{"api_version":"1","generated_at":"2026-10-21T17:39:16+00:00","cve":"CVE-2026-98644","urls":{"html":"https://cve.report/CVE-2026-98644","api":"https://cve.report/api/cve/CVE-2026-98644.json","docs":"https://cve.report/api","cve_org":"https://www.cve.org/CVERecord?id=CVE-2026-98644","nvd":"https://nvd.nist.gov/vuln/detail/CVE-2026-98644"},"summary":{"title":"bpf: Avoid soft lockup in __htab_map_lookup_and_delete_batch()","description":"In the Linux kernel, the following vulnerability has been resolved:\n\nbpf: Avoid soft lockup in __htab_map_lookup_and_delete_batch()\n\n__htab_map_lookup_and_delete_batch() has no rescheduling point. The\nbatch count bounds how many entries are copied out, not how many\nbuckets are visited, so one BPF_MAP_LOOKUP_BATCH call can walk the\nmap end to end. The empty-bucket fast path is worse: it stays inside\na single rcu_read_lock() / bpf_disable_instrumentation() section for\nany run of consecutive empty buckets.\n\nThat holds up on small maps, but it falls apart at scale. On a\n144-CPU arm64 host running a CONFIG_PREEMPT_NONE kernel, periodic\nBPF_MAP_LOOKUP_BATCH calls against an LRU hash map with 16,777,216\nbuckets held a CPU inside the batch op for 77+ seconds and triggered\nthe soft lockup watchdog.\n\nCommit 75134f16e7dd (\"bpf: Add schedule points in batch ops\") fixed this\nsame problem in the generic batch ops, but not in this htab-native path,\nwhich every htab-based hash map variant uses for its lookup[_and_delete]\nbatch ops.\n\nComplete that fix here. Leave the critical section after 64 consecutive\nempty buckets, call cond_resched_tasks_rcu_qs(), and resume at the saved\nbucket cursor. No locks are held at that point, and resuming from the\ncursor is already the function's behavior for non-empty buckets. Add the\nsame call to the per-bucket loop after copy_to_user(), where every lock\nhas been dropped. cond_resched_rcu() is not enough here: sleeping with\nbpf_prog_active elevated makes tracing programs on that CPU silently\nskip their invocations.\n\nPlain cond_resched() is not enough either. It is a no-op under PREEMPT\nand PREEMPT_LAZY, the only models arm64 and x86 have offered since\ncommit 7dadeaa6e851 (\"sched: Further restrict the preemption modes\").\nIt is also never a Tasks RCU quiescent state, in any model: the\nreschedule counts as a preemption. The walking task stays a holdout and\nstalls every synchronize_rcu_tasks() caller, ftrace and BPF trampoline\nteardown included, until the syscall returns [1].\ncond_resched_tasks_rcu_qs() is the usual tool for that [2]. It reports\nthe quiescent state at each yield and still reschedules as\ncond_resched() does on PREEMPT_NONE and PREEMPT_VOLUNTARY kernels.","state":"PUBLISHED","assigner":"Linux","published_at":"2026-10-18 16:17:17","updated_at":"2026-10-19 10:19:28"},"problem_types":[],"metrics":[],"references":[{"url":"https://git.kernel.org/stable/c/ca5bd55fc508fbb5c08c62206d02237a5b6fc7e8","name":"https://git.kernel.org/stable/c/ca5bd55fc508fbb5c08c62206d02237a5b6fc7e8","refsource":"416baaa9-dc9f-4396-8d5f-8c081fb06d67","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://git.kernel.org/stable/c/44f9bcb5ab2b268bc763ed3ebec83308b4972936","name":"https://git.kernel.org/stable/c/44f9bcb5ab2b268bc763ed3ebec83308b4972936","refsource":"416baaa9-dc9f-4396-8d5f-8c081fb06d67","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://git.kernel.org/stable/c/5c8b1869cb99a32a962388848cd19604fb41263e","name":"https://git.kernel.org/stable/c/5c8b1869cb99a32a962388848cd19604fb41263e","refsource":"416baaa9-dc9f-4396-8d5f-8c081fb06d67","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://git.kernel.org/stable/c/4e48fe9b1c77966bede0a73feb3059d7595f642d","name":"https://git.kernel.org/stable/c/4e48fe9b1c77966bede0a73feb3059d7595f642d","refsource":"416baaa9-dc9f-4396-8d5f-8c081fb06d67","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://git.kernel.org/stable/c/85136bf22404474a815fc0ed26ec0d1cbc1bc3f9","name":"https://git.kernel.org/stable/c/85136bf22404474a815fc0ed26ec0d1cbc1bc3f9","refsource":"416baaa9-dc9f-4396-8d5f-8c081fb06d67","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://git.kernel.org/stable/c/f0c09de08ec077098b7e1563f2285f1c136cd816","name":"https://git.kernel.org/stable/c/f0c09de08ec077098b7e1563f2285f1c136cd816","refsource":"416baaa9-dc9f-4396-8d5f-8c081fb06d67","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://git.kernel.org/stable/c/77a3b52b4455e6377e549539e757bc55eedefb51","name":"https://git.kernel.org/stable/c/77a3b52b4455e6377e549539e757bc55eedefb51","refsource":"416baaa9-dc9f-4396-8d5f-8c081fb06d67","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-98644","name":"CVE Program record","refsource":"CVE.ORG","tags":["canonical"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-98644","name":"NVD vulnerability detail","refsource":"NVD","tags":["canonical","analysis"]}],"affected":[{"source":"CNA","vendor":"Linux","product":"Linux","version":"affected 057996380a42bb64ccc04383cfa9c0ace4ea11f0 5c8b1869cb99a32a962388848cd19604fb41263e git","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"affected 057996380a42bb64ccc04383cfa9c0ace4ea11f0 ca5bd55fc508fbb5c08c62206d02237a5b6fc7e8 git","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"affected 057996380a42bb64ccc04383cfa9c0ace4ea11f0 77a3b52b4455e6377e549539e757bc55eedefb51 git","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"affected 057996380a42bb64ccc04383cfa9c0ace4ea11f0 f0c09de08ec077098b7e1563f2285f1c136cd816 git","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"affected 057996380a42bb64ccc04383cfa9c0ace4ea11f0 44f9bcb5ab2b268bc763ed3ebec83308b4972936 git","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"affected 057996380a42bb64ccc04383cfa9c0ace4ea11f0 4e48fe9b1c77966bede0a73feb3059d7595f642d git","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"affected 057996380a42bb64ccc04383cfa9c0ace4ea11f0 85136bf22404474a815fc0ed26ec0d1cbc1bc3f9 git","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"affected 5.6","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"unaffected 5.6 semver","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"unaffected 5.15.222 5.15.* semver","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"unaffected 6.1.189 6.1.* semver","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"unaffected 6.6.158 6.6.* semver","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"unaffected 6.12.112 6.12.* semver","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"unaffected 6.18.55 6.18.* semver","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"unaffected 7.2.9 7.2.* semver","platforms":[]},{"source":"CNA","vendor":"Linux","product":"Linux","version":"unaffected 7.3 * original_commit_for_fix","platforms":[]}],"timeline":[],"solutions":[],"workarounds":[],"exploits":[],"credits":[],"nvd_cpes":[],"vendor_comments":[],"enrichments":{"kev":null,"epss":null,"legacy_qids":[]},"source_records":{"cve_program":{"containers":{"cna":{"affected":[{"defaultStatus":"unaffected","product":"Linux","programFiles":["kernel/bpf/hashtab.c"],"repo":"https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git","vendor":"Linux","versions":[{"lessThan":"5c8b1869cb99a32a962388848cd19604fb41263e","status":"affected","version":"057996380a42bb64ccc04383cfa9c0ace4ea11f0","versionType":"git"},{"lessThan":"ca5bd55fc508fbb5c08c62206d02237a5b6fc7e8","status":"affected","version":"057996380a42bb64ccc04383cfa9c0ace4ea11f0","versionType":"git"},{"lessThan":"77a3b52b4455e6377e549539e757bc55eedefb51","status":"affected","version":"057996380a42bb64ccc04383cfa9c0ace4ea11f0","versionType":"git"},{"lessThan":"f0c09de08ec077098b7e1563f2285f1c136cd816","status":"affected","version":"057996380a42bb64ccc04383cfa9c0ace4ea11f0","versionType":"git"},{"lessThan":"44f9bcb5ab2b268bc763ed3ebec83308b4972936","status":"affected","version":"057996380a42bb64ccc04383cfa9c0ace4ea11f0","versionType":"git"},{"lessThan":"4e48fe9b1c77966bede0a73feb3059d7595f642d","status":"affected","version":"057996380a42bb64ccc04383cfa9c0ace4ea11f0","versionType":"git"},{"lessThan":"85136bf22404474a815fc0ed26ec0d1cbc1bc3f9","status":"affected","version":"057996380a42bb64ccc04383cfa9c0ace4ea11f0","versionType":"git"}]},{"defaultStatus":"affected","product":"Linux","programFiles":["kernel/bpf/hashtab.c"],"repo":"https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git","vendor":"Linux","versions":[{"status":"affected","version":"5.6"},{"lessThan":"5.6","status":"unaffected","version":"0","versionType":"semver"},{"lessThanOrEqual":"5.15.*","status":"unaffected","version":"5.15.222","versionType":"semver"},{"lessThanOrEqual":"6.1.*","status":"unaffected","version":"6.1.189","versionType":"semver"},{"lessThanOrEqual":"6.6.*","status":"unaffected","version":"6.6.158","versionType":"semver"},{"lessThanOrEqual":"6.12.*","status":"unaffected","version":"6.12.112","versionType":"semver"},{"lessThanOrEqual":"6.18.*","status":"unaffected","version":"6.18.55","versionType":"semver"},{"lessThanOrEqual":"7.2.*","status":"unaffected","version":"7.2.9","versionType":"semver"},{"lessThanOrEqual":"*","status":"unaffected","version":"7.3","versionType":"original_commit_for_fix"}]}],"cpeApplicability":[{"nodes":[{"cpeMatch":[{"criteria":"cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*","versionEndExcluding":"5.15.222","versionStartIncluding":"5.6","vulnerable":true},{"criteria":"cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*","versionEndExcluding":"6.1.189","versionStartIncluding":"5.6","vulnerable":true},{"criteria":"cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*","versionEndExcluding":"6.6.158","versionStartIncluding":"5.6","vulnerable":true},{"criteria":"cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*","versionEndExcluding":"6.12.112","versionStartIncluding":"5.6","vulnerable":true},{"criteria":"cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*","versionEndExcluding":"6.18.55","versionStartIncluding":"5.6","vulnerable":true},{"criteria":"cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*","versionEndExcluding":"7.2.9","versionStartIncluding":"5.6","vulnerable":true},{"criteria":"cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*","versionEndExcluding":"7.3","versionStartIncluding":"5.6","vulnerable":true}],"negate":false,"operator":"OR"}]}],"descriptions":[{"lang":"en","value":"In the Linux kernel, the following vulnerability has been resolved:\n\nbpf: Avoid soft lockup in __htab_map_lookup_and_delete_batch()\n\n__htab_map_lookup_and_delete_batch() has no rescheduling point. The\nbatch count bounds how many entries are copied out, not how many\nbuckets are visited, so one BPF_MAP_LOOKUP_BATCH call can walk the\nmap end to end. The empty-bucket fast path is worse: it stays inside\na single rcu_read_lock() / bpf_disable_instrumentation() section for\nany run of consecutive empty buckets.\n\nThat holds up on small maps, but it falls apart at scale. On a\n144-CPU arm64 host running a CONFIG_PREEMPT_NONE kernel, periodic\nBPF_MAP_LOOKUP_BATCH calls against an LRU hash map with 16,777,216\nbuckets held a CPU inside the batch op for 77+ seconds and triggered\nthe soft lockup watchdog.\n\nCommit 75134f16e7dd (\"bpf: Add schedule points in batch ops\") fixed this\nsame problem in the generic batch ops, but not in this htab-native path,\nwhich every htab-based hash map variant uses for its lookup[_and_delete]\nbatch ops.\n\nComplete that fix here. Leave the critical section after 64 consecutive\nempty buckets, call cond_resched_tasks_rcu_qs(), and resume at the saved\nbucket cursor. No locks are held at that point, and resuming from the\ncursor is already the function's behavior for non-empty buckets. Add the\nsame call to the per-bucket loop after copy_to_user(), where every lock\nhas been dropped. cond_resched_rcu() is not enough here: sleeping with\nbpf_prog_active elevated makes tracing programs on that CPU silently\nskip their invocations.\n\nPlain cond_resched() is not enough either. It is a no-op under PREEMPT\nand PREEMPT_LAZY, the only models arm64 and x86 have offered since\ncommit 7dadeaa6e851 (\"sched: Further restrict the preemption modes\").\nIt is also never a Tasks RCU quiescent state, in any model: the\nreschedule counts as a preemption. The walking task stays a holdout and\nstalls every synchronize_rcu_tasks() caller, ftrace and BPF trampoline\nteardown included, until the syscall returns [1].\ncond_resched_tasks_rcu_qs() is the usual tool for that [2]. It reports\nthe quiescent state at each yield and still reschedules as\ncond_resched() does on PREEMPT_NONE and PREEMPT_VOLUNTARY kernels."}],"providerMetadata":{"dateUpdated":"2026-10-19T09:23:13.963Z","orgId":"416baaa9-dc9f-4396-8d5f-8c081fb06d67","shortName":"Linux"},"references":[{"url":"https://git.kernel.org/stable/c/5c8b1869cb99a32a962388848cd19604fb41263e"},{"url":"https://git.kernel.org/stable/c/ca5bd55fc508fbb5c08c62206d02237a5b6fc7e8"},{"url":"https://git.kernel.org/stable/c/77a3b52b4455e6377e549539e757bc55eedefb51"},{"url":"https://git.kernel.org/stable/c/f0c09de08ec077098b7e1563f2285f1c136cd816"},{"url":"https://git.kernel.org/stable/c/44f9bcb5ab2b268bc763ed3ebec83308b4972936"},{"url":"https://git.kernel.org/stable/c/4e48fe9b1c77966bede0a73feb3059d7595f642d"},{"url":"https://git.kernel.org/stable/c/85136bf22404474a815fc0ed26ec0d1cbc1bc3f9"}],"title":"bpf: Avoid soft lockup in __htab_map_lookup_and_delete_batch()","x_generator":{"engine":"bippy-1.2.0"}}},"cveMetadata":{"assignerOrgId":"416baaa9-dc9f-4396-8d5f-8c081fb06d67","assignerShortName":"Linux","cveId":"CVE-2026-98644","datePublished":"2026-10-18T15:20:15.380Z","dateReserved":"2026-09-25T10:25:14.362Z","dateUpdated":"2026-10-19T09:23:13.963Z","state":"PUBLISHED"},"dataType":"CVE_RECORD","dataVersion":"5.2"},"nvd":{"publishedDate":"2026-10-18 16:17:17","lastModifiedDate":"2026-10-19 10:19:28","problem_types":[],"metrics":[],"configurations":[]},"legacy_mitre":{"record":{"CveYear":"2026","CveId":"98644","Ordinal":"1","Title":"bpf: Avoid soft lockup in __htab_map_lookup_and_delete_batch()","CVE":"CVE-2026-98644","Year":"2026"},"notes":[{"CveYear":"2026","CveId":"98644","Ordinal":"1","NoteData":"In the Linux kernel, the following vulnerability has been resolved:\n\nbpf: Avoid soft lockup in __htab_map_lookup_and_delete_batch()\n\n__htab_map_lookup_and_delete_batch() has no rescheduling point. The\nbatch count bounds how many entries are copied out, not how many\nbuckets are visited, so one BPF_MAP_LOOKUP_BATCH call can walk the\nmap end to end. The empty-bucket fast path is worse: it stays inside\na single rcu_read_lock() / bpf_disable_instrumentation() section for\nany run of consecutive empty buckets.\n\nThat holds up on small maps, but it falls apart at scale. On a\n144-CPU arm64 host running a CONFIG_PREEMPT_NONE kernel, periodic\nBPF_MAP_LOOKUP_BATCH calls against an LRU hash map with 16,777,216\nbuckets held a CPU inside the batch op for 77+ seconds and triggered\nthe soft lockup watchdog.\n\nCommit 75134f16e7dd (\"bpf: Add schedule points in batch ops\") fixed this\nsame problem in the generic batch ops, but not in this htab-native path,\nwhich every htab-based hash map variant uses for its lookup[_and_delete]\nbatch ops.\n\nComplete that fix here. Leave the critical section after 64 consecutive\nempty buckets, call cond_resched_tasks_rcu_qs(), and resume at the saved\nbucket cursor. No locks are held at that point, and resuming from the\ncursor is already the function's behavior for non-empty buckets. Add the\nsame call to the per-bucket loop after copy_to_user(), where every lock\nhas been dropped. cond_resched_rcu() is not enough here: sleeping with\nbpf_prog_active elevated makes tracing programs on that CPU silently\nskip their invocations.\n\nPlain cond_resched() is not enough either. It is a no-op under PREEMPT\nand PREEMPT_LAZY, the only models arm64 and x86 have offered since\ncommit 7dadeaa6e851 (\"sched: Further restrict the preemption modes\").\nIt is also never a Tasks RCU quiescent state, in any model: the\nreschedule counts as a preemption. The walking task stays a holdout and\nstalls every synchronize_rcu_tasks() caller, ftrace and BPF trampoline\nteardown included, until the syscall returns [1].\ncond_resched_tasks_rcu_qs() is the usual tool for that [2]. It reports\nthe quiescent state at each yield and still reschedules as\ncond_resched() does on PREEMPT_NONE and PREEMPT_VOLUNTARY kernels.","Type":"Description","Title":"bpf: Avoid soft lockup in __htab_map_lookup_and_delete_batch()"}]}}}