CVE-2026-98644bpf: Avoid soft lockup in __htab_map_lookup_and_delete_batch()
- —Not scoredno CVSS score yet
- 0.21%Exploitation in 30 daysEPSS · top 89% of all CVEs
- NoKnown exploitednot in CISA's KEV catalog
- NonePublic exploitsnone known yet
Description
In the Linux kernel, the following vulnerability has been resolved: bpf: Avoid soft lockup in __htab_map_lookup_and_delete_batch() __htab_map_lookup_and_delete_batch() has no rescheduling point. The batch count bounds how many entries are copied out, not how many buckets are visited, so one BPF_MAP_LOOKUP_BATCH call can walk the map end to end. The empty-bucket fast path is worse: it stays inside a single rcu_read_lock() / bpf_disable_instrumentation() section for any run of consecutive empty buckets. That holds up on small maps, but it falls apart at scale. On a 144-CPU arm64 host running a CONFIG_PREEMPT_NONE kernel, periodic BPF_MAP_LOOKUP_BATCH calls against an LRU hash map with 16,777,216 buckets held a CPU inside the batch op for 77+ seconds and triggered the soft lockup watchdog. Commit 75134f16e7dd ("bpf: Add schedule points in batch ops") fixed this same problem in the generic batch ops, but not in this htab-native path, which every htab-based hash map variant uses for its lookup[_and_delete] batch ops. Complete that fix here. Leave the critical section after 64 consecutive empty buckets, call cond_resched_tasks_rcu_qs(), and resume at the saved bucket cursor. No locks are held at that point, and resuming from the cursor is already the function's behavior for non-empty buckets. Add the same call to the per-bucket loop after copy_to_user(), where every lock has been dropped. cond_resched_rcu() is not enough here: sleeping with bpf_prog_active elevated makes tracing programs on that CPU silently skip their invocations. Plain cond_resched() is not enough either. It is a no-op under PREEMPT and PREEMPT_LAZY, the only models arm64 and x86 have offered since commit 7dadeaa6e851 ("sched: Further restrict the preemption modes"). It is also never a Tasks RCU quiescent state, in any model: the reschedule counts as a preemption. The walking task stays a holdout and stalls every synchronize_rcu_tasks() caller, ftrace and BPF trampoline teardown included, until the syscall returns [1]. cond_resched_tasks_rcu_qs() is the usual tool for that [2]. It reports the quiescent state at each yield and still reschedules as cond_resched() does on PREEMPT_NONE and PREEMPT_VOLUNTARY kernels.
Timeline
ID reserved
By Linux
- 23 days later
· 23 days later
Published
- 1 day later
· 1 day later
Record updated
Changes after publication (a new score, a public exploit, EPSS crossing 1, 10 or 50 %, leaving KEV) are kept since November 2026; earlier ones are not known.
Scores
No CVSS score yet: neither the CNA, CISA nor NVD has scored this CVE. NVD status: Received.
- EPSS (exploitation in 30 days)
- 0.21% · top 89% of all CVEs (13 Nov 2026)
The list uses the assigner's score when there is one, then CISA's, then NVD's: Not scored.
Affected products
- affected 057996380a42bb64ccc04383cfa9c0ace4ea11f0 – < 5c8b1869cb99a32a962388848cd19604fb41263e
- affected 057996380a42bb64ccc04383cfa9c0ace4ea11f0 – < ca5bd55fc508fbb5c08c62206d02237a5b6fc7e8
- affected 057996380a42bb64ccc04383cfa9c0ace4ea11f0 – < 77a3b52b4455e6377e549539e757bc55eedefb51
- affected 057996380a42bb64ccc04383cfa9c0ace4ea11f0 – < f0c09de08ec077098b7e1563f2285f1c136cd816
- affected 057996380a42bb64ccc04383cfa9c0ace4ea11f0 – < 44f9bcb5ab2b268bc763ed3ebec83308b4972936
- affected 057996380a42bb64ccc04383cfa9c0ace4ea11f0 – < 4e48fe9b1c77966bede0a73feb3059d7595f642d
- affected 057996380a42bb64ccc04383cfa9c0ace4ea11f0 – < 85136bf22404474a815fc0ed26ec0d1cbc1bc3f9
- affected 5.6
- unaffected < 5.6
- unaffected 5.15.222 – ≤ 5.15.*
- unaffected 6.1.189 – ≤ 6.1.*
- unaffected 6.6.158 – ≤ 6.6.*
- unaffected 6.12.112 – ≤ 6.12.*
- unaffected 6.18.55 – ≤ 6.18.*
- unaffected 7.2.9 – ≤ 7.2.*
- unaffected 7.3 – ≤ *
References
References7
- https://git.kernel.org/stable/c/5c8b1869cb99a32a962388848cd19604fb41263e (opens in a new tab)
- https://git.kernel.org/stable/c/ca5bd55fc508fbb5c08c62206d02237a5b6fc7e8 (opens in a new tab)
- https://git.kernel.org/stable/c/77a3b52b4455e6377e549539e757bc55eedefb51 (opens in a new tab)
- https://git.kernel.org/stable/c/f0c09de08ec077098b7e1563f2285f1c136cd816 (opens in a new tab)
- https://git.kernel.org/stable/c/44f9bcb5ab2b268bc763ed3ebec83308b4972936 (opens in a new tab)
- https://git.kernel.org/stable/c/4e48fe9b1c77966bede0a73feb3059d7595f642d (opens in a new tab)
- https://git.kernel.org/stable/c/85136bf22404474a815fc0ed26ec0d1cbc1bc3f9 (opens in a new tab)
Sources
The same CVE in the primary databases and aggregators, to check against.
- CVE.org record (opens in a new tab)
- CVE List JSON (GitHub) (opens in a new tab)
- NVD (opens in a new tab)
- FIRST EPSS (opens in a new tab)
- EUVD EUVD-2026-103558 (opens in a new tab)
- OSV.dev (opens in a new tab)
- GitHub Advisories (opens in a new tab)
- CIRCL Vulnerability-Lookup (opens in a new tab)
Badge for a README or a ticket
[](https://cveledger.app/cve/CVE-2026-98644)Record last updated .