cpumf_pmu_add+0x3c/0x80)\n....\nCall Trace:\n [\u003c000003ef8291fd0c\u003e] cpumf_pmu_add+0x3c/0x80\n [\u003c000003ef82bb5e3e\u003e] event_sched_in+0xae/0x190\n [\u003c000003ef82bb60d6\u003e] merge_sched_in+0x1b6/0x390\n [\u003c000003ef82bb65b8\u003e] visit_groups_merge.constprop.0.isra.0+0x308/0x5b0\n [\u003c000003ef82bb689a\u003e] pmu_groups_sched_in+0x3a/0x50\n [\u003c000003ef82bb6a30\u003e] ctx_sched_in+0x180/0x260\n [\u003c000003ef82bb780c\u003e] perf_event_context_sched_in+0x11c/0x2d0\n [\u003c000003ef82bb79ee\u003e] __perf_event_task_sched_in+0x2e/0xc0\n [\u003c000003ef82994834\u003e] finish_task_switch.isra.0+0x1a4/0x250\n....\nLast Breaking-Event-Address:\n [\u003c000003ef8291f1d8\u003e] this_cpu_cfhw+0x38/0x40\n\nThe issue arises only in per-task context when the CPUMF facility is\nused and the scheduler picks a random CPU for such a process to run on.\nThe scheduler enables the CPUMF infrastructure via PMU callback\nfunctions pmu::add() and pmu::del().\n\nIntroduce a CPU hotplug prepare/dead callback pair which creates and\nremoves the per CPU counter data while the CPU is offline. Count the\nusers which track every CPU (cpu == -1), that is perf_event_open()\nevents with task context and /dev/hwctr device sessions, in the new\ncounter cpu_cf_root::tskcnt, protected by pmc_reserve_mutex.\nThis ensures the infrastructure is available when\nnew CPU is selected to run the per-task context process.\n\nIn cpum_cf_free_root() and cpum_cf_free_cpu() ensure the reference\npointer to data structures is set to NULL before the data is freed\nto prevent interrupt handlers to access stale data.\n\n[gor@linux.ibm.com: change commit message]",
"id": "GHSA-qv9g-m2j2-jrgj",
"modified": "2026-09-14T15:32:24Z",
"published": "2026-09-11T21:31:27Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-89460"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/337bd95507a16063687cfc286ea90de5cca48c37"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/71d46de9153e067c63a15f3b00e6364e1c0230f8"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/777d040c2f91d8d929b4a32333dfe4102b27caea"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/991be92489bc7b1b6e7903debb96bd58c892dee4"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/dcce7a06ea690d5cf46a705a9b74cf0398ac091f"
}
],
"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.
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.