ghsa-g7p4-4259-746x
Vulnerability from github
In the Linux kernel, the following vulnerability has been resolved:
perf: Fix hang while freeing sigtrap event
Perf can hang while freeing a sigtrap event if a related deferred signal hadn't managed to be sent before the file got closed:
perf_event_overflow() task_work_add(perf_pending_task)
fput() task_work_add(____fput())
task_work_run() ____fput() perf_release() perf_event_release_kernel() _free_event() perf_pending_task_sync() task_work_cancel() -> FAILED rcuwait_wait_event()
Once task_work_run() is running, the list of pending callbacks is removed from the task_struct and from this point on task_work_cancel() can't remove any pending and not yet started work items, hence the task_work_cancel() failure and the hang on rcuwait_wait_event().
Task work could be changed to remove one work at a time, so a work running on the current task can always cancel a pending one, however the wait / wake design is still subject to inverted dependencies when remote targets are involved, as pictured by Oleg:
T1 T2
fd = perf_event_open(pid => T2->pid); fd = perf_event_open(pid => T1->pid); close(fd) close(fd) perf_event_overflow() perf_event_overflow() task_work_add(perf_pending_task) task_work_add(perf_pending_task) fput() fput() task_work_add(_fput()) taskwork_add(__fput())
task_work_run() task_work_run()
____fput() ____fput()
perf_release() perf_release()
perf_event_release_kernel() perf_event_release_kernel()
_free_event() _free_event()
perf_pending_task_sync() perf_pending_task_sync()
rcuwait_wait_event() rcuwait_wait_event()
Therefore the only option left is to acquire the event reference count upon queueing the perf task work and release it from the task work, just like it was done before 3a5465418f5f ("perf: Fix event leak upon exec and file release") but without the leaks it fixed.
Some adjustments are necessary to make it work:
-
A child event might dereference its parent upon freeing. Care must be taken to release the parent last.
-
Some places assuming the event doesn't have any reference held and therefore can be freed right away must instead put the reference and let the reference counting to its job.
{
"affected": [],
"aliases": [
"CVE-2025-37747"
],
"database_specific": {
"cwe_ids": [],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2025-05-01T13:15:53Z",
"severity": null
},
"details": "In the Linux kernel, the following vulnerability has been resolved:\n\nperf: Fix hang while freeing sigtrap event\n\nPerf can hang while freeing a sigtrap event if a related deferred\nsignal hadn\u0027t managed to be sent before the file got closed:\n\nperf_event_overflow()\n task_work_add(perf_pending_task)\n\nfput()\n task_work_add(____fput())\n\ntask_work_run()\n ____fput()\n perf_release()\n perf_event_release_kernel()\n _free_event()\n perf_pending_task_sync()\n task_work_cancel() -\u003e FAILED\n rcuwait_wait_event()\n\nOnce task_work_run() is running, the list of pending callbacks is\nremoved from the task_struct and from this point on task_work_cancel()\ncan\u0027t remove any pending and not yet started work items, hence the\ntask_work_cancel() failure and the hang on rcuwait_wait_event().\n\nTask work could be changed to remove one work at a time, so a work\nrunning on the current task can always cancel a pending one, however\nthe wait / wake design is still subject to inverted dependencies when\nremote targets are involved, as pictured by Oleg:\n\nT1 T2\n\nfd = perf_event_open(pid =\u003e T2-\u003epid); fd = perf_event_open(pid =\u003e T1-\u003epid);\nclose(fd) close(fd)\n \u003cIRQ\u003e \u003cIRQ\u003e\n perf_event_overflow() perf_event_overflow()\n task_work_add(perf_pending_task) task_work_add(perf_pending_task)\n \u003c/IRQ\u003e \u003c/IRQ\u003e\n fput() fput()\n task_work_add(____fput()) task_work_add(____fput())\n\n task_work_run() task_work_run()\n ____fput() ____fput()\n perf_release() perf_release()\n perf_event_release_kernel() perf_event_release_kernel()\n _free_event() _free_event()\n perf_pending_task_sync() perf_pending_task_sync()\n rcuwait_wait_event() rcuwait_wait_event()\n\nTherefore the only option left is to acquire the event reference count\nupon queueing the perf task work and release it from the task work, just\nlike it was done before 3a5465418f5f (\"perf: Fix event leak upon exec and file release\")\nbut without the leaks it fixed.\n\nSome adjustments are necessary to make it work:\n\n* A child event might dereference its parent upon freeing. Care must be\n taken to release the parent last.\n\n* Some places assuming the event doesn\u0027t have any reference held and\n therefore can be freed right away must instead put the reference and\n let the reference counting to its job.",
"id": "GHSA-g7p4-4259-746x",
"modified": "2025-05-01T15:31:42Z",
"published": "2025-05-01T15:31:42Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2025-37747"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/1267bd38f161c1a27d9b722de017027167a225a0"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/56799bc035658738f362acec3e7647bb84e68933"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/665b87b8f8b3aeb49083ef3b65c4953e7753fc12"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/fa1827fa968c0674e9b6fca223fa9fb4da4493eb"
}
],
"schema_version": "1.4.0",
"severity": []
}
Sightings
| Author | Source | Type | Date |
|---|
Nomenclature
- 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.