ALT-PU-2026-7350-9 — kernel-image-pine

BDU:2026-04784

MEDIUM5.5

Уязвимость функции acpi_processor_errata_piix4() ядра операционной системы Linux, позволяющая нарушителю вызвать повреждение памяти

Published: 2026-04-06Modified: 2026-04-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0MEDIUM 4.6

CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C

References

CVE-2026-23443

BDU:2026-04852

HIGH7.5

Уязвимость функции icmp_tag_validation() ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-04-07Modified: 2026-05-14

CVSS 3.xHIGH 7.5

CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0HIGH 7.8

CVSS:2.0/AV:N/AC:L/Au:N/C:N/I:N/A:C

References

CVE-2026-23398

BDU:2026-04924

HIGH7.8

Уязвимость компонента ksmbd ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-04-08Modified: 2026-05-14

CVSS 3.xHIGH 7.8

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0MEDIUM 6.8

CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C

References

CVE-2026-31410

BDU:2026-04925

HIGH7.0

Уязвимость функции sco_recv_frame() ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Published: 2026-04-08Modified: 2026-05-14

CVSS 3.xHIGH 7.0

CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0MEDIUM 6.0

CVSS:2.0/AV:L/AC:H/Au:S/C:C/I:C/A:C

References

CVE-2026-31408

BDU:2026-04926

MEDIUM5.3

Уязвимость компонента ksmbd ядра операционной системы Linux, позволяющая нарушителю получить несанкционированный доступ к защищаемой информации

Published: 2026-04-08Modified: 2026-05-14

CVSS 3.xMEDIUM 5.3

CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L

CVSS 2.0MEDIUM 5.0

CVSS:2.0/AV:N/AC:L/Au:N/C:N/I:N/A:P

References

CVE-2026-31409

BDU:2026-04968

HIGH7.1

Уязвимость подсистемы управления памятью mm/mseal ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-04-09

CVSS 3.xHIGH 7.1

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:H

CVSS 2.0MEDIUM 6.2

CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:C/A:C

References

CVE-2026-23416

BDU:2026-05099

HIGH7.0

Уязвимость функции nlattr_to_sctp() ядра операционных систем Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Published: 2026-04-12Modified: 2026-05-14

CVSS 3.xHIGH 7.0

CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0MEDIUM 6.0

CVSS:2.0/AV:L/AC:H/Au:S/C:C/I:C/A:C

References

CVE-2026-31407

BDU:2026-05258

HIGH7.0

Уязвимость компонента NFSv4.0 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-04-13Modified: 2026-05-14

CVSS 3.xHIGH 7.0

CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0MEDIUM 6.0

CVSS:2.0/AV:L/AC:H/Au:S/C:C/I:C/A:C

References

BDU:2026-05267

HIGH7.0

Уязвимость функции maybe_fork_scalars() ядра операционных систем Linux, позволяющая нарушителю оказать влияние на конфиденциальность, целостность и доступность защищаемой информации

Published: 2026-04-13Modified: 2026-05-05

CVSS 3.xHIGH 7.0

CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0MEDIUM 6.0

CVSS:2.0/AV:L/AC:H/Au:S/C:C/I:C/A:C

References

BDU:2026-05764

MEDIUM5.5

Уязвимость компонента sunrpc ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-04-23Modified: 2026-05-14

CVSS 3.xMEDIUM 5.5

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0MEDIUM 4.6

CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C

References

BDU:2026-05765

MEDIUM4.4

Уязвимость компонента BPF ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании или раскрыть защищаемую информацию

Published: 2026-04-23Modified: 2026-05-14

CVSS 3.xMEDIUM 4.4

CVSS:3.x/AV:L/AC:L/PR:H/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0MEDIUM 4.6

CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C

References

BDU:2026-05766

MEDIUM5.5

Уязвимость компонента NFSD ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-04-23Modified: 2026-05-14

CVSS 3.xMEDIUM 5.5

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0MEDIUM 4.6

CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C

References

BDU:2026-05767

MEDIUM5.5

Уязвимость модуля управления памятью (MMU) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-04-23

CVSS 3.xMEDIUM 5.5

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0MEDIUM 4.6

CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C

References

BDU:2026-05768

MEDIUM4.7

Уязвимость функции nd_async_device_register() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-04-23Modified: 2026-05-14

CVSS 3.xMEDIUM 4.7

CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0LOW 3.8

CVSS:2.0/AV:L/AC:H/Au:S/C:N/I:N/A:C

References

BDU:2026-05795

MEDIUM5.5

Уязвимость функции svc_export_put() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-04-23

CVSS 3.xMEDIUM 5.5

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0MEDIUM 4.6

CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C

References

BDU:2026-05796

MEDIUM5.5

Уязвимость функции move_pages_huge_pmd() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-04-23

CVSS 3.xMEDIUM 5.5

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0MEDIUM 4.6

CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C

References

CVE-2026-31397

BDU:2026-06123

HIGH7.8

Уязвимость модуля для реализации AEAD-алгоритмов algif_aead ядра операционной системы Linux, позволяющая нарушителю повысить свои привилегии

Published: 2026-04-29Modified: 2026-05-19

CVSS 3.xHIGH 7.8

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0MEDIUM 6.8

CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C

References

CVE-2026-31431

BDU:2026-06493

MEDIUM5.5

Уязвимость функции tc_chain_fill_node() ядра операционных систем Linux, позволяющая нарушителю получить несанкционированный доступ к конфиденциальной информации

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xMEDIUM 5.5

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0MEDIUM 4.6

CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C

References

CVE-2026-43035

BDU:2026-06494

MEDIUM5.5

Уязвимость функции gso_features_check() ядра операционных систем Linux, позволяющая нарушителю получить несанкционированный доступ к конфиденциальной информации

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xMEDIUM 5.5

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0MEDIUM 4.6

CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C

References

CVE-2026-43036

BDU:2026-06495

HIGH8.4

Уязвимость функции pn532_receive_buf() ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xHIGH 8.4

CVSS:3.x/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0HIGH 7.2

CVSS:2.0/AV:L/AC:L/Au:N/C:C/I:C/A:C

References

CVE-2026-43032

BDU:2026-06496

HIGH7.5

Уязвимость функции mptcp_recvmsg() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-05-11

CVSS 3.xHIGH 7.5

CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0HIGH 7.8

CVSS:2.0/AV:N/AC:L/Au:N/C:N/I:N/A:C

References

CVE-2026-43029

BDU:2026-06497

HIGH7.0

Уязвимость функции nf_conntrack_helper_unregister() ядра операционных систем Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xHIGH 7.0

CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0MEDIUM 6.0

CVSS:2.0/AV:L/AC:H/Au:S/C:C/I:C/A:C

References

CVE-2026-43027

BDU:2026-06498

MEDIUM5.5

Уязвимость функции ctnetlink_alloc_expect() ядра операционных систем Linux, позволяющая нарушителю раскрыть конфиденциальную информацию

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xMEDIUM 5.5

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0MEDIUM 4.6

CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C

References

CVE-2026-43026

BDU:2026-06499

HIGH7.3

Уязвимость функции hci_cmd_sync_queue_once() ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xHIGH 7.3

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:H

CVSS 2.0MEDIUM 6.4

CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:P/A:C

References

CVE-2026-43025

BDU:2026-06501

HIGH8.4

Уязвимость функции nft_queue() ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xHIGH 8.4

CVSS:3.x/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0HIGH 7.2

CVSS:2.0/AV:L/AC:L/Au:N/C:C/I:C/A:C

References

CVE-2026-43024

BDU:2026-06503

HIGH7.1

Уязвимость компонента netfilter x_tables ядра операционных систем Linux, позволяющая нарушителю оказать воздействие на конфиденциальность и доступность защищаемой информации

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xHIGH 7.1

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

CVSS 2.0MEDIUM 6.2

CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:N/A:C

References

CVE-2026-43028

BDU:2026-06504

MEDIUM5.5

Уязвимость функции bnxt_hwrm_func_backing_store_qcaps_v2() ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-05-11

CVSS 3.xMEDIUM 5.5

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0MEDIUM 4.6

CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C

References

CVE-2026-43034

BDU:2026-06505

HIGH7.8

Уязвимость функции regsafe() ядра операционных систем Linux, позволяющая нарушителю раскрыть конфиденциальную информацию или вызвать отказ в обслуживании

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xHIGH 7.8

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0MEDIUM 6.8

CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C

References

CVE-2026-43030

BDU:2026-06506

HIGH7.8

Уязвимость модуля crypto/authencesn.c ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xHIGH 7.8

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0MEDIUM 6.8

CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C

References

CVE-2026-43033

BDU:2026-06507

HIGH7.8

Уязвимость функции set_cig_params_sync() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xHIGH 7.8

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0MEDIUM 6.8

CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C

References

CVE-2026-43019

BDU:2026-06508

HIGH8.8

Уязвимость функции hci_le_remote_conn_param_req_evt() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xHIGH 8.8

CVSS:3.x/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0HIGH 8.3

CVSS:2.0/AV:A/AC:L/Au:N/C:C/I:C/A:C

References

CVE-2026-43018

BDU:2026-06509

HIGH7.8

Уязвимость модуля net/core/skmsg.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xHIGH 7.8

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0MEDIUM 6.8

CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C

References

CVE-2026-43016

BDU:2026-06510

MEDIUM5.5

Уязвимость модуля net/bluetooth/mgmt.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xMEDIUM 5.5

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0MEDIUM 4.6

CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C

References

CVE-2026-43017

BDU:2026-06511

HIGH7.8

Уязвимость модуля drivers/net/ethernet/cadence/macb_pci.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-05-11Modified: 2026-05-14

CVSS 3.xHIGH 7.8

CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

CVSS 2.0MEDIUM 6.8

CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C

References

CVE-2026-43015

BDU:2026-07086

HIGH7.5

Уязвимость функции rxgk_verify_response() компонента rxrpc операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Published: 2026-05-19

CVSS 3.xHIGH 7.5

CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

CVSS 2.0HIGH 7.8

CVSS:2.0/AV:N/AC:L/Au:N/C:N/I:N/A:C

References

CVE-2026-31635

CVE-2026-23389

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ice: Fix memory leak in ice_set_ringparam() In ice_set_ringparam, tx_rings and xdp_rings are allocated before rx_rings. If the allocation of rx_rings fails, the code jumps to the done label leaking both tx_rings and xdp_rings. Furthermore, if the setup of an individual Rx ring fails during the loop, the code jumps to the free_tx label which releases tx_rings but leaks xdp_rings. Fix this by introducing a free_xdp label and updating the error paths to ensure both xdp_rings and tx_rings are properly freed if rx_rings allocation or setup fails. Compile tested only. Issue found using a prototype static analysis tool and code review.

Published: 2026-03-25Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23391

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: xt_CT: drop pending enqueued packets on template removal Templates refer to objects that can go away while packets are sitting in nfqueue refer to: - helper, this can be an issue on module removal. - timeout policy, nfnetlink_cttimeout might remove it. The use of templates with zone and event cache filter are safe, since this just copies values. Flush these enqueued packets in case the template rule gets removed.

Published: 2026-03-25Modified: 2026-04-24

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23392

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: release flowtable after rcu grace period on error Call synchronize_rcu() after unregistering the hooks from error path, since a hook that already refers to this flowtable can be already registered, exposing this flowtable to packet path and nfnetlink_hook control plane. This error path is rare, it should only happen by reaching the maximum number hooks or by failing to set up to hardware offload, just call synchronize_rcu(). There is a check for already used device hooks by different flowtable that could result in EEXIST at this late stage. The hook parser can be updated to perform this check earlier to this error path really becomes rarely exercised. Uncovered by KASAN reported as use-after-free from nfnetlink_hook path when dumping hooks.

Published: 2026-03-25Modified: 2026-04-24

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23393

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bridge: cfm: Fix race condition in peer_mep deletion When a peer MEP is being deleted, cancel_delayed_work_sync() is called on ccm_rx_dwork before freeing. However, br_cfm_frame_rx() runs in softirq context under rcu_read_lock (without RTNL) and can re-schedule ccm_rx_dwork via ccm_rx_timer_start() between cancel_delayed_work_sync() returning and kfree_rcu() being called. The following is a simple race scenario: cpu0 cpu1 mep_delete_implementation() cancel_delayed_work_sync(ccm_rx_dwork); br_cfm_frame_rx() // peer_mep still in hlist if (peer_mep->ccm_defect) ccm_rx_timer_start() queue_delayed_work(ccm_rx_dwork) hlist_del_rcu(&peer_mep->head); kfree_rcu(peer_mep, rcu); ccm_rx_work_expired() // on freed peer_mep To prevent this, cancel_delayed_work_sync() is replaced with disable_delayed_work_sync() in both peer MEP deletion paths, so that subsequent queue_delayed_work() calls from br_cfm_frame_rx() are silently rejected. The cc_peer_disable() helper retains cancel_delayed_work_sync() because it is also used for the CC enable/disable toggle path where the work must remain re-schedulable.

Published: 2026-03-25Modified: 2026-04-24

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23394

MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: af_unix: Give up GC if MSG_PEEK intervened. Igor Ushakov reported that GC purged the receive queue of an alive socket due to a race with MSG_PEEK with a nice repro. This is the exact same issue previously fixed by commit cbcf01128d0a ("af_unix: fix garbage collect vs MSG_PEEK"). After GC was replaced with the current algorithm, the cited commit removed the locking dance in unix_peek_fds() and reintroduced the same issue. The problem is that MSG_PEEK bumps a file refcount without interacting with GC. Consider an SCC containing sk-A and sk-B, where sk-A is close()d but can be recv()ed via sk-B. The bad thing happens if sk-A is recv()ed with MSG_PEEK from sk-B and sk-B is close()d while GC is checking unix_vertex_dead() for sk-A and sk-B. GC thread User thread --------- ----------- unix_vertex_dead(sk-A) -> true <------. \ `------ recv(sk-B, MSG_PEEK) invalidate !! -> sk-A's file refcount : 1 -> 2 close(sk-B) -> sk-B's file refcount : 2 -> 1 unix_vertex_dead(sk-B) -> true Initially, sk-A's file refcount is 1 by the inflight fd in sk-B recvq. GC thinks sk-A is dead because the file refcount is the same as the number of its inflight fds. However, sk-A's file refcount is bumped silently by MSG_PEEK, which invalidates the previous evaluation. At this moment, sk-B's file refcount is 2; one by the open fd, and one by the inflight fd in sk-A. The subsequent close() releases one refcount by the former. Finally, GC incorrectly concludes that both sk-A and sk-B are dead. One option is to restore the locking dance in unix_peek_fds(), but we can resolve this more elegantly thanks to the new algorithm. The point is that the issue does not occur without the subsequent close() and we actually do not need to synchronise MSG_PEEK with the dead SCC detection. When the issue occurs, close() and GC touch the same file refcount. If GC sees the refcount being decremented by close(), it can just give up garbage-collecting the SCC. Therefore, we only need to signal the race during MSG_PEEK with a proper memory barrier to make it visible to the GC. Let's use seqcount_t to notify GC when MSG_PEEK occurs and let it defer the SCC to the next run. This way no locking is needed on the MSG_PEEK side, and we can avoid imposing a penalty on every MSG_PEEK unnecessarily. Note that we can retry within unix_scc_dead() if MSG_PEEK is detected, but we do not do so to avoid hung task splat from abusive MSG_PEEK calls.

Published: 2026-03-25Modified: 2026-04-24

CVSS 3.xMEDIUM 4.7

CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23395

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix accepting multiple L2CAP_ECRED_CONN_REQ Currently the code attempts to accept requests regardless of the command identifier which may cause multiple requests to be marked as pending (FLAG_DEFER_SETUP) which can cause more than L2CAP_ECRED_MAX_CID(5) to be allocated in l2cap_ecred_rsp_defer causing an overflow. The spec is quite clear that the same identifier shall not be used on subsequent requests: 'Within each signaling channel a different Identifier shall be used for each successive request or indication.' https://www.bluetooth.com/wp-content/uploads/Files/Specification/HTML/Core-62/out/en/host/logical-link-control-and-adaptation-protocol-specification.html#UUID-32a25a06-4aa4-c6c7-77c5-dcfe3682355d So this attempts to check if there are any channels pending with the same identifier and rejects if any are found.

Published: 2026-03-25Modified: 2026-04-24

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23396

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: fix NULL deref in mesh_matches_local() mesh_matches_local() unconditionally dereferences ie->mesh_config to compare mesh configuration parameters. When called from mesh_rx_csa_frame(), the parsed action-frame elements may not contain a Mesh Configuration IE, leaving ie->mesh_config NULL and triggering a kernel NULL pointer dereference. The other two callers are already safe: - ieee80211_mesh_rx_bcn_presp() checks !elems->mesh_config before calling mesh_matches_local() - mesh_plink_get_event() is only reached through mesh_process_plink_frame(), which checks !elems->mesh_config, too mesh_rx_csa_frame() is the only caller that passes raw parsed elements to mesh_matches_local() without guarding mesh_config. An adjacent attacker can exploit this by sending a crafted CSA action frame that includes a valid Mesh ID IE but omits the Mesh Configuration IE, crashing the kernel. The captured crash log: Oops: general protection fault, probably for non-canonical address ... KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] Workqueue: events_unbound cfg80211_wiphy_work [...] Call Trace: ? __pfx_mesh_matches_local (net/mac80211/mesh.c:65) ieee80211_mesh_rx_queued_mgmt (net/mac80211/mesh.c:1686) [...] ieee80211_iface_work (net/mac80211/iface.c:1754 net/mac80211/iface.c:1802) [...] cfg80211_wiphy_work (net/wireless/core.c:426) process_one_work (net/kernel/workqueue.c:3280) ? assign_work (net/kernel/workqueue.c:1219) worker_thread (net/kernel/workqueue.c:3352) ? __pfx_worker_thread (net/kernel/workqueue.c:3385) kthread (net/kernel/kthread.c:436) [...] ret_from_fork_asm (net/arch/x86/entry/entry_64.S:255) This patch adds a NULL check for ie->mesh_config at the top of mesh_matches_local() to return false early when the Mesh Configuration IE is absent.

Published: 2026-03-26Modified: 2026-04-24

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23397

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: nfnetlink_osf: validate individual option lengths in fingerprints nfnl_osf_add_callback() validates opt_num bounds and string NUL-termination but does not check individual option length fields. A zero-length option causes nf_osf_match_one() to enter the option matching loop even when foptsize sums to zero, which matches packets with no TCP options where ctx->optp is NULL: Oops: general protection fault KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:nf_osf_match_one (net/netfilter/nfnetlink_osf.c:98) Call Trace: nf_osf_match (net/netfilter/nfnetlink_osf.c:227) xt_osf_match_packet (net/netfilter/xt_osf.c:32) ipt_do_table (net/ipv4/netfilter/ip_tables.c:293) nf_hook_slow (net/netfilter/core.c:623) ip_local_deliver (net/ipv4/ip_input.c:262) ip_rcv (net/ipv4/ip_input.c:573) Additionally, an MSS option (kind=2) with length < 4 causes out-of-bounds reads when nf_osf_match_one() unconditionally accesses optp[2] and optp[3] for MSS value extraction. While RFC 9293 section 3.2 specifies that the MSS option is always exactly 4 bytes (Kind=2, Length=4), the check uses "< 4" rather than "!= 4" because lengths greater than 4 do not cause memory safety issues -- the buffer is guaranteed to be at least foptsize bytes by the ctx->optsize == foptsize check. Reject fingerprints where any option has zero length, or where an MSS option has length less than 4, at add time rather than trusting these values in the packet matching hot path.

Published: 2026-03-26Modified: 2026-04-24

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-23398

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: icmp: fix NULL pointer dereference in icmp_tag_validation() icmp_tag_validation() unconditionally dereferences the result of rcu_dereference(inet_protos[proto]) without checking for NULL. The inet_protos[] array is sparse -- only about 15 of 256 protocol numbers have registered handlers. When ip_no_pmtu_disc is set to 3 (hardened PMTU mode) and the kernel receives an ICMP Fragmentation Needed error with a quoted inner IP header containing an unregistered protocol number, the NULL dereference causes a kernel panic in softirq context. Oops: general protection fault, probably for non-canonical address 0xdffffc0000000002: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] RIP: 0010:icmp_unreach (net/ipv4/icmp.c:1085 net/ipv4/icmp.c:1143) Call Trace: icmp_rcv (net/ipv4/icmp.c:1527) ip_protocol_deliver_rcu (net/ipv4/ip_input.c:207) ip_local_deliver_finish (net/ipv4/ip_input.c:242) ip_local_deliver (net/ipv4/ip_input.c:262) ip_rcv (net/ipv4/ip_input.c:573) __netif_receive_skb_one_core (net/core/dev.c:6164) process_backlog (net/core/dev.c:6628) handle_softirqs (kernel/softirq.c:561) Add a NULL check before accessing icmp_strict_tag_validation. If the protocol has no registered handler, return false since it cannot perform strict tag validation.

Published: 2026-03-26Modified: 2026-04-24

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23399

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: nf_tables: nft_dynset: fix possible stateful expression memleak in error path If cloning the second stateful expression in the element via GFP_ATOMIC fails, then the first stateful expression remains in place without being released. unreferenced object (percpu) 0x607b97e9cab8 (size 16): comm "softirq", pid 0, jiffies 4294931867 hex dump (first 16 bytes on cpu 3): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 backtrace (crc 0): pcpu_alloc_noprof+0x453/0xd80 nft_counter_clone+0x9c/0x190 [nf_tables] nft_expr_clone+0x8f/0x1b0 [nf_tables] nft_dynset_new+0x2cb/0x5f0 [nf_tables] nft_rhash_update+0x236/0x11c0 [nf_tables] nft_dynset_eval+0x11f/0x670 [nf_tables] nft_do_chain+0x253/0x1700 [nf_tables] nft_do_chain_ipv4+0x18d/0x270 [nf_tables] nf_hook_slow+0xaa/0x1e0 ip_local_deliver+0x209/0x330

Published: 2026-03-28Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23401

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: KVM: x86/mmu: Drop/zap existing present SPTE even when creating an MMIO SPTE When installing an emulated MMIO SPTE, do so after dropping/zapping the existing SPTE (if it's shadow-present). While commit a54aa15c6bda3 was right about it being impossible to convert a shadow-present SPTE to an MMIO SPTE due to a _guest_ write, it failed to account for writes to guest memory that are outside the scope of KVM. E.g. if host userspace modifies a shadowed gPTE to switch from a memslot to emulted MMIO and then the guest hits a relevant page fault, KVM will install the MMIO SPTE without first zapping the shadow-present SPTE. ------------[ cut here ]------------ is_shadow_present_pte(*sptep) WARNING: arch/x86/kvm/mmu/mmu.c:484 at mark_mmio_spte+0xb2/0xc0 [kvm], CPU#0: vmx_ept_stale_r/4292 Modules linked in: kvm_intel kvm irqbypass CPU: 0 UID: 1000 PID: 4292 Comm: vmx_ept_stale_r Not tainted 7.0.0-rc2-eafebd2d2ab0-sink-vm #319 PREEMPT Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:mark_mmio_spte+0xb2/0xc0 [kvm] Call Trace: mmu_set_spte+0x237/0x440 [kvm] ept_page_fault+0x535/0x7f0 [kvm] kvm_mmu_do_page_fault+0xee/0x1f0 [kvm] kvm_mmu_page_fault+0x8d/0x620 [kvm] vmx_handle_exit+0x18c/0x5a0 [kvm_intel] kvm_arch_vcpu_ioctl_run+0xc55/0x1c20 [kvm] kvm_vcpu_ioctl+0x2d5/0x980 [kvm] __x64_sys_ioctl+0x8a/0xd0 do_syscall_64+0xb5/0x730 entry_SYSCALL_64_after_hwframe+0x4b/0x53 RIP: 0033:0x47fa3f ---[ end trace 0000000000000000 ]---

Published: 2026-04-01Modified: 2026-04-24

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23402

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: KVM: x86/mmu: Only WARN in direct MMUs when overwriting shadow-present SPTE Adjust KVM's sanity check against overwriting a shadow-present SPTE with a another SPTE with a different target PFN to only apply to direct MMUs, i.e. only to MMUs without shadowed gPTEs. While it's impossible for KVM to overwrite a shadow-present SPTE in response to a guest write, writes from outside the scope of KVM, e.g. from host userspace, aren't detected by KVM's write tracking and so can break KVM's shadow paging rules. ------------[ cut here ]------------ pfn != spte_to_pfn(*sptep) WARNING: arch/x86/kvm/mmu/mmu.c:3069 at mmu_set_spte+0x1e4/0x440 [kvm], CPU#0: vmx_ept_stale_r/872 Modules linked in: kvm_intel kvm irqbypass CPU: 0 UID: 1000 PID: 872 Comm: vmx_ept_stale_r Not tainted 7.0.0-rc2-eafebd2d2ab0-sink-vm #319 PREEMPT Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:mmu_set_spte+0x1e4/0x440 [kvm] Call Trace: ept_page_fault+0x535/0x7f0 [kvm] kvm_mmu_do_page_fault+0xee/0x1f0 [kvm] kvm_mmu_page_fault+0x8d/0x620 [kvm] vmx_handle_exit+0x18c/0x5a0 [kvm_intel] kvm_arch_vcpu_ioctl_run+0xc55/0x1c20 [kvm] kvm_vcpu_ioctl+0x2d5/0x980 [kvm] __x64_sys_ioctl+0x8a/0xd0 do_syscall_64+0xb5/0x730 entry_SYSCALL_64_after_hwframe+0x4b/0x53 ---[ end trace 0000000000000000 ]---

Published: 2026-04-01Modified: 2026-04-24

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23412

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: bpf: defer hook memory release until rcu readers are done Yiming Qian reports UaF when concurrent process is dumping hooks via nfnetlink_hooks: BUG: KASAN: slab-use-after-free in nfnl_hook_dump_one.isra.0+0xe71/0x10f0 Read of size 8 at addr ffff888003edbf88 by task poc/79 Call Trace: nfnl_hook_dump_one.isra.0+0xe71/0x10f0 netlink_dump+0x554/0x12b0 nfnl_hook_get+0x176/0x230 [..] Defer release until after concurrent readers have completed.

Published: 2026-04-02Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23413

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: clsact: Fix use-after-free in init/destroy rollback asymmetry Fix a use-after-free in the clsact qdisc upon init/destroy rollback asymmetry. The latter is achieved by first fully initializing a clsact instance, and then in a second step having a replacement failure for the new clsact qdisc instance. clsact_init() initializes ingress first and then takes care of the egress part. This can fail midway, for example, via tcf_block_get_ext(). Upon failure, the kernel will trigger the clsact_destroy() callback. Commit 1cb6f0bae504 ("bpf: Fix too early release of tcx_entry") details the way how the transition is happening. If tcf_block_get_ext on the q->ingress_block ends up failing, we took the tcx_miniq_inc reference count on the ingress side, but not yet on the egress side. clsact_destroy() tests whether the {ingress,egress}_entry was non-NULL. However, even in midway failure on the replacement, both are in fact non-NULL with a valid egress_entry from the previous clsact instance. What we really need to test for is whether the qdisc instance-specific ingress or egress side previously got initialized. This adds a small helper for checking the miniq initialization called mini_qdisc_pair_inited, and utilizes that upon clsact_destroy() in order to fix the use-after-free scenario. Convert the ingress_destroy() side as well so both are consistent to each other.

Published: 2026-04-02Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23414

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: tls: Purge async_hold in tls_decrypt_async_wait() The async_hold queue pins encrypted input skbs while the AEAD engine references their scatterlist data. Once tls_decrypt_async_wait() returns, every AEAD operation has completed and the engine no longer references those skbs, so they can be freed unconditionally. A subsequent patch adds batch async decryption to tls_sw_read_sock(), introducing a new call site that must drain pending AEAD operations and release held skbs. Move __skb_queue_purge(&ctx->async_hold) into tls_decrypt_async_wait() so the purge is centralized and every caller -- recvmsg's drain path, the -EBUSY fallback in tls_do_decryption(), and the new read_sock batch path -- releases held skbs on synchronization without each site managing the purge independently. This fixes a leak when tls_strp_msg_hold() fails part-way through, after having added some cloned skbs to the async_hold queue. tls_decrypt_sg() will then call tls_decrypt_async_wait() to process all pending decrypts, and drop back to synchronous mode, but tls_sw_recvmsg() only flushes the async_hold queue when one record has been processed in "fully-async" mode, which may not be the case here. [pabeni@redhat.com: added leak comment]

Published: 2026-04-02Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23415

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: futex: Fix UaF between futex_key_to_node_opt() and vma_replace_policy() During futex_key_to_node_opt() execution, vma->vm_policy is read under speculative mmap lock and RCU. Concurrently, mbind() may call vma_replace_policy() which frees the old mempolicy immediately via kmem_cache_free(). This creates a race where __futex_key_to_node() dereferences a freed mempolicy pointer, causing a use-after-free read of mpol->mode. [ 151.412631] BUG: KASAN: slab-use-after-free in __futex_key_to_node (kernel/futex/core.c:349) [ 151.414046] Read of size 2 at addr ffff888001c49634 by task e/87 [ 151.415969] Call Trace: [ 151.416732] __asan_load2 (mm/kasan/generic.c:271) [ 151.416777] __futex_key_to_node (kernel/futex/core.c:349) [ 151.416822] get_futex_key (kernel/futex/core.c:374 kernel/futex/core.c:386 kernel/futex/core.c:593) Fix by adding rcu to __mpol_put().

Published: 2026-04-02Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23416

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mm/mseal: update VMA end correctly on merge Previously we stored the end of the current VMA in curr_end, and then upon iterating to the next VMA updated curr_start to curr_end to advance to the next VMA. However, this doesn't take into account the fact that a VMA might be updated due to a merge by vma_modify_flags(), which can result in curr_end being stale and thus, upon setting curr_start to curr_end, ending up with an incorrect curr_start on the next iteration. Resolve the issue by setting curr_end to vma->vm_end unconditionally to ensure this value remains updated should this occur. While we're here, eliminate this entire class of bug by simply setting const curr_[start/end] to be clamped to the input range and VMAs, which also happens to simplify the logic.

Published: 2026-04-02Modified: 2026-04-24

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23417

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix constant blinding for PROBE_MEM32 stores BPF_ST | BPF_PROBE_MEM32 immediate stores are not handled by bpf_jit_blind_insn(), allowing user-controlled 32-bit immediates to survive unblinded into JIT-compiled native code when bpf_jit_harden >= 1. The root cause is that convert_ctx_accesses() rewrites BPF_ST|BPF_MEM to BPF_ST|BPF_PROBE_MEM32 for arena pointer stores during verification, before bpf_jit_blind_constants() runs during JIT compilation. The blinding switch only matches BPF_ST|BPF_MEM (mode 0x60), not BPF_ST|BPF_PROBE_MEM32 (mode 0xa0). The instruction falls through unblinded. Add BPF_ST|BPF_PROBE_MEM32 cases to bpf_jit_blind_insn() alongside the existing BPF_ST|BPF_MEM cases. The blinding transformation is identical: load the blinded immediate into BPF_REG_AX via mov+xor, then convert the immediate store to a register store (BPF_STX). The rewritten STX instruction must preserve the BPF_PROBE_MEM32 mode so the architecture JIT emits the correct arena addressing (R12-based on x86-64). Cannot use the BPF_STX_MEM() macro here because it hardcodes BPF_MEM mode; construct the instruction directly instead.

Published: 2026-04-02Modified: 2026-04-24

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23427

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix use-after-free in durable v2 replay of active file handles parse_durable_handle_context() unconditionally assigns dh_info->fp->conn to the current connection when handling a DURABLE_REQ_V2 context with SMB2_FLAGS_REPLAY_OPERATION. ksmbd_lookup_fd_cguid() does not filter by fp->conn, so it returns file handles that are already actively connected. The unconditional overwrite replaces fp->conn, and when the overwriting connection is subsequently freed, __ksmbd_close_fd() dereferences the stale fp->conn via spin_lock(&fp->conn->llist_lock), causing a use-after-free. KASAN report: [ 7.349357] ================================================================== [ 7.349607] BUG: KASAN: slab-use-after-free in _raw_spin_lock+0x75/0xe0 [ 7.349811] Write of size 4 at addr ffff8881056ac18c by task kworker/1:2/108 [ 7.350010] [ 7.350064] CPU: 1 UID: 0 PID: 108 Comm: kworker/1:2 Not tainted 7.0.0-rc3+ #58 PREEMPTLAZY [ 7.350068] Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 7.350070] Workqueue: ksmbd-io handle_ksmbd_work [ 7.350083] Call Trace: [ 7.350087] [ 7.350087] dump_stack_lvl+0x64/0x80 [ 7.350094] print_report+0xce/0x660 [ 7.350100] ? pfxraw_spin_lock_irqsave+0x10/0x10 [ 7.350101] ? pfx_mod_timer+0x10/0x10 [ 7.350106] ? _raw_spin_lock+0x75/0xe0 [ 7.350108] kasan_report+0xce/0x100 [ 7.350109] ? _raw_spin_lock+0x75/0xe0 [ 7.350114] kasan_check_range+0x105/0x1b0 [ 7.350116] _raw_spin_lock+0x75/0xe0 [ 7.350118] ? pfxraw_spin_lock+0x10/0x10 [ 7.350119] ? __call_rcu_common.constprop.0+0x25e/0x780 [ 7.350125] ? close_id_del_oplock+0x2cc/0x4e0 [ 7.350128] __ksmbd_close_fd+0x27f/0xaf0 [ 7.350131] ksmbd_close_fd+0x135/0x1b0 [ 7.350133] smb2_close+0xb19/0x15b0 [ 7.350142] ? __pfx_smb2_close+0x10/0x10 [ 7.350143] ? xas_load+0x18/0x270 [ 7.350146] ? _raw_spin_lock+0x84/0xe0 [ 7.350148] ? pfxraw_spin_lock+0x10/0x10 [ 7.350150] ? _raw_spin_unlock+0xe/0x30 [ 7.350151] ? ksmbd_smb2_check_message+0xeb2/0x24c0 [ 7.350153] ? ksmbd_tree_conn_lookup+0xcd/0xf0 [ 7.350154] handle_ksmbd_work+0x40f/0x1080 [ 7.350156] process_one_work+0x5fa/0xef0 [ 7.350162] ? assign_work+0x122/0x3e0 [ 7.350163] worker_thread+0x54b/0xf70 [ 7.350165] ? __pfx_worker_thread+0x10/0x10 [ 7.350166] kthread+0x346/0x470 [ 7.350170] ? recalc_sigpending+0x19b/0x230 [ 7.350176] ? __pfx_kthread+0x10/0x10 [ 7.350178] ret_from_fork+0x4fb/0x6c0 [ 7.350183] ? __pfx_ret_from_fork+0x10/0x10 [ 7.350185] ? __switch_to+0x36c/0xbe0 [ 7.350188] ? __pfx_kthread+0x10/0x10 [ 7.350190] ret_from_fork_asm+0x1a/0x30 [ 7.350197] [ 7.350197] [ 7.355160] Allocated by task 123: [ 7.355261] kasan_save_stack+0x33/0x60 [ 7.355373] kasan_save_track+0x14/0x30 [ 7.355484] __kasan_kmalloc+0x8f/0xa0 [ 7.355593] ksmbd_conn_alloc+0x44/0x6d0 [ 7.355711] ksmbd_kthread_fn+0x243/0xd70 [ 7.355839] kthread+0x346/0x470 [ 7.355942] ret_from_fork+0x4fb/0x6c0 [ 7.356051] ret_from_fork_asm+0x1a/0x30 [ 7.356164] [ 7.356214] Freed by task 134: [ 7.356305] kasan_save_stack+0x33/0x60 [ 7.356416] kasan_save_track+0x14/0x30 [ 7.356527] kasan_save_free_info+0x3b/0x60 [ 7.356646] __kasan_slab_free+0x43/0x70 [ 7.356761] kfree+0x1ca/0x430 [ 7.356862] ksmbd_tcp_disconnect+0x59/0xe0 [ 7.356993] ksmbd_conn_handler_loop+0x77e/0xd40 [ 7.357138] kthread+0x346/0x470 [ 7.357240] ret_from_fork+0x4fb/0x6c0 [ 7.357350] ret_from_fork_asm+0x1a/0x30 [ 7.357463] [ 7.357513] The buggy address belongs to the object at ffff8881056ac000 [ 7.357513] which belongs to the cache kmalloc-1k of size 1024 [ 7.357857] The buggy address is located 396 bytes inside of [ 7.357857] freed 1024-byte region ---truncated---

Published: 2026-04-03Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23428

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix use-after-free of share_conf in compound request smb2_get_ksmbd_tcon() reuses work->tcon in compound requests without validating tcon->t_state. ksmbd_tree_conn_lookup() checks t_state == TREE_CONNECTED on the initial lookup path, but the compound reuse path bypasses this check entirely. If a prior command in the compound (SMB2_TREE_DISCONNECT) sets t_state to TREE_DISCONNECTED and frees share_conf via ksmbd_share_config_put(), subsequent commands dereference the freed share_conf through work->tcon->share_conf. KASAN report: [ 4.144653] ================================================================== [ 4.145059] BUG: KASAN: slab-use-after-free in smb2_write+0xc74/0xe70 [ 4.145415] Read of size 4 at addr ffff88810430c194 by task kworker/1:1/44 [ 4.145772] [ 4.145867] CPU: 1 UID: 0 PID: 44 Comm: kworker/1:1 Not tainted 7.0.0-rc3+ #60 PREEMPTLAZY [ 4.145871] Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 4.145875] Workqueue: ksmbd-io handle_ksmbd_work [ 4.145888] Call Trace: [ 4.145892] [ 4.145894] dump_stack_lvl+0x64/0x80 [ 4.145910] print_report+0xce/0x660 [ 4.145919] ? pfxraw_spin_lock_irqsave+0x10/0x10 [ 4.145928] ? smb2_write+0xc74/0xe70 [ 4.145931] kasan_report+0xce/0x100 [ 4.145934] ? smb2_write+0xc74/0xe70 [ 4.145937] smb2_write+0xc74/0xe70 [ 4.145939] ? __pfx_smb2_write+0x10/0x10 [ 4.145942] ? _raw_spin_unlock+0xe/0x30 [ 4.145945] ? ksmbd_smb2_check_message+0xeb2/0x24c0 [ 4.145948] ? smb2_tree_disconnect+0x31c/0x480 [ 4.145951] handle_ksmbd_work+0x40f/0x1080 [ 4.145953] process_one_work+0x5fa/0xef0 [ 4.145962] ? assign_work+0x122/0x3e0 [ 4.145964] worker_thread+0x54b/0xf70 [ 4.145967] ? __pfx_worker_thread+0x10/0x10 [ 4.145970] kthread+0x346/0x470 [ 4.145976] ? recalc_sigpending+0x19b/0x230 [ 4.145980] ? __pfx_kthread+0x10/0x10 [ 4.145984] ret_from_fork+0x4fb/0x6c0 [ 4.145992] ? __pfx_ret_from_fork+0x10/0x10 [ 4.145995] ? __switch_to+0x36c/0xbe0 [ 4.145999] ? __pfx_kthread+0x10/0x10 [ 4.146003] ret_from_fork_asm+0x1a/0x30 [ 4.146013] [ 4.146014] [ 4.149858] Allocated by task 44: [ 4.149953] kasan_save_stack+0x33/0x60 [ 4.150061] kasan_save_track+0x14/0x30 [ 4.150169] __kasan_kmalloc+0x8f/0xa0 [ 4.150274] ksmbd_share_config_get+0x1dd/0xdd0 [ 4.150401] ksmbd_tree_conn_connect+0x7e/0x600 [ 4.150529] smb2_tree_connect+0x2e6/0x1000 [ 4.150645] handle_ksmbd_work+0x40f/0x1080 [ 4.150761] process_one_work+0x5fa/0xef0 [ 4.150873] worker_thread+0x54b/0xf70 [ 4.150978] kthread+0x346/0x470 [ 4.151071] ret_from_fork+0x4fb/0x6c0 [ 4.151176] ret_from_fork_asm+0x1a/0x30 [ 4.151286] [ 4.151332] Freed by task 44: [ 4.151418] kasan_save_stack+0x33/0x60 [ 4.151526] kasan_save_track+0x14/0x30 [ 4.151634] kasan_save_free_info+0x3b/0x60 [ 4.151751] __kasan_slab_free+0x43/0x70 [ 4.151861] kfree+0x1ca/0x430 [ 4.151952] __ksmbd_tree_conn_disconnect+0xc8/0x190 [ 4.152088] smb2_tree_disconnect+0x1cd/0x480 [ 4.152211] handle_ksmbd_work+0x40f/0x1080 [ 4.152326] process_one_work+0x5fa/0xef0 [ 4.152438] worker_thread+0x54b/0xf70 [ 4.152545] kthread+0x346/0x470 [ 4.152638] ret_from_fork+0x4fb/0x6c0 [ 4.152743] ret_from_fork_asm+0x1a/0x30 [ 4.152853] [ 4.152900] The buggy address belongs to the object at ffff88810430c180 [ 4.152900] which belongs to the cache kmalloc-96 of size 96 [ 4.153226] The buggy address is located 20 bytes inside of [ 4.153226] freed 96-byte region [ffff88810430c180, ffff88810430c1e0) [ 4.153549] [ 4.153596] The buggy address belongs to the physical page: [ 4.153750] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff88810430ce80 pfn:0x10430c [ 4.154000] flags: 0x ---truncated---

Published: 2026-04-03Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23429

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: iommu/sva: Fix crash in iommu_sva_unbind_device() domain->mm->iommu_mm can be freed by iommu_domain_free(): iommu_domain_free() mmdrop() __mmdrop() mm_pasid_drop() After iommu_domain_free() returns, accessing domain->mm->iommu_mm may dereference a freed mm structure, leading to a crash. Fix this by moving the code that accesses domain->mm->iommu_mm to before the call to iommu_domain_free().

Published: 2026-04-03Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23430

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/vmwgfx: Don't overwrite KMS surface dirty tracker We were overwriting the surface's dirty tracker here causing a memory leak.

Published: 2026-04-03Modified: 2026-04-23

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23431

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: spi: amlogic-spisg: Fix memory leak in aml_spisg_probe() In aml_spisg_probe(), ctlr is allocated by spi_alloc_target()/spi_alloc_host(), but fails to call spi_controller_put() in several error paths. This leads to a memory leak whenever the driver fails to probe after the initial allocation. Convert to use devm_spi_alloc_host()/devm_spi_alloc_target() to fix the memory leak.

Published: 2026-04-03Modified: 2026-04-23

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23434

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mtd: rawnand: serialize lock/unlock against other NAND operations nand_lock() and nand_unlock() call into chip->ops.lock_area/unlock_area without holding the NAND device lock. On controllers that implement SET_FEATURES via multiple low-level PIO commands, these can race with concurrent UBI/UBIFS background erase/write operations that hold the device lock, resulting in cmd_pending conflicts on the NAND controller. Add nand_get_device()/nand_release_device() around the lock/unlock operations to serialize them against all other NAND controller access.

Published: 2026-04-03Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23435

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: perf/x86: Move event pointer setup earlier in x86_pmu_enable() A production AMD EPYC system crashed with a NULL pointer dereference in the PMU NMI handler: BUG: kernel NULL pointer dereference, address: 0000000000000198 RIP: x86_perf_event_update+0xc/0xa0 Call Trace: amd_pmu_v2_handle_irq+0x1a6/0x390 perf_event_nmi_handler+0x24/0x40 The faulting instruction is `cmpq $0x0, 0x198(%rdi)` with RDI=0, corresponding to the `if (unlikely(!hwc->event_base))` check in x86_perf_event_update() where hwc = &event->hw and event is NULL. drgn inspection of the vmcore on CPU 106 showed a mismatch between cpuc->active_mask and cpuc->events[]: active_mask: 0x1e (bits 1, 2, 3, 4) events[1]: 0xff1100136cbd4f38 (valid) events[2]: 0x0 (NULL, but active_mask bit 2 set) events[3]: 0xff1100076fd2cf38 (valid) events[4]: 0xff1100079e990a90 (valid) The event that should occupy events[2] was found in event_list[2] with hw.idx=2 and hw.state=0x0, confirming x86_pmu_start() had run (which clears hw.state and sets active_mask) but events[2] was never populated. Another event (event_list[0]) had hw.state=0x7 (STOPPED|UPTODATE|ARCH), showing it was stopped when the PMU rescheduled events, confirming the throttle-then-reschedule sequence occurred. The root cause is commit 7e772a93eb61 ("perf/x86: Fix NULL event access and potential PEBS record loss") which moved the cpuc->events[idx] assignment out of x86_pmu_start() and into step 2 of x86_pmu_enable(), after the PERF_HES_ARCH check. This broke any path that calls pmu->start() without going through x86_pmu_enable() -- specifically the unthrottle path: perf_adjust_freq_unthr_events() -> perf_event_unthrottle_group() -> perf_event_unthrottle() -> event->pmu->start(event, 0) -> x86_pmu_start() // sets active_mask but not events[] The race sequence is: 1. A group of perf events overflows, triggering group throttle via perf_event_throttle_group(). All events are stopped: active_mask bits cleared, events[] preserved (x86_pmu_stop no longer clears events[] after commit 7e772a93eb61). 2. While still throttled (PERF_HES_STOPPED), x86_pmu_enable() runs due to other scheduling activity. Stopped events that need to move counters get PERF_HES_ARCH set and events[old_idx] cleared. In step 2 of x86_pmu_enable(), PERF_HES_ARCH causes these events to be skipped -- events[new_idx] is never set. 3. The timer tick unthrottles the group via pmu->start(). Since commit 7e772a93eb61 removed the events[] assignment from x86_pmu_start(), active_mask[new_idx] is set but events[new_idx] remains NULL. 4. A PMC overflow NMI fires. The handler iterates active counters, finds active_mask[2] set, reads events[2] which is NULL, and crashes dereferencing it. Move the cpuc->events[hwc->idx] assignment in x86_pmu_enable() to before the PERF_HES_ARCH check, so that events[] is populated even for events that are not immediately started. This ensures the unthrottle path via pmu->start() always finds a valid event pointer.

Published: 2026-04-03Modified: 2026-04-23

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23436

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: shaper: protect from late creation of hierarchy We look up a netdev during prep of Netlink ops (pre- callbacks) and take a ref to it. Then later in the body of the callback we take its lock or RCU which are the actual protections. The netdev may get unregistered in between the time we take the ref and the time we lock it. We may allocate the hierarchy after flush has already run, which would lead to a leak. Take the instance lock in pre- already, this saves us from the race and removes the need for dedicated lock/unlock callbacks completely. After all, if there's any chance of write happening concurrently with the flush - we're back to leaking the hierarchy. We may take the lock for devices which don't support shapers but we're only dealing with SET operations here, not taking the lock would be optimizing for an error case.

Published: 2026-04-03Modified: 2026-04-23

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23437

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: shaper: protect late read accesses to the hierarchy We look up a netdev during prep of Netlink ops (pre- callbacks) and take a ref to it. Then later in the body of the callback we take its lock or RCU which are the actual protections. This is not proper, a conversion from a ref to a locked netdev must include a liveness check (a check if the netdev hasn't been unregistered already). Fix the read cases (those under RCU). Writes needs a separate change to protect from creating the hierarchy after flush has already run.

Published: 2026-04-03Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23438

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: mvpp2: guard flow control update with global_tx_fc in buffer switching mvpp2_bm_switch_buffers() unconditionally calls mvpp2_bm_pool_update_priv_fc() when switching between per-cpu and shared buffer pool modes. This function programs CM3 flow control registers via mvpp2_cm3_read()/mvpp2_cm3_write(), which dereference priv->cm3_base without any NULL check. When the CM3 SRAM resource is not present in the device tree (the third reg entry added by commit 60523583b07c ("dts: marvell: add CM3 SRAM memory to cp11x ethernet device tree")), priv->cm3_base remains NULL and priv->global_tx_fc is false. Any operation that triggers mvpp2_bm_switch_buffers(), for example an MTU change that crosses the jumbo frame threshold, will crash: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 Mem abort info: ESR = 0x0000000096000006 EC = 0x25: DABT (current EL), IL = 32 bits pc : readl+0x0/0x18 lr : mvpp2_cm3_read.isra.0+0x14/0x20 Call trace: readl+0x0/0x18 mvpp2_bm_pool_update_fc+0x40/0x12c mvpp2_bm_pool_update_priv_fc+0x94/0xd8 mvpp2_bm_switch_buffers.isra.0+0x80/0x1c0 mvpp2_change_mtu+0x140/0x380 __dev_set_mtu+0x1c/0x38 dev_set_mtu_ext+0x78/0x118 dev_set_mtu+0x48/0xa8 dev_ifsioc+0x21c/0x43c dev_ioctl+0x2d8/0x42c sock_ioctl+0x314/0x378 Every other flow control call site in the driver already guards hardware access with either priv->global_tx_fc or port->tx_fc. mvpp2_bm_switch_buffers() is the only place that omits this check. Add the missing priv->global_tx_fc guard to both the disable and re-enable calls in mvpp2_bm_switch_buffers(), consistent with the rest of the driver.

Published: 2026-04-03Modified: 2026-04-23

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23439

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: udp_tunnel: fix NULL deref caused by udp_sock_create6 when CONFIG_IPV6=n When CONFIG_IPV6 is disabled, the udp_sock_create6() function returns 0 (success) without actually creating a socket. Callers such as fou_create() then proceed to dereference the uninitialized socket pointer, resulting in a NULL pointer dereference. The captured NULL deref crash: BUG: kernel NULL pointer dereference, address: 0000000000000018 RIP: 0010:fou_nl_add_doit (net/ipv4/fou_core.c:590 net/ipv4/fou_core.c:764) [...] Call Trace: genl_family_rcv_msg_doit.constprop.0 (net/netlink/genetlink.c:1114) genl_rcv_msg (net/netlink/genetlink.c:1194 net/netlink/genetlink.c:1209) [...] netlink_rcv_skb (net/netlink/af_netlink.c:2550) genl_rcv (net/netlink/genetlink.c:1219) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) __sock_sendmsg (net/socket.c:727 (discriminator 1) net/socket.c:742 (discriminator 1)) __sys_sendto (./include/linux/file.h:62 (discriminator 1) ./include/linux/file.h:83 (discriminator 1) net/socket.c:2183 (discriminator 1)) __x64_sys_sendto (net/socket.c:2213 (discriminator 1) net/socket.c:2209 (discriminator 1) net/socket.c:2209 (discriminator 1)) do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1)) entry_SYSCALL_64_after_hwframe (net/arch/x86/entry/entry_64.S:130) This patch makes udp_sock_create6 return -EPFNOSUPPORT instead, so callers correctly take their error paths. There is only one caller of the vulnerable function and only privileged users can trigger it.

Published: 2026-04-03Modified: 2026-04-23

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23440

MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Fix race condition during IPSec ESN update In IPSec full offload mode, the device reports an ESN (Extended Sequence Number) wrap event to the driver. The driver validates this event by querying the IPSec ASO and checking that the esn_event_arm field is 0x0, which indicates an event has occurred. After handling the event, the driver must re-arm the context by setting esn_event_arm back to 0x1. A race condition exists in this handling path. After validating the event, the driver calls mlx5_accel_esp_modify_xfrm() to update the kernel's xfrm state. This function temporarily releases and re-acquires the xfrm state lock. So, need to acknowledge the event first by setting esn_event_arm to 0x1. This prevents the driver from reprocessing the same ESN update if the hardware sends events for other reason. Since the next ESN update only occurs after nearly 2^31 packets are received, there's no risk of missing an update, as it will happen long after this handling has finished. Processing the event twice causes the ESN high-order bits (esn_msb) to be incremented incorrectly. The driver then programs the hardware with this invalid ESN state, which leads to anti-replay failures and a complete halt of IPSec traffic. Fix this by re-arming the ESN event immediately after it is validated, before calling mlx5_accel_esp_modify_xfrm(). This ensures that any spurious, duplicate events are correctly ignored, closing the race window.

Published: 2026-04-03Modified: 2026-04-27

CVSS 3.xMEDIUM 4.7

CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23441

MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Prevent concurrent access to IPSec ASO context The query or updating IPSec offload object is through Access ASO WQE. The driver uses a single mlx5e_ipsec_aso struct for each PF, which contains a shared DMA-mapped context for all ASO operations. A race condition exists because the ASO spinlock is released before the hardware has finished processing WQE. If a second operation is initiated immediately after, it overwrites the shared context in the DMA area. When the first operation's completion is processed later, it reads this corrupted context, leading to unexpected behavior and incorrect results. This commit fixes the race by introducing a private context within each IPSec offload object. The shared ASO context is now copied to this private context while the ASO spinlock is held. Subsequent processing uses this saved, per-object context, ensuring its integrity is maintained.

Published: 2026-04-03Modified: 2026-04-23

CVSS 3.xMEDIUM 4.7

CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23443

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ACPI: processor: Fix previous acpi_processor_errata_piix4() fix After commi f132e089fe89 ("ACPI: processor: Fix NULL-pointer dereference in acpi_processor_errata_piix4()"), device pointers may be dereferenced after dropping references to the device objects pointed to by them, which may cause a use-after-free to occur. Moreover, debug messages about enabling the errata may be printed if the errata flags corresponding to them are unset. Address all of these issues by moving message printing to the points in the code where the errata flags are set.

Published: 2026-04-03Modified: 2026-04-23

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23444

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: always free skb on ieee80211_tx_prepare_skb() failure ieee80211_tx_prepare_skb() has three error paths, but only two of them free the skb. The first error path (ieee80211_tx_prepare() returning TX_DROP) does not free it, while invoke_tx_handlers() failure and the fragmentation check both do. Add kfree_skb() to the first error path so all three are consistent, and remove the now-redundant frees in callers (ath9k, mt76, mac80211_hwsim) to avoid double-free. Document the skb ownership guarantee in the function's kdoc.

Published: 2026-04-03Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23445

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: igc: fix page fault in XDP TX timestamps handling If an XDP application that requested TX timestamping is shutting down while the link of the interface in use is still up the following kernel splat is reported: [ 883.803618] [ T1554] BUG: unable to handle page fault for address: ffffcfb6200fd008 ... [ 883.803650] [ T1554] Call Trace: [ 883.803652] [ T1554] [ 883.803654] [ T1554] igc_ptp_tx_tstamp_event+0xdf/0x160 [igc] [ 883.803660] [ T1554] igc_tsync_interrupt+0x2d5/0x300 [igc] ... During shutdown of the TX ring the xsk_meta pointers are left behind, so that the IRQ handler is trying to touch them. This issue is now being fixed by cleaning up the stale xsk meta data on TX shutdown. TX timestamps on other queues remain unaffected.

Published: 2026-04-03Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23446

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: usb: aqc111: Do not perform PM inside suspend callback syzbot reports "task hung in rpm_resume" This is caused by aqc111_suspend calling the PM variant of its write_cmd routine. The simplified call trace looks like this: rpm_suspend() usb_suspend_both() - here udev->dev.power.runtime_status == RPM_SUSPENDING aqc111_suspend() - called for the usb device interface aqc111_write32_cmd() usb_autopm_get_interface() pm_runtime_resume_and_get() rpm_resume() - here we call rpm_resume() on our parent rpm_resume() - Here we wait for a status change that will never happen. At this point we block another task which holds rtnl_lock and locks up the whole networking stack. Fix this by replacing the write_cmd calls with their _nopm variants

Published: 2026-04-03Modified: 2026-04-23

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23447

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: usb: cdc_ncm: add ndpoffset to NDP32 nframes bounds check The same bounds-check bug fixed for NDP16 in the previous patch also exists in cdc_ncm_rx_verify_ndp32(). The DPE array size is validated against the total skb length without accounting for ndpoffset, allowing out-of-bounds reads when the NDP32 is placed near the end of the NTB. Add ndpoffset to the nframes bounds check and use struct_size_t() to express the NDP-plus-DPE-array size more clearly. Compile-tested only.

Published: 2026-04-03Modified: 2026-04-23

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23448

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: usb: cdc_ncm: add ndpoffset to NDP16 nframes bounds check cdc_ncm_rx_verify_ndp16() validates that the NDP header and its DPE entries fit within the skb. The first check correctly accounts for ndpoffset: if ((ndpoffset + sizeof(struct usb_cdc_ncm_ndp16)) > skb_in->len) but the second check omits it: if ((sizeof(struct usb_cdc_ncm_ndp16) + ret * (sizeof(struct usb_cdc_ncm_dpe16))) > skb_in->len) This validates the DPE array size against the total skb length as if the NDP were at offset 0, rather than at ndpoffset. When the NDP is placed near the end of the NTB (large wNdpIndex), the DPE entries can extend past the skb data buffer even though the check passes. cdc_ncm_rx_fixup() then reads out-of-bounds memory when iterating the DPE array. Add ndpoffset to the nframes bounds check and use struct_size_t() to express the NDP-plus-DPE-array size more clearly.

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23449

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net/sched: teql: Fix double-free in teql_master_xmit Whenever a TEQL devices has a lockless Qdisc as root, qdisc_reset should be called using the seq_lock to avoid racing with the datapath. Failure to do so may cause crashes like the following: [ 238.028993][ T318] BUG: KASAN: double-free in skb_release_data (net/core/skbuff.c:1139) [ 238.029328][ T318] Free of addr ffff88810c67ec00 by task poc_teql_uaf_ke/318 [ 238.029749][ T318] [ 238.029900][ T318] CPU: 3 UID: 0 PID: 318 Comm: poc_teql_ke Not tainted 7.0.0-rc3-00149-ge5b31d988a41 #704 PREEMPT(full) [ 238.029906][ T318] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 238.029910][ T318] Call Trace: [ 238.029913][ T318] [ 238.029916][ T318] dump_stack_lvl (lib/dump_stack.c:122) [ 238.029928][ T318] print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) [ 238.029940][ T318] ? skb_release_data (net/core/skbuff.c:1139) [ 238.029944][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) ... [ 238.029957][ T318] ? skb_release_data (net/core/skbuff.c:1139) [ 238.029969][ T318] kasan_report_invalid_free (mm/kasan/report.c:221 mm/kasan/report.c:563) [ 238.029979][ T318] ? skb_release_data (net/core/skbuff.c:1139) [ 238.029989][ T318] check_slab_allocation (mm/kasan/common.c:231) [ 238.029995][ T318] kmem_cache_free (mm/slub.c:2637 (discriminator 1) mm/slub.c:6168 (discriminator 1) mm/slub.c:6298 (discriminator 1)) [ 238.030004][ T318] skb_release_data (net/core/skbuff.c:1139) ... [ 238.030025][ T318] sk_skb_reason_drop (net/core/skbuff.c:1256) [ 238.030032][ T318] pfifo_fast_reset (./include/linux/ptr_ring.h:171 ./include/linux/ptr_ring.h:309 ./include/linux/skb_array.h:98 net/sched/sch_generic.c:827) [ 238.030039][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) ... [ 238.030054][ T318] qdisc_reset (net/sched/sch_generic.c:1034) [ 238.030062][ T318] teql_destroy (./include/linux/spinlock.h:395 net/sched/sch_teql.c:157) [ 238.030071][ T318] __qdisc_destroy (./include/net/pkt_sched.h:328 net/sched/sch_generic.c:1077) [ 238.030077][ T318] qdisc_graft (net/sched/sch_api.c:1062 net/sched/sch_api.c:1053 net/sched/sch_api.c:1159) [ 238.030089][ T318] ? __pfx_qdisc_graft (net/sched/sch_api.c:1091) [ 238.030095][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 238.030102][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 238.030106][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 238.030114][ T318] tc_get_qdisc (net/sched/sch_api.c:1529 net/sched/sch_api.c:1556) ... [ 238.072958][ T318] Allocated by task 303 on cpu 5 at 238.026275s: [ 238.073392][ T318] kasan_save_stack (mm/kasan/common.c:58) [ 238.073884][ T318] kasan_save_track (mm/kasan/common.c:64 (discriminator 5) mm/kasan/common.c:79 (discriminator 5)) [ 238.074230][ T318] __kasan_slab_alloc (mm/kasan/common.c:369) [ 238.074578][ T318] kmem_cache_alloc_node_noprof (./include/linux/kasan.h:253 mm/slub.c:4542 mm/slub.c:4869 mm/slub.c:4921) [ 238.076091][ T318] kmalloc_reserve (net/core/skbuff.c:616 (discriminator 107)) [ 238.076450][ T318] __alloc_skb (net/core/skbuff.c:713) [ 238.076834][ T318] alloc_skb_with_frags (./include/linux/skbuff.h:1383 net/core/skbuff.c:6763) [ 238.077178][ T318] sock_alloc_send_pskb (net/core/sock.c:2997) [ 238.077520][ T318] packet_sendmsg (net/packet/af_packet.c:2926 net/packet/af_packet.c:3019 net/packet/af_packet.c:3108) [ 238.081469][ T318] [ 238.081870][ T318] Freed by task 299 on cpu 1 at 238.028496s: [ 238.082761][ T318] kasan_save_stack (mm/kasan/common.c:58) [ 238.083481][ T318] kasan_save_track (mm/kasan/common.c:64 (discriminator 5) mm/kasan/common.c:79 (discriminator 5)) [ 238.085348][ T318] kasan_save_free_info (mm/kasan/generic.c:587 (discriminator 1)) [ 238.085900][ T318] __kasan_slab_free (mm/ ---truncated---

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23450

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: net/smc: fix NULL dereference and UAF in smc_tcp_syn_recv_sock() Syzkaller reported a panic in smc_tcp_syn_recv_sock() [1]. smc_tcp_syn_recv_sock() is called in the TCP receive path (softirq) via icsk_af_ops->syn_recv_sock on the clcsock (TCP listening socket). It reads sk_user_data to get the smc_sock pointer. However, when the SMC listen socket is being closed concurrently, smc_close_active() sets clcsock->sk_user_data to NULL under sk_callback_lock, and then the smc_sock itself can be freed via sock_put() in smc_release(). This leads to two issues: 1) NULL pointer dereference: sk_user_data is NULL when accessed. 2) Use-after-free: sk_user_data is read as non-NULL, but the smc_sock is freed before its fields (e.g., queued_smc_hs, ori_af_ops) are accessed. The race window looks like this (the syzkaller crash [1] triggers via the SYN cookie path: tcp_get_cookie_sock() -> smc_tcp_syn_recv_sock(), but the normal tcp_check_req() path has the same race): CPU A (softirq) CPU B (process ctx) tcp_v4_rcv() TCP_NEW_SYN_RECV: sk = req->rsk_listener sock_hold(sk) /* No lock on listener */ smc_close_active(): write_lock_bh(cb_lock) sk_user_data = NULL write_unlock_bh(cb_lock) ... smc_clcsock_release() sock_put(smc->sk) x2 -> smc_sock freed! tcp_check_req() smc_tcp_syn_recv_sock(): smc = user_data(sk) -> NULL or dangling smc->queued_smc_hs -> crash! Note that the clcsock and smc_sock are two independent objects with separate refcounts. TCP stack holds a reference on the clcsock, which keeps it alive, but this does NOT prevent the smc_sock from being freed. Fix this by using RCU and refcount_inc_not_zero() to safely access smc_sock. Since smc_tcp_syn_recv_sock() is called in the TCP three-way handshake path, taking read_lock_bh on sk_callback_lock is too heavy and would not survive a SYN flood attack. Using rcu_read_lock() is much more lightweight. - Set SOCK_RCU_FREE on the SMC listen socket so that smc_sock freeing is deferred until after the RCU grace period. This guarantees the memory is still valid when accessed inside rcu_read_lock(). - Use rcu_read_lock() to protect reading sk_user_data. - Use refcount_inc_not_zero(&smc->sk.sk_refcnt) to pin the smc_sock. If the refcount has already reached zero (close path completed), it returns false and we bail out safely. Note: smc_hs_congested() has a similar lockless read of sk_user_data without rcu_read_lock(), but it only checks for NULL and accesses the global smc_hs_wq, never dereferencing any smc_sock field, so it is not affected. Reproducer was verified with mdelay injection and smc_run, the issue no longer occurs with this patch applied. [1] https://syzkaller.appspot.com/bug?extid=827ae2bfb3a3529333e9

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23451

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: bonding: prevent potential infinite loop in bond_header_parse() bond_header_parse() can loop if a stack of two bonding devices is setup, because skb->dev always points to the hierarchy top. Add new "const struct net_device *dev" parameter to (struct header_ops)->parse() method to make sure the recursion is bounded, and that the final leaf parse method is called.

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23461

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix use-after-free in l2cap_unregister_user After commit ab4eedb790ca ("Bluetooth: L2CAP: Fix corrupted list in hci_chan_del"), l2cap_conn_del() uses conn->lock to protect access to conn->users. However, l2cap_register_user() and l2cap_unregister_user() don't use conn->lock, creating a race condition where these functions can access conn->users and conn->hchan concurrently with l2cap_conn_del(). This can lead to use-after-free and list corruption bugs, as reported by syzbot. Fix this by changing l2cap_register_user() and l2cap_unregister_user() to use conn->lock instead of hci_dev_lock(), ensuring consistent locking for the l2cap_conn structure.

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23462

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: HIDP: Fix possible UAF This fixes the following trace caused by not dropping l2cap_conn reference when user->remove callback is called: [ 97.809249] l2cap_conn_free: freeing conn ffff88810a171c00 [ 97.809907] CPU: 1 UID: 0 PID: 1419 Comm: repro_standalon Not tainted 7.0.0-rc1-dirty #14 PREEMPT(lazy) [ 97.809935] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014 [ 97.809947] Call Trace: [ 97.809954] [ 97.809961] dump_stack_lvl (lib/dump_stack.c:122) [ 97.809990] l2cap_conn_free (net/bluetooth/l2cap_core.c:1808) [ 97.810017] l2cap_conn_del (./include/linux/kref.h:66 net/bluetooth/l2cap_core.c:1821 net/bluetooth/l2cap_core.c:1798) [ 97.810055] l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7347 (discriminator 1) net/bluetooth/l2cap_core.c:7340 (discriminator 1)) [ 97.810086] ? __pfx_l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7341) [ 97.810117] hci_conn_hash_flush (./include/net/bluetooth/hci_core.h:2152 (discriminator 2) net/bluetooth/hci_conn.c:2644 (discriminator 2)) [ 97.810148] hci_dev_close_sync (net/bluetooth/hci_sync.c:5360) [ 97.810180] ? __pfx_hci_dev_close_sync (net/bluetooth/hci_sync.c:5285) [ 97.810212] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810242] ? up_write (./arch/x86/include/asm/atomic64_64.h:87 (discriminator 5) ./include/linux/atomic/atomic-arch-fallback.h:2852 (discriminator 5) ./include/linux/atomic/atomic-long.h:268 (discriminator 5) ./include/linux/atomic/atomic-instrumented.h:3391 (discriminator 5) kernel/locking/rwsem.c:1385 (discriminator 5) kernel/locking/rwsem.c:1643 (discriminator 5)) [ 97.810267] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810290] ? rcu_is_watching (./arch/x86/include/asm/atomic.h:23 ./include/linux/atomic/atomic-arch-fallback.h:457 ./include/linux/context_tracking.h:128 kernel/rcu/tree.c:752) [ 97.810320] hci_unregister_dev (net/bluetooth/hci_core.c:504 net/bluetooth/hci_core.c:2716) [ 97.810346] vhci_release (drivers/bluetooth/hci_vhci.c:691) [ 97.810375] ? __pfx_vhci_release (drivers/bluetooth/hci_vhci.c:678) [ 97.810404] __fput (fs/file_table.c:470) [ 97.810430] task_work_run (kernel/task_work.c:235) [ 97.810451] ? __pfx_task_work_run (kernel/task_work.c:201) [ 97.810472] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810495] ? do_raw_spin_unlock (./include/asm-generic/qspinlock.h:128 (discriminator 5) kernel/locking/spinlock_debug.c:142 (discriminator 5)) [ 97.810527] do_exit (kernel/exit.c:972) [ 97.810547] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810574] ? __pfx_do_exit (kernel/exit.c:897) [ 97.810594] ? lock_acquire (kernel/locking/lockdep.c:470 (discriminator 6) kernel/locking/lockdep.c:5870 (discriminator 6) kernel/locking/lockdep.c:5825 (discriminator 6)) [ 97.810616] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810639] ? do_raw_spin_lock (kernel/locking/spinlock_debug.c:95 (discriminator 4) kernel/locking/spinlock_debug.c:118 (discriminator 4)) [ 97.810664] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810688] ? find_held_lock (kernel/locking/lockdep.c:5350 (discriminator 1)) [ 97.810721] do_group_exit (kernel/exit.c:1093) [ 97.810745] get_signal (kernel/signal.c:3007 (discriminator 1)) [ 97.810772] ? security_file_permission (./arch/x86/include/asm/jump_label.h:37 security/security.c:2366) [ 97.810803] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810826] ? vfs_read (fs/read_write.c:555) [ 97.810854] ? __pfx_get_signal (kernel/signal.c:2800) [ 97.810880] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810905] ? __pfx_vfs_read (fs/read_write.c:555) [ 97.810932] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810960] arch_do_signal_or_restart (arch/ ---truncated---

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23463

MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: soc: fsl: qbman: fix race condition in qman_destroy_fq When QMAN_FQ_FLAG_DYNAMIC_FQID is set, there's a race condition between fq_table[fq->idx] state and freeing/allocating from the pool and WARN_ON(fq_table[fq->idx]) in qman_create_fq() gets triggered. Indeed, we can have: Thread A Thread B qman_destroy_fq() qman_create_fq() qman_release_fqid() qman_shutdown_fq() gen_pool_free() -- At this point, the fqid is available again -- qman_alloc_fqid() -- so, we can get the just-freed fqid in thread B -- fq->fqid = fqid; fq->idx = fqid * 2; WARN_ON(fq_table[fq->idx]); fq_table[fq->idx] = fq; fq_table[fq->idx] = NULL; And adding some logs between qman_release_fqid() and fq_table[fq->idx] = NULL makes the WARN_ON() trigger a lot more. To prevent that, ensure that fq_table[fq->idx] is set to NULL before gen_pool_free() is called by using smp_wmb().

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xMEDIUM 4.7

CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23464

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: soc: microchip: mpfs: Fix memory leak in mpfs_sys_controller_probe() In mpfs_sys_controller_probe(), if of_get_mtd_device_by_node() fails, the function returns immediately without freeing the allocated memory for sys_controller, leading to a memory leak. Fix this by jumping to the out_free label to ensure the memory is properly freed. Also, consolidate the error handling for the mbox_request_channel() failure case to use the same label.

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23465

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: btrfs: log new dentries when logging parent dir of a conflicting inode If we log the parent directory of a conflicting inode, we are not logging the new dentries of the directory, so when we finish we have the parent directory's inode marked as logged but we did not log its new dentries. As a consequence if the parent directory is explicitly fsynced later and it does not have any new changes since we logged it, the fsync is a no-op and after a power failure the new dentries are missing. Example scenario: $ mkdir foo $ sync $rmdir foo $ mkdir dir1 $ mkdir dir2 # A file with the same name and parent as the directory we just deleted # and was persisted in a past transaction. So the deleted directory's # inode is a conflicting inode of this new file's inode. $ touch foo $ ln foo dir2/link # The fsync on dir2 will log the parent directory (".") because the # conflicting inode (deleted directory) does not exists anymore, but it # it does not log its new dentries (dir1). $ xfs_io -c "fsync" dir2 # This fsync on the parent directory is no-op, since the previous fsync # logged it (but without logging its new dentries). $ xfs_io -c "fsync" . # After log replay dir1 is missing. Fix this by ensuring we log new dir dentries whenever we log the parent directory of a no longer existing conflicting inode. A test case for fstests will follow soon.

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-23466

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: drm/xe: Open-code GGTT MMIO access protection GGTT MMIO access is currently protected by hotplug (drm_dev_enter), which works correctly when the driver loads successfully and is later unbound or unloaded. However, if driver load fails, this protection is insufficient because drm_dev_unplug() is never called. Additionally, devm release functions cannot guarantee that all BOs with GGTT mappings are destroyed before the GGTT MMIO region is removed, as some BOs may be freed asynchronously by worker threads. To address this, introduce an open-coded flag, protected by the GGTT lock, that guards GGTT MMIO access. The flag is cleared during the dev_fini_ggtt devm release function to ensure MMIO access is disabled once teardown begins. (cherry picked from commit 4f3a998a173b4325c2efd90bdadc6ccd3ad9a431)

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-23475

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: spi: fix statistics allocation The controller per-cpu statistics is not allocated until after the controller has been registered with driver core, which leaves a window where accessing the sysfs attributes can trigger a NULL-pointer dereference. Fix this by moving the statistics allocation to controller allocation while tying its lifetime to that of the controller (rather than using implicit devres).

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31389

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: spi: fix use-after-free on controller registration failure Make sure to deregister from driver core also in the unlikely event that per-cpu statistics allocation fails during controller registration to avoid use-after-free (of driver resources) and unclocked register accesses.

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31394

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mac80211: fix crash in ieee80211_chan_bw_change for AP_VLAN stations ieee80211_chan_bw_change() iterates all stations and accesses link->reserved.oper via sta->sdata->link[link_id]. For stations on AP_VLAN interfaces (e.g. 4addr WDS clients), sta->sdata points to the VLAN sdata, whose link never participates in chanctx reservations. This leaves link->reserved.oper zero-initialized with chan == NULL, causing a NULL pointer dereference in __ieee80211_sta_cap_rx_bw() when accessing chandef->chan->band during CSA. Resolve the VLAN sdata to its parent AP sdata using get_bss_sdata() before accessing link data. [also change sta->sdata in ARRAY_SIZE even if it doesn't matter]

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31395

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: bnxt_en: fix OOB access in DBG_BUF_PRODUCER async event handler The ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER handler in bnxt_async_event_process() uses a firmware-supplied 'type' field directly as an index into bp->bs_trace[] without bounds validation. The 'type' field is a 16-bit value extracted from DMA-mapped completion ring memory that the NIC writes directly to host RAM. A malicious or compromised NIC can supply any value from 0 to 65535, causing an out-of-bounds access into kernel heap memory. The bnxt_bs_trace_check_wrap() call then dereferences bs_trace->magic_byte and writes to bs_trace->last_offset and bs_trace->wrapped, leading to kernel memory corruption or a crash. Fix by adding a bounds check and defining BNXT_TRACE_MAX as DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ERR_QPC_TRACE + 1 to cover all currently defined firmware trace types (0x0 through 0xc).

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31396

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: macb: fix use-after-free access to PTP clock PTP clock is registered on every opening of the interface and destroyed on every closing. However it may be accessed via get_ts_info ethtool call which is possible while the interface is just present in the kernel. BUG: KASAN: use-after-free in ptp_clock_index+0x47/0x50 drivers/ptp/ptp_clock.c:426 Read of size 4 at addr ffff8880194345cc by task syz.0.6/948 CPU: 1 PID: 948 Comm: syz.0.6 Not tainted 6.1.164+ #109 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.1-0-g3208b098f51a-prebuilt.qemu.org 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x8d/0xba lib/dump_stack.c:106 print_address_description mm/kasan/report.c:316 [inline] print_report+0x17f/0x496 mm/kasan/report.c:420 kasan_report+0xd9/0x180 mm/kasan/report.c:524 ptp_clock_index+0x47/0x50 drivers/ptp/ptp_clock.c:426 gem_get_ts_info+0x138/0x1e0 drivers/net/ethernet/cadence/macb_main.c:3349 macb_get_ts_info+0x68/0xb0 drivers/net/ethernet/cadence/macb_main.c:3371 __ethtool_get_ts_info+0x17c/0x260 net/ethtool/common.c:558 ethtool_get_ts_info net/ethtool/ioctl.c:2367 [inline] __dev_ethtool net/ethtool/ioctl.c:3017 [inline] dev_ethtool+0x2b05/0x6290 net/ethtool/ioctl.c:3095 dev_ioctl+0x637/0x1070 net/core/dev_ioctl.c:510 sock_do_ioctl+0x20d/0x2c0 net/socket.c:1215 sock_ioctl+0x577/0x6d0 net/socket.c:1320 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x18c/0x210 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:46 [inline] do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Allocated by task 457: kmalloc include/linux/slab.h:563 [inline] kzalloc include/linux/slab.h:699 [inline] ptp_clock_register+0x144/0x10e0 drivers/ptp/ptp_clock.c:235 gem_ptp_init+0x46f/0x930 drivers/net/ethernet/cadence/macb_ptp.c:375 macb_open+0x901/0xd10 drivers/net/ethernet/cadence/macb_main.c:2920 __dev_open+0x2ce/0x500 net/core/dev.c:1501 __dev_change_flags+0x56a/0x740 net/core/dev.c:8651 dev_change_flags+0x92/0x170 net/core/dev.c:8722 do_setlink+0xaf8/0x3a80 net/core/rtnetlink.c:2833 __rtnl_newlink+0xbf4/0x1940 net/core/rtnetlink.c:3608 rtnl_newlink+0x63/0xa0 net/core/rtnetlink.c:3655 rtnetlink_rcv_msg+0x3c6/0xed0 net/core/rtnetlink.c:6150 netlink_rcv_skb+0x15d/0x430 net/netlink/af_netlink.c:2511 netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline] netlink_unicast+0x6d7/0xa30 net/netlink/af_netlink.c:1344 netlink_sendmsg+0x97e/0xeb0 net/netlink/af_netlink.c:1872 sock_sendmsg_nosec net/socket.c:718 [inline] __sock_sendmsg+0x14b/0x180 net/socket.c:730 __sys_sendto+0x320/0x3b0 net/socket.c:2152 __do_sys_sendto net/socket.c:2164 [inline] __se_sys_sendto net/socket.c:2160 [inline] __x64_sys_sendto+0xdc/0x1b0 net/socket.c:2160 do_syscall_x64 arch/x86/entry/common.c:46 [inline] do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Freed by task 938: kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1729 [inline] slab_free_freelist_hook mm/slub.c:1755 [inline] slab_free mm/slub.c:3687 [inline] __kmem_cache_free+0xbc/0x320 mm/slub.c:3700 device_release+0xa0/0x240 drivers/base/core.c:2507 kobject_cleanup lib/kobject.c:681 [inline] kobject_release lib/kobject.c:712 [inline] kref_put include/linux/kref.h:65 [inline] kobject_put+0x1cd/0x350 lib/kobject.c:729 put_device+0x1b/0x30 drivers/base/core.c:3805 ptp_clock_unregister+0x171/0x270 drivers/ptp/ptp_clock.c:391 gem_ptp_remove+0x4e/0x1f0 drivers/net/ethernet/cadence/macb_ptp.c:404 macb_close+0x1c8/0x270 drivers/net/ethernet/cadence/macb_main.c:2966 __dev_close_many+0x1b9/0x310 net/core/dev.c:1585 __dev_close net/core/dev.c:1597 [inline] __dev_change_flags+0x2bb/0x740 net/core/dev.c:8649 dev_change_fl ---truncated---

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31397

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: mm/huge_memory: fix use of NULL folio in move_pages_huge_pmd() move_pages_huge_pmd() handles UFFDIO_MOVE for both normal THPs and huge zero pages. For the huge zero page path, src_folio is explicitly set to NULL, and is used as a sentinel to skip folio operations like lock and rmap. In the huge zero page branch, src_folio is NULL, so folio_mk_pmd(NULL, pgprot) passes NULL through folio_pfn() and page_to_pfn(). With SPARSEMEM_VMEMMAP this silently produces a bogus PFN, installing a PMD pointing to non-existent physical memory. On other memory models it is a NULL dereference. Use page_folio(src_page) to obtain the valid huge zero folio from the page, which was obtained from pmd_page() and remains valid throughout. After commit d82d09e48219 ("mm/huge_memory: mark PMD mappings of the huge zero folio special"), moved huge zero PMDs must remain special so vm_normal_page_pmd() continues to treat them as special mappings. move_pages_huge_pmd() currently reconstructs the destination PMD in the huge zero page branch, which drops PMD state such as pmd_special() on architectures with CONFIG_ARCH_HAS_PTE_SPECIAL. As a result, vm_normal_page_pmd() can treat the moved huge zero PMD as a normal page and corrupt its refcount. Instead of reconstructing the PMD from the folio, derive the destination entry from src_pmdval after pmdp_huge_clear_flush(), then handle the PMD metadata the same way move_huge_pmd() does for moved entries by marking it soft-dirty and clearing uffd-wp.

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31398

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: mm/rmap: fix incorrect pte restoration for lazyfree folios We batch unmap anonymous lazyfree folios by folio_unmap_pte_batch. If the batch has a mix of writable and non-writable bits, we may end up setting the entire batch writable. Fix this by respecting writable bit during batching. Although on a successful unmap of a lazyfree folio, the soft-dirty bit is lost, preserve it on pte restoration by respecting the bit during batching, to make the fix consistent w.r.t both writable bit and soft-dirty bit. I was able to write the below reproducer and crash the kernel. Explanation of reproducer (set 64K mTHP to always): Fault in a 64K large folio. Split the VMA at mid-point with MADV_DONTFORK. fork() - parent points to the folio with 8 writable ptes and 8 non-writable ptes. Merge the VMAs with MADV_DOFORK so that folio_unmap_pte_batch() can determine all the 16 ptes as a batch. Do MADV_FREE on the range to mark the folio as lazyfree. Write to the memory to dirty the pte, eventually rmap will dirty the folio. Then trigger reclaim, we will hit the pte restoration path, and the kernel will crash with the trace given below. The BUG happens at: BUG_ON(atomic_inc_return(&ptc->anon_map_count) > 1 && rw); The code path is asking for anonymous page to be mapped writable into the pagetable. The BUG_ON() firing implies that such a writable page has been mapped into the pagetables of more than one process, which breaks anonymous memory/CoW semantics. [ 21.134473] kernel BUG at mm/page_table_check.c:118! [ 21.134497] Internal error: Oops - BUG: 00000000f2000800 [#1] SMP [ 21.135917] Modules linked in: [ 21.136085] CPU: 1 UID: 0 PID: 1735 Comm: dup-lazyfree Not tainted 7.0.0-rc1-00116-g018018a17770 #1028 PREEMPT [ 21.136858] Hardware name: linux,dummy-virt (DT) [ 21.137019] pstate: 21400005 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) [ 21.137308] pc : page_table_check_set+0x28c/0x2a8 [ 21.137607] lr : page_table_check_set+0x134/0x2a8 [ 21.137885] sp : ffff80008a3b3340 [ 21.138124] x29: ffff80008a3b3340 x28: fffffdffc3d14400 x27: ffffd1a55e03d000 [ 21.138623] x26: 0040000000000040 x25: ffffd1a55f7dd000 x24: 0000000000000001 [ 21.139045] x23: 0000000000000001 x22: 0000000000000001 x21: ffffd1a55f217f30 [ 21.139629] x20: 0000000000134521 x19: 0000000000134519 x18: 005c43e000040000 [ 21.140027] x17: 0001400000000000 x16: 0001700000000000 x15: 000000000000ffff [ 21.140578] x14: 000000000000000c x13: 005c006000000000 x12: 0000000000000020 [ 21.140828] x11: 0000000000000000 x10: 005c000000000000 x9 : ffffd1a55c079ee0 [ 21.141077] x8 : 0000000000000001 x7 : 005c03e000040000 x6 : 000000004000ffff [ 21.141490] x5 : ffff00017fffce00 x4 : 0000000000000001 x3 : 0000000000000002 [ 21.141741] x2 : 0000000000134510 x1 : 0000000000000000 x0 : ffff0000c08228c0 [ 21.141991] Call trace: [ 21.142093] page_table_check_set+0x28c/0x2a8 (P) [ 21.142265] __page_table_check_ptes_set+0x144/0x1e8 [ 21.142441] __set_ptes_anysz.constprop.0+0x160/0x1a8 [ 21.142766] contpte_set_ptes+0xe8/0x140 [ 21.142907] try_to_unmap_one+0x10c4/0x10d0 [ 21.143177] rmap_walk_anon+0x100/0x250 [ 21.143315] try_to_unmap+0xa0/0xc8 [ 21.143441] shrink_folio_list+0x59c/0x18a8 [ 21.143759] shrink_lruvec+0x664/0xbf0 [ 21.144043] shrink_node+0x218/0x878 [ 21.144285] __node_reclaim.constprop.0+0x98/0x338 [ 21.144763] user_proactive_reclaim+0x2a4/0x340 [ 21.145056] reclaim_store+0x3c/0x60 [ 21.145216] dev_attr_store+0x20/0x40 [ 21.145585] sysfs_kf_write+0x84/0xa8 [ 21.145835] kernfs_fop_write_iter+0x130/0x1c8 [ 21.145994] vfs_write+0x2b8/0x368 [ 21.146119] ksys_write+0x70/0x110 [ 21.146240] __arm64_sys_write+0x24/0x38 [ 21.146380] invoke_syscall+0x50/0x120 [ 21.146513] el0_svc_common.constprop.0+0x48/0xf8 [ 21.146679] do_el0_svc+0x28/0x40 [ 21.146798] el0_svc+0x34/0x110 [ 21.146926] el0t ---truncated---

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31399

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: nvdimm/bus: Fix potential use after free in asynchronous initialization Dingisoul with KASAN reports a use after free if device_add() fails in nd_async_device_register(). Commit b6eae0f61db2 ("libnvdimm: Hold reference on parent while scheduling async init") correctly added a reference on the parent device to be held until asynchronous initialization was complete. However, if device_add() results in an allocation failure the ref count of the device drops to 0 prior to the parent pointer being accessed. Thus resulting in use after free. The bug bot AI correctly identified the fix. Save a reference to the parent pointer to be used to drop the parent reference regardless of the outcome of device_add().

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31400

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: sunrpc: fix cache_request leak in cache_release When a reader's file descriptor is closed while in the middle of reading a cache_request (rp->offset != 0), cache_release() decrements the request's readers count but never checks whether it should free the request. In cache_read(), when readers drops to 0 and CACHE_PENDING is clear, the cache_request is removed from the queue and freed along with its buffer and cache_head reference. cache_release() lacks this cleanup. The only other path that frees requests with readers == 0 is cache_dequeue(), but it runs only when CACHE_PENDING transitions from set to clear. If that transition already happened while readers was still non-zero, cache_dequeue() will have skipped the request, and no subsequent call will clean it up. Add the same cleanup logic from cache_read() to cache_release(): after decrementing readers, check if it reached 0 with CACHE_PENDING clear, and if so, dequeue and free the cache_request.

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31401

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: HID: bpf: prevent buffer overflow in hid_hw_request right now the returned value is considered to be always valid. However, when playing with HID-BPF, the return value can be arbitrary big, because it's the return value of dispatch_hid_bpf_raw_requests(), which calls the struct_ops and we have no guarantees that the value makes sense.

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31402

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: nfsd: fix heap overflow in NFSv4.0 LOCK replay cache The NFSv4.0 replay cache uses a fixed 112-byte inline buffer (rp_ibuf[NFSD4_REPLAY_ISIZE]) to store encoded operation responses. This size was calculated based on OPEN responses and does not account for LOCK denied responses, which include the conflicting lock owner as a variable-length field up to 1024 bytes (NFS4_OPAQUE_LIMIT). When a LOCK operation is denied due to a conflict with an existing lock that has a large owner, nfsd4_encode_operation() copies the full encoded response into the undersized replay buffer via read_bytes_from_xdr_buf() with no bounds check. This results in a slab-out-of-bounds write of up to 944 bytes past the end of the buffer, corrupting adjacent heap memory. This can be triggered remotely by an unauthenticated attacker with two cooperating NFSv4.0 clients: one sets a lock with a large owner string, then the other requests a conflicting lock to provoke the denial. We could fix this by increasing NFSD4_REPLAY_ISIZE to allow for a full opaque, but that would increase the size of every stateowner, when most lockowners are not that large. Instead, fix this by checking the encoded response length against NFSD4_REPLAY_ISIZE before copying into the replay buffer. If the response is too large, set rp_buflen to 0 to skip caching the replay payload. The status is still cached, and the client already received the correct response on the original request.

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31403

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: NFSD: Hold net reference for the lifetime of /proc/fs/nfs/exports fd The /proc/fs/nfs/exports proc entry is created at module init and persists for the module's lifetime. exports_proc_open() captures the caller's current network namespace and stores its svc_export_cache in seq->private, but takes no reference on the namespace. If the namespace is subsequently torn down (e.g. container destruction after the opener does setns() to a different namespace), nfsd_net_exit() calls nfsd_export_shutdown() which frees the cache. Subsequent reads on the still-open fd dereference the freed cache_detail, walking a freed hash table. Hold a reference on the struct net for the lifetime of the open file descriptor. This prevents nfsd_net_exit() from running -- and thus prevents nfsd_export_shutdown() from freeing the cache -- while any exports fd is open. cache_detail already stores its net pointer (cd->net, set by cache_create_net()), so exports_release() can retrieve it without additional per-file storage.

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31404

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: NFSD: Defer sub-object cleanup in export put callbacks svc_export_put() calls path_put() and auth_domain_put() immediately when the last reference drops, before the RCU grace period. RCU readers in e_show() and c_show() access both ex_path (via seq_path/d_path) and ex_client->name (via seq_escape) without holding a reference. If cache_clean removes the entry and drops the last reference concurrently, the sub-objects are freed while still in use, producing a NULL pointer dereference in d_path. Commit 2530766492ec ("nfsd: fix UAF when access ex_uuid or ex_stats") moved kfree of ex_uuid and ex_stats into the call_rcu callback, but left path_put() and auth_domain_put() running before the grace period because both may sleep and call_rcu callbacks execute in softirq context. Replace call_rcu/kfree_rcu with queue_rcu_work(), which defers the callback until after the RCU grace period and executes it in process context where sleeping is permitted. This allows path_put() and auth_domain_put() to be moved into the deferred callback alongside the other resource releases. Apply the same fix to expkey_put(), which has the identical pattern with ek_path and ek_client. A dedicated workqueue scopes the shutdown drain to only NFSD export release work items; flushing the shared system_unbound_wq would stall on unrelated work from other subsystems. nfsd_export_shutdown() uses rcu_barrier() followed by flush_workqueue() to ensure all deferred release callbacks complete before the export caches are destroyed. Reviwed-by: Jeff Layton

Published: 2026-04-03Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31406

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini() After cancel_delayed_work_sync() is called from xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining states via __xfrm_state_delete(), which calls xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work. The following is a simple race scenario: cpu0 cpu1 cleanup_net() [Round 1] ops_undo_list() xfrm_net_exit() xfrm_nat_keepalive_net_fini() cancel_delayed_work_sync(nat_keepalive_work); xfrm_state_fini() xfrm_state_flush() xfrm_state_delete(x) __xfrm_state_delete(x) xfrm_nat_keepalive_state_updated(x) schedule_delayed_work(nat_keepalive_work); rcu_barrier(); net_complete_free(); net_passive_dec(net); llist_add(&net->defer_free_list, &defer_free_list); cleanup_net() [Round 2] rcu_barrier(); net_complete_free() kmem_cache_free(net_cachep, net); nat_keepalive_work() // on freed net To prevent this, cancel_delayed_work_sync() is replaced with disable_delayed_work_sync().

Published: 2026-04-06Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31407

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: netfilter: conntrack: add missing netlink policy validations Hyunwoo Kim reports out-of-bounds access in sctp and ctnetlink. These attributes are used by the kernel without any validation. Extend the netlink policies accordingly. Quoting the reporter: nlattr_to_sctp() assigns the user-supplied CTA_PROTOINFO_SCTP_STATE value directly to ct->proto.sctp.state without checking that it is within the valid range. [..] and: ... with exp->dir = 100, the access at ct->master->tuplehash[100] reads 5600 bytes past the start of a 320-byte nf_conn object, causing a slab-out-of-bounds read confirmed by UBSAN.

Published: 2026-04-06Modified: 2026-05-20

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31408

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: SCO: Fix use-after-free in sco_recv_frame() due to missing sock_hold sco_recv_frame() reads conn->sk under sco_conn_lock() but immediately releases the lock without holding a reference to the socket. A concurrent close() can free the socket between the lock release and the subsequent sk->sk_state access, resulting in a use-after-free. Other functions in the same file (sco_sock_timeout(), sco_conn_del()) correctly use sco_sock_hold() to safely hold a reference under the lock. Fix by using sco_sock_hold() to take a reference before releasing the lock, and adding sock_put() on all exit paths.

Published: 2026-04-06Modified: 2026-05-20

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31409

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: ksmbd: unset conn->binding on failed binding request When a multichannel SMB2_SESSION_SETUP request with SMB2_SESSION_REQ_FLAG_BINDING fails ksmbd sets conn->binding = true but never clears it on the error path. This leaves the connection in a binding state where all subsequent ksmbd_session_lookup_all() calls fall back to the global sessions table. This fix it by clearing conn->binding = false in the error path.

Published: 2026-04-06Modified: 2026-05-20

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31410

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ksmbd: use volume UUID in FS_OBJECT_ID_INFORMATION Use sb->s_uuid for a proper volume identifier as the primary choice. For filesystems that do not provide a UUID, fall back to stfs.f_fsid obtained from vfs_statfs().

Published: 2026-04-06Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31413

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix unsound scalar forking in maybe_fork_scalars() for BPF_OR maybe_fork_scalars() is called for both BPF_AND and BPF_OR when the source operand is a constant. When dst has signed range [-1, 0], it forks the verifier state: the pushed path gets dst = 0, the current path gets dst = -1. For BPF_AND this is correct: 0 & K == 0. For BPF_OR this is wrong: 0 | K == K, not 0. The pushed path therefore tracks dst as 0 when the runtime value is K, producing an exploitable verifier/runtime divergence that allows out-of-bounds map access. Fix this by passing env->insn_idx (instead of env->insn_idx + 1) to push_stack(), so the pushed path re-executes the ALU instruction with dst = 0 and naturally computes the correct result for any opcode.

Published: 2026-04-12Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31414

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_expect: use expect->helper Use expect->helper in ctnetlink and /proc to dump the helper name. Using nfct_help() without holding a reference to the master conntrack is unsafe. Use exp->master->helper in ctnetlink path if userspace does not provide an explicit helper when creating an expectation to retain the existing behaviour. The ctnetlink expectation path holds the reference on the master conntrack and nf_conntrack_expect lock and the nfnetlink glue path refers to the master ct that is attached to the skb.

Published: 2026-04-13Modified: 2026-05-20

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31415

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ipv6: avoid overflows in ip6_datagram_send_ctl() Yiming Qian reported : I believe I found a locally triggerable kernel bug in the IPv6 sendmsg ancillary-data path that can panic the kernel via `skb_under_panic()` (local DoS). The core issue is a mismatch between: - a 16-bit length accumulator (`struct ipv6_txoptions::opt_flen`, type `__u16`) and - a pointer to the last provided destination-options header (`opt->dst1opt`) when multiple `IPV6_DSTOPTS` control messages (cmsgs) are provided. - `include/net/ipv6.h`: - `struct ipv6_txoptions::opt_flen` is `__u16` (wrap possible). (lines 291-307, especially 298) - `net/ipv6/datagram.c:ip6_datagram_send_ctl()`: - Accepts repeated `IPV6_DSTOPTS` and accumulates into `opt_flen` without rejecting duplicates. (lines 909-933) - `net/ipv6/ip6_output.c:__ip6_append_data()`: - Uses `opt->opt_flen + opt->opt_nflen` to compute header sizes/headroom decisions. (lines 1448-1466, especially 1463-1465) - `net/ipv6/ip6_output.c:__ip6_make_skb()`: - Calls `ipv6_push_frag_opts()` if `opt->opt_flen` is non-zero. (lines 1930-1934) - `net/ipv6/exthdrs.c:ipv6_push_frag_opts()` / `ipv6_push_exthdr()`: - Push size comes from `ipv6_optlen(opt->dst1opt)` (based on the pointed-to header). (lines 1179-1185 and 1206-1211) 1. `opt_flen` is a 16-bit accumulator: - `include/net/ipv6.h:298` defines `__u16 opt_flen; /* after fragment hdr /`. 2. `ip6_datagram_send_ctl()` accepts repeated* `IPV6_DSTOPTS` cmsgs and increments `opt_flen` each time: - In `net/ipv6/datagram.c:909-933`, for `IPV6_DSTOPTS`: - It computes `len = ((hdr->hdrlen + 1) << 3);` - It checks `CAP_NET_RAW` using `ns_capable(net->user_ns, CAP_NET_RAW)`. (line 922) - Then it does: - `opt->opt_flen += len;` (line 927) - `opt->dst1opt = hdr;` (line 928) There is no duplicate rejection here (unlike the legacy `IPV6_2292DSTOPTS` path which rejects duplicates at `net/ipv6/datagram.c:901-904`). If enough large `IPV6_DSTOPTS` cmsgs are provided, `opt_flen` wraps while `dst1opt` still points to a large (2048-byte) destination-options header. In the attached PoC (`poc.c`): - 32 cmsgs with `hdrlen=255` => `len = (255+1)8 = 2048` - 1 cmsg with `hdrlen=0` => `len = 8` - Total increment: `322048 + 8 = 65544`, so `(__u16)opt_flen == 8` - The last cmsg is 2048 bytes, so `dst1opt` points to a 2048-byte header. 3. The transmit path sizes headers using the wrapped `opt_flen`: - In `net/ipv6/ip6_output.c:1463-1465`: - `headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + ...;` With wrapped `opt_flen`, `headersize`/headroom decisions underestimate what will be pushed later. 4. When building the final skb, the actual push length comes from `dst1opt` and is not limited by wrapped `opt_flen`: - In `net/ipv6/ip6_output.c:1930-1934`: - `if (opt->opt_flen) proto = ipv6_push_frag_opts(skb, opt, proto);` - In `net/ipv6/exthdrs.c:1206-1211`, `ipv6_push_frag_opts()` pushes `dst1opt` via `ipv6_push_exthdr()`. - In `net/ipv6/exthdrs.c:1179-1184`, `ipv6_push_exthdr()` does: - `skb_push(skb, ipv6_optlen(opt));` - `memcpy(h, opt, ipv6_optlen(opt));` With insufficient headroom, `skb_push()` underflows and triggers `skb_under_panic()` -> `BUG()`: - `net/core/skbuff.c:2669-2675` (`skb_push()` calls `skb_under_panic()`) - `net/core/skbuff.c:207-214` (`skb_panic()` ends in `BUG()`) - The `IPV6_DSTOPTS` cmsg path requires `CAP_NET_RAW` in the target netns user namespace (`ns_capable(net->user_ns, CAP_NET_RAW)`). - Root (or any task with `CAP_NET_RAW`) can trigger this without user namespaces. - An unprivileged `uid=1000` user can trigger this if unprivileged user namespaces are enabled and it can create a userns+netns to obtain namespaced `CAP_NET_RAW` (the attached PoC does this). - Local denial of service: kernel BUG/panic (system crash). - ---truncated---

Published: 2026-04-13Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31416

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: nfnetlink_log: account for netlink header size This is a followup to an old bug fix: NLMSG_DONE needs to account for the netlink header size, not just the attribute size. This can result in a WARN splat + drop of the netlink message, but other than this there are no ill effects.

Published: 2026-04-13Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31417

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: net/x25: Fix overflow when accumulating packets Add a check to ensure that `x25_sock.fraglen` does not overflow. The `fraglen` also needs to be resetted when purging `fragment_queue` in `x25_clear_queues()`.

Published: 2026-04-13Modified: 2026-05-20

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31418

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: ipset: drop logically empty buckets in mtype_del mtype_del() counts empty slots below n->pos in k, but it only drops the bucket when both n->pos and k are zero. This misses buckets whose live entries have all been removed while n->pos still points past deleted slots. Treat a bucket as empty when all positions below n->pos are unused and release it directly instead of shrinking it further.

Published: 2026-04-13Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31419

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: bonding: fix use-after-free in bond_xmit_broadcast() bond_xmit_broadcast() reuses the original skb for the last slave (determined by bond_is_last_slave()) and clones it for others. Concurrent slave enslave/release can mutate the slave list during RCU-protected iteration, changing which slave is "last" mid-loop. This causes the original skb to be double-consumed (double-freed). Replace the racy bond_is_last_slave() check with a simple index comparison (i + 1 == slaves_count) against the pre-snapshot slave count taken via READ_ONCE() before the loop. This preserves the zero-copy optimization for the last slave while making the "last" determination stable against concurrent list mutations. The UAF can trigger the following crash: ================================================================== BUG: KASAN: slab-use-after-free in skb_clone Read of size 8 at addr ffff888100ef8d40 by task exploit/147 CPU: 1 UID: 0 PID: 147 Comm: exploit Not tainted 7.0.0-rc3+ #4 PREEMPTLAZY Call Trace: dump_stack_lvl (lib/dump_stack.c:123) print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) kasan_report (mm/kasan/report.c:597) skb_clone (include/linux/skbuff.h:1724 include/linux/skbuff.h:1792 include/linux/skbuff.h:3396 net/core/skbuff.c:2108) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5334) bond_start_xmit (drivers/net/bonding/bond_main.c:5567 drivers/net/bonding/bond_main.c:5593) dev_hard_start_xmit (include/linux/netdevice.h:5325 include/linux/netdevice.h:5334 net/core/dev.c:3871 net/core/dev.c:3887) __dev_queue_xmit (include/linux/netdevice.h:3601 net/core/dev.c:4838) ip6_finish_output2 (include/net/neighbour.h:540 include/net/neighbour.h:554 net/ipv6/ip6_output.c:136) ip6_finish_output (net/ipv6/ip6_output.c:208 net/ipv6/ip6_output.c:219) ip6_output (net/ipv6/ip6_output.c:250) ip6_send_skb (net/ipv6/ip6_output.c:1985) udp_v6_send_skb (net/ipv6/udp.c:1442) udpv6_sendmsg (net/ipv6/udp.c:1733) __sys_sendto (net/socket.c:730 net/socket.c:742 net/socket.c:2206) __x64_sys_sendto (net/socket.c:2209) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Allocated by task 147: Freed by task 147: The buggy address belongs to the object at ffff888100ef8c80 which belongs to the cache skbuff_head_cache of size 224 The buggy address is located 192 bytes inside of freed 224-byte region [ffff888100ef8c80, ffff888100ef8d60) Memory state around the buggy address: ffff888100ef8c00: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc ffff888100ef8c80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff888100ef8d00: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ^ ffff888100ef8d80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb ffff888100ef8e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ==================================================================

Published: 2026-04-13Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31421

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/sched: cls_fw: fix NULL pointer dereference on shared blocks The old-method path in fw_classify() calls tcf_block_q() and dereferences q->handle. Shared blocks leave block->q NULL, causing a NULL deref when an empty cls_fw filter is attached to a shared block and a packet with a nonzero major skb mark is classified. Reject the configuration in fw_change() when the old method (no TCA_OPTIONS) is used on a shared block, since fw_classify()'s old-method path needs block->q which is NULL for shared blocks. The fixed null-ptr-deref calling stack: KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f] RIP: 0010:fw_classify (net/sched/cls_fw.c:81) Call Trace: tcf_classify (./include/net/tc_wrapper.h:197 net/sched/cls_api.c:1764 net/sched/cls_api.c:1860) tc_run (net/core/dev.c:4401) __dev_queue_xmit (net/core/dev.c:4535 net/core/dev.c:4790)

Published: 2026-04-13Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31422

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/sched: cls_flow: fix NULL pointer dereference on shared blocks flow_change() calls tcf_block_q() and dereferences q->handle to derive a default baseclass. Shared blocks leave block->q NULL, causing a NULL deref when a flow filter without a fully qualified baseclass is created on a shared block. Check tcf_block_shared() before accessing block->q and return -EINVAL for shared blocks. This avoids the null-deref shown below: ======================================================================= KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f] RIP: 0010:flow_change (net/sched/cls_flow.c:508) Call Trace: tc_new_tfilter (net/sched/cls_api.c:2432) rtnetlink_rcv_msg (net/core/rtnetlink.c:6980) [...] =======================================================================

Published: 2026-04-13Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31423

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/sched: sch_hfsc: fix divide-by-zero in rtsc_min() m2sm() converts a u32 slope to a u64 scaled value. For large inputs (e.g. m1=4000000000), the result can reach 2^32. rtsc_min() stores the difference of two such u64 values in a u32 variable `dsm` and uses it as a divisor. When the difference is exactly 2^32 the truncation yields zero, causing a divide-by-zero oops in the concave-curve intersection path: Oops: divide error: 0000 RIP: 0010:rtsc_min (net/sched/sch_hfsc.c:601) Call Trace: init_ed (net/sched/sch_hfsc.c:629) hfsc_enqueue (net/sched/sch_hfsc.c:1569) [...] Widen `dsm` to u64 and replace do_div() with div64_u64() so the full difference is preserved.

Published: 2026-04-13Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31424

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: x_tables: restrict xt_check_match/xt_check_target extensions for NFPROTO_ARP Weiming Shi says: xt_match and xt_target structs registered with NFPROTO_UNSPEC can be loaded by any protocol family through nft_compat. When such a match/target sets .hooks to restrict which hooks it may run on, the bitmask uses NF_INET_* constants. This is only correct for families whose hook layout matches NF_INET_*: IPv4, IPv6, INET, and bridge all share the same five hooks (PRE_ROUTING ... POST_ROUTING). ARP only has three hooks (IN=0, OUT=1, FORWARD=2) with different semantics. Because NF_ARP_OUT == 1 == NF_INET_LOCAL_IN, the .hooks validation silently passes for the wrong reasons, allowing matches to run on ARP chains where the hook assumptions (e.g. state->in being set on input hooks) do not hold. This leads to NULL pointer dereferences; xt_devgroup is one concrete example: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000044: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000220-0x0000000000000227] RIP: 0010:devgroup_mt+0xff/0x350 Call Trace: nft_match_eval (net/netfilter/nft_compat.c:407) nft_do_chain (net/netfilter/nf_tables_core.c:285) nft_do_chain_arp (net/netfilter/nft_chain_filter.c:61) nf_hook_slow (net/netfilter/core.c:623) arp_xmit (net/ipv4/arp.c:666) Kernel panic - not syncing: Fatal exception in interrupt Fix it by restricting arptables to NFPROTO_ARP extensions only. Note that arptables-legacy only supports: - arpt_CLASSIFY - arpt_mangle - arpt_MARK that provide explicit NFPROTO_ARP match/target declarations.

Published: 2026-04-13Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31425

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: rds: ib: reject FRMR registration before IB connection is established rds_ib_get_mr() extracts the rds_ib_connection from conn->c_transport_data and passes it to rds_ib_reg_frmr() for FRWR memory registration. On a fresh outgoing connection, ic is allocated in rds_ib_conn_alloc() with i_cm_id = NULL because the connection worker has not yet called rds_ib_conn_path_connect() to create the rdma_cm_id. When sendmsg() with RDS_CMSG_RDMA_MAP is called on such a connection, the sendmsg path parses the control message before any connection establishment, allowing rds_ib_post_reg_frmr() to dereference ic->i_cm_id->qp and crash the kernel. The existing guard in rds_ib_reg_frmr() only checks for !ic (added in commit 9e630bcb7701), which does not catch this case since ic is allocated early and is always non-NULL once the connection object exists. KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] RIP: 0010:rds_ib_post_reg_frmr+0x50e/0x920 Call Trace: rds_ib_post_reg_frmr (net/rds/ib_frmr.c:167) rds_ib_map_frmr (net/rds/ib_frmr.c:252) rds_ib_reg_frmr (net/rds/ib_frmr.c:430) rds_ib_get_mr (net/rds/ib_rdma.c:615) __rds_rdma_map (net/rds/rdma.c:295) rds_cmsg_rdma_map (net/rds/rdma.c:860) rds_sendmsg (net/rds/send.c:1363) ____sys_sendmsg do_syscall_64 Add a check in rds_ib_get_mr() that verifies ic, i_cm_id, and qp are all non-NULL before proceeding with FRMR registration, mirroring the guard already present in rds_ib_post_inv(). Return -ENODEV when the connection is not ready, which the existing error handling in rds_cmsg_send() converts to -EAGAIN for userspace retry and triggers rds_conn_connect_if_down() to start the connection worker.

Published: 2026-04-13Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31426

HIGH7.0

In the Linux kernel, the following vulnerability has been resolved: ACPI: EC: clean up handlers on probe failure in acpi_ec_setup() When ec_install_handlers() returns -EPROBE_DEFER on reduced-hardware platforms, it has already started the EC and installed the address space handler with the struct acpi_ec pointer as handler context. However, acpi_ec_setup() propagates the error without any cleanup. The caller acpi_ec_add() then frees the struct acpi_ec for non-boot instances, leaving a dangling handler context in ACPICA. Any subsequent AML evaluation that accesses an EC OpRegion field dispatches into acpi_ec_space_handler() with the freed pointer, causing a use-after-free: BUG: KASAN: slab-use-after-free in mutex_lock (kernel/locking/mutex.c:289) Write of size 8 at addr ffff88800721de38 by task init/1 Call Trace: mutex_lock (kernel/locking/mutex.c:289) acpi_ec_space_handler (drivers/acpi/ec.c:1362) acpi_ev_address_space_dispatch (drivers/acpi/acpica/evregion.c:293) acpi_ex_access_region (drivers/acpi/acpica/exfldio.c:246) acpi_ex_field_datum_io (drivers/acpi/acpica/exfldio.c:509) acpi_ex_extract_from_field (drivers/acpi/acpica/exfldio.c:700) acpi_ex_read_data_from_field (drivers/acpi/acpica/exfield.c:327) acpi_ex_resolve_node_to_value (drivers/acpi/acpica/exresolv.c:392) Allocated by task 1: acpi_ec_alloc (drivers/acpi/ec.c:1424) acpi_ec_add (drivers/acpi/ec.c:1692) Freed by task 1: kfree (mm/slub.c:6876) acpi_ec_add (drivers/acpi/ec.c:1751) The bug triggers on reduced-hardware EC platforms (ec->gpe < 0) when the GPIO IRQ provider defers probing. Once the stale handler exists, any unprivileged sysfs read that causes AML to touch an EC OpRegion (battery, thermal, backlight) exercises the dangling pointer. Fix this by calling ec_remove_handlers() in the error path of acpi_ec_setup() before clearing first_ec. ec_remove_handlers() checks each EC_FLAGS_* bit before acting, so it is safe to call regardless of how far ec_install_handlers() progressed: -ENODEV (handler not installed): only calls acpi_ec_stop() -EPROBE_DEFER (handler installed): removes handler, stops EC

Published: 2026-04-13Modified: 2026-05-20

CVSS 3.xHIGH 7.0

CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31427

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_sip: fix use of uninitialized rtp_addr in process_sdp process_sdp() declares union nf_inet_addr rtp_addr on the stack and passes it to the nf_nat_sip sdp_session hook after walking the SDP media descriptions. However rtp_addr is only initialized inside the media loop when a recognized media type with a non-zero port is found. If the SDP body contains no m= lines, only inactive media sections (m=audio 0 ...) or only unrecognized media types, rtp_addr is never assigned. Despite that, the function still calls hooks->sdp_session() with &rtp_addr, causing nf_nat_sdp_session() to format the stale stack value as an IP address and rewrite the SDP session owner and connection lines with it. With CONFIG_INIT_STACK_ALL_ZERO (default on most distributions) this results in the session-level o= and c= addresses being rewritten to 0.0.0.0 for inactive SDP sessions. Without stack auto-init the rewritten address is whatever happened to be on the stack. Fix this by pre-initializing rtp_addr from the session-level connection address (caddr) when available, and tracking via a have_rtp_addr flag whether any valid address was established. Skip the sdp_session hook entirely when no valid address exists.

Published: 2026-04-13Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31428

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: nfnetlink_log: fix uninitialized padding leak in NFULA_PAYLOAD __build_packet_message() manually constructs the NFULA_PAYLOAD netlink attribute using skb_put() and skb_copy_bits(), bypassing the standard nla_reserve()/nla_put() helpers. While nla_total_size(data_len) bytes are allocated (including NLA alignment padding), only data_len bytes of actual packet data are copied. The trailing nla_padlen(data_len) bytes (1-3 when data_len is not 4-byte aligned) are never initialized, leaking stale heap contents to userspace via the NFLOG netlink socket. Replace the manual attribute construction with nla_reserve(), which handles the tailroom check, header setup, and padding zeroing via __nla_reserve(). The subsequent skb_copy_bits() fills in the payload data on top of the properly initialized attribute.

Published: 2026-04-13Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31429

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: skb: fix cross-cache free of KFENCE-allocated skb head SKB_SMALL_HEAD_CACHE_SIZE is intentionally set to a non-power-of-2 value (e.g. 704 on x86_64) to avoid collisions with generic kmalloc bucket sizes. This ensures that skb_kfree_head() can reliably use skb_end_offset to distinguish skb heads allocated from skb_small_head_cache vs. generic kmalloc caches. However, when KFENCE is enabled, kfence_ksize() returns the exact requested allocation size instead of the slab bucket size. If a caller (e.g. bpf_test_init) allocates skb head data via kzalloc() and the requested size happens to equal SKB_SMALL_HEAD_CACHE_SIZE, then slab_build_skb() -> ksize() returns that exact value. After subtracting skb_shared_info overhead, skb_end_offset ends up matching SKB_SMALL_HEAD_HEADROOM, causing skb_kfree_head() to incorrectly free the object to skb_small_head_cache instead of back to the original kmalloc cache, resulting in a slab cross-cache free: kmem_cache_free(skbuff_small_head): Wrong slab cache. Expected skbuff_small_head but got kmalloc-1k Fix this by always calling kfree(head) in skb_kfree_head(). This keeps the free path generic and avoids allocator-specific misclassification for KFENCE objects.

Published: 2026-04-20Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31431

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: crypto: algif_aead - Revert to operating out-of-place This mostly reverts commit 72548b093ee3 except for the copying of the associated data. There is no benefit in operating in-place in algif_aead since the source and destination come from different mappings. Get rid of all the complexity added for in-place operation and just copy the AD directly.

Published: 2026-04-22Modified: 2026-05-18

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31434

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: btrfs: fix leak of kobject name for sub-group space_info When create_space_info_sub_group() allocates elements of space_info->sub_group[], kobject_init_and_add() is called for each element via btrfs_sysfs_add_space_info_type(). However, when check_removing_space_info() frees these elements, it does not call btrfs_sysfs_remove_space_info() on them. As a result, kobject_put() is not called and the associated kobj->name objects are leaked. This memory leak is reproduced by running the blktests test case zbd/009 on kernels built with CONFIG_DEBUG_KMEMLEAK. The kmemleak feature reports the following error: unreferenced object 0xffff888112877d40 (size 16): comm "mount", pid 1244, jiffies 4294996972 hex dump (first 16 bytes): 64 61 74 61 2d 72 65 6c 6f 63 00 c4 c6 a7 cb 7f data-reloc...... backtrace (crc 53ffde4d): __kmalloc_node_track_caller_noprof+0x619/0x870 kstrdup+0x42/0xc0 kobject_set_name_vargs+0x44/0x110 kobject_init_and_add+0xcf/0x150 btrfs_sysfs_add_space_info_type+0xfc/0x210 [btrfs] create_space_info_sub_group.constprop.0+0xfb/0x1b0 [btrfs] create_space_info+0x211/0x320 [btrfs] btrfs_init_space_info+0x15a/0x1b0 [btrfs] open_ctree+0x33c7/0x4a50 [btrfs] btrfs_get_tree.cold+0x9f/0x1ee [btrfs] vfs_get_tree+0x87/0x2f0 vfs_cmd_create+0xbd/0x280 __do_sys_fsconfig+0x3df/0x990 do_syscall_64+0x136/0x1540 entry_SYSCALL_64_after_hwframe+0x76/0x7e To avoid the leak, call btrfs_sysfs_remove_space_info() instead of kfree() for the elements.

Published: 2026-04-22Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31435

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: netfs: Fix read abandonment during retry Under certain circumstances, all the remaining subrequests from a read request will get abandoned during retry. The abandonment process expects the 'subreq' variable to be set to the place to start abandonment from, but it doesn't always have a useful value (it will be uninitialised on the first pass through the loop and it may point to a deleted subrequest on later passes). Fix the first jump to "abandon:" to set subreq to the start of the first subrequest expected to need retry (which, in this abandonment case, turned out unexpectedly to no longer have NEED_RETRY set). Also clear the subreq pointer after discarding superfluous retryable subrequests to cause an oops if we do try to access it.

Published: 2026-04-22Modified: 2026-05-19

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

References

CVE-2026-31436

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: fix possible wrong descriptor completion in llist_abort_desc() At the end of this function, d is the traversal cursor of flist, but the code completes found instead. This can lead to issues such as NULL pointer dereferences, double completion, or descriptor leaks. Fix this by completing d instead of found in the final list_for_each_entry_safe() loop.

Published: 2026-04-22Modified: 2026-05-19

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31437

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfs: Fix NULL pointer dereference in netfs_unbuffered_write() on retry When a write subrequest is marked NETFS_SREQ_NEED_RETRY, the retry path in netfs_unbuffered_write() unconditionally calls stream->prepare_write() without checking if it is NULL. Filesystems such as 9P do not set the prepare_write operation, so stream->prepare_write remains NULL. When get_user_pages() fails with -EFAULT and the subrequest is flagged for retry, this results in a NULL pointer dereference at fs/netfs/direct_write.c:189. Fix this by mirroring the pattern already used in write_retry.c: if stream->prepare_write is NULL, skip renegotiation and directly reissue the subrequest via netfs_reissue_write(), which handles iterator reset, IN_PROGRESS flag, stats update and reissue internally.

Published: 2026-04-22Modified: 2026-05-19

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31438

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfs: Fix kernel BUG in netfs_limit_iter() for ITER_KVEC iterators When a process crashes and the kernel writes a core dump to a 9P filesystem, __kernel_write() creates an ITER_KVEC iterator. This iterator reaches netfs_limit_iter() via netfs_unbuffered_write(), which only handles ITER_FOLIOQ, ITER_BVEC and ITER_XARRAY iterator types, hitting the BUG() for any other type. Fix this by adding netfs_limit_kvec() following the same pattern as netfs_limit_bvec(), since both kvec and bvec are simple segment arrays with pointer and length fields. Dispatch it from netfs_limit_iter() when the iterator type is ITER_KVEC.

Published: 2026-04-22Modified: 2026-05-19

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31439

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: dmaengine: xilinx: xdma: Fix regmap init error handling devm_regmap_init_mmio returns an ERR_PTR() upon error, not NULL. Fix the error check and also fix the error message. Use the error code from ERR_PTR() instead of the wrong value in ret.

Published: 2026-04-22Modified: 2026-05-19

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31440

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Fix leaking event log memory During the device remove process, the device is reset, causing the configuration registers to go back to their default state, which is zero. As the driver is checking if the event log support was enabled before deallocating, it will fail if a reset happened before. Do not check if the support was enabled, the check for 'idxd->evl' being valid (only allocated if the HW capability is available) is enough.

Published: 2026-04-22Modified: 2026-05-17

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31441

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Fix memory leak when a wq is reset idxd_wq_disable_cleanup() which is called from the reset path for a workqueue, sets the wq type to NONE, which for other parts of the driver mean that the wq is empty (all its resources were released). Only set the wq type to NONE after its resources are released.

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31442

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Fix possible invalid memory access after FLR In the case that the first Function Level Reset (FLR) concludes correctly, but in the second FLR the scratch area for the saved configuration cannot be allocated, it's possible for a invalid memory access to happen. Always set the deallocated scratch area to NULL after FLR completes.

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31443

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Fix crash when the event log is disabled If reporting errors to the event log is not supported by the hardware, and an error that causes Function Level Reset (FLR) is received, the driver will try to restore the event log even if it was not allocated. Also, only try to free the event log if it was properly allocated.

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31444

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix use-after-free and NULL deref in smb_grant_oplock() smb_grant_oplock() has two issues in the oplock publication sequence: 1) opinfo is linked into ci->m_op_list (via opinfo_add) before add_lease_global_list() is called. If add_lease_global_list() fails (kmalloc returns NULL), the error path frees the opinfo via __free_opinfo() while it is still linked in ci->m_op_list. Concurrent m_op_list readers (opinfo_get_list, or direct iteration in smb_break_all_levII_oplock) dereference the freed node. 2) opinfo->o_fp is assigned after add_lease_global_list() publishes the opinfo on the global lease list. A concurrent find_same_lease_key() can walk the lease list and dereference opinfo->o_fp->f_ci while o_fp is still NULL. Fix by restructuring the publication sequence to eliminate post-publish failure: - Set opinfo->o_fp before any list publication (fixes NULL deref). - Preallocate lease_table via alloc_lease_table() before opinfo_add() so add_lease_global_list() becomes infallible after publication. - Keep the original m_op_list publication order (opinfo_add before lease list) so concurrent opens via same_client_has_lease() and opinfo_get_list() still see the in-flight grant. - Use opinfo_put() instead of __free_opinfo() on err_out so that the RCU-deferred free path is used. This also requires splitting add_lease_global_list() to take a preallocated lease_table and changing its return type from int to void, since it can no longer fail.

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31445

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mm/damon/core: avoid use of half-online-committed context One major usage of damon_call() is online DAMON parameters update. It is done by calling damon_commit_ctx() inside the damon_call() callback function. damon_commit_ctx() can fail for two reasons: 1) invalid parameters and 2) internal memory allocation failures. In case of failures, the damon_ctx that attempted to be updated (commit destination) can be partially updated (or, corrupted from a perspective), and therefore shouldn't be used anymore. The function only ensures the damon_ctx object can safely deallocated using damon_destroy_ctx(). The API callers are, however, calling damon_commit_ctx() only after asserting the parameters are valid, to avoid damon_commit_ctx() fails due to invalid input parameters. But it can still theoretically fail if the internal memory allocation fails. In the case, DAMON may run with the partially updated damon_ctx. This can result in unexpected behaviors including even NULL pointer dereference in case of damos_commit_dests() failure [1]. Such allocation failure is arguably too small to fail, so the real world impact would be rare. But, given the bad consequence, this needs to be fixed. Avoid such partially-committed (maybe-corrupted) damon_ctx use by saving the damon_commit_ctx() failure on the damon_ctx object. For this, introduce damon_ctx->maybe_corrupted field. damon_commit_ctx() sets it when it is failed. kdamond_call() checks if the field is set after each damon_call_control->fn() is executed. If it is set, ignore remaining callback requests and return. All kdamond_call() callers including kdamond_fn() also check the maybe_corrupted field right after kdamond_call() invocations. If the field is set, break the kdamond_fn() main loop so that DAMON sill doesn't use the context that might be corrupted. [sj@kernel.org: let kdamond_call() with cancel regardless of maybe_corrupted]

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31446

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ext4: fix use-after-free in update_super_work when racing with umount Commit b98535d09179 ("ext4: fix bug_on in start_this_handle during umount filesystem") moved ext4_unregister_sysfs() before flushing s_sb_upd_work to prevent new error work from being queued via /proc/fs/ext4/xx/mb_groups reads during unmount. However, this introduced a use-after-free because update_super_work calls ext4_notify_error_sysfs() -> sysfs_notify() which accesses the kobject's kernfs_node after it has been freed by kobject_del() in ext4_unregister_sysfs(): update_super_work ext4_put_super ----------------- -------------- ext4_unregister_sysfs(sb) kobject_del(&sbi->s_kobj) __kobject_del() sysfs_remove_dir() kobj->sd = NULL sysfs_put(sd) kernfs_put() // RCU free ext4_notify_error_sysfs(sbi) sysfs_notify(&sbi->s_kobj) kn = kobj->sd // stale pointer kernfs_get(kn) // UAF on freed kernfs_node ext4_journal_destroy() flush_work(&sbi->s_sb_upd_work) Instead of reordering the teardown sequence, fix this by making ext4_notify_error_sysfs() detect that sysfs has already been torn down by checking s_kobj.state_in_sysfs, and skipping the sysfs_notify() call in that case. A dedicated mutex (s_error_notify_mutex) serializes ext4_notify_error_sysfs() against kobject_del() in ext4_unregister_sysfs() to prevent TOCTOU races where the kobject could be deleted between the state_in_sysfs check and the sysfs_notify() call.

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

References

CVE-2026-31447

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ext4: reject mount if bigalloc with s_first_data_block != 0 bigalloc with s_first_data_block != 0 is not supported, reject mounting it.

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

References

CVE-2026-31448

CRITICAL9.4

In the Linux kernel, the following vulnerability has been resolved: ext4: avoid infinite loops caused by residual data On the mkdir/mknod path, when mapping logical blocks to physical blocks, if inserting a new extent into the extent tree fails (in this example, because the file system disabled the huge file feature when marking the inode as dirty), ext4_ext_map_blocks() only calls ext4_free_blocks() to reclaim the physical block without deleting the corresponding data in the extent tree. This causes subsequent mkdir operations to reference the previously reclaimed physical block number again, even though this physical block is already being used by the xattr block. Therefore, a situation arises where both the directory and xattr are using the same buffer head block in memory simultaneously. The above causes ext4_xattr_block_set() to enter an infinite loop about "inserted" and cannot release the inode lock, ultimately leading to the 143s blocking problem mentioned in [1]. If the metadata is corrupted, then trying to remove some extent space can do even more harm. Also in case EXT4_GET_BLOCKS_DELALLOC_RESERVE was passed, remove space wrongly update quota information. Jan Kara suggests distinguishing between two cases: 1) The error is ENOSPC or EDQUOT - in this case the filesystem is fully consistent and we must maintain its consistency including all the accounting. However these errors can happen only early before we've inserted the extent into the extent tree. So current code works correctly for this case. 2) Some other error - this means metadata is corrupted. We should strive to do as few modifications as possible to limit damage. So I'd just skip freeing of allocated blocks. [1] INFO: task syz.0.17:5995 blocked for more than 143 seconds. Call Trace: inode_lock_nested include/linux/fs.h:1073 [inline] __start_dirop fs/namei.c:2923 [inline] start_dirop fs/namei.c:2934 [inline]

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xCRITICAL 9.4

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H

References

CVE-2026-31449

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ext4: validate p_idx bounds in ext4_ext_correct_indexes ext4_ext_correct_indexes() walks up the extent tree correcting index entries when the first extent in a leaf is modified. Before accessing path[k].p_idx->ei_block, there is no validation that p_idx falls within the valid range of index entries for that level. If the on-disk extent header contains a corrupted or crafted eh_entries value, p_idx can point past the end of the allocated buffer, causing a slab-out-of-bounds read. Fix this by validating path[k].p_idx against EXT_LAST_INDEX() at both access sites: before the while loop and inside it. Return -EFSCORRUPTED if the index pointer is out of range, consistent with how other bounds violations are handled in the ext4 extent tree code.

Published: 2026-04-22Modified: 2026-05-17

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

References

CVE-2026-31450

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: ext4: publish jinode after initialization ext4_inode_attach_jinode() publishes ei->jinode to concurrent users. It used to set ei->jinode before jbd2_journal_init_jbd_inode(), allowing a reader to observe a non-NULL jinode with i_vfs_inode still unset. The fast commit flush path can then pass this jinode to jbd2_wait_inode_data(), which dereferences i_vfs_inode->i_mapping and may crash. Below is the crash I observe: ``` BUG: unable to handle page fault for address: 000000010beb47f4 PGD 110e51067 P4D 110e51067 PUD 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 1 UID: 0 PID: 4850 Comm: fc_fsync_bench_ Not tainted 6.18.0-00764-g795a690c06a5 #1 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.17.0-2-2 04/01/2014 RIP: 0010:xas_find_marked+0x3d/0x2e0 Code: e0 03 48 83 f8 02 0f 84 f0 01 00 00 48 8b 47 08 48 89 c3 48 39 c6 0f 82 fd 01 00 00 48 85 c9 74 3d 48 83 f9 03 77 63 4c 8b 0f <49> 8b 71 08 48 c7 47 18 00 00 00 00 48 89 f1 83 e1 03 48 83 f9 02 RSP: 0018:ffffbbee806e7bf0 EFLAGS: 00010246 RAX: 000000000010beb4 RBX: 000000000010beb4 RCX: 0000000000000003 RDX: 0000000000000001 RSI: 0000002000300000 RDI: ffffbbee806e7c10 RBP: 0000000000000001 R08: 0000002000300000 R09: 000000010beb47ec R10: ffff9ea494590090 R11: 0000000000000000 R12: 0000002000300000 R13: ffffbbee806e7c90 R14: ffff9ea494513788 R15: ffffbbee806e7c88 FS: 00007fc2f9e3e6c0(0000) GS:ffff9ea6b1444000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000010beb47f4 CR3: 0000000119ac5000 CR4: 0000000000750ef0 PKRU: 55555554 Call Trace: filemap_get_folios_tag+0x87/0x2a0 __filemap_fdatawait_range+0x5f/0xd0 ? srso_alias_return_thunk+0x5/0xfbef5 ? __schedule+0x3e7/0x10c0 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 ? cap_safe_nice+0x37/0x70 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 filemap_fdatawait_range_keep_errors+0x12/0x40 ext4_fc_commit+0x697/0x8b0 ? ext4_file_write_iter+0x64b/0x950 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 ? vfs_write+0x356/0x480 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ext4_sync_file+0xf7/0x370 do_fsync+0x3b/0x80 ? syscall_trace_enter+0x108/0x1d0 __x64_sys_fdatasync+0x16/0x20 do_syscall_64+0x62/0x2c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e ... ``` Fix this by initializing the jbd2_inode first. Use smp_wmb() and WRITE_ONCE() to publish ei->jinode after initialization. Readers use READ_ONCE() to fetch the pointer.

Published: 2026-04-22Modified: 2026-05-06

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31451

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ext4: replace BUG_ON with proper error handling in ext4_read_inline_folio Replace BUG_ON() with proper error handling when inline data size exceeds PAGE_SIZE. This prevents kernel panic and allows the system to continue running while properly reporting the filesystem corruption. The error is logged via ext4_error_inode(), the buffer head is released to prevent memory leak, and -EFSCORRUPTED is returned to indicate filesystem corruption.

Published: 2026-04-22Modified: 2026-05-06

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31452

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ext4: convert inline data to extents when truncate exceeds inline size Add a check in ext4_setattr() to convert files from inline data storage to extent-based storage when truncate() grows the file size beyond the inline capacity. This prevents the filesystem from entering an inconsistent state where the inline data flag is set but the file size exceeds what can be stored inline. Without this fix, the following sequence causes a kernel BUG_ON(): 1. Mount filesystem with inode that has inline flag set and small size 2. truncate(file, 50MB) - grows size but inline flag remains set 3. sendfile() attempts to write data 4. ext4_write_inline_data() hits BUG_ON(write_size > inline_capacity) The crash occurs because ext4_write_inline_data() expects inline storage to accommodate the write, but the actual inline capacity (~60 bytes for i_block + ~96 bytes for xattrs) is far smaller than the file size and write request. The fix checks if the new size from setattr exceeds the inode's actual inline capacity (EXT4_I(inode)->i_inline_size) and converts the file to extent-based storage before proceeding with the size change. This addresses the root cause by ensuring the inline data flag and file size remain consistent during truncate operations.

Published: 2026-04-22Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31453

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: xfs: avoid dereferencing log items after push callbacks After xfsaild_push_item() calls iop_push(), the log item may have been freed if the AIL lock was dropped during the push. Background inode reclaim or the dquot shrinker can free the log item while the AIL lock is not held, and the tracepoints in the switch statement dereference the log item after iop_push() returns. Fix this by capturing the log item type, flags, and LSN before calling xfsaild_push_item(), and introducing a new xfs_ail_push_class trace event class that takes these pre-captured values and the ailp pointer instead of the log item pointer.

Published: 2026-04-22Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31454

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: xfs: save ailp before dropping the AIL lock in push callbacks In xfs_inode_item_push() and xfs_qm_dquot_logitem_push(), the AIL lock is dropped to perform buffer IO. Once the cluster buffer no longer protects the log item from reclaim, the log item may be freed by background reclaim or the dquot shrinker. The subsequent spin_lock() call dereferences lip->li_ailp, which is a use-after-free. Fix this by saving the ailp pointer in a local variable while the AIL lock is held and the log item is guaranteed to be valid.

Published: 2026-04-22Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31455

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: xfs: stop reclaim before pushing AIL during unmount The unmount sequence in xfs_unmount_flush_inodes() pushed the AIL while background reclaim and inodegc are still running. This is broken independently of any use-after-free issues - background reclaim and inodegc should not be running while the AIL is being pushed during unmount, as inodegc can dirty and insert inodes into the AIL during the flush, and background reclaim can race to abort and free dirty inodes. Reorder xfs_unmount_flush_inodes() to stop inodegc and cancel background reclaim before pushing the AIL. Stop inodegc before cancelling m_reclaim_work because the inodegc worker can re-queue m_reclaim_work via xfs_inodegc_set_reclaimable.

Published: 2026-04-22Modified: 2026-05-05

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31456

MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: mm/pagewalk: fix race between concurrent split and refault The splitting of a PUD entry in walk_pud_range() can race with a concurrent thread refaulting the PUD leaf entry causing it to try walking a PMD range that has disappeared. An example and reproduction of this is to try reading numa_maps of a process while VFIO-PCI is setting up DMA (specifically the vfio_pin_pages_remote call) on a large BAR for that process. This will trigger a kernel BUG: vfio-pci 0000:03:00.0: enabling device (0000 -> 0002) BUG: unable to handle page fault for address: ffffa23980000000 PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP NOPTI ... RIP: 0010:walk_pgd_range+0x3b5/0x7a0 Code: 8d 43 ff 48 89 44 24 28 4d 89 ce 4d 8d a7 00 00 20 00 48 8b 4c 24 28 49 81 e4 00 00 e0 ff 49 8d 44 24 ff 48 39 c8 4c 0f 43 e3 <49> f7 06 9f ff ff ff 75 3b 48 8b 44 24 20 48 8b 40 28 48 85 c0 74 RSP: 0018:ffffac23e1ecf808 EFLAGS: 00010287 RAX: 00007f44c01fffff RBX: 00007f4500000000 RCX: 00007f44ffffffff RDX: 0000000000000000 RSI: 000ffffffffff000 RDI: ffffffff93378fe0 RBP: ffffac23e1ecf918 R08: 0000000000000004 R09: ffffa23980000000 R10: 0000000000000020 R11: 0000000000000004 R12: 00007f44c0200000 R13: 00007f44c0000000 R14: ffffa23980000000 R15: 00007f44c0000000 FS: 00007fe884739580(0000) GS:ffff9b7d7a9c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffa23980000000 CR3: 000000c0650e2005 CR4: 0000000000770ef0 PKRU: 55555554 Call Trace: __walk_page_range+0x195/0x1b0 walk_page_vma+0x62/0xc0 show_numa_map+0x12b/0x3b0 seq_read_iter+0x297/0x440 seq_read+0x11d/0x140 vfs_read+0xc2/0x340 ksys_read+0x5f/0xe0 do_syscall_64+0x68/0x130 ? get_page_from_freelist+0x5c2/0x17e0 ? mas_store_prealloc+0x17e/0x360 ? vma_set_page_prot+0x4c/0xa0 ? __alloc_pages_noprof+0x14e/0x2d0 ? __mod_memcg_lruvec_state+0x8d/0x140 ? __lruvec_stat_mod_folio+0x76/0xb0 ? __folio_mod_stat+0x26/0x80 ? do_anonymous_page+0x705/0x900 ? __handle_mm_fault+0xa8d/0x1000 ? __count_memcg_events+0x53/0xf0 ? handle_mm_fault+0xa5/0x360 ? do_user_addr_fault+0x342/0x640 ? arch_exit_to_user_mode_prepare.constprop.0+0x16/0xa0 ? irqentry_exit_to_user_mode+0x24/0x100 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7fe88464f47e Code: c0 e9 b6 fe ff ff 50 48 8d 3d be 07 0b 00 e8 69 01 02 00 66 0f 1f 84 00 00 00 00 00 64 8b 04 25 18 00 00 00 85 c0 75 14 0f 05 <48> 3d 00 f0 ff ff 77 5a c3 66 0f 1f 84 00 00 00 00 00 48 83 ec 28 RSP: 002b:00007ffe6cd9a9b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 RAX: ffffffffffffffda RBX: 0000000000020000 RCX: 00007fe88464f47e RDX: 0000000000020000 RSI: 00007fe884543000 RDI: 0000000000000003 RBP: 00007fe884543000 R08: 00007fe884542010 R09: 0000000000000000 R10: fffffffffffffbc5 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000003 R14: 0000000000020000 R15: 0000000000020000 Fix this by validating the PUD entry in walk_pmd_range() using a stable snapshot (pudp_get()). If the PUD is not present or is a leaf, retry the walk via ACTION_AGAIN instead of descending further. This mirrors the retry logic in walk_pte_range(), which lets walk_pmd_range() retry if the PTE is not being got by pte_offset_map_lock().

Published: 2026-04-22Modified: 2026-05-05

CVSS 3.xMEDIUM 4.7

CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31457

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mm/damon/sysfs: check contexts->nr in repeat_call_fn damon_sysfs_repeat_call_fn() calls damon_sysfs_upd_tuned_intervals(), damon_sysfs_upd_schemes_stats(), and damon_sysfs_upd_schemes_effective_quotas() without checking contexts->nr. If nr_contexts is set to 0 via sysfs while DAMON is running, these functions dereference contexts_arr[0] and cause a NULL pointer dereference. Add the missing check. For example, the issue can be reproduced using DAMON sysfs interface and DAMON user-space tool (damo) [1] like below. $ sudo damo start --refresh_interval 1s $ echo 0 | sudo tee \ /sys/kernel/mm/damon/admin/kdamonds/0/contexts/nr_contexts

Published: 2026-04-22Modified: 2026-05-05

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31458

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mm/damon/sysfs: check contexts->nr before accessing contexts_arr[0] Multiple sysfs command paths dereference contexts_arr[0] without first verifying that kdamond->contexts->nr == 1. A user can set nr_contexts to 0 via sysfs while DAMON is running, causing NULL pointer dereferences. In more detail, the issue can be triggered by privileged users like below. First, start DAMON and make contexts directory empty (kdamond->contexts->nr == 0). # damo start # cd /sys/kernel/mm/damon/admin/kdamonds/0 # echo 0 > contexts/nr_contexts Then, each of below commands will cause the NULL pointer dereference. # echo update_schemes_stats > state # echo update_schemes_tried_regions > state # echo update_schemes_tried_bytes > state # echo update_schemes_effective_quotas > state # echo update_tuned_intervals > state Guard all commands (except OFF) at the entry point of damon_sysfs_handle_cmd().

Published: 2026-04-22Modified: 2026-05-05

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31459

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mm/damon/sysfs: fix param_ctx leak on damon_sysfs_new_test_ctx() failure Patch series "mm/damon/sysfs: fix memory leak and NULL dereference issues", v4. DAMON_SYSFS can leak memory under allocation failure, and do NULL pointer dereference when a privileged user make wrong sequences of control. Fix those. This patch (of 3): When damon_sysfs_new_test_ctx() fails in damon_sysfs_commit_input(), param_ctx is leaked because the early return skips the cleanup at the out label. Destroy param_ctx before returning.

Published: 2026-04-22Modified: 2026-05-06

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31461

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix drm_edid leak in amdgpu_dm [WHAT] When a sink is connected, aconnector->drm_edid was overwritten without freeing the previous allocation, causing a memory leak on resume. [HOW] Free the previous drm_edid before updating it. (cherry picked from commit 52024a94e7111366141cfc5d888b2ef011f879e5)

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31462

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: prevent immediate PASID reuse case PASID resue could cause interrupt issue when process immediately runs into hw state left by previous process exited with the same PASID, it's possible that page faults are still pending in the IH ring buffer when the process exits and frees up its PASID. To prevent the case, it uses idr cyclic allocator same as kernel pid's. (cherry picked from commit 8f1de51f49be692de137c8525106e0fce2d1912d)

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31464

HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: scsi: ibmvfc: Fix OOB access in ibmvfc_discover_targets_done() A malicious or compromised VIO server can return a num_written value in the discover targets MAD response that exceeds max_targets. This value is stored directly in vhost->num_targets without validation, and is then used as the loop bound in ibmvfc_alloc_targets() to index into disc_buf[], which is only allocated for max_targets entries. Indices at or beyond max_targets access kernel memory outside the DMA-coherent allocation. The out-of-bounds data is subsequently embedded in Implicit Logout and PLOGI MADs that are sent back to the VIO server, leaking kernel memory. Fix by clamping num_written to max_targets before storing it.

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xHIGH 8.1

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31465

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: writeback: don't block sync for filesystems with no data integrity guarantees Add a SB_I_NO_DATA_INTEGRITY superblock flag for filesystems that cannot guarantee data persistence on sync (eg fuse). For superblocks with this flag set, sync kicks off writeback of dirty inodes but does not wait for the flusher threads to complete the writeback. This replaces the per-inode AS_NO_DATA_INTEGRITY mapping flag added in commit f9a49aa302a0 ("fs/writeback: skip AS_NO_DATA_INTEGRITY mappings in wait_sb_inodes()"). The flag belongs at the superblock level because data integrity is a filesystem-wide property, not a per-inode one. Having this flag at the superblock level also allows us to skip having to iterate every dirty inode in wait_sb_inodes() only to skip each inode individually. Prior to this commit, mappings with no data integrity guarantees skipped waiting on writeback completion but still waited on the flusher threads to finish initiating the writeback. Waiting on the flusher threads is unnecessary. This commit kicks off writeback but does not wait on the flusher threads. This change properly addresses a recent report [1] for a suspend-to-RAM hang seen on fuse-overlayfs that was caused by waiting on the flusher threads to finish: Workqueue: pm_fs_sync pm_fs_sync_work_fn Call Trace: __schedule+0x457/0x1720 schedule+0x27/0xd0 wb_wait_for_completion+0x97/0xe0 sync_inodes_sb+0xf8/0x2e0 __iterate_supers+0xdc/0x160 ksys_sync+0x43/0xb0 pm_fs_sync_work_fn+0x17/0xa0 process_one_work+0x193/0x350 worker_thread+0x1a1/0x310 kthread+0xfc/0x240 ret_from_fork+0x243/0x280 ret_from_fork_asm+0x1a/0x30 On fuse this is problematic because there are paths that may cause the flusher thread to block (eg if systemd freezes the user session cgroups first, which freezes the fuse daemon, before invoking the kernel suspend. The kernel suspend triggers ->write_node() which on fuse issues a synchronous setattr request, which cannot be processed since the daemon is frozen. Or if the daemon is buggy and cannot properly complete writeback, initiating writeback on a dirty folio already under writeback leads to writeback_get_folio() -> folio_prepare_writeback() -> unconditional wait on writeback to finish, which will cause a hang). This commit restores fuse to its prior behavior before tmp folios were removed, where sync was essentially a no-op. [1] https://lore.kernel.org/linux-fsdevel/CAJnrk1a-asuvfrbKXbEwwDSctvemF+6zfhdnuzO65Pt8HsFSRw@mail.gmail.com/T/#m632c4648e9cafc4239299887109ebd880ac6c5c1

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31466

MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: mm/huge_memory: fix folio isn't locked in softleaf_to_folio() On arm64 server, we found folio that get from migration entry isn't locked in softleaf_to_folio(). This issue triggers when mTHP splitting and zap_nonpresent_ptes() races, and the root cause is lack of memory barrier in softleaf_to_folio(). The race is as follows: CPU0 CPU1 deferred_split_scan() zap_nonpresent_ptes() lock folio split_folio() unmap_folio() change ptes to migration entries __split_folio_to_order() softleaf_to_folio() set flags(including PG_locked) for tail pages folio = pfn_folio(softleaf_to_pfn(entry)) smp_wmb() VM_WARN_ON_ONCE(!folio_test_locked(folio)) prep_compound_page() for tail pages In __split_folio_to_order(), smp_wmb() guarantees page flags of tail pages are visible before the tail page becomes non-compound. smp_wmb() should be paired with smp_rmb() in softleaf_to_folio(), which is missed. As a result, if zap_nonpresent_ptes() accesses migration entry that stores tail pfn, softleaf_to_folio() may see the updated compound_head of tail page before page->flags. This issue will trigger VM_WARN_ON_ONCE() in pfn_swap_entry_folio() because of the race between folio split and zap_nonpresent_ptes() leading to a folio incorrectly undergoing modification without a folio lock being held. This is a BUG_ON() before commit 93976a20345b ("mm: eliminate further swapops predicates"), which in merged in v6.19-rc1. To fix it, add missing smp_rmb() if the softleaf entry is migration entry in softleaf_to_folio() and softleaf_to_page(). [tujinjiang@huawei.com: update function name and comments]

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xMEDIUM 4.7

CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31467

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: erofs: add GFP_NOIO in the bio completion if needed The bio completion path in the process context (e.g. dm-verity) will directly call into decompression rather than trigger another workqueue context for minimal scheduling latencies, which can then call vm_map_ram() with GFP_KERNEL. Due to insufficient memory, vm_map_ram() may generate memory swapping I/O, which can cause submit_bio_wait to deadlock in some scenarios. Trimmed down the call stack, as follows: f2fs_submit_read_io submit_bio //bio_list is initialized. mmc_blk_mq_recovery z_erofs_endio vm_map_ram __pte_alloc_kernel __alloc_pages_direct_reclaim shrink_folio_list __swap_writepage submit_bio_wait //bio_list is non-NULL, hang!!! Use memalloc_noio_{save,restore}() to wrap up this path.

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31469

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: virtio_net: Fix UAF on dst_ops when IFF_XMIT_DST_RELEASE is cleared and napi_tx is false A UAF issue occurs when the virtio_net driver is configured with napi_tx=N and the device's IFF_XMIT_DST_RELEASE flag is cleared (e.g., during the configuration of tc route filter rules). When IFF_XMIT_DST_RELEASE is removed from the net_device, the network stack expects the driver to hold the reference to skb->dst until the packet is fully transmitted and freed. In virtio_net with napi_tx=N, skbs may remain in the virtio transmit ring for an extended period. If the network namespace is destroyed while these skbs are still pending, the corresponding dst_ops structure has freed. When a subsequent packet is transmitted, free_old_xmit() is triggered to clean up old skbs. It then calls dst_release() on the skb associated with the stale dst_entry. Since the dst_ops (referenced by the dst_entry) has already been freed, a UAF kernel paging request occurs. fix it by adds skb_dst_drop(skb) in start_xmit to explicitly release the dst reference before the skb is queued in virtio_net. Call Trace: Unable to handle kernel paging request at virtual address ffff80007e150000 CPU: 2 UID: 0 PID: 6236 Comm: ping Kdump: loaded Not tainted 7.0.0-rc1+ #6 PREEMPT ... percpu_counter_add_batch+0x3c/0x158 lib/percpu_counter.c:98 (P) dst_release+0xe0/0x110 net/core/dst.c:177 skb_release_head_state+0xe8/0x108 net/core/skbuff.c:1177 sk_skb_reason_drop+0x54/0x2d8 net/core/skbuff.c:1255 dev_kfree_skb_any_reason+0x64/0x78 net/core/dev.c:3469 napi_consume_skb+0x1c4/0x3a0 net/core/skbuff.c:1527 __free_old_xmit+0x164/0x230 drivers/net/virtio_net.c:611 [virtio_net] free_old_xmit drivers/net/virtio_net.c:1081 [virtio_net] start_xmit+0x7c/0x530 drivers/net/virtio_net.c:3329 [virtio_net] ... Reproduction Steps: NETDEV="enp3s0" config_qdisc_route_filter() { tc qdisc del dev $NETDEV root tc qdisc add dev $NETDEV root handle 1: prio tc filter add dev $NETDEV parent 1:0 \ protocol ip prio 100 route to 100 flowid 1:1 ip route add 192.168.1.100/32 dev $NETDEV realm 100 } test_ns() { ip netns add testns ip link set $NETDEV netns testns ip netns exec testns ifconfig $NETDEV 10.0.32.46/24 ip netns exec testns ping -c 1 10.0.32.1 ip netns del testns } config_qdisc_route_filter test_ns sleep 2 test_ns

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31470

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: virt: tdx-guest: Fix handling of host controlled 'quote' buffer length Validate host controlled value `quote_buf->out_len` that determines how many bytes of the quote are copied out to guest userspace. In TDX environments with remote attestation, quotes are not considered private, and can be forwarded to an attestation server. Catch scenarios where the host specifies a response length larger than the guest's allocation, or otherwise races modifying the response while the guest consumes it. This prevents contents beyond the pages allocated for `quote_buf` (up to TSM_REPORT_OUTBLOB_MAX) from being read out to guest userspace, and possibly forwarded in attestation requests. Recall that some deployments want per-container configs-tsm-report interfaces, so the leak may cross container protection boundaries, not just local root.

Published: 2026-04-22Modified: 2026-05-07

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31471

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: xfrm: iptfs: only publish mode_data after clone setup iptfs_clone_state() stores x->mode_data before allocating the reorder window. If that allocation fails, the code frees the cloned state and returns -ENOMEM, leaving x->mode_data pointing at freed memory. The xfrm clone unwind later runs destroy_state() through x->mode_data, so the failed clone path tears down IPTFS state that clone_state() already freed. Keep the cloned IPTFS state private until all allocations succeed so failed clones leave x->mode_data unset. The destroy path already handles a NULL mode_data pointer.

Published: 2026-04-22Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31472

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xfrm: iptfs: validate inner IPv4 header length in IPTFS payload Add validation of the inner IPv4 packet tot_len and ihl fields parsed from decrypted IPTFS payloads in __input_process_payload(). A crafted ESP packet containing an inner IPv4 header with tot_len=0 causes an infinite loop: iplen=0 leads to capturelen=min(0, remaining)=0, so the data offset never advances and the while(data < tail) loop never terminates, spinning forever in softirq context. Reject inner IPv4 packets where tot_len < ihl4 or ihl4 < sizeof(struct iphdr), which catches both the tot_len=0 case and malformed ihl values. The normal IP stack performs this validation in ip_rcv_core(), but IPTFS extracts and processes inner packets before they reach that layer.

Published: 2026-04-22Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31473

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: media: mc, v4l2: serialize REINIT and REQBUFS with req_queue_mutex MEDIA_REQUEST_IOC_REINIT can run concurrently with VIDIOC_REQBUFS(0) queue teardown paths. This can race request object cleanup against vb2 queue cancellation and lead to use-after-free reports. We already serialize request queueing against STREAMON/OFF with req_queue_mutex. Extend that serialization to REQBUFS, and also take the same mutex in media_request_ioctl_reinit() so REINIT is in the same exclusion domain. This keeps request cleanup and queue cancellation from running in parallel for request-capable devices.

Published: 2026-04-22Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31474

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: can: isotp: fix tx.buf use-after-free in isotp_sendmsg() isotp_sendmsg() uses only cmpxchg() on so->tx.state to serialize access to so->tx.buf. isotp_release() waits for ISOTP_IDLE via wait_event_interruptible() and then calls kfree(so->tx.buf). If a signal interrupts the wait_event_interruptible() inside close() while tx.state is ISOTP_SENDING, the loop exits early and release proceeds to force ISOTP_SHUTDOWN and continues to kfree(so->tx.buf) while sendmsg may still be reading so->tx.buf for the final CAN frame in isotp_fill_dataframe(). The so->tx.buf can be allocated once when the standard tx.buf length needs to be extended. Move the kfree() of this potentially extended tx.buf to sk_destruct time when either isotp_sendmsg() and isotp_release() are done.

Published: 2026-04-22Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31475

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ASoC: sma1307: fix double free of devm_kzalloc() memory A previous change added NULL checks and cleanup for allocation failures in sma1307_setting_loaded(). However, the cleanup for mode_set entries is wrong. Those entries are allocated with devm_kzalloc(), so they are device-managed resources and must not be freed with kfree(). Manually freeing them in the error path can lead to a double free when devres later releases the same memory. Drop the manual kfree() loop and let devres handle the cleanup.

Published: 2026-04-22Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31476

HIGH8.2

In the Linux kernel, the following vulnerability has been resolved: ksmbd: do not expire session on binding failure When a multichannel session binding request fails (e.g. wrong password), the error path unconditionally sets sess->state = SMB2_SESSION_EXPIRED. However, during binding, sess points to the target session looked up via ksmbd_session_lookup_slowpath() -- which belongs to another connection's user. This allows a remote attacker to invalidate any active session by simply sending a binding request with a wrong password (DoS). Fix this by skipping session expiration when the failed request was a binding attempt, since the session does not belong to the current connection. The reference taken by ksmbd_session_lookup_slowpath() is still correctly released via ksmbd_user_session_put().

Published: 2026-04-22Modified: 2026-04-27

CVSS 3.xHIGH 8.2

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:H

References

CVE-2026-31477

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix memory leaks and NULL deref in smb2_lock() smb2_lock() has three error handling issues after list_del() detaches smb_lock from lock_list at no_check_cl: 1) If vfs_lock_file() returns an unexpected error in the non-UNLOCK path, goto out leaks smb_lock and its flock because the out: handler only iterates lock_list and rollback_list, neither of which contains the detached smb_lock. 2) If vfs_lock_file() returns -ENOENT in the UNLOCK path, goto out leaks smb_lock and flock for the same reason. The error code returned to the dispatcher is also stale. 3) In the rollback path, smb_flock_init() can return NULL on allocation failure. The result is dereferenced unconditionally, causing a kernel NULL pointer dereference. Add a NULL check to prevent the crash and clean up the bookkeeping; the VFS lock itself cannot be rolled back without the allocation and will be released at file or connection teardown. Fix cases 1 and 2 by hoisting the locks_free_lock()/kfree() to before the if(!rc) check in the UNLOCK branch so all exit paths share one free site, and by freeing smb_lock and flock before goto out in the non-UNLOCK branch. Propagate the correct error code in both cases. Fix case 3 by wrapping the VFS unlock in an if(rlock) guard and adding a NULL check for locks_free_lock(rlock) in the shared cleanup. Found via call-graph analysis using sqry.

Published: 2026-04-22Modified: 2026-04-27

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31478

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ksmbd: replace hardcoded hdr2_len with offsetof() in smb2_calc_max_out_buf_len() After this commit (e2b76ab8b5c9 "ksmbd: add support for read compound"), response buffer management was changed to use dynamic iov array. In the new design, smb2_calc_max_out_buf_len() expects the second argument (hdr2_len) to be the offset of ->Buffer field in the response structure, not a hardcoded magic number. Fix the remaining call sites to use the correct offsetof() value.

Published: 2026-04-22Modified: 2026-04-27

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31479

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: drm/xe: always keep track of remap prev/next During 3D workload, user is reporting hitting: [ 413.361679] WARNING: drivers/gpu/drm/xe/xe_vm.c:1217 at vm_bind_ioctl_ops_unwind+0x1e2/0x2e0 [xe], CPU#7: vkd3d_queue/9925 [ 413.361944] CPU: 7 UID: 1000 PID: 9925 Comm: vkd3d_queue Kdump: loaded Not tainted 7.0.0-070000rc3-generic #202603090038 PREEMPT(lazy) [ 413.361949] RIP: 0010:vm_bind_ioctl_ops_unwind+0x1e2/0x2e0 [xe] [ 413.362074] RSP: 0018:ffffd4c25c3df930 EFLAGS: 00010282 [ 413.362077] RAX: 0000000000000000 RBX: ffff8f3ee817ed10 RCX: 0000000000000000 [ 413.362078] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 [ 413.362079] RBP: ffffd4c25c3df980 R08: 0000000000000000 R09: 0000000000000000 [ 413.362081] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8f41fbf99380 [ 413.362082] R13: ffff8f3ee817e968 R14: 00000000ffffffef R15: ffff8f43d00bd380 [ 413.362083] FS: 00000001040ff6c0(0000) GS:ffff8f4696d89000(0000) knlGS:00000000330b0000 [ 413.362085] CS: 0010 DS: 002b ES: 002b CR0: 0000000080050033 [ 413.362086] CR2: 00007ddfc4747000 CR3: 00000002e6262005 CR4: 0000000000f72ef0 [ 413.362088] PKRU: 55555554 [ 413.362089] Call Trace: [ 413.362092] [ 413.362096] xe_vm_bind_ioctl+0xa9a/0xc60 [xe] Which seems to hint that the vma we are re-inserting for the ops unwind is either invalid or overlapping with something already inserted in the vm. It shouldn't be invalid since this is a re-insertion, so must have worked before. Leaving the likely culprit as something already placed where we want to insert the vma. Following from that, for the case where we do something like a rebind in the middle of a vma, and one or both mapped ends are already compatible, we skip doing the rebind of those vma and set next/prev to NULL. As well as then adjust the original unmap va range, to avoid unmapping the ends. However, if we trigger the unwind path, we end up with three va, with the two ends never being removed and the original va range in the middle still being the shrunken size. If this occurs, one failure mode is when another unwind op needs to interact with that range, which can happen with a vector of binds. For example, if we need to re-insert something in place of the original va. In this case the va is still the shrunken version, so when removing it and then doing a re-insert it can overlap with the ends, which were never removed, triggering a warning like above, plus leaving the vm in a bad state. With that, we need two things here: 1) Stop nuking the prev/next tracking for the skip cases. Instead relying on checking for skip prev/next, where needed. That way on the unwind path, we now correctly remove both ends. 2) Undo the unmap va shrinkage, on the unwind path. With the two ends now removed the unmap va should expand back to the original size again, before re-insertion. v2: - Update the explanation in the commit message, based on an actual IGT of triggering this issue, rather than conjecture. - Also undo the unmap shrinkage, for the skip case. With the two ends now removed, the original unmap va range should expand back to the original range. v3: - Track the old start/range separately. vma_size/start() uses the va info directly. (cherry picked from commit aec6969f75afbf4e01fd5fb5850ed3e9c27043ac)

Published: 2026-04-22Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31480

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: tracing: Fix potential deadlock in cpu hotplug with osnoise The following sequence may leads deadlock in cpu hotplug: task1 task2 task3 ----- ----- ----- mutex_lock(&interface_lock) [CPU GOING OFFLINE] cpus_write_lock(); osnoise_cpu_die(); kthread_stop(task3); wait_for_completion(); osnoise_sleep(); mutex_lock(&interface_lock); cpus_read_lock(); [DEAD LOCK] Fix by swap the order of cpus_read_lock() and mutex_lock(&interface_lock).

Published: 2026-04-22Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31482

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: s390/entry: Scrub r12 register on kernel entry Before commit f33f2d4c7c80 ("s390/bp: remove TIF_ISOLATE_BP"), all entry handlers loaded r12 with the current task pointer (lg %r12,__LC_CURRENT) for use by the BPENTER/BPEXIT macros. That commit removed TIF_ISOLATE_BP, dropping both the branch prediction macros and the r12 load, but did not add r12 to the register clearing sequence. Add the missing xgr %r12,%r12 to make the register scrub consistent across all entry points.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31483

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: s390/syscalls: Add spectre boundary for syscall dispatch table The s390 syscall number is directly controlled by userspace, but does not have an array_index_nospec() boundary to prevent access past the syscall function pointer tables.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31485

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: spi: spi-fsl-lpspi: fix teardown order issue (UAF) There is a teardown order issue in the driver. The SPI controller is registered using devm_spi_register_controller(), which delays unregistration of the SPI controller until after the fsl_lpspi_remove() function returns. As the fsl_lpspi_remove() function synchronously tears down the DMA channels, a running SPI transfer triggers the following NULL pointer dereference due to use after free: | fsl_lpspi 42550000.spi: I/O Error in DMA RX | Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [...] | Call trace: | fsl_lpspi_dma_transfer+0x260/0x340 [spi_fsl_lpspi] | fsl_lpspi_transfer_one+0x198/0x448 [spi_fsl_lpspi] | spi_transfer_one_message+0x49c/0x7c8 | __spi_pump_transfer_message+0x120/0x420 | __spi_sync+0x2c4/0x520 | spi_sync+0x34/0x60 | spidev_message+0x20c/0x378 [spidev] | spidev_ioctl+0x398/0x750 [spidev] [...] Switch from devm_spi_register_controller() to spi_register_controller() in fsl_lpspi_probe() and add the corresponding spi_unregister_controller() in fsl_lpspi_remove().

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31486

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: hwmon: (pmbus/core) Protect regulator operations with mutex The regulator operations pmbus_regulator_get_voltage(), pmbus_regulator_set_voltage(), and pmbus_regulator_list_voltage() access PMBus registers and shared data but were not protected by the update_lock mutex. This could lead to race conditions. However, adding mutex protection directly to these functions causes a deadlock because pmbus_regulator_notify() (which calls regulator_notifier_call_chain()) is often called with the mutex already held (e.g., from pmbus_fault_handler()). If a regulator callback then calls one of the now-protected voltage functions, it will attempt to acquire the same mutex. Rework pmbus_regulator_notify() to utilize a worker function to send notifications outside of the mutex protection. Events are stored as atomics in a per-page bitmask and processed by the worker. Initialize the worker and its associated data during regulator registration, and ensure it is cancelled on device removal using devm_add_action_or_reset(). While at it, remove the unnecessary include of linux/of.h.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:H

References

CVE-2026-31487

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: spi: use generic driver_override infrastructure When a driver is probed through __driver_attach(), the bus' match() callback is called without the device lock held, thus accessing the driver_override field without a lock, which can cause a UAF. Fix this by using the driver-core driver_override infrastructure taking care of proper locking internally. Note that calling match() from __driver_attach() without the device lock held is intentional. [1] Also note that we do not enable the driver_override feature of struct bus_type, as SPI - in contrast to most other buses - passes "" to sysfs_emit() when the driver_override pointer is NULL. Thus, printing "\n" instead of "(null)\n".

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31488

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Do not skip unrelated mode changes in DSC validation Starting with commit 17ce8a6907f7 ("drm/amd/display: Add dsc pre-validation in atomic check"), amdgpu resets the CRTC state mode_changed flag to false when recomputing the DSC configuration results in no timing change for a particular stream. However, this is incorrect in scenarios where a change in MST/DSC configuration happens in the same KMS commit as another (unrelated) mode change. For example, the integrated panel of a laptop may be configured differently (e.g., HDR enabled/disabled) depending on whether external screens are attached. In this case, plugging in external DP-MST screens may result in the mode_changed flag being dropped incorrectly for the integrated panel if its DSC configuration did not change during precomputation in pre_validate_dsc(). At this point, however, dm_update_crtc_state() has already created new streams for CRTCs with DSC-independent mode changes. In turn, amdgpu_dm_commit_streams() will never release the old stream, resulting in a memory leak. amdgpu_dm_atomic_commit_tail() will never acquire a reference to the new stream either, which manifests as a use-after-free when the stream gets disabled later on: BUG: KASAN: use-after-free in dc_stream_release+0x25/0x90 [amdgpu] Write of size 4 at addr ffff88813d836524 by task kworker/9:9/29977 Workqueue: events drm_mode_rmfb_work_fn Call Trace: dump_stack_lvl+0x6e/0xa0 print_address_description.constprop.0+0x88/0x320 ? dc_stream_release+0x25/0x90 [amdgpu] print_report+0xfc/0x1ff ? srso_alias_return_thunk+0x5/0xfbef5 ? __virt_addr_valid+0x225/0x4e0 ? dc_stream_release+0x25/0x90 [amdgpu] kasan_report+0xe1/0x180 ? dc_stream_release+0x25/0x90 [amdgpu] kasan_check_range+0x125/0x200 dc_stream_release+0x25/0x90 [amdgpu] dc_state_destruct+0x14d/0x5c0 [amdgpu] dc_state_release.part.0+0x4e/0x130 [amdgpu] dm_atomic_destroy_state+0x3f/0x70 [amdgpu] drm_atomic_state_default_clear+0x8ee/0xf30 ? drm_mode_object_put.part.0+0xb1/0x130 __drm_atomic_state_free+0x15c/0x2d0 atomic_remove_fb+0x67e/0x980 Since there is no reliable way of figuring out whether a CRTC has unrelated mode changes pending at the time of DSC validation, remember the value of the mode_changed flag from before the point where a CRTC was marked as potentially affected by a change in DSC configuration. Reset the mode_changed flag to this earlier value instead in pre_validate_dsc(). (cherry picked from commit cc7c7121ae082b7b82891baa7280f1ff2608f22b)

Published: 2026-04-22Modified: 2026-05-17

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31489

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: spi: meson-spicc: Fix double-put in remove path meson_spicc_probe() registers the controller with devm_spi_register_controller(), so teardown already drops the controller reference via devm cleanup. Calling spi_controller_put() again in meson_spicc_remove() causes a double-put.

Published: 2026-04-22Modified: 2026-05-17

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31491

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: RDMA/irdma: Harden depth calculation functions An issue was exposed where OS can pass in U32_MAX for SQ/RQ/SRQ size. This can cause integer overflow and truncation of SQ/RQ/SRQ depth returning a success when it should have failed. Harden the functions to do all depth calculations and boundary checking in u64 sizes.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31492

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: RDMA/irdma: Initialize free_qp completion before using it In irdma_create_qp, if ib_copy_to_udata fails, it will call irdma_destroy_qp to clean up which will attempt to wait on the free_qp completion, which is not initialized yet. Fix this by initializing the completion before the ib_copy_to_udata call.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31493

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: RDMA/efa: Fix use of completion ctx after free On admin queue completion handling, if the admin command completed with error we print data from the completion context. The issue is that we already freed the completion context in polling/interrupts handler which means we print data from context in an unknown state (it might be already used again). Change the admin submission flow so alloc/dealloc of the context will be symmetric and dealloc will be called after any potential use of the context.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31494

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: macb: use the current queue number for stats There's a potential mismatch between the memory reserved for statistics and the amount of memory written. gem_get_sset_count() correctly computes the number of stats based on the active queues, whereas gem_get_ethtool_stats() indiscriminately copies data using the maximum number of queues, and in the case the number of active queues is less than MACB_MAX_QUEUES, this results in a OOB write as observed in the KASAN splat. ================================================================== BUG: KASAN: vmalloc-out-of-bounds in gem_get_ethtool_stats+0x54/0x78 [macb] Write of size 760 at addr ffff80008080b000 by task ethtool/1027 CPU: [...] Tainted: [E]=UNSIGNED_MODULE Hardware name: raspberrypi rpi/rpi, BIOS 2025.10 10/01/2025 Call trace: show_stack+0x20/0x38 (C) dump_stack_lvl+0x80/0xf8 print_report+0x384/0x5e0 kasan_report+0xa0/0xf0 kasan_check_range+0xe8/0x190 __asan_memcpy+0x54/0x98 gem_get_ethtool_stats+0x54/0x78 [macb 926c13f3af83b0c6fe64badb21ec87d5e93fcf65] dev_ethtool+0x1220/0x38c0 dev_ioctl+0x4ac/0xca8 sock_do_ioctl+0x170/0x1d8 sock_ioctl+0x484/0x5d8 __arm64_sys_ioctl+0x12c/0x1b8 invoke_syscall+0xd4/0x258 el0_svc_common.constprop.0+0xb4/0x240 do_el0_svc+0x48/0x68 el0_svc+0x40/0xf8 el0t_64_sync_handler+0xa0/0xe8 el0t_64_sync+0x1b0/0x1b8 The buggy address belongs to a 1-page vmalloc region starting at 0xffff80008080b000 allocated at dev_ethtool+0x11f0/0x38c0 The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff00000a333000 pfn:0xa333 flags: 0x7fffc000000000(node=0|zone=0|lastcpupid=0x1ffff) raw: 007fffc000000000 0000000000000000 dead000000000122 0000000000000000 raw: ffff00000a333000 0000000000000000 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff80008080b080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff80008080b100: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff80008080b180: 00 00 00 00 00 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ^ ffff80008080b200: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ffff80008080b280: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ================================================================== Fix it by making sure the copied size only considers the active number of queues.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31495

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: use netlink policy range checks Replace manual range and mask validations with netlink policy annotations in ctnetlink code paths, so that the netlink core rejects invalid values early and can generate extack errors. - CTA_PROTOINFO_TCP_STATE: reject values > TCP_CONNTRACK_SYN_SENT2 at policy level, removing the manual >= TCP_CONNTRACK_MAX check. - CTA_PROTOINFO_TCP_WSCALE_ORIGINAL/REPLY: reject values > TCP_MAX_WSCALE (14). The normal TCP option parsing path already clamps to this value, but the ctnetlink path accepted 0-255, causing undefined behavior when used as a u32 shift count. - CTA_FILTER_ORIG_FLAGS/REPLY_FLAGS: use NLA_POLICY_MASK with CTA_FILTER_F_ALL, removing the manual mask checks. - CTA_EXPECT_FLAGS: use NLA_POLICY_MASK with NF_CT_EXPECT_MASK, adding a new mask define grouping all valid expect flags. Extracted from a broader nf-next patch by Florian Westphal, scoped to ctnetlink for the fixes tree.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31496

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_expect: skip expectations in other netns via proc Skip expectations that do not reside in this netns. Similar to e77e6ff502ea ("netfilter: conntrack: do not dump other netns's conntrack entries via proc").

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31497

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: btusb: clamp SCO altsetting table indices btusb_work() maps the number of active SCO links to USB alternate settings through a three-entry lookup table when CVSD traffic uses transparent voice settings. The lookup currently indexes alts[] with data->sco_num - 1 without first constraining sco_num to the number of available table entries. While the table only defines alternate settings for up to three SCO links, data->sco_num comes from hci_conn_num() and is used directly. Cap the lookup to the last table entry before indexing it so the driver keeps selecting the highest supported alternate setting without reading past alts[].

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31498

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix ERTM re-init and zero pdu_len infinite loop l2cap_config_req() processes CONFIG_REQ for channels in BT_CONNECTED state to support L2CAP reconfiguration (e.g. MTU changes). However, since both CONF_INPUT_DONE and CONF_OUTPUT_DONE are already set from the initial configuration, the reconfiguration path falls through to l2cap_ertm_init(), which re-initializes tx_q, srej_q, srej_list, and retrans_list without freeing the previous allocations and sets chan->sdu to NULL without freeing the existing skb. This leaks all previously allocated ERTM resources. Additionally, l2cap_parse_conf_req() does not validate the minimum value of remote_mps derived from the RFC max_pdu_size option. A zero value propagates to l2cap_segment_sdu() where pdu_len becomes zero, causing the while loop to never terminate since len is never decremented, exhausting all available memory. Fix the double-init by skipping l2cap_ertm_init() and l2cap_chan_ready() when the channel is already in BT_CONNECTED state, while still allowing the reconfiguration parameters to be updated through l2cap_parse_conf_req(). Also add a pdu_len zero check in l2cap_segment_sdu() as a safeguard.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31499

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix deadlock in l2cap_conn_del() l2cap_conn_del() calls cancel_delayed_work_sync() for both info_timer and id_addr_timer while holding conn->lock. However, the work functions l2cap_info_timeout() and l2cap_conn_update_id_addr() both acquire conn->lock, creating a potential AB-BA deadlock if the work is already executing when l2cap_conn_del() takes the lock. Move the work cancellations before acquiring conn->lock and use disable_delayed_work_sync() to additionally prevent the works from being rearmed after cancellation, consistent with the pattern used in hci_conn_del().

Published: 2026-04-22Modified: 2026-05-14

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31500

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: btintel: serialize btintel_hw_error() with hci_req_sync_lock btintel_hw_error() issues two __hci_cmd_sync() calls (HCI_OP_RESET and Intel exception-info retrieval) without holding hci_req_sync_lock(). This lets it race against hci_dev_do_close() -> btintel_shutdown_combined(), which also runs __hci_cmd_sync() under the same lock. When both paths manipulate hdev->req_status/req_rsp concurrently, the close path may free the response skb first, and the still-running hw_error path hits a slab-use-after-free in kfree_skb(). Wrap the whole recovery sequence in hci_req_sync_lock/unlock so it is serialized with every other synchronous HCI command issuer. Below is the data race report and the kasan report: BUG: data-race in __hci_cmd_sync_sk / btintel_shutdown_combined read of hdev->req_rsp at net/bluetooth/hci_sync.c:199 by task kworker/u17:1/83: __hci_cmd_sync_sk+0x12f2/0x1c30 net/bluetooth/hci_sync.c:200 __hci_cmd_sync+0x55/0x80 net/bluetooth/hci_sync.c:223 btintel_hw_error+0x114/0x670 drivers/bluetooth/btintel.c:254 hci_error_reset+0x348/0xa30 net/bluetooth/hci_core.c:1030 write/free by task ioctl/22580: btintel_shutdown_combined+0xd0/0x360 drivers/bluetooth/btintel.c:3648 hci_dev_close_sync+0x9ae/0x2c10 net/bluetooth/hci_sync.c:5246 hci_dev_do_close+0x232/0x460 net/bluetooth/hci_core.c:526 BUG: KASAN: slab-use-after-free in sk_skb_reason_drop+0x43/0x380 net/core/skbuff.c:1202 Read of size 4 at addr ffff888144a738dc by task kworker/u17:1/83: __hci_cmd_sync_sk+0x12f2/0x1c30 net/bluetooth/hci_sync.c:200 __hci_cmd_sync+0x55/0x80 net/bluetooth/hci_sync.c:223 btintel_hw_error+0x186/0x670 drivers/bluetooth/btintel.c:260

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31502

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: team: fix header_ops type confusion with non-Ethernet ports Similar to commit 950803f72547 ("bonding: fix type confusion in bond_setup_by_slave()") team has the same class of header_ops type confusion. For non-Ethernet ports, team_setup_by_port() copies port_dev->header_ops directly. When the team device later calls dev_hard_header() or dev_parse_header(), these callbacks can run with the team net_device instead of the real lower device, so netdev_priv(dev) is interpreted as the wrong private type and can crash. The syzbot report shows a crash in bond_header_create(), but the root cause is in team: the topology is gre -> bond -> team, and team calls the inherited header_ops with its own net_device instead of the lower device, so bond_header_create() receives a team device and interprets netdev_priv() as bonding private data, causing a type confusion crash. Fix this by introducing team header_ops wrappers for create/parse, selecting a team port under RCU, and calling the lower device callbacks with port->dev, so each callback always sees the correct net_device context. Also pass the selected lower device to the lower parse callback, so recursion is bounded in stacked non-Ethernet topologies and parse callbacks always run with the correct device context.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31503

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: udp: Fix wildcard bind conflict check when using hash2 When binding a udp_sock to a local address and port, UDP uses two hashes (udptable->hash and udptable->hash2) for collision detection. The current code switches to "hash2" when hslot->count > 10. "hash2" is keyed by local address and local port. "hash" is keyed by local port only. The issue can be shown in the following bind sequence (pseudo code): bind(fd1, "[fd00::1]:8888") bind(fd2, "[fd00::2]:8888") bind(fd3, "[fd00::3]:8888") bind(fd4, "[fd00::4]:8888") bind(fd5, "[fd00::5]:8888") bind(fd6, "[fd00::6]:8888") bind(fd7, "[fd00::7]:8888") bind(fd8, "[fd00::8]:8888") bind(fd9, "[fd00::9]:8888") bind(fd10, "[fd00::10]:8888") /* Correctly return -EADDRINUSE because "hash" is used * instead of "hash2". udp_lib_lport_inuse() detects the * conflict. / bind(fail_fd, "[::]:8888") / After one more socket is bound to "[fd00::11]:8888", * hslot->count exceeds 10 and "hash2" is used instead. / bind(fd11, "[fd00::11]:8888") bind(fail_fd, "[::]:8888") / succeeds unexpectedly */ The same issue applies to the IPv4 wildcard address "0.0.0.0" and the IPv4-mapped wildcard address "::ffff:0.0.0.0". For example, if there are existing sockets bound to "192.168.1.[1-11]:8888", then binding "0.0.0.0:8888" or "[::ffff:0.0.0.0]:8888" can also miss the conflict when hslot->count > 10. TCP inet_csk_get_port() already has the correct check in inet_use_bhash2_on_bind(). Rename it to inet_use_hash2_on_bind() and move it to inet_hashtables.h so udp.c can reuse it in this fix.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31504

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: fix fanout UAF in packet_release() via NETDEV_UP race `packet_release()` has a race window where `NETDEV_UP` can re-register a socket into a fanout group's `arr[]` array. The re-registration is not cleaned up by `fanout_release()`, leaving a dangling pointer in the fanout array. `packet_release()` does NOT zero `po->num` in its `bind_lock` section. After releasing `bind_lock`, `po->num` is still non-zero and `po->ifindex` still matches the bound device. A concurrent `packet_notifier(NETDEV_UP)` that already found the socket in `sklist` can re-register the hook. For fanout sockets, this re-registration calls `__fanout_link(sk, po)` which adds the socket back into `f->arr[]` and increments `f->num_members`, but does NOT increment `f->sk_ref`. The fix sets `po->num` to zero in `packet_release` while `bind_lock` is held to prevent NETDEV_UP from linking, preventing the race window. This bug was found following an additional audit with Claude Code based on CVE-2025-38617.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31505

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: iavf: fix out-of-bounds writes in iavf_get_ethtool_stats() iavf incorrectly uses real_num_tx_queues for ETH_SS_STATS. Since the value could change in runtime, we should use num_tx_queues instead. Moreover iavf_get_ethtool_stats() uses num_active_queues while iavf_get_sset_count() and iavf_get_stat_strings() use real_num_tx_queues, which triggers out-of-bounds writes when we do "ethtool -L" and "ethtool -S" simultaneously [1]. For example when we change channels from 1 to 8, Thread 3 could be scheduled before Thread 2, and out-of-bounds writes could be triggered in Thread 3: Thread 1 (ethtool -L) Thread 2 (work) Thread 3 (ethtool -S) iavf_set_channels() ... iavf_alloc_queues() -> num_active_queues = 8 iavf_schedule_finish_config() iavf_get_sset_count() real_num_tx_queues: 1 -> buffer for 1 queue iavf_get_ethtool_stats() num_active_queues: 8 -> out-of-bounds! iavf_finish_config() -> real_num_tx_queues = 8 Use immutable num_tx_queues in all related functions to avoid the issue. [1] BUG: KASAN: vmalloc-out-of-bounds in iavf_add_one_ethtool_stat+0x200/0x270 Write of size 8 at addr ffffc900031c9080 by task ethtool/5800 CPU: 1 UID: 0 PID: 5800 Comm: ethtool Not tainted 6.19.0-enjuk-08403-g8137e3db7f1c #241 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 Call Trace: dump_stack_lvl+0x6f/0xb0 print_report+0x170/0x4f3 kasan_report+0xe1/0x180 iavf_add_one_ethtool_stat+0x200/0x270 iavf_get_ethtool_stats+0x14c/0x2e0 __dev_ethtool+0x3d0c/0x5830 dev_ethtool+0x12d/0x270 dev_ioctl+0x53c/0xe30 sock_do_ioctl+0x1a9/0x270 sock_ioctl+0x3d4/0x5e0 __x64_sys_ioctl+0x137/0x1c0 do_syscall_64+0xf3/0x690 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f7da0e6e36d ... The buggy address belongs to a 1-page vmalloc region starting at 0xffffc900031c9000 allocated at __dev_ethtool+0x3cc9/0x5830 The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88813a013de0 pfn:0x13a013 flags: 0x200000000000000(node=0|zone=2) raw: 0200000000000000 0000000000000000 dead000000000122 0000000000000000 raw: ffff88813a013de0 0000000000000000 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffffc900031c8f80: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ffffc900031c9000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffffc900031c9080: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ^ ffffc900031c9100: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ffffc900031c9180: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31506

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: bcmasp: fix double free of WoL irq We do not need to free wol_irq since it was instantiated with devm_request_irq(). So devres will free for us.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31507

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net/smc: fix double-free of smc_spd_priv when tee() duplicates splice pipe buffer smc_rx_splice() allocates one smc_spd_priv per pipe_buffer and stores the pointer in pipe_buffer.private. The pipe_buf_operations for these buffers used .get = generic_pipe_buf_get, which only increments the page reference count when tee(2) duplicates a pipe buffer. The smc_spd_priv pointer itself was not handled, so after tee() both the original and the cloned pipe_buffer share the same smc_spd_priv *. When both pipes are subsequently released, smc_rx_pipe_buf_release() is called twice against the same object: 1st call: kfree(priv) sock_put(sk) smc_rx_update_cons() [correct] 2nd call: kfree(priv) sock_put(sk) smc_rx_update_cons() [UAF] KASAN reports a slab-use-after-free in smc_rx_pipe_buf_release(), which then escalates to a NULL-pointer dereference and kernel panic via smc_rx_update_consumer() when it chases the freed priv->smc pointer: BUG: KASAN: slab-use-after-free in smc_rx_pipe_buf_release+0x78/0x2a0 Read of size 8 at addr ffff888004a45740 by task smc_splice_tee_/74 Call Trace: dump_stack_lvl+0x53/0x70 print_report+0xce/0x650 kasan_report+0xc6/0x100 smc_rx_pipe_buf_release+0x78/0x2a0 free_pipe_info+0xd4/0x130 pipe_release+0x142/0x160 fput+0x1c6/0x490 x64_sys_close+0x4f/0x90 do_syscall_64+0xa6/0x1a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f BUG: kernel NULL pointer dereference, address: 0000000000000020 RIP: 0010:smc_rx_update_consumer+0x8d/0x350 Call Trace: smc_rx_pipe_buf_release+0x121/0x2a0 free_pipe_info+0xd4/0x130 pipe_release+0x142/0x160 fput+0x1c6/0x490 x64_sys_close+0x4f/0x90 do_syscall_64+0xa6/0x1a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f Kernel panic - not syncing: Fatal exception Beyond the memory-safety problem, duplicating an SMC splice buffer is semantically questionable: smc_rx_update_cons() would advance the consumer cursor twice for the same data, corrupting receive-window accounting. A refcount on smc_spd_priv could fix the double-free, but the cursor-accounting issue would still need to be addressed separately. The .get callback is invoked by both tee(2) and splice_pipe_to_pipe() for partial transfers; both will now return -EFAULT. Users who need to duplicate SMC socket data must use a copy-based read path.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31508

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: openvswitch: Avoid releasing netdev before teardown completes The patch cited in the Fixes tag below changed the teardown code for OVS ports to no longer unconditionally take the RTNL. After this change, the netdev_destroy() callback can proceed immediately to the call_rcu() invocation if the IFF_OVS_DATAPATH flag is already cleared on the netdev. The ovs_netdev_detach_dev() function clears the flag before completing the unregistration, and if it gets preempted after clearing the flag (as can happen on an -rt kernel), netdev_destroy() can complete and the device can be freed before the unregistration completes. This leads to a splat like: [ 998.393867] Oops: general protection fault, probably for non-canonical address 0xff00000001000239: 0000 [#1] SMP PTI [ 998.393877] CPU: 42 UID: 0 PID: 55177 Comm: ip Kdump: loaded Not tainted 6.12.0-211.1.1.el10_2.x86_64+rt #1 PREEMPT_RT [ 998.393886] Hardware name: Dell Inc. PowerEdge R740/0JMK61, BIOS 2.24.0 03/27/2025 [ 998.393889] RIP: 0010:dev_set_promiscuity+0x8d/0xa0 [ 998.393901] Code: 00 00 75 d8 48 8b 53 08 48 83 ba b0 02 00 00 00 75 ca 48 83 c4 08 5b c3 cc cc cc cc 48 83 bf 48 09 00 00 00 75 91 48 8b 47 08 <48> 83 b8 b0 02 00 00 00 74 97 eb 81 0f 1f 80 00 00 00 00 90 90 90 [ 998.393906] RSP: 0018:ffffce5864a5f6a0 EFLAGS: 00010246 [ 998.393912] RAX: ff00000000ffff89 RBX: ffff894d0adf5a05 RCX: 0000000000000000 [ 998.393917] RDX: 0000000000000000 RSI: 00000000ffffffff RDI: ffff894d0adf5a05 [ 998.393921] RBP: ffff894d19252000 R08: ffff894d19252000 R09: 0000000000000000 [ 998.393924] R10: ffff894d19252000 R11: ffff894d192521b8 R12: 0000000000000006 [ 998.393927] R13: ffffce5864a5f738 R14: 00000000ffffffe2 R15: 0000000000000000 [ 998.393931] FS: 00007fad61971800(0000) GS:ffff894cc0140000(0000) knlGS:0000000000000000 [ 998.393936] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 998.393940] CR2: 000055df0a2a6e40 CR3: 000000011c7fe003 CR4: 00000000007726f0 [ 998.393944] PKRU: 55555554 [ 998.393946] Call Trace: [ 998.393949] [ 998.393952] ? show_trace_log_lvl+0x1b0/0x2f0 [ 998.393961] ? show_trace_log_lvl+0x1b0/0x2f0 [ 998.393975] ? dp_device_event+0x41/0x80 [openvswitch] [ 998.394009] ? __die_body.cold+0x8/0x12 [ 998.394016] ? die_addr+0x3c/0x60 [ 998.394027] ? exc_general_protection+0x16d/0x390 [ 998.394042] ? asm_exc_general_protection+0x26/0x30 [ 998.394058] ? dev_set_promiscuity+0x8d/0xa0 [ 998.394066] ? ovs_netdev_detach_dev+0x3a/0x80 [openvswitch] [ 998.394092] dp_device_event+0x41/0x80 [openvswitch] [ 998.394102] notifier_call_chain+0x5a/0xd0 [ 998.394106] unregister_netdevice_many_notify+0x51b/0xa60 [ 998.394110] rtnl_dellink+0x169/0x3e0 [ 998.394121] ? rt_mutex_slowlock.constprop.0+0x95/0xd0 [ 998.394125] rtnetlink_rcv_msg+0x142/0x3f0 [ 998.394128] ? avc_has_perm_noaudit+0x69/0xf0 [ 998.394130] ? __pfx_rtnetlink_rcv_msg+0x10/0x10 [ 998.394132] netlink_rcv_skb+0x50/0x100 [ 998.394138] netlink_unicast+0x292/0x3f0 [ 998.394141] netlink_sendmsg+0x21b/0x470 [ 998.394145] ____sys_sendmsg+0x39d/0x3d0 [ 998.394149] ___sys_sendmsg+0x9a/0xe0 [ 998.394156] __sys_sendmsg+0x7a/0xd0 [ 998.394160] do_syscall_64+0x7f/0x170 [ 998.394162] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 998.394165] RIP: 0033:0x7fad61bf4724 [ 998.394188] Code: 89 02 b8 ff ff ff ff eb bb 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 f3 0f 1e fa 80 3d c5 e9 0c 00 00 74 13 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 48 83 ec 28 89 54 24 1c 48 89 [ 998.394189] RSP: 002b:00007ffd7e2f7cb8 EFLAGS: 00000202 ORIG_RAX: 000000000000002e [ 998.394191] RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007fad61bf4724 [ 998.394193] RDX: 0000000000000000 RSI: 00007ffd7e2f7d20 RDI: 0000000000000003 [ 998.394194] RBP: 00007ffd7e2f7d90 R08: 0000000000000010 R09: 000000000000003f [ 998.394195] R10: 000055df11558010 R11: 0000000000000202 R12: 00007ffd7e2 ---truncated---

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31509

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: nfc: nci: fix circular locking dependency in nci_close_device nci_close_device() flushes rx_wq and tx_wq while holding req_lock. This causes a circular locking dependency because nci_rx_work() running on rx_wq can end up taking req_lock too: nci_rx_work -> nci_rx_data_packet -> nci_data_exchange_complete -> __sk_destruct -> rawsock_destruct -> nfc_deactivate_target -> nci_deactivate_target -> nci_request -> mutex_lock(&ndev->req_lock) Move the flush of rx_wq after req_lock has been released. This should safe (I think) because NCI_UP has already been cleared and the transport is closed, so the work will see it and return -ENETDOWN. NIPA has been hitting this running the nci selftest with a debug kernel on roughly 4% of the runs.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31510

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix null-ptr-deref on l2cap_sock_ready_cb Before using sk pointer, check if it is null. Fix the following: KASAN: null-ptr-deref in range [0x0000000000000260-0x0000000000000267] CPU: 0 UID: 0 PID: 5985 Comm: kworker/0:5 Not tainted 7.0.0-rc4-00029-ga989fde763f4 #1 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-9.fc43 06/10/2025 Workqueue: events l2cap_info_timeout RIP: 0010:kasan_byte_accessible+0x12/0x30 Code: 79 ff ff ff 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 40 d6 48 c1 ef 03 48 b8 00 00 00 00 00 fc ff df <0f> b6 04 07 3c 08 0f 92 c0 c3 cc cce veth0_macvtap: entered promiscuous mode RSP: 0018:ffffc90006e0f808 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffffffff89746018 RCX: 0000000080000001 RDX: 0000000000000000 RSI: ffffffff89746018 RDI: 000000000000004c RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: dffffc0000000000 R11: ffffffff8aae3e70 R12: 0000000000000000 R13: 0000000000000260 R14: 0000000000000260 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8880983c2000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005582615a5008 CR3: 000000007007e000 CR4: 0000000000752ef0 PKRU: 55555554 Call Trace: __kasan_check_byte+0x12/0x40 lock_acquire+0x79/0x2e0 lock_sock_nested+0x48/0x100 ? l2cap_sock_ready_cb+0x46/0x160 l2cap_sock_ready_cb+0x46/0x160 l2cap_conn_start+0x779/0xff0 ? __pfx_l2cap_conn_start+0x10/0x10 ? l2cap_info_timeout+0x60/0xa0 ? pfx_mutex_lock+0x10/0x10 l2cap_info_timeout+0x68/0xa0 ? process_scheduled_works+0xa8d/0x18c0 process_scheduled_works+0xb6e/0x18c0 ? __pfx_process_scheduled_works+0x10/0x10 ? assign_work+0x3d5/0x5e0 worker_thread+0xa53/0xfc0 kthread+0x388/0x470 ? __pfx_worker_thread+0x10/0x10 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x51e/0xb90 ? __pfx_ret_from_fork+0x10/0x10 veth1_macvtap: entered promiscuous mode ? __switch_to+0xc7d/0x1450 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 Modules linked in: ---[ end trace 0000000000000000 ]--- batman_adv: batadv0: Interface activated: batadv_slave_0 batman_adv: batadv0: Interface activated: batadv_slave_1 netdevsim netdevsim7 netdevsim0: set [1, 0] type 2 family 0 port 6081 - 0 netdevsim netdevsim7 netdevsim1: set [1, 0] type 2 family 0 port 6081 - 0 netdevsim netdevsim7 netdevsim2: set [1, 0] type 2 family 0 port 6081 - 0 netdevsim netdevsim7 netdevsim3: set [1, 0] type 2 family 0 port 6081 - 0 RIP: 0010:kasan_byte_accessible+0x12/0x30 Code: 79 ff ff ff 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 40 d6 48 c1 ef 03 48 b8 00 00 00 00 00 fc ff df <0f> b6 04 07 3c 08 0f 92 c0 c3 cc cce ieee80211 phy39: Selected rate control algorithm 'minstrel_ht' RSP: 0018:ffffc90006e0f808 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffffffff89746018 RCX: 0000000080000001 RDX: 0000000000000000 RSI: ffffffff89746018 RDI: 000000000000004c RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: dffffc0000000000 R11: ffffffff8aae3e70 R12: 0000000000000000 R13: 0000000000000260 R14: 0000000000000260 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8880983c2000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f7e16139e9c CR3: 000000000e74e000 CR4: 0000000000752ef0 PKRU: 55555554 Kernel panic - not syncing: Fatal exception

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31511

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: MGMT: Fix dangling pointer on mgmt_add_adv_patterns_monitor_complete This fixes the condition checking so mgmt_pending_valid is executed whenever status != -ECANCELED otherwise calling mgmt_pending_free(cmd) would kfree(cmd) without unlinking it from the list first, leaving a dangling pointer. Any subsequent list traversal (e.g., mgmt_pending_foreach during __mgmt_power_off, or another mgmt_pending_valid call) would dereference freed memory.

Published: 2026-04-22Modified: 2026-05-17

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31512

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Validate PDU length before reading SDU length in l2cap_ecred_data_rcv() l2cap_ecred_data_rcv() reads the SDU length field from skb->data using get_unaligned_le16() without first verifying that skb contains at least L2CAP_SDULEN_SIZE (2) bytes. When skb->len is less than 2, this reads past the valid data in the skb. The ERTM reassembly path correctly calls pskb_may_pull() before reading the SDU length (l2cap_reassemble_sdu, L2CAP_SAR_START case). Apply the same validation to the Enhanced Credit Based Flow Control data path.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31513

HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix stack-out-of-bounds read in l2cap_ecred_conn_req Syzbot reported a KASAN stack-out-of-bounds read in l2cap_build_cmd() that is triggered by a malformed Enhanced Credit Based Connection Request. The vulnerability stems from l2cap_ecred_conn_req(). The function allocates a local stack buffer (`pdu`) designed to hold a maximum of 5 Source Channel IDs (SCIDs), totaling 18 bytes. When an attacker sends a request with more than 5 SCIDs, the function calculates `rsp_len` based on this unvalidated `cmd_len` before checking if the number of SCIDs exceeds L2CAP_ECRED_MAX_CID. If the SCID count is too high, the function correctly jumps to the `response` label to reject the packet, but `rsp_len` retains the attacker's oversized value. Consequently, l2cap_send_cmd() is instructed to read past the end of the 18-byte `pdu` buffer, triggering a KASAN panic. Fix this by moving the assignment of `rsp_len` to after the `num_scid` boundary check. If the packet is rejected, `rsp_len` will safely remain 0, and the error response will only read the 8-byte base header from the stack.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 8.1

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31514

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: erofs: set fileio bio failed in short read case For file-backed mount, IO requests are handled by vfs_iocb_iter_read(). However, it can be interrupted by SIGKILL, returning the number of bytes actually copied. Unused folios in bio are unexpectedly marked as uptodate. vfs_read filemap_read filemap_get_pages filemap_readahead erofs_fileio_readahead erofs_fileio_rq_submit vfs_iocb_iter_read filemap_read filemap_get_pages <= detect signal erofs_fileio_ki_complete <= set all folios uptodate This patch addresses this by setting short read bio with an error directly.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31515

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: af_key: validate families in pfkey_send_migrate() syzbot was able to trigger a crash in skb_put() [1] Issue is that pfkey_send_migrate() does not check old/new families, and that set_ipsecrequest() @family argument was truncated, thus possibly overfilling the skb. Validate families early, do not wait set_ipsecrequest(). [1] skbuff: skb_over_panic: text:ffffffff8a752120 len:392 put:16 head:ffff88802a4ad040 data:ffff88802a4ad040 tail:0x188 end:0x180 dev: kernel BUG at net/core/skbuff.c:214 ! Call Trace: skb_over_panic net/core/skbuff.c:219 [inline] skb_put+0x159/0x210 net/core/skbuff.c:2655 skb_put_zero include/linux/skbuff.h:2788 [inline] set_ipsecrequest net/key/af_key.c:3532 [inline] pfkey_send_migrate+0x1270/0x2e50 net/key/af_key.c:3636 km_migrate+0x155/0x260 net/xfrm/xfrm_state.c:2848 xfrm_migrate+0x2140/0x2450 net/xfrm/xfrm_policy.c:4705 xfrm_do_migrate+0x8ff/0xaa0 net/xfrm/xfrm_user.c:3150

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31516

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: xfrm: prevent policy_hthresh.work from racing with netns teardown A XFRM_MSG_NEWSPDINFO request can queue the per-net work item policy_hthresh.work onto the system workqueue. The queued callback, xfrm_hash_rebuild(), retrieves the enclosing struct net via container_of(). If the net namespace is torn down before that work runs, the associated struct net may already have been freed, and xfrm_hash_rebuild() may then dereference stale memory. xfrm_policy_fini() already flushes policy_hash_work during teardown, but it does not synchronize policy_hthresh.work. Synchronize policy_hthresh.work in xfrm_policy_fini() as well, so the queued work cannot outlive the net namespace teardown and access a freed struct net.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31517

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xfrm: iptfs: fix skb_put() panic on non-linear skb during reassembly In iptfs_reassem_cont(), IP-TFS attempts to append data to the new inner packet 'newskb' that is being reassembled. First a zero-copy approach is tried if it succeeds then newskb becomes non-linear. When a subsequent fragment in the same datagram does not meet the fast-path conditions, a memory copy is performed. It calls skb_put() to append the data and as newskb is non-linear it triggers SKB_LINEAR_ASSERT check. Oops: invalid opcode: 0000 [#1] SMP NOPTI [...] RIP: 0010:skb_put+0x3c/0x40 [...] Call Trace: iptfs_reassem_cont+0x1ab/0x5e0 [xfrm_iptfs] iptfs_input_ordered+0x2af/0x380 [xfrm_iptfs] iptfs_input+0x122/0x3e0 [xfrm_iptfs] xfrm_input+0x91e/0x1a50 xfrm4_esp_rcv+0x3a/0x110 ip_protocol_deliver_rcu+0x1d7/0x1f0 ip_local_deliver_finish+0xbe/0x1e0 __netif_receive_skb_core.constprop.0+0xb56/0x1120 __netif_receive_skb_list_core+0x133/0x2b0 netif_receive_skb_list_internal+0x1ff/0x3f0 napi_complete_done+0x81/0x220 virtnet_poll+0x9d6/0x116e [virtio_net] __napi_poll.constprop.0+0x2b/0x270 net_rx_action+0x162/0x360 handle_softirqs+0xdc/0x510 __irq_exit_rcu+0xe7/0x110 irq_exit_rcu+0xe/0x20 common_interrupt+0x85/0xa0 Fix this by checking if the skb is non-linear. If it is, linearize it by calling skb_linearize(). As the initial allocation of newskb originally reserved enough tailroom for the entire reassembled packet we do not need to check if we have enough tailroom or extend it.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31518

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: esp: fix skb leak with espintcp and async crypto When the TX queue for espintcp is full, esp_output_tail_tcp will return an error and not free the skb, because with synchronous crypto, the common xfrm output code will drop the packet for us. With async crypto (esp_output_done), we need to drop the skb when esp_output_tail_tcp returns an error.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31519

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: btrfs: set BTRFS_ROOT_ORPHAN_CLEANUP during subvol create We have recently observed a number of subvolumes with broken dentries. ls-ing the parent dir looks like: drwxrwxrwt 1 root root 16 Jan 23 16:49 . drwxr-xr-x 1 root root 24 Jan 23 16:48 .. d????????? ? ? ? ? ? broken_subvol and similarly stat-ing the file fails. In this state, deleting the subvol fails with ENOENT, but attempting to create a new file or subvol over it errors out with EEXIST and even aborts the fs. Which leaves us a bit stuck. dmesg contains a single notable error message reading: "could not do orphan cleanup -2" 2 is ENOENT and the error comes from the failure handling path of btrfs_orphan_cleanup(), with the stack leading back up to btrfs_lookup(). btrfs_lookup btrfs_lookup_dentry btrfs_orphan_cleanup // prints that message and returns -ENOENT After some detailed inspection of the internal state, it became clear that: - there are no orphan items for the subvol - the subvol is otherwise healthy looking, it is not half-deleted or anything, there is no drop progress, etc. - the subvol was created a while ago and does the meaningful first btrfs_orphan_cleanup() call that sets BTRFS_ROOT_ORPHAN_CLEANUP much later. - after btrfs_orphan_cleanup() fails, btrfs_lookup_dentry() returns -ENOENT, which results in a negative dentry for the subvolume via d_splice_alias(NULL, dentry), leading to the observed behavior. The bug can be mitigated by dropping the dentry cache, at which point we can successfully delete the subvolume if we want. i.e., btrfs_lookup() btrfs_lookup_dentry() if (!sb_rdonly(inode->vfs_inode)->vfs_inode) btrfs_orphan_cleanup(sub_root) test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP) btrfs_search_slot() // finds orphan item for inode N ... prints "could not do orphan cleanup -2" if (inode == ERR_PTR(-ENOENT)) inode = NULL; return d_splice_alias(NULL, dentry) // NEGATIVE DENTRY for valid subvolume btrfs_orphan_cleanup() does test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP) on the root when it runs, so it cannot run more than once on a given root, so something else must run concurrently. However, the obvious routes to deleting an orphan when nlinks goes to 0 should not be able to run without first doing a lookup into the subvolume, which should run btrfs_orphan_cleanup() and set the bit. The final important observation is that create_subvol() calls d_instantiate_new() but does not set BTRFS_ROOT_ORPHAN_CLEANUP, so if the dentry cache gets dropped, the next lookup into the subvolume will make a real call into btrfs_orphan_cleanup() for the first time. This opens up the possibility of concurrently deleting the inode/orphan items but most typical evict() paths will be holding a reference on the parent dentry (child dentry holds parent->d_lockref.count via dget in d_alloc(), released in __dentry_kill()) and prevent the parent from being removed from the dentry cache. The one exception is delayed iputs. Ordered extent creation calls igrab() on the inode. If the file is unlinked and closed while those refs are held, iput() in __dentry_kill() decrements i_count but does not trigger eviction (i_count > 0). The child dentry is freed and the subvol dentry's d_lockref.count drops to 0, making it evictable while the inode is still alive. Since there are two races (the race between writeback and unlink and the race between lookup and delayed iputs), and there are too many moving parts, the following three diagrams show the complete picture. (Only the second and third are races) Phase 1: Create Subvol in dentry cache without BTRFS_ROOT_ORPHAN_CLEANUP set btrfs_mksubvol() lookup_one_len() __lookup_slow() d_alloc_parallel() __d_alloc() // d_lockref.count = 1 create_subvol(dentry) // doesn't touch the bit.. d_instantiate_new(dentry, inode) // dentry in cache with d_lockref.c ---truncated---

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31520

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: HID: apple: avoid memory leak in apple_report_fixup() The apple_report_fixup() function was returning a newly kmemdup()-allocated buffer, but never freeing it. The caller of report_fixup() does not take ownership of the returned pointer, but it is permitted to return a sub-portion of the input rdesc, whose lifetime is managed by the caller.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31521

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: module: Fix kernel panic when a symbol st_shndx is out of bounds The module loader doesn't check for bounds of the ELF section index in simplify_symbols(): for (i = 1; i < symsec->sh_size / sizeof(Elf_Sym); i++) { const char name = info->strtab + sym[i].st_name; switch (sym[i].st_shndx) { case SHN_COMMON: [...] default: / Divert to percpu allocation if a percpu var. */ if (sym[i].st_shndx == info->index.pcpu) secbase = (unsigned long)mod_percpu(mod); else / HERE --> / secbase = info->sechdrs[sym[i].st_shndx].sh_addr; sym[i].st_value += secbase; break; } } A symbol with an out-of-bounds st_shndx value, for example 0xffff (known as SHN_XINDEX or SHN_HIRESERVE), may cause a kernel panic: BUG: unable to handle page fault for address: ... RIP: 0010:simplify_symbols+0x2b2/0x480 ... Kernel panic - not syncing: Fatal exception This can happen when module ELF is legitimately using SHN_XINDEX or when it is corrupted. Add a bounds check in simplify_symbols() to validate that st_shndx is within the valid range before using it. This issue was discovered due to a bug in llvm-objcopy, see relevant discussion for details [1]. [1] https://lore.kernel.org/linux-modules/20251224005752.201911-1-ihor.solodrai@linux.dev/

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31522

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: HID: magicmouse: avoid memory leak in magicmouse_report_fixup() The magicmouse_report_fixup() function was returning a newly kmemdup()-allocated buffer, but never freeing it. The caller of report_fixup() does not take ownership of the returned pointer, but it is permitted to return a sub-portion of the input rdesc, whose lifetime is managed by the caller.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31523

MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: nvme-pci: ensure we're polling a polled queue A user can change the polled queue count at run time. There's a brief window during a reset where a hipri task may try to poll that queue before the block layer has updated the queue maps, which would race with the now interrupt driven queue and may cause double completions.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 4.7

CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31524

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: HID: asus: avoid memory leak in asus_report_fixup() The asus_report_fixup() function was returning a newly allocated kmemdup()-allocated buffer, but never freeing it. Switch to devm_kzalloc() to ensure the memory is managed and freed automatically when the device is removed. The caller of report_fixup() does not take ownership of the returned pointer, but it is permitted to return a pointer whose lifetime is at least that of the input buffer. Also fix a harmless out-of-bounds read by copying only the original descriptor size.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31525

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix undefined behavior in interpreter sdiv/smod for INT_MIN The BPF interpreter's signed 32-bit division and modulo handlers use the kernel abs() macro on s32 operands. The abs() macro documentation (include/linux/math.h) explicitly states the result is undefined when the input is the type minimum. When DST contains S32_MIN (0x80000000), abs((s32)DST) triggers undefined behavior and returns S32_MIN unchanged on arm64/x86. This value is then sign-extended to u64 as 0xFFFFFFFF80000000, causing do_div() to compute the wrong result. The verifier's abstract interpretation (scalar32_min_max_sdiv) computes the mathematically correct result for range tracking, creating a verifier/interpreter mismatch that can be exploited for out-of-bounds map value access. Introduce abs_s32() which handles S32_MIN correctly by casting to u32 before negating, avoiding signed overflow entirely. Replace all 8 abs((s32)...) call sites in the interpreter's sdiv32/smod32 handlers. s32 is the only affected case -- the s64 division/modulo handlers do not use abs().

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31526

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix exception exit lock checking for subprogs process_bpf_exit_full() passes check_lock = !curframe to check_resource_leak(), which is false in cases when bpf_throw() is called from a static subprog. This makes check_resource_leak() to skip validation of active_rcu_locks, active_preempt_locks, and active_irq_id on exception exits from subprogs. At runtime bpf_throw() unwinds the stack via ORC without releasing any user-acquired locks, which may cause various issues as the result. Fix by setting check_lock = true for exception exits regardless of curframe, since exceptions bypass all intermediate frame cleanup. Update the error message prefix to "bpf_throw" for exception exits to distinguish them from normal BPF_EXIT. Fix reject_subprog_with_rcu_read_lock test which was previously passing for the wrong reason. Test program returned directly from the subprog call without closing the RCU section, so the error was triggered by the unclosed RCU lock on normal exit, not by bpf_throw. Update __msg annotations for affected tests to match the new "bpf_throw" error prefix. The spin_lock case is not affected because they are already checked [1] at the call site in do_check_insn() before bpf_throw can run. [1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/kernel/bpf/verifier.c?h=v7.0-rc4#n21098

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31527

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: driver core: platform: use generic driver_override infrastructure When a driver is probed through __driver_attach(), the bus' match() callback is called without the device lock held, thus accessing the driver_override field without a lock, which can cause a UAF. Fix this by using the driver-core driver_override infrastructure taking care of proper locking internally. Note that calling match() from __driver_attach() without the device lock held is intentional. [1]

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31528

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: perf: Make sure to use pmu_ctx->pmu for groups Oliver reported that x86_pmu_del() ended up doing an out-of-bound memory access when group_sched_in() fails and needs to roll back. This should be handled by the transaction callbacks, but he found that when the group leader is a software event, the transaction handlers of the wrong PMU are used. Despite the move_group case in perf_event_open() and group_sched_in() using pmu_ctx->pmu. Turns out, inherit uses event->pmu to clone the events, effectively undoing the move_group case for all inherited contexts. Fix this by also making inherit use pmu_ctx->pmu, ensuring all inherited counters end up in the same pmu context. Similarly, __perf_event_read() should use equally use pmu_ctx->pmu for the group case.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31530

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: cxl/port: Fix use after free of parent_port in cxl_detach_ep() cxl_detach_ep() is called during bottom-up removal when all CXL memory devices beneath a switch port have been removed. For each port in the hierarchy it locks both the port and its parent, removes the endpoint, and if the port is now empty, marks it dead and unregisters the port by calling delete_switch_port(). There are two places during this work where the parent_port may be used after freeing: First, a concurrent detach may have already processed a port by the time a second worker finds it via bus_find_device(). Without pinning parent_port, it may already be freed when we discover port->dead and attempt to unlock the parent_port. In a production kernel that's a silent memory corruption, with lock debug, it looks like this: []DEBUG_LOCKS_WARN_ON(__owner_task(owner) != get_current()) []WARNING: kernel/locking/mutex.c:949 at __mutex_unlock_slowpath+0x1ee/0x310 []Call Trace: []mutex_unlock+0xd/0x20 []cxl_detach_ep+0x180/0x400 [cxl_core] []devm_action_release+0x10/0x20 []devres_release_all+0xa8/0xe0 []device_unbind_cleanup+0xd/0xa0 []really_probe+0x1a6/0x3e0 Second, delete_switch_port() releases three devm actions registered against parent_port. The last of those is unregister_port() and it calls device_unregister() on the child port, which can cascade. If parent_port is now also empty the device core may unregister and free it too. So by the time delete_switch_port() returns, parent_port may be free, and the subsequent device_unlock(&parent_port->dev) operates on freed memory. The kernel log looks same as above, with a different offset in cxl_detach_ep(). Both of these issues stem from the absence of a lifetime guarantee between a child port and its parent port. Establish a lifetime rule for ports: child ports hold a reference to their parent device until release. Take the reference when the port is allocated and drop it when released. This ensures the parent is valid for the full lifetime of the child and eliminates the use after free window in cxl_detach_ep(). This is easily reproduced with a reload of cxl_acpi in QEMU with CXL devices present.

Published: 2026-04-22Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31531

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ipv4: nexthop: allocate skb dynamically in rtm_get_nexthop() When querying a nexthop object via RTM_GETNEXTHOP, the kernel currently allocates a fixed-size skb using NLMSG_GOODSIZE. While sufficient for single nexthops and small Equal-Cost Multi-Path groups, this fixed allocation fails for large nexthop groups like 512 nexthops. This results in the following warning splat: WARNING: net/ipv4/nexthop.c:3395 at rtm_get_nexthop+0x176/0x1c0, CPU#20: rep/4608 [...] RIP: 0010:rtm_get_nexthop (net/ipv4/nexthop.c:3395) [...] Call Trace: rtnetlink_rcv_msg (net/core/rtnetlink.c:6989) netlink_rcv_skb (net/netlink/af_netlink.c:2550) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) ____sys_sendmsg (net/socket.c:721 net/socket.c:736 net/socket.c:2585) ___sys_sendmsg (net/socket.c:2641) __sys_sendmsg (net/socket.c:2671) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Fix this by allocating the size dynamically using nh_nlmsg_size() and using nlmsg_new(), this is consistent with nexthop_notify() behavior. In addition, adjust nh_nlmsg_size_grp() so it calculates the size needed based on flags passed. While at it, also add the size of NHA_FDB for nexthop group size calculation as it was missing too. This cannot be reproduced via iproute2 as the group size is currently limited and the command fails as follows: addattr_l ERROR: message exceeded bound of 1048

Published: 2026-04-23Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31532

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: can: raw: fix ro->uniq use-after-free in raw_rcv() raw_release() unregisters raw CAN receive filters via can_rx_unregister(), but receiver deletion is deferred with call_rcu(). This leaves a window where raw_rcv() may still be running in an RCU read-side critical section after raw_release() frees ro->uniq, leading to a use-after-free of the percpu uniq storage. Move free_percpu(ro->uniq) out of raw_release() and into a raw-specific socket destructor. can_rx_unregister() takes an extra reference to the socket and only drops it from the RCU callback, so freeing uniq from sk_destruct ensures the percpu area is not released until the relevant callbacks have drained. [mkl: applied manually]

Published: 2026-04-23Modified: 2026-04-29

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31533

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: net/tls: fix use-after-free in -EBUSY error path of tls_do_encryption The -EBUSY handling in tls_do_encryption(), introduced by commit 859054147318 ("net: tls: handle backlogging of crypto requests"), has a use-after-free due to double cleanup of encrypt_pending and the scatterlist entry. When crypto_aead_encrypt() returns -EBUSY, the request is enqueued to the cryptd backlog and the async callback tls_encrypt_done() will be invoked upon completion. That callback unconditionally restores the scatterlist entry (sge->offset, sge->length) and decrements ctx->encrypt_pending. However, if tls_encrypt_async_wait() returns an error, the synchronous error path in tls_do_encryption() performs the same cleanup again, double-decrementing encrypt_pending and double-restoring the scatterlist. The double-decrement corrupts the encrypt_pending sentinel (initialized to 1), making tls_encrypt_async_wait() permanently skip the wait for pending async callbacks. A subsequent sendmsg can then free the tls_rec via bpf_exec_tx_verdict() while a cryptd callback is still pending, resulting in a use-after-free when the callback fires on the freed record. Fix this by skipping the synchronous cleanup when the -EBUSY async wait returns an error, since the callback has already handled encrypt_pending and sge restoration.

Published: 2026-04-23Modified: 2026-04-29

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31540

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/i915/gt: Check set_default_submission() before deferencing When the i915 driver firmware binaries are not present, the set_default_submission pointer is not set. This pointer is dereferenced during suspend anyways. Add a check to make sure it is set before dereferencing. [ 23.289926] PM: suspend entry (deep) [ 23.293558] Filesystems sync: 0.000 seconds [ 23.298010] Freezing user space processes [ 23.302771] Freezing user space processes completed (elapsed 0.000 seconds) [ 23.309766] OOM killer disabled. [ 23.313027] Freezing remaining freezable tasks [ 23.318540] Freezing remaining freezable tasks completed (elapsed 0.001 seconds) [ 23.342038] serial 00:05: disabled [ 23.345719] serial 00:02: disabled [ 23.349342] serial 00:01: disabled [ 23.353782] sd 0:0:0:0: [sda] Synchronizing SCSI cache [ 23.358993] sd 1:0:0:0: [sdb] Synchronizing SCSI cache [ 23.361635] ata1.00: Entering standby power mode [ 23.368863] ata2.00: Entering standby power mode [ 23.445187] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 23.452194] #PF: supervisor instruction fetch in kernel mode [ 23.457896] #PF: error_code(0x0010) - not-present page [ 23.463065] PGD 0 P4D 0 [ 23.465640] Oops: Oops: 0010 [#1] SMP NOPTI [ 23.469869] CPU: 8 UID: 0 PID: 211 Comm: kworker/u48:18 Tainted: G S W 6.19.0-rc4-00020-gf0b9d8eb98df #10 PREEMPT(voluntary) [ 23.482512] Tainted: [S]=CPU_OUT_OF_SPEC, [W]=WARN [ 23.496511] Workqueue: async async_run_entry_fn [ 23.501087] RIP: 0010:0x0 [ 23.503755] Code: Unable to access opcode bytes at 0xffffffffffffffd6. [ 23.510324] RSP: 0018:ffffb4a60065fca8 EFLAGS: 00010246 [ 23.515592] RAX: 0000000000000000 RBX: ffff9f428290e000 RCX: 000000000000000f [ 23.522765] RDX: 0000000000000000 RSI: 0000000000000282 RDI: ffff9f428290e000 [ 23.529937] RBP: ffff9f4282907070 R08: ffff9f4281130428 R09: 00000000ffffffff [ 23.537111] R10: 0000000000000000 R11: 0000000000000001 R12: ffff9f42829070f8 [ 23.544284] R13: ffff9f4282906028 R14: ffff9f4282900000 R15: ffff9f4282906b68 [ 23.551457] FS: 0000000000000000(0000) GS:ffff9f466b2cf000(0000) knlGS:0000000000000000 [ 23.559588] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 23.565365] CR2: ffffffffffffffd6 CR3: 000000031c230001 CR4: 0000000000f70ef0 [ 23.572539] PKRU: 55555554 [ 23.575281] Call Trace: [ 23.577770] [ 23.579905] intel_engines_reset_default_submission+0x42/0x60 [ 23.585695] __intel_gt_unset_wedged+0x191/0x200 [ 23.590360] intel_gt_unset_wedged+0x20/0x40 [ 23.594675] gt_sanitize+0x15e/0x170 [ 23.598290] i915_gem_suspend_late+0x6b/0x180 [ 23.602692] i915_drm_suspend_late+0x35/0xf0 [ 23.607008] ? __pfx_pci_pm_suspend_late+0x10/0x10 [ 23.611843] dpm_run_callback+0x78/0x1c0 [ 23.615817] device_suspend_late+0xde/0x2e0 [ 23.620037] async_suspend_late+0x18/0x30 [ 23.624082] async_run_entry_fn+0x25/0xa0 [ 23.628129] process_one_work+0x15b/0x380 [ 23.632182] worker_thread+0x2a5/0x3c0 [ 23.635973] ? __pfx_worker_thread+0x10/0x10 [ 23.640279] kthread+0xf6/0x1f0 [ 23.643464] ? __pfx_kthread+0x10/0x10 [ 23.647263] ? __pfx_kthread+0x10/0x10 [ 23.651045] ret_from_fork+0x131/0x190 [ 23.654837] ? __pfx_kthread+0x10/0x10 [ 23.658634] ret_from_fork_asm+0x1a/0x30 [ 23.662597] [ 23.664826] Modules linked in: [ 23.667914] CR2: 0000000000000000 [ 23.671271] ------------[ cut here ]------------ (cherry picked from commit daa199abc3d3d1740c9e3a2c3e9216ae5b447cad)

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31541

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: tracing: Fix trace_marker copy link list updates When the "copy_trace_marker" option is enabled for an instance, anything written into /sys/kernel/tracing/trace_marker is also copied into that instances buffer. When the option is set, that instance's trace_array descriptor is added to the marker_copies link list. This list is protected by RCU, as all iterations uses an RCU protected list traversal. When the instance is deleted, all the flags that were enabled are cleared. This also clears the copy_trace_marker flag and removes the trace_array descriptor from the list. The issue is after the flags are called, a direct call to update_marker_trace() is performed to clear the flag. This function returns true if the state of the flag changed and false otherwise. If it returns true here, synchronize_rcu() is called to make sure all readers see that its removed from the list. But since the flag was already cleared, the state does not change and the synchronization is never called, leaving a possible UAF bug. Move the clearing of all flags below the updating of the copy_trace_marker option which then makes sure the synchronization is performed. Also use the flag for checking the state in update_marker_trace() instead of looking at if the list is empty.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31542

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: x86/platform/uv: Handle deconfigured sockets When a socket is deconfigured, it's mapped to SOCK_EMPTY (0xffff). This causes a panic while allocating UV hub info structures. Fix this by using NUMA_NO_NODE, allowing UV hub info structures to be allocated on valid nodes.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31543

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: crash_dump: don't log dm-crypt key bytes in read_key_from_user_keying When debug logging is enabled, read_key_from_user_keying() logs the first 8 bytes of the key payload and partially exposes the dm-crypt key. Stop logging any key bytes.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31544

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: firmware: arm_scmi: Fix NULL dereference on notify error path Since commit b5daf93b809d1 ("firmware: arm_scmi: Avoid notifier registration for unsupported events") the call chains leading to the helper __scmi_event_handler_get_ops expect an ERR_PTR to be returned on failure to get an handler for the requested event key, while the current helper can still return a NULL when no handler could be found or created. Fix by forcing an ERR_PTR return value when the handler reference is NULL.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31545

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: NFC: nxp-nci: allow GPIOs to sleep Allow the firmware and enable GPIOs to sleep. This fixes a `WARN_ON' and allows the driver to operate GPIOs which are connected to I2C GPIO expanders. -- >8 -- kernel: WARNING: CPU: 3 PID: 2636 at drivers/gpio/gpiolib.c:3880 gpiod_set_value+0x88/0x98 -- >8 --

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31546

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: bonding: fix NULL deref in bond_debug_rlb_hash_show rlb_clear_slave intentionally keeps RLB hash-table entries on the rx_hashtbl_used_head list with slave set to NULL when no replacement slave is available. However, bond_debug_rlb_hash_show visites client_info->slave without checking if it's NULL. Other used-list iterators in bond_alb.c already handle this NULL-slave state safely: - rlb_update_client returns early on !client_info->slave - rlb_req_update_slave_clients, rlb_clear_slave, and rlb_rebalance compare slave values before visiting - lb_req_update_subnet_clients continues if slave is NULL The following NULL deref crash can be trigger in bond_debug_rlb_hash_show: [ 1.289791] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 1.292058] RIP: 0010:bond_debug_rlb_hash_show (drivers/net/bonding/bond_debugfs.c:41) [ 1.293101] RSP: 0018:ffffc900004a7d00 EFLAGS: 00010286 [ 1.293333] RAX: 0000000000000000 RBX: ffff888102b48200 RCX: ffff888102b48204 [ 1.293631] RDX: ffff888102b48200 RSI: ffffffff839daad5 RDI: ffff888102815078 [ 1.293924] RBP: ffff888102815078 R08: ffff888102b4820e R09: 0000000000000000 [ 1.294267] R10: 0000000000000000 R11: 0000000000000000 R12: ffff888100f929c0 [ 1.294564] R13: ffff888100f92a00 R14: 0000000000000001 R15: ffffc900004a7ed8 [ 1.294864] FS: 0000000001395380(0000) GS:ffff888196e75000(0000) knlGS:0000000000000000 [ 1.295239] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1.295480] CR2: 0000000000000000 CR3: 0000000102adc004 CR4: 0000000000772ef0 [ 1.295897] Call Trace: [ 1.296134] seq_read_iter (fs/seq_file.c:231) [ 1.296341] seq_read (fs/seq_file.c:164) [ 1.296493] full_proxy_read (fs/debugfs/file.c:378 (discriminator 1)) [ 1.296658] vfs_read (fs/read_write.c:572) [ 1.296981] ksys_read (fs/read_write.c:717) [ 1.297132] do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1)) [ 1.297325] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Add a NULL check and print "(none)" for entries with no assigned slave.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31548

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: wifi: cfg80211: cancel pmsr_free_wk in cfg80211_pmsr_wdev_down When the nl80211 socket that originated a PMSR request is closed, cfg80211_release_pmsr() sets the request's nl_portid to zero and schedules pmsr_free_wk to process the abort asynchronously. If the interface is concurrently torn down before that work runs, cfg80211_pmsr_wdev_down() calls cfg80211_pmsr_process_abort() directly. However, the already- scheduled pmsr_free_wk work item remains pending and may run after the interface has been removed from the driver. This could cause the driver's abort_pmsr callback to operate on a torn-down interface, leading to undefined behavior and potential crashes. Cancel pmsr_free_wk synchronously in cfg80211_pmsr_wdev_down() before calling cfg80211_pmsr_process_abort(). This ensures any pending or in-progress work is drained before interface teardown proceeds, preventing the work from invoking the driver abort callback after the interface is gone.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31549

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: i2c: cp2615: fix serial string NULL-deref at probe The cp2615 driver uses the USB device serial string as the i2c adapter name but does not make sure that the string exists. Verify that the device has a serial number before accessing it to avoid triggering a NULL-pointer dereference (e.g. with malicious devices).

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31550

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: pmdomain: bcm: bcm2835-power: Increase ASB control timeout The bcm2835_asb_control() function uses a tight polling loop to wait for the ASB bridge to acknowledge a request. During intensive workloads, this handshake intermittently fails for V3D's master ASB on BCM2711, resulting in "Failed to disable ASB master for v3d" errors during runtime PM suspend. As a consequence, the failed power-off leaves V3D in a broken state, leading to bus faults or system hangs on later accesses. As the timeout is insufficient in some scenarios, increase the polling timeout from 1us to 5us, which is still negligible in the context of a power domain transition. Also, replace the open-coded ktime_get_ns()/ cpu_relax() polling loop with readl_poll_timeout_atomic().

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31551

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: Fix static_branch_dec() underflow for aql_disable. syzbot reported static_branch_dec() underflow in aql_enable_write(). [0] The problem is that aql_enable_write() does not serialise concurrent write()s to the debugfs. aql_enable_write() checks static_key_false(&aql_disable.key) and later calls static_branch_inc() or static_branch_dec(), but the state may change between the two calls. aql_disable does not need to track inc/dec. Let's use static_branch_enable() and static_branch_disable(). [0]: val == 0 WARNING: kernel/jump_label.c:311 at __static_key_slow_dec_cpuslocked.part.0+0x107/0x120 kernel/jump_label.c:311, CPU#0: syz.1.3155/20288 Modules linked in: CPU: 0 UID: 0 PID: 20288 Comm: syz.1.3155 Tainted: G U L syzkaller #0 PREEMPT(full) Tainted: [U]=USER, [L]=SOFTLOCKUP Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/24/2026 RIP: 0010:__static_key_slow_dec_cpuslocked.part.0+0x107/0x120 kernel/jump_label.c:311 Code: f2 c9 ff 5b 5d c3 cc cc cc cc e8 54 f2 c9 ff 48 89 df e8 ac f9 ff ff eb ad e8 45 f2 c9 ff 90 0f 0b 90 eb a2 e8 3a f2 c9 ff 90 <0f> 0b 90 eb 97 48 89 df e8 5c 4b 33 00 e9 36 ff ff ff 0f 1f 80 00 RSP: 0018:ffffc9000b9f7c10 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffffffff9b3e5d40 RCX: ffffffff823c57b4 RDX: ffff8880285a0000 RSI: ffffffff823c5846 RDI: ffff8880285a0000 RBP: 0000000000000000 R08: 0000000000000005 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 000000000000000a R13: 1ffff9200173ef88 R14: 0000000000000001 R15: ffffc9000b9f7e98 FS: 00007f530dd726c0(0000) GS:ffff8881245e3000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000200000001140 CR3: 000000007cc4a000 CR4: 00000000003526f0 Call Trace: __static_key_slow_dec_cpuslocked kernel/jump_label.c:297 [inline] __static_key_slow_dec kernel/jump_label.c:321 [inline] static_key_slow_dec+0x7c/0xc0 kernel/jump_label.c:336 aql_enable_write+0x2b2/0x310 net/mac80211/debugfs.c:343 short_proxy_write+0x133/0x1a0 fs/debugfs/file.c:383 vfs_write+0x2aa/0x1070 fs/read_write.c:684 ksys_pwrite64 fs/read_write.c:793 [inline] __do_sys_pwrite64 fs/read_write.c:801 [inline] __se_sys_pwrite64 fs/read_write.c:798 [inline] __x64_sys_pwrite64+0x1eb/0x250 fs/read_write.c:798 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xc9/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f530cf9aeb9 Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f530dd72028 EFLAGS: 00000246 ORIG_RAX: 0000000000000012 RAX: ffffffffffffffda RBX: 00007f530d215fa0 RCX: 00007f530cf9aeb9 RDX: 0000000000000003 RSI: 0000000000000000 RDI: 0000000000000010 RBP: 00007f530d008c1f R08: 0000000000000000 R09: 0000000000000000 R10: 4200000000000005 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f530d216038 R14: 00007f530d215fa0 R15: 00007ffde89fb978

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31552

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: wifi: wlcore: Return -ENOMEM instead of -EAGAIN if there is not enough headroom Since upstream commit e75665dd0968 ("wifi: wlcore: ensure skb headroom before skb_push"), wl1271_tx_allocate() and with it wl1271_prepare_tx_frame() returns -EAGAIN if pskb_expand_head() fails. However, in wlcore_tx_work_locked(), a return value of -EAGAIN from wl1271_prepare_tx_frame() is interpreted as the aggregation buffer being full. This causes the code to flush the buffer, put the skb back at the head of the queue, and immediately retry the same skb in a tight while loop. Because wlcore_tx_work_locked() holds wl->mutex, and the retry happens immediately with GFP_ATOMIC, this will result in an infinite loop and a CPU soft lockup. Return -ENOMEM instead so the packet is dropped and the loop terminates. The problem was found by an experimental code review agent based on gemini-3.1-pro while reviewing backports into v6.18.y.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31554

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: futex: Require sys_futex_requeue() to have identical flags Nicholas reported that his LLM found it was possible to create a UaF when sys_futex_requeue() is used with different flags. The initial motivation for allowing different flags was the variable sized futex, but since that hasn't been merged (yet), simply mandate the flags are identical, as is the case for the old style sys_futex() requeue operations.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31555

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: futex: Clear stale exiting pointer in futex_lock_pi() retry path Fuzzying/stressing futexes triggered: WARNING: kernel/futex/core.c:825 at wait_for_owner_exiting+0x7a/0x80, CPU#11: futex_lock_pi_s/524 When futex_lock_pi_atomic() sees the owner is exiting, it returns -EBUSY and stores a refcounted task pointer in 'exiting'. After wait_for_owner_exiting() consumes that reference, the local pointer is never reset to nil. Upon a retry, if futex_lock_pi_atomic() returns a different error, the bogus pointer is passed to wait_for_owner_exiting(). CPU0 CPU1 CPU2 futex_lock_pi(uaddr) // acquires the PI futex exit() futex_cleanup_begin() futex_state = EXITING; futex_lock_pi(uaddr) futex_lock_pi_atomic() attach_to_pi_owner() // observes EXITING exiting = owner; // takes ref return -EBUSY wait_for_owner_exiting(-EBUSY, owner) put_task_struct(); // drops ref // exiting still points to owner goto retry; futex_lock_pi_atomic() lock_pi_update_atomic() cmpxchg(uaddr) uaddr ^= WAITERS // whatever // value changed return -EAGAIN; wait_for_owner_exiting(-EAGAIN, exiting) // stale WARN_ON_ONCE(exiting) Fix this by resetting upon retry, essentially aligning it with requeue_pi.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31556

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xfs: scrub: unlock dquot before early return in quota scrub xchk_quota_item can return early after calling xchk_fblock_process_error. When that helper returns false, the function returned immediately without dropping dq->q_qlock, which can leave the dquot lock held and risk lock leaks or deadlocks in later quota operations. Fix this by unlocking dq->q_qlock before the early return.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31557

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: nvmet: move async event work off nvmet-wq For target nvmet_ctrl_free() flushes ctrl->async_event_work. If nvmet_ctrl_free() runs on nvmet-wq, the flush re-enters workqueue completion for the same worker:- A. Async event work queued on nvmet-wq (prior to disconnect): nvmet_execute_async_event() queue_work(nvmet_wq, &ctrl->async_event_work) nvmet_add_async_event() queue_work(nvmet_wq, &ctrl->async_event_work) B. Full pre-work chain (RDMA CM path): nvmet_rdma_cm_handler() nvmet_rdma_queue_disconnect() __nvmet_rdma_queue_disconnect() queue_work(nvmet_wq, &queue->release_work) process_one_work() lock((wq_completion)nvmet-wq) <--------- 1st nvmet_rdma_release_queue_work() C. Recursive path (same worker): nvmet_rdma_release_queue_work() nvmet_rdma_free_queue() nvmet_sq_destroy() nvmet_ctrl_put() nvmet_ctrl_free() flush_work(&ctrl->async_event_work) __flush_work() touch_wq_lockdep_map() lock((wq_completion)nvmet-wq) <--------- 2nd Lockdep splat: ============================================ WARNING: possible recursive locking detected 6.19.0-rc3nvme+ #14 Tainted: G N -------------------------------------------- kworker/u192:42/44933 is trying to acquire lock: ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: touch_wq_lockdep_map+0x26/0x90 but task is already holding lock: ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: process_one_work+0x53e/0x660 3 locks held by kworker/u192:42/44933: #0: ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: process_one_work+0x53e/0x660 #1: ffffc9000e6cbe28 ((work_completion)(&queue->release_work)){+.+.}-{0:0}, at: process_one_work+0x1c5/0x660 #2: ffffffff82d4db60 (rcu_read_lock){....}-{1:3}, at: __flush_work+0x62/0x530 Workqueue: nvmet-wq nvmet_rdma_release_queue_work [nvmet_rdma] Call Trace: __flush_work+0x268/0x530 nvmet_ctrl_free+0x140/0x310 [nvmet] nvmet_cq_put+0x74/0x90 [nvmet] nvmet_rdma_free_queue+0x23/0xe0 [nvmet_rdma] nvmet_rdma_release_queue_work+0x19/0x50 [nvmet_rdma] process_one_work+0x206/0x660 worker_thread+0x184/0x320 kthread+0x10c/0x240 ret_from_fork+0x319/0x390 Move async event work to a dedicated nvmet-aen-wq to avoid reentrant flush on nvmet-wq.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31558

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: LoongArch: KVM: Make kvm_get_vcpu_by_cpuid() more robust kvm_get_vcpu_by_cpuid() takes a cpuid parameter whose type is int, so cpuid can be negative. Let kvm_get_vcpu_by_cpuid() return NULL for this case so as to make it more robust. This fix an out-of-bounds access to kvm_arch::phyid_map::phys_map[].

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

References

CVE-2026-31559

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: LoongArch: Fix missing NULL checks for kstrdup() 1. Replace "of_find_node_by_path("/")" with "of_root" to avoid multiple calls to "of_node_put()". 2. Fix a potential kernel oops during early boot when memory allocation fails while parsing CPU model from device tree.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31561

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: x86/cpu: Remove X86_CR4_FRED from the CR4 pinned bits mask Commit in Fixes added the FRED CR4 bit to the CR4 pinned bits mask so that whenever something else modifies CR4, that bit remains set. Which in itself is a perfectly fine idea. However, there's an issue when during boot FRED is initialized: first on the BSP and later on the APs. Thus, there's a window in time when exceptions cannot be handled. This becomes particularly nasty when running as SEV-{ES,SNP} or TDX guests which, when they manage to trigger exceptions during that short window described above, triple fault due to FRED MSRs not being set up yet. See Link tag below for a much more detailed explanation of the situation. So, as a result, the commit in that Link URL tried to address this shortcoming by temporarily disabling CR4 pinning when an AP is not online yet. However, that is a problem in itself because in this case, an attack on the kernel needs to only modify the online bit - a single bit in RW memory - and then disable CR4 pinning and then disable SM*P, leading to more and worse things to happen to the system. So, instead, remove the FRED bit from the CR4 pinning mask, thus obviating the need to temporarily disable CR4 pinning. If someone manages to disable FRED when poking at CR4, then idt_invalidate() would make sure the system would crash'n'burn on the first exception triggered, which is a much better outcome security-wise.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31562

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/mediatek: dsi: Store driver data before invoking mipi_dsi_host_register The call to mipi_dsi_host_register triggers a callback to mtk_dsi_bind, which uses dev_get_drvdata to retrieve the mtk_dsi struct, so this structure needs to be stored inside the driver data before invoking it. As drvdata is currently uninitialized it leads to a crash when registering the DSI DRM encoder right after acquiring the mode_config.idr_mutex, blocking all subsequent DRM operations. Fixes the following crash during mediatek-drm probe (tested on Xiaomi Smart Clock x04g): Unable to handle kernel NULL pointer dereference at virtual address 0000000000000040 [...] Modules linked in: mediatek_drm(+) drm_display_helper cec drm_client_lib drm_dma_helper drm_kms_helper panel_simple [...] Call trace: drm_mode_object_add+0x58/0x98 (P) __drm_encoder_init+0x48/0x140 drm_encoder_init+0x6c/0xa0 drm_simple_encoder_init+0x20/0x34 [drm_kms_helper] mtk_dsi_bind+0x34/0x13c [mediatek_drm] component_bind_all+0x120/0x280 mtk_drm_bind+0x284/0x67c [mediatek_drm] try_to_bring_up_aggregate_device+0x23c/0x320 __component_add+0xa4/0x198 component_add+0x14/0x20 mtk_dsi_host_attach+0x78/0x100 [mediatek_drm] mipi_dsi_attach+0x2c/0x50 panel_simple_dsi_probe+0x4c/0x9c [panel_simple] mipi_dsi_drv_probe+0x1c/0x28 really_probe+0xc0/0x3dc __driver_probe_device+0x80/0x160 driver_probe_device+0x40/0x120 __device_attach_driver+0xbc/0x17c bus_for_each_drv+0x88/0xf0 __device_attach+0x9c/0x1cc device_initial_probe+0x54/0x60 bus_probe_device+0x34/0xa0 device_add+0x5b0/0x800 mipi_dsi_device_register_full+0xdc/0x16c mipi_dsi_host_register+0xc4/0x17c mtk_dsi_probe+0x10c/0x260 [mediatek_drm] platform_probe+0x5c/0xa4 really_probe+0xc0/0x3dc __driver_probe_device+0x80/0x160 driver_probe_device+0x40/0x120 __driver_attach+0xc8/0x1f8 bus_for_each_dev+0x7c/0xe0 driver_attach+0x24/0x30 bus_add_driver+0x11c/0x240 driver_register+0x68/0x130 __platform_register_drivers+0x64/0x160 mtk_drm_init+0x24/0x1000 [mediatek_drm] do_one_initcall+0x60/0x1d0 do_init_module+0x54/0x240 load_module+0x1838/0x1dc0 init_module_from_file+0xd8/0xf0 __arm64_sys_finit_module+0x1b4/0x428 invoke_syscall.constprop.0+0x48/0xc8 do_el0_svc+0x3c/0xb8 el0_svc+0x34/0xe8 el0t_64_sync_handler+0xa0/0xe4 el0t_64_sync+0x198/0x19c Code: 52800022 941004ab 2a0003f3 37f80040 (29005a80)

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31563

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: net: macb: Use dev_consume_skb_any() to free TX SKBs The napi_consume_skb() function is not intended to be called in an IRQ disabled context. However, after commit 6bc8a5098bf4 ("net: macb: Fix tx_ptr_lock locking"), the freeing of TX SKBs is performed with IRQs disabled. To resolve the following call trace, use dev_consume_skb_any() for freeing TX SKBs: WARNING: kernel/softirq.c:430 at __local_bh_enable_ip+0x174/0x188, CPU#0: ksoftirqd/0/15 Modules linked in: CPU: 0 UID: 0 PID: 15 Comm: ksoftirqd/0 Not tainted 7.0.0-rc4-next-20260319-yocto-standard-dirty #37 PREEMPT Hardware name: ZynqMP ZCU102 Rev1.1 (DT) pstate: 200000c5 (nzCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : __local_bh_enable_ip+0x174/0x188 lr : local_bh_enable+0x24/0x38 sp : ffff800082b3bb10 x29: ffff800082b3bb10 x28: ffff0008031f3c00 x27: 000000000011ede0 x26: ffff000800a7ff00 x25: ffff800083937ce8 x24: 0000000000017a80 x23: ffff000803243a78 x22: 0000000000000040 x21: 0000000000000000 x20: ffff000800394c80 x19: 0000000000000200 x18: 0000000000000001 x17: 0000000000000001 x16: ffff000803240000 x15: 0000000000000000 x14: ffffffffffffffff x13: 0000000000000028 x12: ffff000800395650 x11: ffff8000821d1528 x10: ffff800081c2bc08 x9 : ffff800081c1e258 x8 : 0000000100000301 x7 : ffff8000810426ec x6 : 0000000000000000 x5 : 0000000000000001 x4 : 0000000000000001 x3 : 0000000000000000 x2 : 0000000000000008 x1 : 0000000000000200 x0 : ffff8000810428dc Call trace: __local_bh_enable_ip+0x174/0x188 (P) local_bh_enable+0x24/0x38 skb_attempt_defer_free+0x190/0x1d8 napi_consume_skb+0x58/0x108 macb_tx_poll+0x1a4/0x558 __napi_poll+0x50/0x198 net_rx_action+0x1f4/0x3d8 handle_softirqs+0x16c/0x560 run_ksoftirqd+0x44/0x80 smpboot_thread_fn+0x1d8/0x338 kthread+0x120/0x150 ret_from_fork+0x10/0x20 irq event stamp: 29751 hardirqs last enabled at (29750): [] _raw_spin_unlock_irqrestore+0x44/0x88 hardirqs last disabled at (29751): [] _raw_spin_lock_irqsave+0x38/0x98 softirqs last enabled at (29150): [] handle_softirqs+0x504/0x560 softirqs last disabled at (29153): [] run_ksoftirqd+0x44/0x80

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31565

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: RDMA/irdma: Fix deadlock during netdev reset with active connections Resolve deadlock that occurs when user executes netdev reset while RDMA applications (e.g., rping) are active. The netdev reset causes ice driver to remove irdma auxiliary driver, triggering device_delete and subsequent client removal. During client removal, uverbs_client waits for QP reference count to reach zero while cma_client holds the final reference, creating circular dependency and indefinite wait in iWARP mode. Skip QP reference count wait during device reset to prevent deadlock.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31566

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix fence put before wait in amdgpu_amdkfd_submit_ib amdgpu_amdkfd_submit_ib() submits a GPU job and gets a fence from amdgpu_ib_schedule(). This fence is used to wait for job completion. Currently, the code drops the fence reference using dma_fence_put() before calling dma_fence_wait(). If dma_fence_put() releases the last reference, the fence may be freed before dma_fence_wait() is called. This can lead to a use-after-free. Fix this by waiting on the fence first and releasing the reference only after dma_fence_wait() completes. Fixes the below: drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c:697 amdgpu_amdkfd_submit_ib() warn: passing freed memory 'f' (line 696) (cherry picked from commit 8b9e5259adc385b61a6590a13b82ae0ac2bd3482)

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31567

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: PM: sleep: Drop spurious WARN_ON() from pm_restore_gfp_mask() Commit 35e4a69b2003f ("PM: sleep: Allow pm_restrict_gfp_mask() stacking") introduced refcount-based GFP mask management that warns when pm_restore_gfp_mask() is called with saved_gfp_count == 0. Some hibernation paths call pm_restore_gfp_mask() defensively where the GFP mask may or may not be restricted depending on the execution path. For example, the uswsusp interface invokes it in SNAPSHOT_CREATE_IMAGE, SNAPSHOT_UNFREEZE, and snapshot_release(). Before the stacking change this was a silent no-op; it now triggers a spurious WARNING. Remove the WARN_ON() wrapper from the !saved_gfp_count check while retaining the check itself, so that defensive calls remain harmless without producing false warnings. [ rjw: Subject tweak ]

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31568

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: s390/mm: Add missing secure storage access fixups for donated memory There are special cases where secure storage access exceptions happen in a kernel context for pages that don't have the PG_arch_1 bit set. That bit is set for non-exported guest secure storage (memory) but is absent on storage donated to the Ultravisor since the kernel isn't allowed to export donated pages. Prior to this patch we would try to export the page by calling arch_make_folio_accessible() which would instantly return since the arch bit is absent signifying that the page was already exported and no further action is necessary. This leads to secure storage access exception loops which can never be resolved. With this patch we unconditionally try to export and if that fails we fixup.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31569

HIGH7.3

In the Linux kernel, the following vulnerability has been resolved: LoongArch: KVM: Handle the case that EIOINTC's coremap is empty EIOINTC's coremap in eiointc_update_sw_coremap() can be empty, currently we get a cpuid with -1 in this case, but we actually need 0 because it's similar as the case that cpuid >= 4. This fix an out-of-bounds access to kvm_arch::phyid_map::phys_map[].

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.3

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:H

References

CVE-2026-31570

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: can: gw: fix OOB heap access in cgw_csum_crc8_rel() cgw_csum_crc8_rel() correctly computes bounds-safe indices via calc_idx(): int from = calc_idx(crc8->from_idx, cf->len); int to = calc_idx(crc8->to_idx, cf->len); int res = calc_idx(crc8->result_idx, cf->len); if (from < 0 || to < 0 || res < 0) return; However, the loop and the result write then use the raw s8 fields directly instead of the computed variables: for (i = crc8->from_idx; ...) /* BUG: raw negative index / cf->data[crc8->result_idx] = ...; / BUG: raw negative index */ With from_idx = to_idx = result_idx = -64 on a 64-byte CAN FD frame, calc_idx(-64, 64) = 0 so the guard passes, but the loop iterates with i = -64, reading cf->data[-64], and the write goes to cf->data[-64]. This write might end up to 56 (7.0-rc) or 40 (<= 6.19) bytes before the start of the canfd_frame on the heap. The companion function cgw_csum_xor_rel() uses `from`/`to`/`res` correctly throughout; fix cgw_csum_crc8_rel() to match. Confirmed with KASAN on linux-7.0-rc2: BUG: KASAN: slab-out-of-bounds in cgw_csum_crc8_rel+0x515/0x5b0 Read of size 1 at addr ffff8880076619c8 by task poc_cgw_oob/62 To configure the can-gw crc8 checksums CAP_NET_ADMIN is needed.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31571

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/i915: Unlink NV12 planes earlier unlink_nv12_plane() will clobber parts of the plane state potentially already set up by plane_atomic_check(), so we must make sure not to call the two in the wrong order. The problem happens when a plane previously selected as a Y plane is now configured as a normal plane by user space. plane_atomic_check() will first compute the proper plane state based on the userspace request, and unlink_nv12_plane() later clears some of the state. This used to work on account of unlink_nv12_plane() skipping the state clearing based on the plane visibility. But I removed that check, thinking it was an impossible situation. Now when that situation happens unlink_nv12_plane() will just WARN and proceed to clobber the state. Rather than reverting to the old way of doing things, I think it's more clear if we unlink the NV12 planes before we even compute the new plane state. (cherry picked from commit 017ecd04985573eeeb0745fa2c23896fb22ee0cc)

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31572

MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: i2c: designware: amdisp: Fix resume-probe race condition issue Identified resume-probe race condition in kernel v7.0 with the commit 38fa29b01a6a ("i2c: designware: Combine the init functions"),but this issue existed from the beginning though not detected. The amdisp i2c device requires ISP to be in power-on state for probe to succeed. To meet this requirement, this device is added to genpd to control ISP power using runtime PM. The pm_runtime_get_sync() called before i2c_dw_probe() triggers PM resume, which powers on ISP and also invokes the amdisp i2c runtime resume before the probe completes resulting in this race condition and a NULL dereferencing issue in v7.0 Fix this race condition by using the genpd APIs directly during probe: - Call dev_pm_genpd_resume() to Power ON ISP before probe - Call dev_pm_genpd_suspend() to Power OFF ISP after probe - Set the device to suspended state with pm_runtime_set_suspended() - Enable runtime PM only after the device is fully initialized

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 4.7

CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31575

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mm/userfaultfd: fix hugetlb fault mutex hash calculation In mfill_atomic_hugetlb(), linear_page_index() is used to calculate the page index for hugetlb_fault_mutex_hash(). However, linear_page_index() returns the index in PAGE_SIZE units, while hugetlb_fault_mutex_hash() expects the index in huge page units. This mismatch means that different addresses within the same huge page can produce different hash values, leading to the use of different mutexes for the same huge page. This can cause races between faulting threads, which can corrupt the reservation map and trigger the BUG_ON in resv_map_release(). Fix this by introducing hugetlb_linear_page_index(), which returns the page index in huge page granularity, and using it in place of linear_page_index().

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31576

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: media: hackrf: fix to not free memory after the device is registered in hackrf_probe() In hackrf driver, the following race condition occurs: ``` CPU0 CPU1 hackrf_probe() kzalloc(); // alloc hackrf_dev .... v4l2_device_register(); .... fd = sys_open("/path/to/dev"); // open hackrf fd .... v4l2_device_unregister(); .... kfree(); // free hackrf_dev .... sys_ioctl(fd, ...); v4l2_ioctl(); video_is_registered() // UAF!! .... sys_close(fd); v4l2_release() // UAF!! hackrf_video_release() kfree(); // DFB!! ``` When a V4L2 or video device is unregistered, the device node is removed so new open() calls are blocked. However, file descriptors that are already open-and any in-flight I/O-do not terminate immediately; they remain valid until the last reference is dropped and the driver's release() is invoked. Therefore, freeing device memory on the error path after hackrf_probe() has registered dev it will lead to a race to use-after-free vuln, since those already-open handles haven't been released yet. And since release() free memory too, race to use-after-free and double-free vuln occur. To prevent this, if device is registered from probe(), it should be modified to free memory only through release() rather than calling kfree() directly.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31577

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: nilfs2: fix NULL i_assoc_inode dereference in nilfs_mdt_save_to_shadow_map The DAT inode's btree node cache (i_assoc_inode) is initialized lazily during btree operations. However, nilfs_mdt_save_to_shadow_map() assumes i_assoc_inode is already initialized when copying dirty pages to the shadow map during GC. If NILFS_IOCTL_CLEAN_SEGMENTS is called immediately after mount before any btree operation has occurred on the DAT inode, i_assoc_inode is NULL leading to a general protection fault. Fix this by calling nilfs_attach_btree_node_cache() on the DAT inode in nilfs_dat_read() at mount time, ensuring i_assoc_inode is always initialized before any GC operation can use it.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31578

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: media: as102: fix to not free memory after the device is registered in as102_usb_probe() In as102_usb driver, the following race condition occurs: ``` CPU0 CPU1 as102_usb_probe() kzalloc(); // alloc as102_dev_t .... usb_register_dev(); fd = sys_open("/path/to/dev"); // open as102 fd .... usb_deregister_dev(); .... kfree(); // free as102_dev_t .... sys_close(fd); as102_release() // UAF!! as102_usb_release() kfree(); // DFB!! ``` When a USB character device registered with usb_register_dev() is later unregistered (via usb_deregister_dev() or disconnect), the device node is removed so new open() calls fail. However, file descriptors that are already open do not go away immediately: they remain valid until the last reference is dropped and the driver's .release() is invoked. In as102, as102_usb_probe() calls usb_register_dev() and then, on an error path, does usb_deregister_dev() and frees as102_dev_t right away. If userspace raced a successful open() before the deregistration, that open FD will later hit as102_release() --> as102_usb_release() and access or free as102_dev_t again, occur a race to use-after-free and double-free vuln. The fix is to never kfree(as102_dev_t) directly once usb_register_dev() has succeeded. After deregistration, defer freeing memory to .release(). In other words, let release() perform the last kfree when the final open FD is closed.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31579

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wireguard: device: use exit_rtnl callback instead of manual rtnl_lock in pre_exit wg_netns_pre_exit() manually acquires rtnl_lock() inside the pernet .pre_exit callback. This causes a hung task when another thread holds rtnl_mutex - the cleanup_net workqueue (or the setup_net failure rollback path) blocks indefinitely in wg_netns_pre_exit() waiting to acquire the lock. Convert to .exit_rtnl, introduced in commit 7a60d91c690b ("net: Add ->exit_rtnl() hook to struct pernet_operations."), where the framework already holds RTNL and batches all callbacks under a single rtnl_lock()/rtnl_unlock() pair, eliminating the contention window. The rcu_assign_pointer(wg->creating_net, NULL) is safe to move from .pre_exit to .exit_rtnl (which runs after synchronize_rcu()) because all RCU readers of creating_net either use maybe_get_net() - which returns NULL for a dying namespace with zero refcount - or access net->user_ns which remains valid throughout the entire ops_undo_list sequence. [ Jason: added __net_exit and __read_mostly annotations that were missing. ]

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31580

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bcache: fix cached_dev.sb_bio use-after-free and crash In our production environment, we have received multiple crash reports regarding libceph, which have caught our attention: ``` [6888366.280350] Call Trace: [6888366.280452] blk_update_request+0x14e/0x370 [6888366.280561] blk_mq_end_request+0x1a/0x130 [6888366.280671] rbd_img_handle_request+0x1a0/0x1b0 [rbd] [6888366.280792] rbd_obj_handle_request+0x32/0x40 [rbd] [6888366.280903] __complete_request+0x22/0x70 [libceph] [6888366.281032] osd_dispatch+0x15e/0xb40 [libceph] [6888366.281164] ? inet_recvmsg+0x5b/0xd0 [6888366.281272] ? ceph_tcp_recvmsg+0x6f/0xa0 [libceph] [6888366.281405] ceph_con_process_message+0x79/0x140 [libceph] [6888366.281534] ceph_con_v1_try_read+0x5d7/0xf30 [libceph] [6888366.281661] ceph_con_workfn+0x329/0x680 [libceph] ``` After analyzing the coredump file, we found that the address of dc->sb_bio has been freed. We know that cached_dev is only freed when it is stopped. Since sb_bio is a part of struct cached_dev, rather than an alloc every time. If the device is stopped while writing to the superblock, the released address will be accessed at endio. This patch hopes to wait for sb_write to complete in cached_dev_free. It should be noted that we analyzed the cause of the problem, then tell all details to the QWEN and adopted the modifications it made.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31581

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ALSA: 6fire: fix use-after-free on disconnect In usb6fire_chip_abort(), the chip struct is allocated as the card's private data (via snd_card_new with sizeof(struct sfire_chip)). When snd_card_free_when_closed() is called and no file handles are open, the card and embedded chip are freed synchronously. The subsequent chip->card = NULL write then hits freed slab memory. Call trace: usb6fire_chip_abort sound/usb/6fire/chip.c:59 [inline] usb6fire_chip_disconnect+0x348/0x358 sound/usb/6fire/chip.c:182 usb_unbind_interface+0x1a8/0x88c drivers/usb/core/driver.c:458 ... hub_event+0x1a04/0x4518 drivers/usb/core/hub.c:5953 Fix by moving the card lifecycle out of usb6fire_chip_abort() and into usb6fire_chip_disconnect(). The card pointer is saved in a local before any teardown, snd_card_disconnect() is called first to prevent new opens, URBs are aborted while chip is still valid, and snd_card_free_when_closed() is called last so chip is never accessed after the card may be freed.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31582

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: hwmon: (powerz) Fix use-after-free on USB disconnect After powerz_disconnect() frees the URB and releases the mutex, a subsequent powerz_read() call can acquire the mutex and call powerz_read_data(), which dereferences the freed URB pointer. Fix by: - Setting priv->urb to NULL in powerz_disconnect() so that powerz_read_data() can detect the disconnected state. - Adding a !priv->urb check at the start of powerz_read_data() to return -ENODEV on a disconnected device. - Moving usb_set_intfdata() before hwmon registration so the disconnect handler can always find the priv pointer.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31583

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: media: em28xx: fix use-after-free in em28xx_v4l2_open() em28xx_v4l2_open() reads dev->v4l2 without holding dev->lock, creating a race with em28xx_v4l2_init()'s error path and em28xx_v4l2_fini(), both of which free the em28xx_v4l2 struct and set dev->v4l2 to NULL under dev->lock. This race leads to two issues: - use-after-free in v4l2_fh_init() when accessing vdev->ctrl_handler, since the video_device is embedded in the freed em28xx_v4l2 struct. - NULL pointer dereference in em28xx_resolution_set() when accessing v4l2->norm, since dev->v4l2 has been set to NULL. Fix this by moving the mutex_lock() before the dev->v4l2 read and adding a NULL check for dev->v4l2 under the lock.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31584

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: media: mediatek: vcodec: fix use-after-free in encoder release path The fops_vcodec_release() function frees the context structure (ctx) without first cancelling any pending or running work in ctx->encode_work. This creates a race window where the workqueue handler (mtk_venc_worker) may still be accessing the context memory after it has been freed. Race condition: CPU 0 (release path) CPU 1 (workqueue) --------------------- ------------------ fops_vcodec_release() v4l2_m2m_ctx_release() v4l2_m2m_cancel_job() // waits for m2m job "done" mtk_venc_worker() v4l2_m2m_job_finish() // m2m job "done" // BUT worker still running! // post-job_finish access: other ctx dereferences // UAF if ctx already freed // returns (job "done") kfree(ctx) // ctx freed Root cause: The v4l2_m2m_ctx_release() only waits for the m2m job lifecycle (via TRANS_RUNNING flag), not the workqueue lifecycle. After v4l2_m2m_job_finish() is called, the m2m framework considers the job complete and v4l2_m2m_ctx_release() returns, but the worker function continues executing and may still access ctx. The work is queued during encode operations via: queue_work(ctx->dev->encode_workqueue, &ctx->encode_work) The worker function accesses ctx->m2m_ctx, ctx->dev, and other ctx fields even after calling v4l2_m2m_job_finish(). This vulnerability was confirmed with KASAN by running an instrumented test module that widens the post-job_finish race window. KASAN detected: BUG: KASAN: slab-use-after-free in mtk_venc_worker+0x159/0x180 Read of size 4 at addr ffff88800326e000 by task kworker/u8:0/12 Workqueue: mtk_vcodec_enc_wq mtk_venc_worker Allocated by task 47: __kasan_kmalloc+0x7f/0x90 fops_vcodec_open+0x85/0x1a0 Freed by task 47: __kasan_slab_free+0x43/0x70 kfree+0xee/0x3a0 fops_vcodec_release+0xb7/0x190 Fix this by calling cancel_work_sync(&ctx->encode_work) before kfree(ctx). This ensures the workqueue handler is both cancelled (if pending) and synchronized (waits for any running handler to complete) before the context is freed. Placement rationale: The fix is placed after v4l2_ctrl_handler_free() and before list_del_init(&ctx->list). At this point, all m2m operations are done (v4l2_m2m_ctx_release() has returned), and we need to ensure the workqueue is synchronized before removing ctx from the list and freeing it. Note: The open error path does NOT need cancel_work_sync() because INIT_WORK() only initializes the work structure - it does not schedule it. Work is only scheduled later during device_run() operations.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31585

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: media: vidtv: fix nfeeds state corruption on start_streaming failure syzbot reported a memory leak in vidtv_psi_service_desc_init [1]. When vidtv_start_streaming() fails inside vidtv_start_feed(), the nfeeds counter is left incremented even though no feed was actually started. This corrupts the driver state: subsequent start_feed calls see nfeeds > 1 and skip starting the mux, while stop_feed calls eventually try to stop a non-existent stream. This state corruption can also lead to memory leaks, since the mux and channel resources may be partially allocated during a failed start_streaming but never cleaned up, as the stop path finds dvb->streaming == false and returns early. Fix by decrementing nfeeds back when start_streaming fails, keeping the counter in sync with the actual number of active feeds. [1] BUG: memory leak unreferenced object 0xffff888145b50820 (size 32): comm "syz.0.17", pid 6068, jiffies 4294944486 backtrace (crc 90a0c7d4): vidtv_psi_service_desc_init+0x74/0x1b0 drivers/media/test-drivers/vidtv/vidtv_psi.c:288 vidtv_channel_s302m_init+0xb1/0x2a0 drivers/media/test-drivers/vidtv/vidtv_channel.c:83 vidtv_channels_init+0x1b/0x40 drivers/media/test-drivers/vidtv/vidtv_channel.c:524 vidtv_mux_init+0x516/0xbe0 drivers/media/test-drivers/vidtv/vidtv_mux.c:518 vidtv_start_streaming drivers/media/test-drivers/vidtv/vidtv_bridge.c:194 [inline] vidtv_start_feed+0x33e/0x4d0 drivers/media/test-drivers/vidtv/vidtv_bridge.c:239

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31586

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: mm: blk-cgroup: fix use-after-free in cgwb_release_workfn() cgwb_release_workfn() calls css_put(wb->blkcg_css) and then later accesses wb->blkcg_css again via blkcg_unpin_online(). If css_put() drops the last reference, the blkcg can be freed asynchronously (css_free_rwork_fn -> blkcg_css_free -> kfree) before blkcg_unpin_online() dereferences the pointer to access blkcg->online_pin, resulting in a use-after-free: BUG: KASAN: slab-use-after-free in blkcg_unpin_online (./include/linux/instrumented.h:112 ./include/linux/atomic/atomic-instrumented.h:400 ./include/linux/refcount.h:389 ./include/linux/refcount.h:432 ./include/linux/refcount.h:450 block/blk-cgroup.c:1367) Write of size 4 at addr ff11000117aa6160 by task kworker/71:1/531 Workqueue: cgwb_release cgwb_release_workfn Call Trace: blkcg_unpin_online (./include/linux/instrumented.h:112 ./include/linux/atomic/atomic-instrumented.h:400 ./include/linux/refcount.h:389 ./include/linux/refcount.h:432 ./include/linux/refcount.h:450 block/blk-cgroup.c:1367) cgwb_release_workfn (mm/backing-dev.c:629) process_scheduled_works (kernel/workqueue.c:3278 kernel/workqueue.c:3385) Freed by task 1016: kfree (./include/linux/kasan.h:235 mm/slub.c:2689 mm/slub.c:6246 mm/slub.c:6561) css_free_rwork_fn (kernel/cgroup/cgroup.c:5542) process_scheduled_works (kernel/workqueue.c:3302 kernel/workqueue.c:3385) ** Stack based on commit 66672af7a095 ("Add linux-next specific files for 20260410") I am seeing this crash sporadically in Meta fleet across multiple kernel versions. A full reproducer is available at: https://github.com/leitao/debug/blob/main/reproducers/repro_blkcg_uaf.sh (The race window is narrow. To make it easily reproducible, inject a msleep(100) between css_put() and blkcg_unpin_online() in cgwb_release_workfn(). With that delay and a KASAN-enabled kernel, the reproducer triggers the splat reliably in less than a second.) Fix this by moving blkcg_unpin_online() before css_put(), so the cgwb's CSS reference keeps the blkcg alive while blkcg_unpin_online() accesses it.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31587

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ASoC: qcom: q6apm: move component registration to unmanaged version q6apm component registers dais dynamically from ASoC toplology, which are allocated using device managed version apis. Allocating both component and dynamic dais using managed version could lead to incorrect free ordering, dai will be freed while component still holding references to it. Fix this issue by moving component to unmanged version so that the dai pointers are only freeded after the component is removed. ================================================================== BUG: KASAN: slab-use-after-free in snd_soc_del_component_unlocked+0x3d4/0x400 [snd_soc_core] Read of size 8 at addr ffff00084493a6e8 by task kworker/u48:0/3426 Tainted: [W]=WARN Hardware name: LENOVO 21N2ZC5PUS/21N2ZC5PUS, BIOS N42ET57W (1.31 ) 08/08/2024 Workqueue: pdr_notifier_wq pdr_notifier_work [pdr_interface] Call trace: show_stack+0x28/0x7c (C) dump_stack_lvl+0x60/0x80 print_report+0x160/0x4b4 kasan_report+0xac/0xfc __asan_report_load8_noabort+0x20/0x34 snd_soc_del_component_unlocked+0x3d4/0x400 [snd_soc_core] snd_soc_unregister_component_by_driver+0x50/0x88 [snd_soc_core] devm_component_release+0x30/0x5c [snd_soc_core] devres_release_all+0x13c/0x210 device_unbind_cleanup+0x20/0x190 device_release_driver_internal+0x350/0x468 device_release_driver+0x18/0x30 bus_remove_device+0x1a0/0x35c device_del+0x314/0x7f0 device_unregister+0x20/0xbc apr_remove_device+0x5c/0x7c [apr] device_for_each_child+0xd8/0x160 apr_pd_status+0x7c/0xa8 [apr] pdr_notifier_work+0x114/0x240 [pdr_interface] process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20 Allocated by task 77: kasan_save_stack+0x40/0x68 kasan_save_track+0x20/0x40 kasan_save_alloc_info+0x44/0x58 __kasan_kmalloc+0xbc/0xdc __kmalloc_node_track_caller_noprof+0x1f4/0x620 devm_kmalloc+0x7c/0x1c8 snd_soc_register_dai+0x50/0x4f0 [snd_soc_core] soc_tplg_pcm_elems_load+0x55c/0x1eb8 [snd_soc_core] snd_soc_tplg_component_load+0x4f8/0xb60 [snd_soc_core] audioreach_tplg_init+0x124/0x1fc [snd_q6apm] q6apm_audio_probe+0x10/0x1c [snd_q6apm] snd_soc_component_probe+0x5c/0x118 [snd_soc_core] soc_probe_component+0x44c/0xaf0 [snd_soc_core] snd_soc_bind_card+0xad0/0x2370 [snd_soc_core] snd_soc_register_card+0x3b0/0x4c0 [snd_soc_core] devm_snd_soc_register_card+0x50/0xc8 [snd_soc_core] x1e80100_platform_probe+0x208/0x368 [snd_soc_x1e80100] platform_probe+0xc0/0x188 really_probe+0x188/0x804 __driver_probe_device+0x158/0x358 driver_probe_device+0x60/0x190 __device_attach_driver+0x16c/0x2a8 bus_for_each_drv+0x100/0x194 __device_attach+0x174/0x380 device_initial_probe+0x14/0x20 bus_probe_device+0x124/0x154 deferred_probe_work_func+0x140/0x220 process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20 Freed by task 3426: kasan_save_stack+0x40/0x68 kasan_save_track+0x20/0x40 __kasan_save_free_info+0x4c/0x80 __kasan_slab_free+0x78/0xa0 kfree+0x100/0x4a4 devres_release_all+0x144/0x210 device_unbind_cleanup+0x20/0x190 device_release_driver_internal+0x350/0x468 device_release_driver+0x18/0x30 bus_remove_device+0x1a0/0x35c device_del+0x314/0x7f0 device_unregister+0x20/0xbc apr_remove_device+0x5c/0x7c [apr] device_for_each_child+0xd8/0x160 apr_pd_status+0x7c/0xa8 [apr] pdr_notifier_work+0x114/0x240 [pdr_interface] process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31588

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: KVM: x86: Use scratch field in MMIO fragment to hold small write values When exiting to userspace to service an emulated MMIO write, copy the to-be-written value to a scratch field in the MMIO fragment if the size of the data payload is 8 bytes or less, i.e. can fit in a single chunk, instead of pointing the fragment directly at the source value. This fixes a class of use-after-free bugs that occur when the emulator initiates a write using an on-stack, local variable as the source, the write splits a page boundary, and both pages are MMIO pages. Because KVM's ABI only allows for physically contiguous MMIO requests, accesses that split MMIO pages are separated into two fragments, and are sent to userspace one at a time. When KVM attempts to complete userspace MMIO in response to KVM_RUN after the first fragment, KVM will detect the second fragment and generate a second userspace exit, and reference the on-stack variable. The issue is most visible if the second KVM_RUN is performed by a separate task, in which case the stack of the initiating task can show up as truly freed data. ================================================================== BUG: KASAN: use-after-free in complete_emulated_mmio+0x305/0x420 Read of size 1 at addr ffff888009c378d1 by task syz-executor417/984 CPU: 1 PID: 984 Comm: syz-executor417 Not tainted 5.10.0-182.0.0.95.h2627.eulerosv2r13.x86_64 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack+0xbe/0xfd print_address_description.constprop.0+0x19/0x170 __kasan_report.cold+0x6c/0x84 kasan_report+0x3a/0x50 check_memory_region+0xfd/0x1f0 memcpy+0x20/0x60 complete_emulated_mmio+0x305/0x420 kvm_arch_vcpu_ioctl_run+0x63f/0x6d0 kvm_vcpu_ioctl+0x413/0xb20 __se_sys_ioctl+0x111/0x160 do_syscall_64+0x30/0x40 entry_SYSCALL_64_after_hwframe+0x67/0xd1 RIP: 0033:0x42477d Code: <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007faa8e6890e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00000000004d7338 RCX: 000000000042477d RDX: 0000000000000000 RSI: 000000000000ae80 RDI: 0000000000000005 RBP: 00000000004d7330 R08: 00007fff28d546df R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000004d733c R13: 0000000000000000 R14: 000000000040a200 R15: 00007fff28d54720 The buggy address belongs to the page: page:0000000029f6a428 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x9c37 flags: 0xfffffc0000000(node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc0000000 0000000000000000 ffffea0000270dc8 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888009c37780: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888009c37800: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff >ffff888009c37880: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ^ ffff888009c37900: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888009c37980: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ================================================================== The bug can also be reproduced with a targeted KVM-Unit-Test by hacking KVM to fill a large on-stack variable in complete_emulated_mmio(), i.e. by overwrite the data value with garbage. Limit the use of the scratch fields to 8-byte or smaller accesses, and to just writes, as larger accesses and reads are not affected thanks to implementation details in the emulator, but add a sanity check to ensure those details don't change in the future. Specifically, KVM never uses on-stack variables for accesses larger that 8 bytes, e.g. uses an operand in the emulator context, and *al ---truncated---

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

References

CVE-2026-31590

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Drop WARN on large size for KVM_MEMORY_ENCRYPT_REG_REGION Drop the WARN in sev_pin_memory() on npages overflowing an int, as the WARN is comically trivially to trigger from userspace, e.g. by doing: struct kvm_enc_region range = { .addr = 0, .size = -1ul, }; __vm_ioctl(vm, KVM_MEMORY_ENCRYPT_REG_REGION, &range); Note, the checks in sev_mem_enc_register_region() that presumably exist to verify the incoming address+size are completely worthless, as both "addr" and "size" are u64s and SEV is 64-bit only, i.e. they _can't_ be greater than ULONG_MAX. That wart will be cleaned up in the near future. if (range->addr > ULONG_MAX || range->size > ULONG_MAX) return -EINVAL; Opportunistically add a comment to explain why the code calculates the number of pages the "hard" way, e.g. instead of just shifting @ulen.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31591

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Lock all vCPUs when synchronzing VMSAs for SNP launch finish Lock all vCPUs when synchronizing and encrypting VMSAs for SNP guests, as allowing userspace to manipulate and/or run a vCPU while its state is being synchronized would at best corrupt vCPU state, and at worst crash the host kernel. Opportunistically assert that vcpu->mutex is held when synchronizing its VMSA (the SEV-ES path already locks vCPUs).

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31592

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Protect all of sev_mem_enc_register_region() with kvm->lock Take and hold kvm->lock for before checking sev_guest() in sev_mem_enc_register_region(), as sev_guest() isn't stable unless kvm->lock is held (or KVM can guarantee KVM_SEV_INIT{2} has completed and can't rollack state). If KVM_SEV_INIT{2} fails, KVM can end up trying to add to a not-yet-initialized sev->regions_list, e.g. triggering a #GP Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 110 UID: 0 PID: 72717 Comm: syz.15.11462 Tainted: G U W O 6.16.0-smp-DEV #1 NONE Tainted: [U]=USER, [W]=WARN, [O]=OOT_MODULE Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 12.52.0-0 10/28/2024 RIP: 0010:sev_mem_enc_register_region+0x3f0/0x4f0 ../include/linux/list.h:83 Code: <41> 80 3c 04 00 74 08 4c 89 ff e8 f1 c7 a2 00 49 39 ed 0f 84 c6 00 RSP: 0018:ffff88838647fbb8 EFLAGS: 00010256 RAX: dffffc0000000000 RBX: 1ffff92015cf1e0b RCX: dffffc0000000000 RDX: 0000000000000000 RSI: 0000000000001000 RDI: ffff888367870000 RBP: ffffc900ae78f050 R08: ffffea000d9e0007 R09: 1ffffd4001b3c000 R10: dffffc0000000000 R11: fffff94001b3c001 R12: 0000000000000000 R13: ffff8982ab0bde00 R14: ffffc900ae78f058 R15: 0000000000000000 FS: 00007f34e9dc66c0(0000) GS:ffff89ee64d33000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe180adef98 CR3: 000000047210e000 CR4: 0000000000350ef0 Call Trace: kvm_arch_vm_ioctl+0xa72/0x1240 ../arch/x86/kvm/x86.c:7371 kvm_vm_ioctl+0x649/0x990 ../virt/kvm/kvm_main.c:5363 __se_sys_ioctl+0x101/0x170 ../fs/ioctl.c:51 do_syscall_x64 ../arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x6f/0x1f0 ../arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f34e9f7e9a9 Code: <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f34e9dc6038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007f34ea1a6080 RCX: 00007f34e9f7e9a9 RDX: 0000200000000280 RSI: 000000008010aebb RDI: 0000000000000007 RBP: 00007f34ea000d69 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00007f34ea1a6080 R15: 00007ffce77197a8 with a syzlang reproducer that looks like: syz_kvm_add_vcpu$x86(0x0, &(0x7f0000000040)={0x0, &(0x7f0000000180)=ANY=[], 0x70}) (async) syz_kvm_add_vcpu$x86(0x0, &(0x7f0000000080)={0x0, &(0x7f0000000180)=ANY=[@ANYBLOB="..."], 0x4f}) (async) r0 = openat$kvm(0xffffffffffffff9c, &(0x7f0000000200), 0x0, 0x0) r1 = ioctl$KVM_CREATE_VM(r0, 0xae01, 0x0) r2 = openat$kvm(0xffffffffffffff9c, &(0x7f0000000240), 0x0, 0x0) r3 = ioctl$KVM_CREATE_VM(r2, 0xae01, 0x0) ioctl$KVM_SET_CLOCK(r3, 0xc008aeba, &(0x7f0000000040)={0x1, 0x8, 0x0, 0x5625e9b0}) (async) ioctl$KVM_SET_PIT2(r3, 0x8010aebb, &(0x7f0000000280)={[...], 0x5}) (async) ioctl$KVM_SET_PIT2(r1, 0x4070aea0, 0x0) (async) r4 = ioctl$KVM_CREATE_VM(0xffffffffffffffff, 0xae01, 0x0) openat$kvm(0xffffffffffffff9c, 0x0, 0x0, 0x0) (async) ioctl$KVM_SET_USER_MEMORY_REGION(r4, 0x4020ae46, &(0x7f0000000400)={0x0, 0x0, 0x0, 0x2000, &(0x7f0000001000/0x2000)=nil}) (async) r5 = ioctl$KVM_CREATE_VCPU(r4, 0xae41, 0x2) close(r0) (async) openat$kvm(0xffffffffffffff9c, &(0x7f0000000000), 0x8000, 0x0) (async) ioctl$KVM_SET_GUEST_DEBUG(r5, 0x4048ae9b, &(0x7f0000000300)={0x4376ea830d46549b, 0x0, [0x46, 0x0, 0x0, 0x0, 0x0, 0x1000]}) (async) ioctl$KVM_RUN(r5, 0xae80, 0x0) Opportunistically use guard() to avoid having to define a new error label and goto usage.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31593

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Reject attempts to sync VMSA of an already-launched/encrypted vCPU Reject synchronizing vCPU state to its associated VMSA if the vCPU has already been launched, i.e. if the VMSA has already been encrypted. On a host with SNP enabled, accessing guest-private memory generates an RMP #PF and panics the host. BUG: unable to handle page fault for address: ff1276cbfdf36000 #PF: supervisor write access in kernel mode #PF: error_code(0x80000003) - RMP violation PGD 5a31801067 P4D 5a31802067 PUD 40ccfb5063 PMD 40e5954063 PTE 80000040fdf36163 SEV-SNP: PFN 0x40fdf36, RMP entry: [0x6010fffffffff001 - 0x000000000000001f] Oops: Oops: 0003 [#1] SMP NOPTI CPU: 33 UID: 0 PID: 996180 Comm: qemu-system-x86 Tainted: G OE Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Hardware name: Dell Inc. PowerEdge R7625/0H1TJT, BIOS 1.5.8 07/21/2023 RIP: 0010:sev_es_sync_vmsa+0x54/0x4c0 [kvm_amd] Call Trace: snp_launch_update_vmsa+0x19d/0x290 [kvm_amd] snp_launch_finish+0xb6/0x380 [kvm_amd] sev_mem_enc_ioctl+0x14e/0x720 [kvm_amd] kvm_arch_vm_ioctl+0x837/0xcf0 [kvm] kvm_vm_ioctl+0x3fd/0xcc0 [kvm] __x64_sys_ioctl+0xa3/0x100 x64_sys_call+0xfe0/0x2350 do_syscall_64+0x81/0x10f0 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7ffff673287d Note, the KVM flaw has been present since commit ad73109ae7ec ("KVM: SVM: Provide support to launch and run an SEV-ES guest"), but has only been actively dangerous for the host since SNP support was added. With SEV-ES, KVM would "just" clobber guest state, which is totally fine from a host kernel perspective since userspace can clobber guest state any time before sev_launch_update_vmsa().

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31594

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-vntb: Remove duplicate resource teardown epf_ntb_epc_destroy() duplicates the teardown that the caller is supposed to perform later. This leads to an oops when .allow_link fails or when .drop_link is performed. The following is an example oops of the former case: Unable to handle kernel paging request at virtual address dead000000000108 [...] [dead000000000108] address between user and kernel address ranges Internal error: Oops: 0000000096000044 [#1] SMP [...] Call trace: pci_epc_remove_epf+0x78/0xe0 (P) pci_primary_epc_epf_link+0x88/0xa8 configfs_symlink+0x1f4/0x5a0 vfs_symlink+0x134/0x1d8 do_symlinkat+0x88/0x138 __arm64_sys_symlinkat+0x74/0xe0 [...] Remove the helper, and drop pci_epc_put(). EPC device refcounting is tied to the configfs EPC group lifetime, and pci_epc_put() in the .drop_link path is sufficient.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31595

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-vntb: Stop cmd_handler work in epf_ntb_epc_cleanup Disable the delayed work before clearing BAR mappings and doorbells to avoid running the handler after resources have been torn down. Unable to handle kernel paging request at virtual address ffff800083f46004 [...] Internal error: Oops: 0000000096000007 [#1] SMP [...] Call trace: epf_ntb_cmd_handler+0x54/0x200 [pci_epf_vntb] (P) process_one_work+0x154/0x3b0 worker_thread+0x2c8/0x400 kthread+0x148/0x210 ret_from_fork+0x10/0x20

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31596

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ocfs2: handle invalid dinode in ocfs2_group_extend [BUG] kernel BUG at fs/ocfs2/resize.c:308! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI RIP: 0010:ocfs2_group_extend+0x10aa/0x1ae0 fs/ocfs2/resize.c:308 Code: 8b8520ff ffff83f8 860f8580 030000e8 5cc3c1fe Call Trace: ... ocfs2_ioctl+0x175/0x6e0 fs/ocfs2/ioctl.c:869 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl fs/ioctl.c:583 [inline] __x64_sys_ioctl+0x197/0x1e0 fs/ioctl.c:583 x64_sys_call+0x1144/0x26a0 arch/x86/include/generated/asm/syscalls_64.h:17 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x93/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e ... [CAUSE] ocfs2_group_extend() assumes that the global bitmap inode block returned from ocfs2_inode_lock() has already been validated and BUG_ONs when the signature is not a dinode. That assumption is too strong for crafted filesystems because the JBD2-managed buffer path can bypass structural validation and return an invalid dinode to the resize ioctl. [FIX] Validate the dinode explicitly in ocfs2_group_extend(). If the global bitmap buffer does not contain a valid dinode, report filesystem corruption with ocfs2_error() and fail the resize operation instead of crashing the kernel.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31597

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ocfs2: fix use-after-free in ocfs2_fault() when VM_FAULT_RETRY filemap_fault() may drop the mmap_lock before returning VM_FAULT_RETRY, as documented in mm/filemap.c: "If our return value has VM_FAULT_RETRY set, it's because the mmap_lock may be dropped before doing I/O or by lock_folio_maybe_drop_mmap()." When this happens, a concurrent munmap() can call remove_vma() and free the vm_area_struct via RCU. The saved 'vma' pointer in ocfs2_fault() then becomes a dangling pointer, and the subsequent trace_ocfs2_fault() call dereferences it -- a use-after-free. Fix this by saving ip_blkno as a plain integer before calling filemap_fault(), and removing vma from the trace event. Since ip_blkno is copied by value before the lock can be dropped, it remains valid regardless of what happens to the vma or inode afterward.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31598

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: ocfs2: fix possible deadlock between unlink and dio_end_io_write ocfs2_unlink takes orphan dir inode_lock first and then ip_alloc_sem, while in ocfs2_dio_end_io_write, it acquires these locks in reverse order. This creates an ABBA lock ordering violation on lock classes ocfs2_sysfile_lock_key[ORPHAN_DIR_SYSTEM_INODE] and ocfs2_file_ip_alloc_sem_key. Lock Chain #0 (orphan dir inode_lock -> ip_alloc_sem): ocfs2_unlink ocfs2_prepare_orphan_dir ocfs2_lookup_lock_orphan_dir inode_lock(orphan_dir_inode) <- lock A __ocfs2_prepare_orphan_dir ocfs2_prepare_dir_for_insert ocfs2_extend_dir ocfs2_expand_inline_dir down_write(&oi->ip_alloc_sem) <- Lock B Lock Chain #1 (ip_alloc_sem -> orphan dir inode_lock): ocfs2_dio_end_io_write down_write(&oi->ip_alloc_sem) <- Lock B ocfs2_del_inode_from_orphan() inode_lock(orphan_dir_inode) <- Lock A Deadlock Scenario: CPU0 (unlink) CPU1 (dio_end_io_write) ------ ------ inode_lock(orphan_dir_inode) down_write(ip_alloc_sem) down_write(ip_alloc_sem) inode_lock(orphan_dir_inode) Since ip_alloc_sem is to protect allocation changes, which is unrelated with operations in ocfs2_del_inode_from_orphan. So move ocfs2_del_inode_from_orphan out of ip_alloc_sem to fix the deadlock.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31599

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: media: vidtv: fix NULL pointer dereference in vidtv_channel_pmt_match_sections syzbot reported a general protection fault in vidtv_psi_desc_assign [1]. vidtv_psi_pmt_stream_init() can return NULL on memory allocation failure, but vidtv_channel_pmt_match_sections() does not check for this. When tail is NULL, the subsequent call to vidtv_psi_desc_assign(&tail->descriptor, desc) dereferences a NULL pointer offset, causing a general protection fault. Add a NULL check after vidtv_psi_pmt_stream_init(). On failure, clean up the already-allocated stream chain and return. [1] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:vidtv_psi_desc_assign+0x24/0x90 drivers/media/test-drivers/vidtv/vidtv_psi.c:629 Call Trace: vidtv_channel_pmt_match_sections drivers/media/test-drivers/vidtv/vidtv_channel.c:349 [inline] vidtv_channel_si_init+0x1445/0x1a50 drivers/media/test-drivers/vidtv/vidtv_channel.c:479 vidtv_mux_init+0x526/0xbe0 drivers/media/test-drivers/vidtv/vidtv_mux.c:519 vidtv_start_streaming drivers/media/test-drivers/vidtv/vidtv_bridge.c:194 [inline] vidtv_start_feed+0x33e/0x4d0 drivers/media/test-drivers/vidtv/vidtv_bridge.c:239

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31600

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: arm64: mm: Handle invalid large leaf mappings correctly It has been possible for a long time to mark ptes in the linear map as invalid. This is done for secretmem, kfence, realm dma memory un/share, and others, by simply clearing the PTE_VALID bit. But until commit a166563e7ec37 ("arm64: mm: support large block mapping when rodata=full") large leaf mappings were never made invalid in this way. It turns out various parts of the code base are not equipped to handle invalid large leaf mappings (in the way they are currently encoded) and I've observed a kernel panic while booting a realm guest on a BBML2_NOABORT system as a result: [ 15.432706] software IO TLB: Memory encryption is active and system is using DMA bounce buffers [ 15.476896] Unable to handle kernel paging request at virtual address ffff000019600000 [ 15.513762] Mem abort info: [ 15.527245] ESR = 0x0000000096000046 [ 15.548553] EC = 0x25: DABT (current EL), IL = 32 bits [ 15.572146] SET = 0, FnV = 0 [ 15.592141] EA = 0, S1PTW = 0 [ 15.612694] FSC = 0x06: level 2 translation fault [ 15.640644] Data abort info: [ 15.661983] ISV = 0, ISS = 0x00000046, ISS2 = 0x00000000 [ 15.694875] CM = 0, WnR = 1, TnD = 0, TagAccess = 0 [ 15.723740] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 15.755776] swapper pgtable: 4k pages, 48-bit VAs, pgdp=0000000081f3f000 [ 15.800410] [ffff000019600000] pgd=0000000000000000, p4d=180000009ffff403, pud=180000009fffe403, pmd=00e8000199600704 [ 15.855046] Internal error: Oops: 0000000096000046 [#1] SMP [ 15.886394] Modules linked in: [ 15.900029] CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 7.0.0-rc4-dirty #4 PREEMPT [ 15.935258] Hardware name: linux,dummy-virt (DT) [ 15.955612] pstate: 21400005 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) [ 15.986009] pc : __pi_memcpy_generic+0x128/0x22c [ 16.006163] lr : swiotlb_bounce+0xf4/0x158 [ 16.024145] sp : ffff80008000b8f0 [ 16.038896] x29: ffff80008000b8f0 x28: 0000000000000000 x27: 0000000000000000 [ 16.069953] x26: ffffb3976d261ba8 x25: 0000000000000000 x24: ffff000019600000 [ 16.100876] x23: 0000000000000001 x22: ffff0000043430d0 x21: 0000000000007ff0 [ 16.131946] x20: 0000000084570010 x19: 0000000000000000 x18: ffff00001ffe3fcc [ 16.163073] x17: 0000000000000000 x16: 00000000003fffff x15: 646e612065766974 [ 16.194131] x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 [ 16.225059] x11: 0000000000000000 x10: 0000000000000010 x9 : 0000000000000018 [ 16.256113] x8 : 0000000000000018 x7 : 0000000000000000 x6 : 0000000000000000 [ 16.287203] x5 : ffff000019607ff0 x4 : ffff000004578000 x3 : ffff000019600000 [ 16.318145] x2 : 0000000000007ff0 x1 : ffff000004570010 x0 : ffff000019600000 [ 16.349071] Call trace: [ 16.360143] __pi_memcpy_generic+0x128/0x22c (P) [ 16.380310] swiotlb_tbl_map_single+0x154/0x2b4 [ 16.400282] swiotlb_map+0x5c/0x228 [ 16.415984] dma_map_phys+0x244/0x2b8 [ 16.432199] dma_map_page_attrs+0x44/0x58 [ 16.449782] virtqueue_map_page_attrs+0x38/0x44 [ 16.469596] virtqueue_map_single_attrs+0xc0/0x130 [ 16.490509] virtnet_rq_alloc.isra.0+0xa4/0x1fc [ 16.510355] try_fill_recv+0x2a4/0x584 [ 16.526989] virtnet_open+0xd4/0x238 [ 16.542775] __dev_open+0x110/0x24c [ 16.558280] __dev_change_flags+0x194/0x20c [ 16.576879] netif_change_flags+0x24/0x6c [ 16.594489] dev_change_flags+0x48/0x7c [ 16.611462] ip_auto_config+0x258/0x1114 [ 16.628727] do_one_initcall+0x80/0x1c8 [ 16.645590] kernel_init_freeable+0x208/0x2f0 [ 16.664917] kernel_init+0x24/0x1e0 [ 16.680295] ret_from_fork+0x10/0x20 [ 16.696369] Code: 927cec03 cb0e0021 8b0e0042 a9411c26 (a900340c) [ 16.723106] ---[ end trace 0000000000000000 ]--- [ 16.752866] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b [ 16.792556] Kernel Offset: 0x3396ea200000 from 0xffff8000800000 ---truncated---

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31602

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ALSA: ctxfi: Limit PTP to a single page Commit 391e69143d0a increased CT_PTP_NUM from 1 to 4 to support 256 playback streams, but the additional pages are not used by the card correctly. The CT20K2 hardware already has multiple VMEM_PTPAL registers, but using them separately would require refactoring the entire virtual memory allocation logic. ct_vm_map() always uses PTEs in vm->ptp[0].area regardless of CT_PTP_NUM. On AMD64 systems, a single PTP covers 512 PTEs (2M). When aggregate memory allocations exceed this limit, ct_vm_map() tries to access beyond the allocated space and causes a page fault: BUG: unable to handle page fault for address: ffffd4ae8a10a000 Oops: Oops: 0002 [#1] SMP PTI RIP: 0010:ct_vm_map+0x17c/0x280 [snd_ctxfi] Call Trace: atc_pcm_playback_prepare+0x225/0x3b0 ct_pcm_playback_prepare+0x38/0x60 snd_pcm_do_prepare+0x2f/0x50 snd_pcm_action_single+0x36/0x90 snd_pcm_action_nonatomic+0xbf/0xd0 snd_pcm_ioctl+0x28/0x40 __x64_sys_ioctl+0x97/0xe0 do_syscall_64+0x81/0x610 entry_SYSCALL_64_after_hwframe+0x76/0x7e Revert CT_PTP_NUM to 1. The 256 SRC_RESOURCE_NUM and playback_count remain unchanged.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31603

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: staging: sm750fb: fix division by zero in ps_to_hz() ps_to_hz() is called from hw_sm750_crtc_set_mode() without validating that pixclock is non-zero. A zero pixclock passed via FBIOPUT_VSCREENINFO causes a division by zero. Fix by rejecting zero pixclock in lynxfb_ops_check_var(), consistent with other framebuffer drivers.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31604

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: fix device leak on probe failure Driver core holds a reference to the USB interface and its parent USB device while the interface is bound to a driver and there is no need to take additional references unless the structures are needed after disconnect. This driver takes a reference to the USB device during probe but does not to release it on all probe errors (e.g. when descriptor parsing fails). Drop the redundant device reference to fix the leak, reduce cargo culting, make it easier to spot drivers where an extra reference is needed, and reduce the risk of further memory leaks.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31605

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: fbdev: udlfb: avoid divide-by-zero on FBIOPUT_VSCREENINFO Much like commit 19f953e74356 ("fbdev: fb_pm2fb: Avoid potential divide by zero error"), we also need to prevent that same crash from happening in the udlfb driver as it uses pixclock directly when dividing, which will crash.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31606

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_hid: don't call cdev_init while cdev in use When calling unbind, then bind again, cdev_init reinitialized the cdev, even though there may still be references to it. That's the case when the /dev/hidg* device is still opened. This obviously unsafe behavior like oopes. This fixes this by using cdev_alloc to put the cdev on the heap. That way, we can simply allocate a new one in hidg_bind.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31607

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: usbip: validate number_of_packets in usbip_pack_ret_submit() When a USB/IP client receives a RET_SUBMIT response, usbip_pack_ret_submit() unconditionally overwrites urb->number_of_packets from the network PDU. This value is subsequently used as the loop bound in usbip_recv_iso() and usbip_pad_iso() to iterate over urb->iso_frame_desc[], a flexible array whose size was fixed at URB allocation time based on the original number_of_packets from the CMD_SUBMIT. A malicious USB/IP server can set number_of_packets in the response to a value larger than what was originally submitted, causing a heap out-of-bounds write when usbip_recv_iso() writes to urb->iso_frame_desc[i] beyond the allocated region. KASAN confirmed this with kernel 7.0.0-rc5: BUG: KASAN: slab-out-of-bounds in usbip_recv_iso+0x46a/0x640 Write of size 4 at addr ffff888106351d40 by task vhci_rx/69 The buggy address is located 0 bytes to the right of allocated 320-byte region [ffff888106351c00, ffff888106351d40) The server side (stub_rx.c) and gadget side (vudc_rx.c) already validate number_of_packets in the CMD_SUBMIT path since commits c6688ef9f297 ("usbip: fix stub_rx: harden CMD_SUBMIT path to handle malicious input") and b78d830f0049 ("usbip: fix vudc_rx: harden CMD_SUBMIT path to handle malicious input"). The server side validates against USBIP_MAX_ISO_PACKETS because no URB exists yet at that point. On the client side we have the original URB, so we can use the tighter bound: the response must not exceed the original number_of_packets. This mirrors the existing validation of actual_length against transfer_buffer_length in usbip_recv_xbuff(), which checks the response value against the original allocation size. Kelvin Mbogo's series ("usb: usbip: fix integer overflow in usbip_recv_iso()", v2) hardens the receive-side functions themselves; this patch complements that work by catching the bad value at its source -- in usbip_pack_ret_submit() before the overwrite -- and using the tighter per-URB allocation bound rather than the global USBIP_MAX_ISO_PACKETS limit. Fix this by checking rpdu->number_of_packets against urb->number_of_packets in usbip_pack_ret_submit() before the overwrite. On violation, clamp to zero so that usbip_recv_iso() and usbip_pad_iso() safely return early.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31608

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: smb: server: avoid double-free in smb_direct_free_sendmsg after smb_direct_flush_send_list() smb_direct_flush_send_list() already calls smb_direct_free_sendmsg(), so we should not call it again after post_sendmsg() moved it to the batch list.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31609

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: smb: client: avoid double-free in smbd_free_send_io() after smbd_send_batch_flush() smbd_send_batch_flush() already calls smbd_free_send_io(), so we should not call it again after smbd_post_send() moved it to the batch list.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31610

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix mechToken leak when SPNEGO decode fails after token alloc The kernel ASN.1 BER decoder calls action callbacks incrementally as it walks the input. When ksmbd_decode_negTokenInit() reaches the mechToken [2] OCTET STRING element, ksmbd_neg_token_alloc() allocates conn->mechToken immediately via kmemdup_nul(). If a later element in the same blob is malformed, then the decoder will return nonzero after the allocation is already live. This could happen if mechListMIC [3] overrunse the enclosing SEQUENCE. decode_negotiation_token() then sets conn->use_spnego = false because both the negTokenInit and negTokenTarg grammars failed. The cleanup at the bottom of smb2_sess_setup() is gated on use_spnego: if (conn->use_spnego && conn->mechToken) { kfree(conn->mechToken); conn->mechToken = NULL; } so the kfree is skipped, causing the mechToken to never be freed. This codepath is reachable pre-authentication, so untrusted clients can cause slow memory leaks on a server without even being properly authenticated. Fix this up by not checking check for use_spnego, as it's not required, so the memory will always be properly freed. At the same time, always free the memory in ksmbd_conn_free() incase some other failure path forgot to free it.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31611

HIGH8.6

In the Linux kernel, the following vulnerability has been resolved: ksmbd: require 3 sub-authorities before reading sub_auth[2] parse_dacl() compares each ACE SID against sid_unix_NFS_mode and on match reads sid.sub_auth[2] as the file mode. If sid_unix_NFS_mode is the prefix S-1-5-88-3 with num_subauth = 2 then compare_sids() compares only min(num_subauth, 2) sub-authorities so a client SID with num_subauth = 2 and sub_auth = {88, 3} will match. If num_subauth = 2 and the ACE is placed at the very end of the security descriptor, sub_auth[2] will be 4 bytes past end_of_acl. The out-of-band bytes will then be masked to the low 9 bits and applied as the file's POSIX mode, probably not something that is good to have happen. Fix this up by forcing the SID to actually carry a third sub-authority before reading it at all.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xHIGH 8.6

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H

References

CVE-2026-31612

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: ksmbd: validate EaNameLength in smb2_get_ea() smb2_get_ea() reads ea_req->EaNameLength from the client request and passes it directly to strncmp() as the comparison length without verifying that the length of the name really is the size of the input buffer received. Fix this up by properly checking the size of the name based on the value received and the overall size of the request, to prevent a later strncmp() call to use the length as a "trusted" size of the buffer. Without this check, uninitialized heap values might be slowly leaked to the client.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

References

CVE-2026-31613

HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: smb: client: fix OOB reads parsing symlink error response When a CREATE returns STATUS_STOPPED_ON_SYMLINK, smb2_check_message() returns success without any length validation, leaving the symlink parsers as the only defense against an untrusted server. symlink_data() walks SMB 3.1.1 error contexts with the loop test "p < end", but reads p->ErrorId at offset 4 and p->ErrorDataLength at offset 0. When the server-controlled ErrorDataLength advances p to within 1-7 bytes of end, the next iteration will read past it. When the matching context is found, sym->SymLinkErrorTag is read at offset 4 from p->ErrorContextData with no check that the symlink header itself fits. smb2_parse_symlink_response() then bounds-checks the substitute name using SMB2_SYMLINK_STRUCT_SIZE as the offset of PathBuffer from iov_base. That value is computed as sizeof(smb2_err_rsp) + sizeof(smb2_symlink_err_rsp), which is correct only when ErrorContextCount == 0. With at least one error context the symlink data sits 8 bytes deeper, and each skipped non-matching context shifts it further by 8 + ALIGN(ErrorDataLength, 8). The check is too short, allowing the substitute name read to run past iov_len. The out-of-bound heap bytes are UTF-16-decoded into the symlink target and returned to userspace via readlink(2). Fix this all up by making the loops test require the full context header to fit, rejecting sym if its header runs past end, and bound the substitute name against the actual position of sym->PathBuffer rather than a fixed offset. Because sub_offs and sub_len are 16bits, the pointer math will not overflow here with the new greater-than.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xHIGH 8.1

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:H

References

CVE-2026-31614

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: smb: client: fix off-by-8 bounds check in check_wsl_eas() The bounds check uses (u8 )ea + nlen + 1 + vlen as the end of the EA name and value, but ea_data sits at offset sizeof(struct smb2_file_full_ea_info) = 8 from ea, not at offset 0. The strncmp() later reads ea->ea_data[0..nlen-1] and the value bytes follow at ea_data[nlen+1..nlen+vlen], so the actual end is ea->ea_data + nlen + 1 + vlen. Isn't pointer math fun? The earlier check (u8 )ea > end - sizeof(*ea) only guarantees the 8-byte header is in bounds, but since the last EA is placed within 8 bytes of the end of the response, the name and value bytes are read past the end of iov. Fix this mess all up by using ea->ea_data as the base for the bounds check. An "untrusted" server can use this to leak up to 8 bytes of kernel heap into the EA name comparison and influence which WSL xattr the data is interpreted as.

Published: 2026-04-24Modified: 2026-04-29

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31615

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: renesas_usb3: validate endpoint index in standard request handlers The GET_STATUS and SET/CLEAR_FEATURE handlers extract the endpoint number from the host-supplied wIndex without any sort of validation. Fix this up by validating the number of endpoints actually match up with the number the device has before attempting to dereference a pointer based on this math. This is just like what was done in commit ee0d382feb44 ("usb: gadget: aspeed_udc: validate endpoint index for ast udc") for the aspeed driver.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31616

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_phonet: fix skb frags[] overflow in pn_rx_complete() A broken/bored/mean USB host can overflow the skb_shared_info->frags[] array on a Linux gadget exposing a Phonet function by sending an unbounded sequence of full-page OUT transfers. pn_rx_complete() finalizes the skb only when req->actual < req->length, where req->length is set to PAGE_SIZE by the gadget. If the host always sends exactly PAGE_SIZE bytes per transfer, fp->rx.skb will never be reset and each completion will add another fragment via skb_add_rx_frag(). Once nr_frags exceeds MAX_SKB_FRAGS (default 17), subsequent frag stores overwrite memory adjacent to the shinfo on the heap. Drop the skb and account a length error when the frag limit is reached, matching the fix applied in t7xx by commit f0813bcd2d9d ("net: wwan: t7xx: fix potential skb->frags overflow in RX path").

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31617

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_ncm: validate minimum block_len in ncm_unwrap_ntb() The block_len read from the host-supplied NTB header is checked against ntb_max but has no lower bound. When block_len is smaller than opts->ndp_size, the bounds check of: ndp_index > (block_len - opts->ndp_size) will underflow producing a huge unsigned value that ndp_index can never exceed, defeating the check entirely. The same underflow occurs in the datagram index checks against block_len - opts->dpe_size. With those checks neutered, a malicious USB host can choose ndp_index and datagram offsets that point past the actual transfer, and the skb_put_data() copies adjacent kernel memory into the network skb. Fix this by rejecting block lengths that cannot hold at least the NTB header plus one NDP. This will make block_len - opts->ndp_size and block_len - opts->dpe_size both well-defined. Commit 8d2b1a1ec9f5 ("CDC-NCM: avoid overflow in sanity checking") fixed a related class of issues on the host side of NCM.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31618

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: fbdev: tdfxfb: avoid divide-by-zero on FBIOPUT_VSCREENINFO Much like commit 19f953e74356 ("fbdev: fb_pm2fb: Avoid potential divide by zero error"), we also need to prevent that same crash from happening in the udlfb driver as it uses pixclock directly when dividing, which will crash.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31619

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ALSA: fireworks: bound device-supplied status before string array lookup The status field in an EFW response is a 32-bit value supplied by the firewire device. efr_status_names[] has 17 entries so a status value outside that range goes off into the weeds when looking at the %s value. Even worse, the status could return EFR_STATUS_INCOMPLETE which is 0x80000000, and is obviously not in that array of potential strings. Fix this up by properly bounding the index against the array size and printing "unknown" if it's not recognized.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31620

MEDIUM4.6

In the Linux kernel, the following vulnerability has been resolved: ALSA: usx2y: us144mkii: fix NULL deref on missing interface 0 A malicious USB device with the TASCAM US-144MKII device id can have a configuration containing bInterfaceNumber=1 but no interface 0. USB configuration descriptors are not required to assign interface numbers sequentially, so usb_ifnum_to_if(dev, 0) returns will NULL, which will then be dereferenced directly. Fix this up by checking the return value properly.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 4.6

CVSS:3.x/CVSS:3.1/AV:P/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31622

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: NFC: digital: Bounds check NFC-A cascade depth in SDD response handler The NFC-A anti-collision cascade in digital_in_recv_sdd_res() appends 3 or 4 bytes to target->nfcid1 on each round, but the number of cascade rounds is controlled entirely by the peer device. The peer sets the cascade tag in the SDD_RES (deciding 3 vs 4 bytes) and the cascade-incomplete bit in the SEL_RES (deciding whether another round follows). ISO 14443-3 limits NFC-A to three cascade levels and target->nfcid1 is sized accordingly (NFC_NFCID1_MAXSIZE = 10), but nothing in the driver actually enforces this. This means a malicious peer can keep the cascade running, writing past the heap-allocated nfc_target with each round. Fix this by rejecting the response when the accumulated UID would exceed the buffer. Commit e329e71013c9 ("NFC: nci: Bounds check struct nfc_target arrays") fixed similar missing checks against the same field on the NCI path.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31623

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: usb: cdc-phonet: fix skb frags[] overflow in rx_complete() A malicious USB device claiming to be a CDC Phonet modem can overflow the skb_shared_info->frags[] array by sending an unbounded sequence of full-page bulk transfers. Drop the skb and increment the length error when the frag limit is reached. This matches the same fix that commit f0813bcd2d9d ("net: wwan: t7xx: fix potential skb->frags overflow in RX path") did for the t7xx driver.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31624

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: HID: core: clamp report_size in s32ton() to avoid undefined shift s32ton() shifts by n-1 where n is the field's report_size, a value that comes directly from a HID device. The HID parser bounds report_size only to <= 256, so a broken HID device can supply a report descriptor with a wide field that triggers shift exponents up to 256 on a 32-bit type when an output report is built via hid_output_field() or hid_set_field(). Commit ec61b41918587 ("HID: core: fix shift-out-of-bounds in hid_report_raw_event") added the same n > 32 clamp to the function snto32(), but s32ton() was never given the same fix as I guess syzbot hadn't figured out how to fuzz a device the same way. Fix this up by just clamping the max value of n, just like snto32() does.

Published: 2026-04-24Modified: 2026-04-28

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31625

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: HID: alps: fix NULL pointer dereference in alps_raw_event() Commit ecfa6f34492c ("HID: Add HID_CLAIMED_INPUT guards in raw_event callbacks missing them") attempted to fix up the HID drivers that had missed the previous fix that was done in 2ff5baa9b527 ("HID: appleir: Fix potential NULL dereference at raw event handle"), but the alps driver was missed. Fix this up by properly checking in the hid-alps driver that it had been claimed correctly before attempting to process the raw event.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31626

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: staging: rtl8723bs: initialize le_tmp64 in rtw_BIP_verify() Initialize le_tmp64 to zero in rtw_BIP_verify() to prevent using uninitialized data. Smatch warns that only 6 bytes are copied to this 8-byte (u64) variable, leaving the last two bytes uninitialized: drivers/staging/rtl8723bs/core/rtw_security.c:1308 rtw_BIP_verify() warn: not copying enough bytes for '&le_tmp64' (8 vs 6 bytes) Initializing the variable at the start of the function fixes this warning and ensures predictable behavior.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:H

References

CVE-2026-31627

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: i2c: s3c24xx: check the size of the SMBUS message before using it The first byte of an i2c SMBUS message is the size, and it should be verified to ensure that it is in the range of 0..I2C_SMBUS_BLOCK_MAX before processing it. This is the same logic that was added in commit a6e04f05ce0b ("i2c: tegra: check msg length in SMBUS block read") to the i2c tegra driver.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31628

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: x86/CPU: Fix FPDSS on Zen1 Zen1's hardware divider can leave, under certain circumstances, partial results from previous operations. Those results can be leaked by another, attacker thread. Fix that with a chicken bit.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31629

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: nfc: llcp: add missing return after LLCP_CLOSED checks In nfc_llcp_recv_hdlc() and nfc_llcp_recv_disc(), when the socket state is LLCP_CLOSED, the code correctly calls release_sock() and nfc_llcp_sock_put() but fails to return. Execution falls through to the remainder of the function, which calls release_sock() and nfc_llcp_sock_put() again. This results in a double release_sock() and a refcount underflow via double nfc_llcp_sock_put(), leading to a use-after-free. Add the missing return statements after the LLCP_CLOSED branches in both functions to prevent the fall-through.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31630

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: rxrpc: proc: size address buffers for %pISpc output The AF_RXRPC procfs helpers format local and remote socket addresses into fixed 50-byte stack buffers with "%pISpc". That is too small for the longest current-tree IPv6-with-port form the formatter can produce. In lib/vsprintf.c, the compressed IPv6 path uses a dotted-quad tail not only for v4mapped addresses, but also for ISATAP addresses via ipv6_addr_is_isatap(). As a result, a case such as [ffff:ffff:ffff:ffff:0:5efe:255.255.255.255]:65535 is possible with the current formatter. That is 50 visible characters, so 51 bytes including the trailing NUL, which does not fit in the existing char[50] buffers used by net/rxrpc/proc.c. Size the buffers from the formatter's maximum textual form and switch the call sites to scnprintf(). Changes since v1: - correct the changelog to cite the actual maximum current-tree case explicitly - frame the proof around the ISATAP formatting path instead of the earlier mapped-v4 example

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31631

HIGH8.2

In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix buffer overread in rxgk_do_verify_authenticator() Fix rxgk_do_verify_authenticator() to check the buffer size before checking the nonce.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 8.2

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H

References

CVE-2026-31632

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix leak of rxgk context in rxgk_verify_response() Fix rxgk_verify_response() to clean up the rxgk context it creates.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31633

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix integer overflow in rxgk_verify_response() In rxgk_verify_response(), there's a potential integer overflow due to rounding up token_len before checking it, thereby allowing the length check to be bypassed. Fix this by checking the unrounded value against len too (len is limited as the response must fit in a single UDP packet).

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31634

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: rxrpc: fix reference count leak in rxrpc_server_keyring() This patch fixes a reference count leak in rxrpc_server_keyring() by checking if rx->securities is already set.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31635

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: rxrpc: fix oversized RESPONSE authenticator length check rxgk_verify_response() decodes auth_len from the packet and is supposed to verify that it fits in the remaining bytes. The existing check is inverted, so oversized RESPONSE authenticators are accepted and passed to rxgk_decrypt_skb(), which can later reach skb_to_sgvec() with an impossible length and hit BUG_ON(len). Decoded from the original latest-net reproduction logs with scripts/decode_stacktrace.sh: RIP: __skb_to_sgvec() [net/core/skbuff.c:5285 (discriminator 1)] Call Trace: skb_to_sgvec() [net/core/skbuff.c:5305] rxgk_decrypt_skb() [net/rxrpc/rxgk_common.h:81] rxgk_verify_response() [net/rxrpc/rxgk.c:1268] rxrpc_process_connection() [net/rxrpc/conn_event.c:266 net/rxrpc/conn_event.c:364 net/rxrpc/conn_event.c:386] process_one_work() [kernel/workqueue.c:3281] worker_thread() [kernel/workqueue.c:3353 kernel/workqueue.c:3440] kthread() [kernel/kthread.c:436] ret_from_fork() [arch/x86/kernel/process.c:164] Reject authenticator lengths that exceed the remaining packet payload.

Published: 2026-04-24Modified: 2026-05-18

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31636

CRITICAL9.1

In the Linux kernel, the following vulnerability has been resolved: rxrpc: fix RESPONSE authenticator parser OOB read rxgk_verify_authenticator() copies auth_len bytes into a temporary buffer and then passes p + auth_len as the parser limit to rxgk_do_verify_authenticator(). Since p is a __be32 *, that inflates the parser end pointer by a factor of four and lets malformed RESPONSE authenticators read past the kmalloc() buffer. Decoded from the original latest-net reproduction logs with scripts/decode_stacktrace.sh: BUG: KASAN: slab-out-of-bounds in rxgk_verify_response() Call Trace: dump_stack_lvl() [lib/dump_stack.c:123] print_report() [mm/kasan/report.c:379 mm/kasan/report.c:482] kasan_report() [mm/kasan/report.c:597] rxgk_verify_response() [net/rxrpc/rxgk.c:1103 net/rxrpc/rxgk.c:1167 net/rxrpc/rxgk.c:1274] rxrpc_process_connection() [net/rxrpc/conn_event.c:266 net/rxrpc/conn_event.c:364 net/rxrpc/conn_event.c:386] process_one_work() [kernel/workqueue.c:3281] worker_thread() [kernel/workqueue.c:3353 kernel/workqueue.c:3440] kthread() [kernel/kthread.c:436] ret_from_fork() [arch/x86/kernel/process.c:164] Allocated by task 54: rxgk_verify_response() [include/linux/slab.h:954 net/rxrpc/rxgk.c:1155 net/rxrpc/rxgk.c:1274] rxrpc_process_connection() [net/rxrpc/conn_event.c:266 net/rxrpc/conn_event.c:364 net/rxrpc/conn_event.c:386] Convert the byte count to __be32 units before constructing the parser limit.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xCRITICAL 9.1

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31637

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: rxrpc: reject undecryptable rxkad response tickets rxkad_decrypt_ticket() decrypts the RXKAD response ticket and then parses the buffer as plaintext without checking whether crypto_skcipher_decrypt() succeeded. A malformed RESPONSE can therefore use a non-block-aligned ticket length, make the decrypt operation fail, and still drive the ticket parser with attacker-controlled bytes. Check the decrypt result and abort the connection with RXKADBADTICKET when ticket decryption fails.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31638

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: rxrpc: Only put the call ref if one was acquired rxrpc_input_packet_on_conn() can process a to-client packet after the current client call on the channel has already been torn down. In that case chan->call is NULL, rxrpc_try_get_call() returns NULL and there is no reference to drop. The client-side implicit-end error path does not account for that and unconditionally calls rxrpc_put_call(). This turns a protocol error path into a kernel crash instead of rejecting the packet. Only drop the call reference if one was actually acquired. Keep the existing protocol error handling unchanged.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31639

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix key reference count leak from call->key When creating a client call in rxrpc_alloc_client_call(), the code obtains a reference to the key. This is never cleaned up and gets leaked when the call is destroyed. Fix this by freeing call->key in rxrpc_destroy_call(). Before the patch, it shows the key reference counter elevated: $ cat /proc/keys | grep afs@54321 1bffe9cd I--Q--i 8053480 4169w 3b010000 1000 1000 rxrpc afs@54321: ka $ After the patch, the invalidated key is removed when the code exits: $ cat /proc/keys | grep afs@54321 $

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31640

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix use of wrong skb when comparing queued RESP challenge serial In rxrpc_post_response(), the code should be comparing the challenge serial number from the cached response before deciding to switch to a newer response, but looks at the newer packet private data instead, rendering the comparison always false. Fix this by switching to look at the older packet. Fix further[1] to substitute the new packet in place of the old one if newer and also to release whichever we don't use.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31641

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix RxGK token loading to check bounds rxrpc_preparse_xdr_yfs_rxgk() reads the raw key length and ticket length from the XDR token as u32 values and passes each through round_up(x, 4) before using the rounded value for validation and allocation. When the raw length is >= 0xfffffffd, round_up() wraps to 0, so the bounds check and kzalloc both use 0 while the subsequent memcpy still copies the original ~4 GiB value, producing a heap buffer overflow reachable from an unprivileged add_key() call. Fix this by: (1) Rejecting raw key lengths above AFSTOKEN_GK_KEY_MAX and raw ticket lengths above AFSTOKEN_GK_TOKEN_MAX before rounding, consistent with the caps that the RxKAD path already enforces via AFSTOKEN_RK_TIX_MAX. (2) Sizing the flexible-array allocation from the validated raw key length via struct_size_t() instead of the rounded value. (3) Caching the raw lengths so that the later field assignments and memcpy calls do not re-read from the token, eliminating a class of TOCTOU re-parse. The control path (valid token with lengths within bounds) is unaffected.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31642

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix call removal to use RCU safe deletion Fix rxrpc call removal from the rxnet->calls list to use list_del_rcu() rather than list_del_init() to prevent stuffing up reading /proc/net/rxrpc/calls from potentially getting into an infinite loop. This, however, means that list_empty() no longer works on an entry that's been deleted from the list, making it harder to detect prior deletion. Fix this by: Firstly, make rxrpc_destroy_all_calls() only dump the first ten calls that are unexpectedly still on the list. Limiting the number of steps means there's no need to call cond_resched() or to remove calls from the list here, thereby eliminating the need for rxrpc_put_call() to check for that. rxrpc_put_call() can then be fixed to unconditionally delete the call from the list as it is the only place that the deletion occurs.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31643

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix key parsing memleak In rxrpc_preparse_xdr_yfs_rxgk(), the memory attached to token->rxgk can be leaked in a few error paths after it's allocated. Fix this by freeing it in the "reject_token:" case.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31644

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: lan966x: fix use-after-free and leak in lan966x_fdma_reload() When lan966x_fdma_reload() fails to allocate new RX buffers, the restore path restarts DMA using old descriptors whose pages were already freed via lan966x_fdma_rx_free_pages(). Since page_pool_put_full_page() can release pages back to the buddy allocator, the hardware may DMA into memory now owned by other kernel subsystems. Additionally, on the restore path, the newly created page pool (if allocation partially succeeded) is overwritten without being destroyed, leaking it. Fix both issues by deferring the release of old pages until after the new allocation succeeds. Save the old page array before the allocation so old pages can be freed on the success path. On the failure path, the old descriptors, pages and page pool are all still valid, making the restore safe. Also ensure the restore path re-enables NAPI and wakes the netdev, matching the success path.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31645

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: lan966x: fix page pool leak in error paths lan966x_fdma_rx_alloc() creates a page pool but does not destroy it if the subsequent fdma_alloc_coherent() call fails, leaking the pool. Similarly, lan966x_fdma_init() frees the coherent DMA memory when lan966x_fdma_tx_alloc() fails but does not destroy the page pool that was successfully created by lan966x_fdma_rx_alloc(), leaking it. Add the missing page_pool_destroy() calls in both error paths.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31646

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: lan966x: fix page_pool error handling in lan966x_fdma_rx_alloc_page_pool() page_pool_create() can return an ERR_PTR on failure. The return value is used unconditionally in the loop that follows, passing the error pointer through xdp_rxq_info_reg_mem_model() into page_pool_use_xdp_mem(), which dereferences it, causing a kernel oops. Add an IS_ERR check after page_pool_create() to return early on failure.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31647

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: idpf: fix PREEMPT_RT raw/bh spinlock nesting for async VC handling Switch from using the completion's raw spinlock to a local lock in the idpf_vc_xn struct. The conversion is safe because complete/_all() are called outside the lock and there is no reason to share the completion lock in the current logic. This avoids invalid wait context reported by the kernel due to the async handler taking BH spinlock: [ 805.726977] ============================= [ 805.726991] [ BUG: Invalid wait context ] [ 805.727006] 7.0.0-rc2-net-devq-031026+ #28 Tainted: G S OE [ 805.727026] ----------------------------- [ 805.727038] kworker/u261:0/572 is trying to lock: [ 805.727051] ff190da6a8dbb6a0 (&vport_config->mac_filter_list_lock){+...}-{3:3}, at: idpf_mac_filter_async_handler+0xe9/0x260 [idpf] [ 805.727099] other info that might help us debug this: [ 805.727111] context-{5:5} [ 805.727119] 3 locks held by kworker/u261:0/572: [ 805.727132] #0: ff190da6db3e6148 ((wq_completion)idpf-0000:83:00.0-mbx){+.+.}-{0:0}, at: process_one_work+0x4b5/0x730 [ 805.727163] #1: ff3c6f0a6131fe50 ((work_completion)(&(&adapter->mbx_task)->work)){+.+.}-{0:0}, at: process_one_work+0x1e5/0x730 [ 805.727191] #2: ff190da765190020 (&x->wait#34){+.+.}-{2:2}, at: idpf_recv_mb_msg+0xc8/0x710 [idpf] [ 805.727218] stack backtrace: ... [ 805.727238] Workqueue: idpf-0000:83:00.0-mbx idpf_mbx_task [idpf] [ 805.727247] Call Trace: [ 805.727249] [ 805.727251] dump_stack_lvl+0x77/0xb0 [ 805.727259] __lock_acquire+0xb3b/0x2290 [ 805.727268] ? __irq_work_queue_local+0x59/0x130 [ 805.727275] lock_acquire+0xc6/0x2f0 [ 805.727277] ? idpf_mac_filter_async_handler+0xe9/0x260 [idpf] [ 805.727284] ? _printk+0x5b/0x80 [ 805.727290] _raw_spin_lock_bh+0x38/0x50 [ 805.727298] ? idpf_mac_filter_async_handler+0xe9/0x260 [idpf] [ 805.727303] idpf_mac_filter_async_handler+0xe9/0x260 [idpf] [ 805.727310] idpf_recv_mb_msg+0x1c8/0x710 [idpf] [ 805.727317] process_one_work+0x226/0x730 [ 805.727322] worker_thread+0x19e/0x340 [ 805.727325] ? __pfx_worker_thread+0x10/0x10 [ 805.727328] kthread+0xf4/0x130 [ 805.727333] ? __pfx_kthread+0x10/0x10 [ 805.727336] ret_from_fork+0x32c/0x410 [ 805.727345] ? __pfx_kthread+0x10/0x10 [ 805.727347] ret_from_fork_asm+0x1a/0x30 [ 805.727354]

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31648

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: mm: filemap: fix nr_pages calculation overflow in filemap_map_pages() When running stress-ng on my Arm64 machine with v7.0-rc3 kernel, I encountered some very strange crash issues showing up as "Bad page state": " [ 734.496287] BUG: Bad page state in process stress-ng-env pfn:415735fb [ 734.496427] page: refcount:0 mapcount:1 mapping:0000000000000000 index:0x4cf316 pfn:0x415735fb [ 734.496434] flags: 0x57fffe000000800(owner_2|node=1|zone=2|lastcpupid=0x3ffff) [ 734.496439] raw: 057fffe000000800 0000000000000000 dead000000000122 0000000000000000 [ 734.496440] raw: 00000000004cf316 0000000000000000 0000000000000000 0000000000000000 [ 734.496442] page dumped because: nonzero mapcount " After analyzing this page’s state, it is hard to understand why the mapcount is not 0 while the refcount is 0, since this page is not where the issue first occurred. By enabling the CONFIG_DEBUG_VM config, I can reproduce the crash as well and captured the first warning where the issue appears: " [ 734.469226] page: refcount:33 mapcount:0 mapping:00000000bef2d187 index:0x81a0 pfn:0x415735c0 [ 734.469304] head: order:5 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [ 734.469315] memcg:ffff000807a8ec00 [ 734.469320] aops:ext4_da_aops ino:100b6f dentry name(?):"stress-ng-mmaptorture-9397-0-2736200540" [ 734.469335] flags: 0x57fffe400000069(locked|uptodate|lru|head|node=1|zone=2|lastcpupid=0x3ffff) ...... [ 734.469364] page dumped because: VM_WARN_ON_FOLIO((_Generic((page + nr_pages - 1), const struct page : (const struct folio )_compound_head(page + nr_pages - 1), struct page : (struct folio )_compound_head(page + nr_pages - 1))) != folio) [ 734.469390] ------------[ cut here ]------------ [ 734.469393] WARNING: ./include/linux/rmap.h:351 at folio_add_file_rmap_ptes+0x3b8/0x468, CPU#90: stress-ng-mlock/9430 [ 734.469551] folio_add_file_rmap_ptes+0x3b8/0x468 (P) [ 734.469555] set_pte_range+0xd8/0x2f8 [ 734.469566] filemap_map_folio_range+0x190/0x400 [ 734.469579] filemap_map_pages+0x348/0x638 [ 734.469583] do_fault_around+0x140/0x198 ...... [ 734.469640] el0t_64_sync+0x184/0x188 " The code that triggers the warning is: "VM_WARN_ON_FOLIO(page_folio(page + nr_pages - 1) != folio, folio)", which indicates that set_pte_range() tried to map beyond the large folio’s size. By adding more debug information, I found that 'nr_pages' had overflowed in filemap_map_pages(), causing set_pte_range() to establish mappings for a range exceeding the folio size, potentially corrupting fields of pages that do not belong to this folio (e.g., page->_mapcount). After above analysis, I think the possible race is as follows: CPU 0 CPU 1 filemap_map_pages() ext4_setattr() //get and lock folio with old inode->i_size next_uptodate_folio() ....... //shrink the inode->i_size i_size_write(inode, attr->ia_size); //calculate the end_pgoff with the new inode->i_size file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1; end_pgoff = min(end_pgoff, file_end); ...... //nr_pages can be overflowed, cause xas.xa_index > end_pgoff end = folio_next_index(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; ...... //map large folio filemap_map_folio_range() ...... //truncate folios truncate_pagecache(inode, inode->i_size); To fix this issue, move the 'end_pgoff' calculation before next_uptodate_folio(), so the retrieved folio stays consistent with the file end to avoid ---truncated---

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31649

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: net: stmmac: fix integer underflow in chain mode The jumbo_frm() chain-mode implementation unconditionally computes len = nopaged_len - bmax; where nopaged_len = skb_headlen(skb) (linear bytes only) and bmax is BUF_SIZE_8KiB or BUF_SIZE_2KiB. However, the caller stmmac_xmit() decides to invoke jumbo_frm() based on skb->len (total length including page fragments): is_jumbo = stmmac_is_jumbo_frm(priv, skb->len, enh_desc); When a packet has a small linear portion (nopaged_len <= bmax) but a large total length due to page fragments (skb->len > bmax), the subtraction wraps as an unsigned integer, producing a huge len value (~0xFFFFxxxx). This causes the while (len != 0) loop to execute hundreds of thousands of iterations, passing skb->data + bmax * i pointers far beyond the skb buffer to dma_map_single(). On IOMMU-less SoCs (the typical deployment for stmmac), this maps arbitrary kernel memory to the DMA engine, constituting a kernel memory disclosure and potential memory corruption from hardware. Fix this by introducing a buf_len local variable clamped to min(nopaged_len, bmax). Computing len = nopaged_len - buf_len is then always safe: it is zero when the linear portion fits within a single descriptor, causing the while (len != 0) loop to be skipped naturally, and the fragment loop in stmmac_xmit() handles page fragments afterward.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31650

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: mmc: vub300: fix use-after-free on disconnect The vub300 driver maintains an explicit reference count for the controller and its driver data and the last reference can in theory be dropped after the driver has been unbound. This specifically means that the controller allocation must not be device managed as that can lead to use-after-free. Note that the lifetime is currently also incorrectly tied the parent USB device rather than interface, which can lead to memory leaks if the driver is unbound without its device being physically disconnected (e.g. on probe deferral). Fix both issues by reverting to non-managed allocation of the controller.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31651

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mmc: vub300: fix NULL-deref on disconnect Make sure to deregister the controller before dropping the reference to the driver data on disconnect to avoid NULL-pointer dereferences or use-after-free.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31652

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: mm/damon/stat: deallocate damon_call() failure leaking damon_ctx damon_stat_start() always allocates the module's damon_ctx object (damon_stat_context). Meanwhile, if damon_call() in the function fails, the damon_ctx object is not deallocated. Hence, if the damon_call() is failed, and the user writes Y to “enabled” again, the previously allocated damon_ctx object is leaked. This cannot simply be fixed by deallocating the damon_ctx object when damon_call() fails. That's because damon_call() failure doesn't guarantee the kdamond main function, which accesses the damon_ctx object, is completely finished. In other words, if damon_stat_start() deallocates the damon_ctx object after damon_call() failure, the not-yet-terminated kdamond could access the freed memory (use-after-free). Fix the leak while avoiding the use-after-free by keeping returning damon_stat_start() without deallocating the damon_ctx object after damon_call() failure, but deallocating it when the function is invoked again and the kdamond is completely terminated. If the kdamond is not yet terminated, simply return -EAGAIN, as the kdamond will soon be terminated. The issue was discovered [1] by sashiko.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31653

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mm/damon/sysfs: dealloc repeat_call_control if damon_call() fails damon_call() for repeat_call_control of DAMON_SYSFS could fail if somehow the kdamond is stopped before the damon_call(). It could happen, for example, when te damon context was made for monitroing of a virtual address processes, and the process is terminated immediately, before the damon_call() invocation. In the case, the dyanmically allocated repeat_call_control is not deallocated and leaked. Fix the leak by deallocating the repeat_call_control under the damon_call() failure. This issue is discovered by sashiko [1].

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31655

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: pmdomain: imx8mp-blk-ctrl: Keep the NOC_HDCP clock enabled Keep the NOC_HDCP clock always enabled to fix the potential hang caused by the NoC ADB400 port power down handshake.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31656

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: drm/i915/gt: fix refcount underflow in intel_engine_park_heartbeat A use-after-free / refcount underflow is possible when the heartbeat worker and intel_engine_park_heartbeat() race to release the same engine->heartbeat.systole request. The heartbeat worker reads engine->heartbeat.systole and calls i915_request_put() on it when the request is complete, but clears the pointer in a separate, non-atomic step. Concurrently, a request retirement on another CPU can drop the engine wakeref to zero, triggering __engine_park() -> intel_engine_park_heartbeat(). If the heartbeat timer is pending at that point, cancel_delayed_work() returns true and intel_engine_park_heartbeat() reads the stale non-NULL systole pointer and calls i915_request_put() on it again, causing a refcount underflow: ``` <4> [487.221889] Workqueue: i915-unordered engine_retire [i915] <4> [487.222640] RIP: 0010:refcount_warn_saturate+0x68/0xb0 ... <4> [487.222707] Call Trace: <4> [487.222711] <4> [487.222716] intel_engine_park_heartbeat.part.0+0x6f/0x80 [i915] <4> [487.223115] intel_engine_park_heartbeat+0x25/0x40 [i915] <4> [487.223566] __engine_park+0xb9/0x650 [i915] <4> [487.223973] ____intel_wakeref_put_last+0x2e/0xb0 [i915] <4> [487.224408] __intel_wakeref_put_last+0x72/0x90 [i915] <4> [487.224797] intel_context_exit_engine+0x7c/0x80 [i915] <4> [487.225238] intel_context_exit+0xf1/0x1b0 [i915] <4> [487.225695] i915_request_retire.part.0+0x1b9/0x530 [i915] <4> [487.226178] i915_request_retire+0x1c/0x40 [i915] <4> [487.226625] engine_retire+0x122/0x180 [i915] <4> [487.227037] process_one_work+0x239/0x760 <4> [487.227060] worker_thread+0x200/0x3f0 <4> [487.227068] ? __pfx_worker_thread+0x10/0x10 <4> [487.227075] kthread+0x10d/0x150 <4> [487.227083] ? __pfx_kthread+0x10/0x10 <4> [487.227092] ret_from_fork+0x3d4/0x480 <4> [487.227099] ? __pfx_kthread+0x10/0x10 <4> [487.227107] ret_from_fork_asm+0x1a/0x30 <4> [487.227141] ``` Fix this by replacing the non-atomic pointer read + separate clear with xchg() in both racing paths. xchg() is a single indivisible hardware instruction that atomically reads the old pointer and writes NULL. This guarantees only one of the two concurrent callers obtains the non-NULL pointer and performs the put, the other gets NULL and skips it. (cherry picked from commit 13238dc0ee4f9ab8dafa2cca7295736191ae2f42)

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31657

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: batman-adv: hold claim backbone gateways by reference batadv_bla_add_claim() can replace claim->backbone_gw and drop the old gateway's last reference while readers still follow the pointer. The netlink claim dump path dereferences claim->backbone_gw->orig and takes claim->backbone_gw->crc_lock without pinning the underlying backbone gateway. batadv_bla_check_claim() still has the same naked pointer access pattern. Reuse batadv_bla_claim_get_backbone_gw() in both readers so they operate on a stable gateway reference until the read-side work is complete. This keeps the dump and claim-check paths aligned with the lifetime rules introduced for the other BLA claim readers.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31658

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: altera-tse: fix skb leak on DMA mapping error in tse_start_xmit() When dma_map_single() fails in tse_start_xmit(), the function returns NETDEV_TX_OK without freeing the skb. Since NETDEV_TX_OK tells the stack the packet was consumed, the skb is never freed, leaking memory on every DMA mapping failure. Add dev_kfree_skb_any() before returning to properly free the skb.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31659

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: batman-adv: reject oversized global TT response buffers batadv_tt_prepare_tvlv_global_data() builds the allocation length for a global TT response in 16-bit temporaries. When a remote originator advertises a large enough global TT, the TT payload length plus the VLAN header offset can exceed 65535 and wrap before kmalloc(). The full-table response path still uses the original TT payload length when it fills tt_change, so the wrapped allocation is too small and batadv_tt_prepare_tvlv_global_data() writes past the end of the heap object before the later packet-size check runs. Fix this by rejecting TT responses whose TVLV value length cannot fit in the 16-bit TVLV payload length field.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31660

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: nfc: pn533: allocate rx skb before consuming bytes pn532_receive_buf() reports the number of accepted bytes to the serdev core. The current code consumes bytes into recv_skb and may already hand a complete frame to pn533_recv_frame() before allocating a fresh receive buffer. If that alloc_skb() fails, the callback returns 0 even though it has already consumed bytes, and it leaves recv_skb as NULL for the next receive callback. That breaks the receive_buf() accounting contract and can also lead to a NULL dereference on the next skb_put_u8(). Allocate the receive skb lazily before consuming the next byte instead. If allocation fails, return the number of bytes already accepted.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31661

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wifi: brcmsmac: Fix dma_free_coherent() size dma_alloc_consistent() may change the size to align it. The new size is saved in alloced. Change the free size to match the allocation size.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31662

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: tipc: fix bc_ackers underflow on duplicate GRP_ACK_MSG The GRP_ACK_MSG handler in tipc_group_proto_rcv() currently decrements bc_ackers on every inbound group ACK, even when the same member has already acknowledged the current broadcast round. Because bc_ackers is a u16, a duplicate ACK received after the last legitimate ACK wraps the counter to 65535. Once wrapped, tipc_group_bc_cong() keeps reporting congestion and later group broadcasts on the affected socket stay blocked until the group is recreated. Fix this by ignoring duplicate or stale ACKs before touching bc_acked or bc_ackers. This makes repeated GRP_ACK_MSG handling idempotent and prevents the underflow path.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31663

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: xfrm: hold dev ref until after transport_finish NF_HOOK After async crypto completes, xfrm_input_resume() calls dev_put() immediately on re-entry before the skb reaches transport_finish. The skb->dev pointer is then used inside NF_HOOK and its okfn, which can race with device teardown. Remove the dev_put from the async resumption entry and instead drop the reference after the NF_HOOK call in transport_finish, using a saved device pointer since NF_HOOK may consume the skb. This covers NF_DROP, NF_QUEUE and NF_STOLEN paths that skip the okfn. For non-transport exits (decaps, gro, drop) and secondary async return points, release the reference inline when async is set.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31664

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xfrm: clear trailing padding in build_polexpire() build_expire() clears the trailing padding bytes of struct xfrm_user_expire after setting the hard field via memset_after(), but the analogous function build_polexpire() does not do this for struct xfrm_user_polexpire. The padding bytes after the __u8 hard field are left uninitialized from the heap allocation, and are then sent to userspace via netlink multicast to XFRMNLGRP_EXPIRE listeners, leaking kernel heap memory contents. Add the missing memset_after() call, matching build_expire().

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31665

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_ct: fix use-after-free in timeout object destroy nft_ct_timeout_obj_destroy() frees the timeout object with kfree() immediately after nf_ct_untimeout(), without waiting for an RCU grace period. Concurrent packet processing on other CPUs may still hold RCU-protected references to the timeout object obtained via rcu_dereference() in nf_ct_timeout_data(). Add an rcu_head to struct nf_ct_timeout and use kfree_rcu() to defer freeing until after an RCU grace period, matching the approach already used in nfnetlink_cttimeout.c. KASAN report: BUG: KASAN: slab-use-after-free in nf_conntrack_tcp_packet+0x1381/0x29d0 Read of size 4 at addr ffff8881035fe19c by task exploit/80 Call Trace: nf_conntrack_tcp_packet+0x1381/0x29d0 nf_conntrack_in+0x612/0x8b0 nf_hook_slow+0x70/0x100 __ip_local_out+0x1b2/0x210 tcp_sendmsg_locked+0x722/0x1580 __sys_sendto+0x2d8/0x320 Allocated by task 75: nft_ct_timeout_obj_init+0xf6/0x290 nft_obj_init+0x107/0x1b0 nf_tables_newobj+0x680/0x9c0 nfnetlink_rcv_batch+0xc29/0xe00 Freed by task 26: nft_obj_destroy+0x3f/0xa0 nf_tables_trans_destroy_work+0x51c/0x5c0 process_one_work+0x2c4/0x5a0

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31666

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: btrfs: fix incorrect return value after changing leaf in lookup_extent_data_ref() After commit 1618aa3c2e01 ("btrfs: simplify return variables in lookup_extent_data_ref()"), the err and ret variables were merged into a single ret variable. However, when btrfs_next_leaf() returns 0 (success), ret is overwritten from -ENOENT to 0. If the first key in the next leaf does not match (different objectid or type), the function returns 0 instead of -ENOENT, making the caller believe the lookup succeeded when it did not. This can lead to operations on the wrong extent tree item, potentially causing extent tree corruption. Fix this by returning -ENOENT directly when the key does not match, instead of relying on the ret variable.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31667

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Input: uinput - fix circular locking dependency with ff-core A lockdep circular locking dependency warning can be triggered reproducibly when using a force-feedback gamepad with uinput (for example, playing ELDEN RING under Wine with a Flydigi Vader 5 controller): ff->mutex -> udev->mutex -> input_mutex -> dev->mutex -> ff->mutex The cycle is caused by four lock acquisition paths: 1. ff upload: input_ff_upload() holds ff->mutex and calls uinput_dev_upload_effect() -> uinput_request_submit() -> uinput_request_send(), which acquires udev->mutex. 2. device create: uinput_ioctl_handler() holds udev->mutex and calls uinput_create_device() -> input_register_device(), which acquires input_mutex. 3. device register: input_register_device() holds input_mutex and calls kbd_connect() -> input_register_handle(), which acquires dev->mutex. 4. evdev release: evdev_release() calls input_flush_device() under dev->mutex, which calls input_ff_flush() acquiring ff->mutex. Fix this by introducing a new state_lock spinlock to protect udev->state and udev->dev access in uinput_request_send() instead of acquiring udev->mutex. The function only needs to atomically check device state and queue an input event into the ring buffer via uinput_dev_event() -- both operations are safe under a spinlock (ktime_get_ts64() and wake_up_interruptible() do not sleep). This breaks the ff->mutex -> udev->mutex link since a spinlock is a leaf in the lock ordering and cannot form cycles with mutexes. To keep state transitions visible to uinput_request_send(), protect writes to udev->state in uinput_create_device() and uinput_destroy_device() with the same state_lock spinlock. Additionally, move init_completion(&request->done) from uinput_request_send() to uinput_request_submit() before uinput_request_reserve_slot(). Once the slot is allocated, uinput_flush_requests() may call complete() on it at any time from the destroy path, so the completion must be initialised before the request becomes visible. Lock ordering after the fix: ff->mutex -> state_lock (spinlock, leaf) udev->mutex -> state_lock (spinlock, leaf) udev->mutex -> input_mutex -> dev->mutex -> ff->mutex (no back-edge)

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31668

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: seg6: separate dst_cache for input and output paths in seg6 lwtunnel The seg6 lwtunnel uses a single dst_cache per encap route, shared between seg6_input_core() and seg6_output_core(). These two paths can perform the post-encap SID lookup in different routing contexts (e.g., ip rules matching on the ingress interface, or VRF table separation). Whichever path runs first populates the cache, and the other reuses it blindly, bypassing its own lookup. Fix this by splitting the cache into cache_input and cache_output, so each path maintains its own cached dst independently.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31669

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: mptcp: fix slab-use-after-free in __inet_lookup_established The ehash table lookups are lockless and rely on SLAB_TYPESAFE_BY_RCU to guarantee socket memory stability during RCU read-side critical sections. Both tcp_prot and tcpv6_prot have their slab caches created with this flag via proto_register(). However, MPTCP's mptcp_subflow_init() copies tcpv6_prot into tcpv6_prot_override during inet_init() (fs_initcall, level 5), before inet6_init() (module_init/device_initcall, level 6) has called proto_register(&tcpv6_prot). At that point, tcpv6_prot.slab is still NULL, so tcpv6_prot_override.slab remains NULL permanently. This causes MPTCP v6 subflow child sockets to be allocated via kmalloc (falling into kmalloc-4k) instead of the TCPv6 slab cache. The kmalloc-4k cache lacks SLAB_TYPESAFE_BY_RCU, so when these sockets are freed without SOCK_RCU_FREE (which is cleared for child sockets by design), the memory can be immediately reused. Concurrent ehash lookups under rcu_read_lock can then access freed memory, triggering a slab-use-after-free in __inet_lookup_established. Fix this by splitting the IPv6-specific initialization out of mptcp_subflow_init() into a new mptcp_subflow_v6_init(), called from mptcp_proto_v6_init() before protocol registration. This ensures tcpv6_prot_override.slab correctly inherits the SLAB_TYPESAFE_BY_RCU slab cache.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31670

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: rfkill: prevent unlimited numbers of rfkill events from being created Userspace can create an unlimited number of rfkill events if the system is so configured, while not consuming them from the rfkill file descriptor, causing a potential out of memory situation. Prevent this from bounding the number of pending rfkill events at a "large" number (i.e. 1000) to prevent abuses like this.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31671

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xfrm_user: fix info leak in build_report() struct xfrm_user_report is a __u8 proto field followed by a struct xfrm_selector which means there is three "empty" bytes of padding, but the padding is never zeroed before copying to userspace. Fix that up by zeroing the structure before setting individual member variables.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31672

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wifi: rt2x00usb: fix devres lifetime USB drivers bind to USB interfaces and any device managed resources should have their lifetime tied to the interface rather than parent USB device. This avoids issues like memory leaks when drivers are unbound without their devices being physically disconnected (e.g. on probe deferral or configuration changes). Fix the USB anchor lifetime so that it is released on driver unbind.

Published: 2026-04-24Modified: 2026-04-27

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31673

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: af_unix: read UNIX_DIAG_VFS data under unix_state_lock Exact UNIX diag lookups hold a reference to the socket, but not to u->path. Meanwhile, unix_release_sock() clears u->path under unix_state_lock() and drops the path reference after unlocking. Read the inode and device numbers for UNIX_DIAG_VFS while holding unix_state_lock(), then emit the netlink attribute after dropping the lock. This keeps the VFS data stable while the reply is being built.

Published: 2026-04-25Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31674

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: netfilter: ip6t_rt: reject oversized addrnr in rt_mt6_check() Reject rt match rules whose addrnr exceeds IP6T_RT_HOPS. rt_mt6() expects addrnr to stay within the bounds of rtinfo->addrs[]. Validate addrnr during rule installation so malformed rules are rejected before the match logic can use an out-of-range value.

Published: 2026-04-25Modified: 2026-05-06

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31675

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net/sched: sch_netem: fix out-of-bounds access in packet corruption In netem_enqueue(), the packet corruption logic uses get_random_u32_below(skb_headlen(skb)) to select an index for modifying skb->data. When an AF_PACKET TX_RING sends fully non-linear packets over an IPIP tunnel, skb_headlen(skb) evaluates to 0. Passing 0 to get_random_u32_below() takes the variable-ceil slow path which returns an unconstrained 32-bit random integer. Using this unconstrained value as an offset into skb->data results in an out-of-bounds memory access. Fix this by verifying skb_headlen(skb) is non-zero before attempting to corrupt the linear data area. Fully non-linear packets will silently bypass the corruption logic.

Published: 2026-04-25Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31676

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: rxrpc: only handle RESPONSE during service challenge Only process RESPONSE packets while the service connection is still in RXRPC_CONN_SERVICE_CHALLENGING. Check that state under state_lock before running response verification and security initialization, then use a local secured flag to decide whether to queue the secured-connection work after the state transition. This keeps duplicate or late RESPONSE packets from re-running the setup path and removes the unlocked post-transition state test.

Published: 2026-04-25Modified: 2026-05-06

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31677

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: crypto: af_alg - limit RX SG extraction by receive buffer budget Make af_alg_get_rsgl() limit each RX scatterlist extraction to the remaining receive buffer budget. af_alg_get_rsgl() currently uses af_alg_readable() only as a gate before extracting data into the RX scatterlist. Limit each extraction to the remaining af_alg_rcvbuf(sk) budget so that receive-side accounting matches the amount of data attached to the request. If skcipher cannot obtain enough RX space for at least one chunk while more data remains to be processed, reject the recvmsg call instead of rounding the request length down to zero.

Published: 2026-04-25Modified: 2026-05-06

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31678

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: openvswitch: defer tunnel netdev_put to RCU release ovs_netdev_tunnel_destroy() may run after NETDEV_UNREGISTER already detached the device. Dropping the netdev reference in destroy can race with concurrent readers that still observe vport->dev. Do not release vport->dev in ovs_netdev_tunnel_destroy(). Instead, let vport_netdev_free() drop the reference from the RCU callback, matching the non-tunnel destroy path and avoiding additional synchronization under RTNL.

Published: 2026-04-25Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31679

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: openvswitch: validate MPLS set/set_masked payload length validate_set() accepted OVS_KEY_ATTR_MPLS as variable-sized payload for SET/SET_MASKED actions. In action handling, OVS expects fixed-size MPLS key data (struct ovs_key_mpls). Use the already normalized key_len (masked case included) and reject non-matching MPLS action key sizes. Reject invalid MPLS action payload lengths early.

Published: 2026-04-25Modified: 2026-05-06

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31680

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: ipv6: flowlabel: defer exclusive option free until RCU teardown `ip6fl_seq_show()` walks the global flowlabel hash under the seq-file RCU read-side lock and prints `fl->opt->opt_nflen` when an option block is present. Exclusive flowlabels currently free `fl->opt` as soon as `fl->users` drops to zero in `fl_release()`. However, the surrounding `struct ip6_flowlabel` remains visible in the global hash table until later garbage collection removes it and `fl_free_rcu()` finally tears it down. A concurrent `/proc/net/ip6_flowlabel` reader can therefore race that early `kfree()` and dereference freed option state, triggering a crash in `ip6fl_seq_show()`. Fix this by keeping `fl->opt` alive until `fl_free_rcu()`. That matches the lifetime already required for the enclosing flowlabel while readers can still reach it under RCU.

Published: 2026-04-25Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31681

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: xt_multiport: validate range encoding in checkentry ports_match_v1() treats any non-zero pflags entry as the start of a port range and unconditionally consumes the next ports[] element as the range end. The checkentry path currently validates protocol, flags and count, but it does not validate the range encoding itself. As a result, malformed rules can mark the last slot as a range start or place two range starts back to back, leaving ports_match_v1() to step past the last valid ports[] element while interpreting the rule. Reject malformed multiport v1 rules in checkentry by validating that each range start has a following element and that the following element is not itself marked as another range start.

Published: 2026-04-25Modified: 2026-05-06

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31682

CRITICAL9.1

In the Linux kernel, the following vulnerability has been resolved: bridge: br_nd_send: linearize skb before parsing ND options br_nd_send() parses neighbour discovery options from ns->opt[] and assumes that these options are in the linear part of request. Its callers only guarantee that the ICMPv6 header and target address are available, so the option area can still be non-linear. Parsing ns->opt[] in that case can access data past the linear buffer. Linearize request before option parsing and derive ns from the linear network header.

Published: 2026-04-25Modified: 2026-05-06

CVSS 3.xCRITICAL 9.1

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31683

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: batman-adv: avoid OGM aggregation when skb tailroom is insufficient When OGM aggregation state is toggled at runtime, an existing forwarded packet may have been allocated with only packet_len bytes, while a later packet can still be selected for aggregation. Appending in this case can hit skb_put overflow conditions. Reject aggregation when the target skb tailroom cannot accommodate the new packet. The caller then falls back to creating a new forward packet instead of appending.

Published: 2026-04-25Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31684

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: sched: act_csum: validate nested VLAN headers tcf_csum_act() walks nested VLAN headers directly from skb->data when an skb still carries in-payload VLAN tags. The current code reads vlan->h_vlan_encapsulated_proto and then pulls VLAN_HLEN bytes without first ensuring that the full VLAN header is present in the linear area. If only part of an inner VLAN header is linearized, accessing h_vlan_encapsulated_proto reads past the linear area, and the following skb_pull(VLAN_HLEN) may violate skb invariants. Fix this by requiring pskb_may_pull(skb, VLAN_HLEN) before accessing and pulling each nested VLAN header. If the header still is not fully available, drop the packet through the existing error path.

Published: 2026-04-25Modified: 2026-05-06

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31685

CRITICAL9.4

In the Linux kernel, the following vulnerability has been resolved: netfilter: ip6t_eui64: reject invalid MAC header for all packets `eui64_mt6()` derives a modified EUI-64 from the Ethernet source address and compares it with the low 64 bits of the IPv6 source address. The existing guard only rejects an invalid MAC header when `par->fragoff != 0`. For packets with `par->fragoff == 0`, `eui64_mt6()` can still reach `eth_hdr(skb)` even when the MAC header is not valid. Fix this by removing the `par->fragoff != 0` condition so that packets with an invalid MAC header are rejected before accessing `eth_hdr(skb)`.

Published: 2026-04-25Modified: 2026-05-06

CVSS 3.xCRITICAL 9.4

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:H

References

CVE-2026-31686

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: mm/kasan: fix double free for kasan pXds kasan_free_pxd() assumes the page table is always struct page aligned. But that's not always the case for all architectures. E.g. In case of powerpc with 64K pagesize, PUD table (of size 4096) comes from slab cache named pgtable-2^9. Hence instead of page_to_virt(pxd_page()) let's just directly pass the start of the pxd table which is passed as the 1st argument. This fixes the below double free kasan issue seen with PMEM: radix-mmu: Mapped 0x0000047d10000000-0x0000047f90000000 with 2.00 MiB pages ================================================================== BUG: KASAN: double-free in kasan_remove_zero_shadow+0x9c4/0xa20 Free of addr c0000003c38e0000 by task ndctl/2164 CPU: 34 UID: 0 PID: 2164 Comm: ndctl Not tainted 6.19.0-rc1-00048-gea1013c15392 #157 VOLUNTARY Hardware name: IBM,9080-HEX POWER10 (architected) 0x800200 0xf000006 of:IBM,FW1060.00 (NH1060_012) hv:phyp pSeries Call Trace: dump_stack_lvl+0x88/0xc4 (unreliable) print_report+0x214/0x63c kasan_report_invalid_free+0xe4/0x110 check_slab_allocation+0x100/0x150 kmem_cache_free+0x128/0x6e0 kasan_remove_zero_shadow+0x9c4/0xa20 memunmap_pages+0x2b8/0x5c0 devm_action_release+0x54/0x70 release_nodes+0xc8/0x1a0 devres_release_all+0xe0/0x140 device_unbind_cleanup+0x30/0x120 device_release_driver_internal+0x3e4/0x450 unbind_store+0xfc/0x110 drv_attr_store+0x78/0xb0 sysfs_kf_write+0x114/0x140 kernfs_fop_write_iter+0x264/0x3f0 vfs_write+0x3bc/0x7d0 ksys_write+0xa4/0x190 system_call_exception+0x190/0x480 system_call_vectored_common+0x15c/0x2ec ---- interrupt: 3000 at 0x7fff93b3d3f4 NIP: 00007fff93b3d3f4 LR: 00007fff93b3d3f4 CTR: 0000000000000000 REGS: c0000003f1b07e80 TRAP: 3000 Not tainted (6.19.0-rc1-00048-gea1013c15392) MSR: 800000000280f033 CR: 48888208 XER: 00000000 <...> NIP [00007fff93b3d3f4] 0x7fff93b3d3f4 LR [00007fff93b3d3f4] 0x7fff93b3d3f4 ---- interrupt: 3000 The buggy address belongs to the object at c0000003c38e0000 which belongs to the cache pgtable-2^9 of size 4096 The buggy address is located 0 bytes inside of 4096-byte region [c0000003c38e0000, c0000003c38e1000) The buggy address belongs to the physical page: page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x3c38c head: order:2 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 memcg:c0000003bfd63e01 flags: 0x63ffff800000040(head|node=6|zone=0|lastcpupid=0x7ffff) page_type: f5(slab) raw: 063ffff800000040 c000000140058980 5deadbeef0000122 0000000000000000 raw: 0000000000000000 0000000080200020 00000000f5000000 c0000003bfd63e01 head: 063ffff800000040 c000000140058980 5deadbeef0000122 0000000000000000 head: 0000000000000000 0000000080200020 00000000f5000000 c0000003bfd63e01 head: 063ffff800000002 c00c000000f0e301 00000000ffffffff 00000000ffffffff head: ffffffffffffffff 0000000000000000 00000000ffffffff 0000000000000004 page dumped because: kasan: bad access detected [ 138.953636] [ T2164] Memory state around the buggy address: [ 138.953643] [ T2164] c0000003c38dff00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 138.953652] [ T2164] c0000003c38dff80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 138.953661] [ T2164] >c0000003c38e0000: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 138.953669] [ T2164] ^ [ 138.953675] [ T2164] c0000003c38e0080: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 138.953684] [ T2164] c0000003c38e0100: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 138.953692] [ T2164] ================================================================== [ 138.953701] [ T2164] Disabling lock debugging due to kernel taint

Published: 2026-04-27Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31689

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: EDAC/mc: Fix error path ordering in edac_mc_alloc() When the mci->pvt_info allocation in edac_mc_alloc() fails, the error path will call put_device() which will end up calling the device's release function. However, the init ordering is wrong such that device_initialize() happens after the failed allocation and thus the device itself and the release function pointer are not initialized yet when they're called: MCE: In-kernel MCE decoding enabled. ------------[ cut here ]------------ kobject: '(null)': is not initialized, yet kobject_put() is being called. WARNING: lib/kobject.c:734 at kobject_put, CPU#22: systemd-udevd CPU: 22 UID: 0 PID: 538 Comm: systemd-udevd Not tainted 7.0.0-rc1+ #2 PREEMPT(full) RIP: 0010:kobject_put Call Trace: edac_mc_alloc+0xbe/0xe0 [edac_core] amd64_edac_init+0x7a4/0xff0 [amd64_edac] ? __pfx_amd64_edac_init+0x10/0x10 [amd64_edac] do_one_initcall ... Reorder the calling sequence so that the device is initialized and thus the release function pointer is properly set before it can be used. This was found by Claude while reviewing another EDAC patch.

Published: 2026-04-27Modified: 2026-05-06

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31690

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: firmware: thead: Fix buffer overflow and use standard endian macros Addresses two issues in the TH1520 AON firmware protocol driver: 1. Fix a potential buffer overflow where the code used unsafe pointer arithmetic to access the 'mode' field through the 'resource' pointer with an offset. This was flagged by Smatch static checker as: "buffer overflow 'data' 2 <= 3" 2. Replace custom RPC_SET_BE* and RPC_GET_BE* macros with standard kernel endianness conversion macros (cpu_to_be16, etc.) for better portability and maintainability. The functionality was re-tested with the GPU power-up sequence, confirming the GPU powers up correctly and the driver probes successfully. [ 12.702370] powervr ffef400000.gpu: [drm] loaded firmware powervr/rogue_36.52.104.182_v1.fw [ 12.711043] powervr ffef400000.gpu: [drm] FW version v1.0 (build 6645434 OS) [ 12.719787] [drm] Initialized powervr 1.0.0 for ffef400000.gpu on minor 0

Published: 2026-04-27Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31691

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: igb: remove napi_synchronize() in igb_down() When an AF_XDP zero-copy application terminates abruptly (e.g., kill -9), the XSK buffer pool is destroyed but NAPI polling continues. igb_clean_rx_irq_zc() repeatedly returns the full budget, preventing napi_complete_done() from clearing NAPI_STATE_SCHED. igb_down() calls napi_synchronize() before napi_disable() for each queue vector. napi_synchronize() spins waiting for NAPI_STATE_SCHED to clear, which never happens. igb_down() blocks indefinitely, the TX watchdog fires, and the TX queue remains permanently stalled. napi_disable() already handles this correctly: it sets NAPI_STATE_DISABLE. After a full-budget poll, __napi_poll() checks napi_disable_pending(). If set, it forces completion and clears NAPI_STATE_SCHED, breaking the loop that napi_synchronize() cannot. napi_synchronize() was added in commit 41f149a285da ("igb: Fix possible panic caused by Rx traffic arrival while interface is down"). napi_disable() provides stronger guarantees: it prevents further scheduling and waits for any active poll to exit. Other Intel drivers (ixgbe, ice, i40e) use napi_disable() without a preceding napi_synchronize() in their down paths. Remove redundant napi_synchronize() call and reorder napi_disable() before igb_set_queue_napi() so the queue-to-NAPI mapping is only cleared after polling has fully stopped.

Published: 2026-04-27Modified: 2026-05-06

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31692

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: rtnetlink: add missing netlink_ns_capable() check for peer netns rtnl_newlink() lacks a CAP_NET_ADMIN capability check on the peer network namespace when creating paired devices (veth, vxcan, netkit). This allows an unprivileged user with a user namespace to create interfaces in arbitrary network namespaces, including init_net. Add a netlink_ns_capable() check for CAP_NET_ADMIN in the peer namespace before allowing device creation to proceed.

Published: 2026-04-30Modified: 2026-05-06

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31694

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: fuse: reject oversized dirents in page cache fuse_add_dirent_to_cache() computes a serialized dirent size from the server-controlled namelen field and copies the dirent into a single page-cache page. The existing logic only checks whether the dirent fits in the remaining space of the current page and advances to a fresh page if not. It never checks whether the dirent itself exceeds PAGE_SIZE. As a result, a malicious FUSE server can return a dirent with namelen=4095, producing a serialized record size of 4120 bytes. On 4 KiB page systems this causes memcpy() to overflow the cache page by 24 bytes into the following kernel page. Reject dirents that cannot fit in a single page before copying them into the readdir cache.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31695

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: wifi: virt_wifi: remove SET_NETDEV_DEV to avoid use-after-free Currently we execute `SET_NETDEV_DEV(dev, &priv->lowerdev->dev)` for the virt_wifi net devices. However, unregistering a virt_wifi device in netdev_run_todo() can happen together with the device referenced by SET_NETDEV_DEV(). It can result in use-after-free during the ethtool operations performed on a virt_wifi device that is currently being unregistered. Such a net device can have the `dev.parent` field pointing to the freed memory, but ethnl_ops_begin() calls `pm_runtime_get_sync(dev->dev.parent)`. Let's remove SET_NETDEV_DEV for virt_wifi to avoid bugs like this: ================================================================== BUG: KASAN: slab-use-after-free in __pm_runtime_resume+0xe2/0xf0 Read of size 2 at addr ffff88810cfc46f8 by task pm/606 Call Trace: dump_stack_lvl+0x4d/0x70 print_report+0x170/0x4f3 ? pfxraw_spin_lock_irqsave+0x10/0x10 kasan_report+0xda/0x110 ? __pm_runtime_resume+0xe2/0xf0 ? __pm_runtime_resume+0xe2/0xf0 __pm_runtime_resume+0xe2/0xf0 ethnl_ops_begin+0x49/0x270 ethnl_set_features+0x23c/0xab0 ? __pfx_ethnl_set_features+0x10/0x10 ? kvm_sched_clock_read+0x11/0x20 ? local_clock_noinstr+0xf/0xf0 ? local_clock+0x10/0x30 ? kasan_save_track+0x25/0x60 ? __kasan_kmalloc+0x7f/0x90 ? genl_family_rcv_msg_attrs_parse.isra.0+0x150/0x2c0 genl_family_rcv_msg_doit+0x1e7/0x2c0 ? __pfx_genl_family_rcv_msg_doit+0x10/0x10 ? __pfx_cred_has_capability.isra.0+0x10/0x10 ? stack_trace_save+0x8e/0xc0 genl_rcv_msg+0x411/0x660 ? __pfx_genl_rcv_msg+0x10/0x10 ? __pfx_ethnl_set_features+0x10/0x10 netlink_rcv_skb+0x121/0x380 ? __pfx_genl_rcv_msg+0x10/0x10 ? __pfx_netlink_rcv_skb+0x10/0x10 ? __pfx_down_read+0x10/0x10 genl_rcv+0x23/0x30 netlink_unicast+0x60f/0x830 ? __pfx_netlink_unicast+0x10/0x10 ? pfx_alloc_skb+0x10/0x10 netlink_sendmsg+0x6ea/0xbc0 ? __pfx_netlink_sendmsg+0x10/0x10 ? __futex_queue+0x10b/0x1f0 ____sys_sendmsg+0x7a2/0x950 ? copy_msghdr_from_user+0x26b/0x430 ? pfx___sys_sendmsg+0x10/0x10 ? __pfx_copy_msghdr_from_user+0x10/0x10 ___sys_sendmsg+0xf8/0x180 ? pfx__sys_sendmsg+0x10/0x10 ? __pfx_futex_wait+0x10/0x10 ? fdget+0x2e4/0x4a0 __sys_sendmsg+0x11f/0x1c0 ? pfx_sys_sendmsg+0x10/0x10 do_syscall_64+0xe2/0x570 ? exc_page_fault+0x66/0xb0 entry_SYSCALL_64_after_hwframe+0x77/0x7f This fix may be combined with another one in the ethtool subsystem: https://lore.kernel.org/all/20260322075917.254874-1-alex.popov@linux.com/T/#u

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31696

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix missing validation of ticket length in non-XDR key preparsing In rxrpc_preparse(), there are two paths for parsing key payloads: the XDR path (for large payloads) and the non-XDR path (for payloads <= 28 bytes). While the XDR path (rxrpc_preparse_xdr_rxkad()) correctly validates the ticket length against AFSTOKEN_RK_TIX_MAX, the non-XDR path fails to do so. This allows an unprivileged user to provide a very large ticket length. When this key is later read via rxrpc_read(), the total token size (toksize) calculation results in a value that exceeds AFSTOKEN_LENGTH_MAX, triggering a WARN_ON(). [ 2001.302904] WARNING: CPU: 2 PID: 2108 at net/rxrpc/key.c:778 rxrpc_read+0x109/0x5c0 [rxrpc] Fix this by adding a check in the non-XDR parsing path of rxrpc_preparse() to ensure the ticket length does not exceed AFSTOKEN_RK_TIX_MAX, bringing it into parity with the XDR parsing logic.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31697

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: crypto: ccp: Don't attempt to copy ID to userspace if PSP command failed When retrieving the ID for the CPU, don't attempt to copy the ID blob to userspace if the firmware command failed. If the failure was due to an invalid length, i.e. the userspace buffer+length was too small, copying the number of bytes _firmware_ requires will overflow the kernel-allocated buffer and leak data to userspace. BUG: KASAN: slab-out-of-bounds in instrument_copy_to_user ../include/linux/instrumented.h:129 [inline] BUG: KASAN: slab-out-of-bounds in _inline_copy_to_user ../include/linux/uaccess.h:205 [inline] BUG: KASAN: slab-out-of-bounds in _copy_to_user+0x66/0xa0 ../lib/usercopy.c:26 Read of size 64 at addr ffff8881867f5960 by task syz.0.906/24388 CPU: 130 UID: 0 PID: 24388 Comm: syz.0.906 Tainted: G U O 7.0.0-smp-DEV #28 PREEMPTLAZY Tainted: [U]=USER, [O]=OOT_MODULE Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 12.62.0-0 11/19/2025 Call Trace: dump_stack_lvl+0xc5/0x110 ../lib/dump_stack.c:120 print_address_description ../mm/kasan/report.c:378 [inline] print_report+0xbc/0x260 ../mm/kasan/report.c:482 kasan_report+0xa2/0xe0 ../mm/kasan/report.c:595 check_region_inline ../mm/kasan/generic.c:-1 [inline] kasan_check_range+0x264/0x2c0 ../mm/kasan/generic.c:200 instrument_copy_to_user ../include/linux/instrumented.h:129 [inline] _inline_copy_to_user ../include/linux/uaccess.h:205 [inline] _copy_to_user+0x66/0xa0 ../lib/usercopy.c:26 copy_to_user ../include/linux/uaccess.h:236 [inline] sev_ioctl_do_get_id2+0x361/0x490 ../drivers/crypto/ccp/sev-dev.c:2222 sev_ioctl+0x25f/0x490 ../drivers/crypto/ccp/sev-dev.c:2575 vfs_ioctl ../fs/ioctl.c:51 [inline] __do_sys_ioctl ../fs/ioctl.c:597 [inline] __se_sys_ioctl+0x11d/0x1b0 ../fs/ioctl.c:583 do_syscall_x64 ../arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xe0/0x800 ../arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e WARN if the driver says the command succeeded, but the firmware error code says otherwise, as __sev_do_cmd_locked() is expected to return -EIO on any firwmware error.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31698

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: crypto: ccp: Don't attempt to copy PDH cert to userspace if PSP command failed When retrieving the PDH cert, don't attempt to copy the blobs to userspace if the firmware command failed. If the failure was due to an invalid length, i.e. the userspace buffer+length was too small, copying the number of bytes _firmware_ requires will overflow the kernel-allocated buffer and leak data to userspace. BUG: KASAN: slab-out-of-bounds in instrument_copy_to_user ../include/linux/instrumented.h:129 [inline] BUG: KASAN: slab-out-of-bounds in _inline_copy_to_user ../include/linux/uaccess.h:205 [inline] BUG: KASAN: slab-out-of-bounds in _copy_to_user+0x66/0xa0 ../lib/usercopy.c:26 Read of size 2084 at addr ffff8885c4ab8aa0 by task syz.0.186/21033 CPU: 51 UID: 0 PID: 21033 Comm: syz.0.186 Tainted: G U O 7.0.0-smp-DEV #28 PREEMPTLAZY Tainted: [U]=USER, [O]=OOT_MODULE Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 34.84.12-0 11/17/2025 Call Trace: dump_stack_lvl+0xc5/0x110 ../lib/dump_stack.c:120 print_address_description ../mm/kasan/report.c:378 [inline] print_report+0xbc/0x260 ../mm/kasan/report.c:482 kasan_report+0xa2/0xe0 ../mm/kasan/report.c:595 check_region_inline ../mm/kasan/generic.c:-1 [inline] kasan_check_range+0x264/0x2c0 ../mm/kasan/generic.c:200 instrument_copy_to_user ../include/linux/instrumented.h:129 [inline] _inline_copy_to_user ../include/linux/uaccess.h:205 [inline] _copy_to_user+0x66/0xa0 ../lib/usercopy.c:26 copy_to_user ../include/linux/uaccess.h:236 [inline] sev_ioctl_do_pdh_export+0x3d3/0x7c0 ../drivers/crypto/ccp/sev-dev.c:2347 sev_ioctl+0x2a2/0x490 ../drivers/crypto/ccp/sev-dev.c:2568 vfs_ioctl ../fs/ioctl.c:51 [inline] __do_sys_ioctl ../fs/ioctl.c:597 [inline] __se_sys_ioctl+0x11d/0x1b0 ../fs/ioctl.c:583 do_syscall_x64 ../arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xe0/0x800 ../arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e WARN if the driver says the command succeeded, but the firmware error code says otherwise, as __sev_do_cmd_locked() is expected to return -EIO on any firwmware error.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31699

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: crypto: ccp: Don't attempt to copy CSR to userspace if PSP command failed When retrieving the PEK CSR, don't attempt to copy the blob to userspace if the firmware command failed. If the failure was due to an invalid length, i.e. the userspace buffer+length was too small, copying the number of bytes _firmware_ requires will overflow the kernel-allocated buffer and leak data to userspace. BUG: KASAN: slab-out-of-bounds in instrument_copy_to_user ../include/linux/instrumented.h:129 [inline] BUG: KASAN: slab-out-of-bounds in _inline_copy_to_user ../include/linux/uaccess.h:205 [inline] BUG: KASAN: slab-out-of-bounds in _copy_to_user+0x66/0xa0 ../lib/usercopy.c:26 Read of size 2084 at addr ffff898144612e20 by task syz.9.219/21405 CPU: 14 UID: 0 PID: 21405 Comm: syz.9.219 Tainted: G U O 7.0.0-smp-DEV #28 PREEMPTLAZY Tainted: [U]=USER, [O]=OOT_MODULE Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 12.62.0-0 11/19/2025 Call Trace: dump_stack_lvl+0xc5/0x110 ../lib/dump_stack.c:120 print_address_description ../mm/kasan/report.c:378 [inline] print_report+0xbc/0x260 ../mm/kasan/report.c:482 kasan_report+0xa2/0xe0 ../mm/kasan/report.c:595 check_region_inline ../mm/kasan/generic.c:-1 [inline] kasan_check_range+0x264/0x2c0 ../mm/kasan/generic.c:200 instrument_copy_to_user ../include/linux/instrumented.h:129 [inline] _inline_copy_to_user ../include/linux/uaccess.h:205 [inline] _copy_to_user+0x66/0xa0 ../lib/usercopy.c:26 copy_to_user ../include/linux/uaccess.h:236 [inline] sev_ioctl_do_pek_csr+0x31f/0x590 ../drivers/crypto/ccp/sev-dev.c:1872 sev_ioctl+0x3a4/0x490 ../drivers/crypto/ccp/sev-dev.c:2562 vfs_ioctl ../fs/ioctl.c:51 [inline] __do_sys_ioctl ../fs/ioctl.c:597 [inline] __se_sys_ioctl+0x11d/0x1b0 ../fs/ioctl.c:583 do_syscall_x64 ../arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xe0/0x800 ../arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e WARN if the driver says the command succeeded, but the firmware error code says otherwise, as __sev_do_cmd_locked() is expected to return -EIO on any firwmware error.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31700

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net/packet: fix TOCTOU race on mmap'd vnet_hdr in tpacket_snd() In tpacket_snd(), when PACKET_VNET_HDR is enabled, vnet_hdr points directly into the mmap'd TX ring buffer shared with userspace. The kernel validates the header via __packet_snd_vnet_parse() but then re-reads all fields later in virtio_net_hdr_to_skb(). A concurrent userspace thread can modify the vnet_hdr fields between validation and use, bypassing all safety checks. The non-TPACKET path (packet_snd()) already correctly copies vnet_hdr to a stack-local variable. All other vnet_hdr consumers in the kernel (tun.c, tap.c, virtio_net.c) also use stack copies. The TPACKET TX path is the only caller of virtio_net_hdr_to_skb() that reads directly from user-controlled shared memory. Fix this by copying vnet_hdr from the mmap'd ring buffer to a stack-local variable before validation and use, consistent with the approach used in packet_snd() and all other callers.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31701

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ALSA: caiaq: take a reference on the USB device in create_card() The caiaq driver stores a pointer to the parent USB device in cdev->chip.dev but never takes a reference on it. The card's private_free callback, snd_usb_caiaq_card_free(), can run asynchronously via snd_card_free_when_closed() after the USB device has already been disconnected and freed, so any access to cdev->chip.dev in that path dereferences a freed usb_device. On top of the refcounting issue, the current card_free implementation calls usb_reset_device(cdev->chip.dev). A reset in a free callback is inappropriate: the device is going away, the call takes the device lock in a teardown context, and the reset races with the disconnect path that the callback is already cleaning up after. Take a reference on the USB device in create_card() with usb_get_dev(), drop it with usb_put_dev() in the free callback, and remove the usb_reset_device() call.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31702

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: f2fs: fix use-after-free of sbi in f2fs_compress_write_end_io() In f2fs_compress_write_end_io(), dec_page_count(sbi, type) can bring the F2FS_WB_CP_DATA counter to zero, unblocking f2fs_wait_on_all_pages() in f2fs_put_super() on a concurrent unmount CPU. The unmount path then proceeds to call f2fs_destroy_page_array_cache(sbi), which destroys sbi->page_array_slab via kmem_cache_destroy(), and eventually kfree(sbi). Meanwhile, the bio completion callback is still executing: when it reaches page_array_free(sbi, ...), it dereferences sbi->page_array_slab — a destroyed slab cache — to call kmem_cache_free(), causing a use-after-free. This is the same class of bug as CVE-2026-23234 (which fixed the equivalent race in f2fs_write_end_io() in data.c), but in the compressed writeback completion path that was not covered by that fix. Fix this by moving dec_page_count() to after page_array_free(), so that all sbi accesses complete before the counter decrement that can unblock unmount. For non-last folios (where atomic_dec_return on cic->pending_pages is nonzero), dec_page_count is called immediately before returning — page_array_free is not reached on this path, so there is no post-decrement sbi access. For the last folio, page_array_free runs while the F2FS_WB_CP_DATA counter is still nonzero (this folio has not yet decremented it), keeping sbi alive, and dec_page_count runs as the final operation.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31703

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: writeback: Fix use after free in inode_switch_wbs_work_fn() inode_switch_wbs_work_fn() has a loop like: wb_get(new_wb); while (1) { list = llist_del_all(&new_wb->switch_wbs_ctxs); /* Nothing to do? */ if (!list) break; ... process the items ... } Now adding of items to the list looks like: wb_queue_isw() if (llist_add(&isw->list, &wb->switch_wbs_ctxs)) queue_work(isw_wq, &wb->switch_work); Because inode_switch_wbs_work_fn() loops when processing isw items, it can happen that wb->switch_work is pending while wb->switch_wbs_ctxs is empty. This is a problem because in that case wb can get freed (no isw items -> no wb reference) while the work is still pending causing use-after-free issues. We cannot just fix this by cancelling work when freeing wb because that could still trigger problematic 0 -> 1 transitions on wb refcount due to wb_get() in inode_switch_wbs_work_fn(). It could be all handled with more careful code but that seems unnecessarily complex so let's avoid that until it is proven that the looping actually brings practical benefit. Just remove the loop from inode_switch_wbs_work_fn() instead. That way when wb_queue_isw() queues work, we are guaranteed we have added the first item to wb->switch_wbs_ctxs and nobody is going to remove it (and drop the wb reference it holds) until the queued work runs.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31704

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ksmbd: use check_add_overflow() to prevent u16 DACL size overflow set_posix_acl_entries_dacl() and set_ntacl_dacl() accumulate ACE sizes in u16 variables. When a file has many POSIX ACL entries, the accumulated size can wrap past 65535, causing the pointer arithmetic (char )pndace + size to land within already-written ACEs. Subsequent writes then overwrite earlier entries, and pndacl->size gets a truncated value. Use check_add_overflow() at each accumulation point to detect the wrap before it corrupts the buffer, consistent with existing check_mul_overflow() usage elsewhere in smbacl.c.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31705

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix out-of-bounds write in smb2_get_ea() EA alignment smb2_get_ea() applies 4-byte alignment padding via memset() after writing each EA entry. The bounds check on buf_free_len is performed before the value memcpy, but the alignment memset fires unconditionally afterward with no check on remaining space. When the EA value exactly fills the remaining buffer (buf_free_len == 0 after value subtraction), the alignment memset writes 1-3 NUL bytes past the buf_free_len boundary. In compound requests where the response buffer is shared across commands, the first command (e.g., READ) can consume most of the buffer, leaving a tight remainder for the QUERY_INFO EA response. The alignment memset then overwrites past the physical kvmalloc allocation into adjacent kernel heap memory. Add a bounds check before the alignment memset to ensure buf_free_len can accommodate the padding bytes. This is the same bug pattern fixed by commit beef2634f81f ("ksmbd: fix potencial OOB in get_file_all_info() for compound requests") and commit fda9522ed6af ("ksmbd: fix OOB write in QUERY_INFO for compound requests"), both of which added bounds checks before unconditional writes in QUERY_INFO response handlers.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31706

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: ksmbd: validate num_aces and harden ACE walk in smb_inherit_dacl() smb_inherit_dacl() trusts the on-disk num_aces value from the parent directory's DACL xattr and uses it to size a heap allocation: aces_base = kmalloc(sizeof(struct smb_ace) * num_aces * 2, ...); num_aces is a u16 read from le16_to_cpu(parent_pdacl->num_aces) without checking that it is consistent with the declared pdacl_size. An authenticated client whose parent directory's security.NTACL is tampered (e.g. via offline xattr corruption or a concurrent path that bypasses parse_dacl()) can present num_aces = 65535 with minimal actual ACE data. This causes a ~8 MB allocation (not kzalloc, so uninitialized) that the subsequent loop only partially populates, and may also overflow the three-way size_t multiply on 32-bit kernels. Additionally, the ACE walk loop uses the weaker offsetof(struct smb_ace, access_req) minimum size check rather than the minimum valid on-wire ACE size, and does not reject ACEs whose declared size is below the minimum. Reproduced on UML + KASAN + LOCKDEP against the real ksmbd code path. A legitimate mount.cifs client creates a parent directory over SMB (ksmbd writes a valid security.NTACL xattr), then the NTACL blob on the backing filesystem is rewritten to set num_aces = 0xFFFF while keeping the posix_acl_hash bytes intact so ksmbd_vfs_get_sd_xattr()'s hash check still passes. A subsequent SMB2 CREATE of a child under that parent drives smb2_open() into smb_inherit_dacl() (share has "vfs objects = acl_xattr" set), which fails the page allocator: WARNING: mm/page_alloc.c:5226 at __alloc_frozen_pages_noprof+0x46c/0x9c0 Workqueue: ksmbd-io handle_ksmbd_work __alloc_frozen_pages_noprof+0x46c/0x9c0 ___kmalloc_large_node+0x68/0x130 __kmalloc_large_node_noprof+0x24/0x70 __kmalloc_noprof+0x4c9/0x690 smb_inherit_dacl+0x394/0x2430 smb2_open+0x595d/0xabe0 handle_ksmbd_work+0x3d3/0x1140 With the patch applied the added guard rejects the tampered value with -EINVAL before any large allocation runs, smb2_open() falls back to smb2_create_sd_buffer(), and the child is created with a default SD. No warning, no splat. Fix by: 1. Validating num_aces against pdacl_size using the same formula applied in parse_dacl(). 2. Replacing the raw kmalloc(sizeof * num_aces * 2) with kmalloc_array(num_aces * 2, sizeof(...)) for overflow-safe allocation. 3. Tightening the per-ACE loop guard to require the minimum valid ACE size (offsetof(smb_ace, sid) + CIFS_SID_BASE_SIZE) and rejecting under-sized ACEs, matching the hardening in smb_check_perm_dacl() and parse_dacl(). v1 -> v2: - Replace the synthetic test-module splat in the changelog with a real-path UML + KASAN reproduction driven through mount.cifs and SMB2 CREATE; Namjae flagged the kcifs3_test_inherit_dacl_old name in v1 since it does not exist in ksmbd. - Drop the commit-hash citation from the code comment per Namjae's review; keep the parse_dacl() pointer.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31707

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: ksmbd: validate response sizes in ipc_validate_msg() ipc_validate_msg() computes the expected message size for each response type by adding (or multiplying) attacker-controlled fields from the daemon response to a fixed struct size in unsigned int arithmetic. Three cases can overflow: KSMBD_EVENT_RPC_REQUEST: msg_sz = sizeof(struct ksmbd_rpc_command) + resp->payload_sz; KSMBD_EVENT_SHARE_CONFIG_REQUEST: msg_sz = sizeof(struct ksmbd_share_config_response) + resp->payload_sz; KSMBD_EVENT_LOGIN_REQUEST_EXT: msg_sz = sizeof(struct ksmbd_login_response_ext) + resp->ngroups * sizeof(gid_t); resp->payload_sz is u32 and resp->ngroups is s32. Each addition can wrap in unsigned int; the multiplication by sizeof(gid_t) mixes signed and size_t, so a negative ngroups is converted to SIZE_MAX before the multiply. A wrapped value of msg_sz that happens to equal entry->msg_sz bypasses the size check on the next line, and downstream consumers (smb2pdu.c:6742 memcpy using rpc_resp->payload_sz, kmemdup in ksmbd_alloc_user using resp_ext->ngroups) then trust the unverified length. Use check_add_overflow() on the RPC_REQUEST and SHARE_CONFIG_REQUEST paths to detect integer overflow without constraining functional payload size; userspace ksmbd-tools grows NDR responses in 4096-byte chunks for calls like NetShareEnumAll, so a hard transport cap is unworkable on the response side. For LOGIN_REQUEST_EXT, reject resp->ngroups outside the signed [0, NGROUPS_MAX] range up front and report the error from ipc_validate_msg() so it fires at the IPC boundary; with that bound the subsequent multiplication and addition stay well below UINT_MAX. The now-redundant ngroups check and pr_err in ksmbd_alloc_user() are removed. This is the response-side analogue of aab98e2dbd64 ("ksmbd: fix integer overflows on 32 bit systems"), which hardened the request side.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31708

HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: smb: client: fix OOB read in smb2_ioctl_query_info QUERY_INFO path smb2_ioctl_query_info() has two response-copy branches: PASSTHRU_FSCTL and the default QUERY_INFO path. The QUERY_INFO branch clamps qi.input_buffer_length to the server-reported OutputBufferLength and then copies qi.input_buffer_length bytes from qi_rsp->Buffer to userspace, but it never verifies that the flexible-array payload actually fits within rsp_iov[1].iov_len. A malicious server can return OutputBufferLength larger than the actual QUERY_INFO response, causing copy_to_user() to walk past the response buffer and expose adjacent kernel heap to userspace. Guard the QUERY_INFO copy with a bounds check on the actual Buffer payload. Use struct_size(qi_rsp, Buffer, qi.input_buffer_length) rather than an open-coded addition so the guard cannot overflow on 32-bit builds.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 8.1

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:H

References

CVE-2026-31711

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: smb: server: fix active_num_conn leak on transport allocation failure Commit 77ffbcac4e56 ("smb: server: fix leak of active_num_conn in ksmbd_tcp_new_connection()") addressed the kthread_run() failure path. The earlier alloc_transport() == NULL path in the same function has the same leak, is reachable pre-authentication via any TCP connect to port 445, and was empirically reproduced on UML (ARCH=um, v7.0-rc7): a small number of forced allocation failures were sufficient to put ksmbd into a state where every subsequent connection attempt was rejected for the remainder of the boot. ksmbd_kthread_fn() increments active_num_conn before calling ksmbd_tcp_new_connection() and discards the return value, so when alloc_transport() returns NULL the socket is released and -ENOMEM returned without decrementing the counter. Each such failure permanently consumes one slot from the max_connections pool; once cumulative failures reach the cap, atomic_inc_return() hits the threshold on every subsequent accept and every new connection is rejected. The counter is only reset by module reload. An unauthenticated remote attacker can drive the server toward the memory pressure that makes alloc_transport() fail by holding open connections with large RFC1002 lengths up to MAX_STREAM_PROT_LEN (0x00FFFFFF); natural transient allocation failures on a loaded host produce the same drift more slowly. Mirror the existing rollback pattern in ksmbd_kthread_fn(): on the alloc_transport() failure path, decrement active_num_conn gated on server_conf.max_connections. Repro details: with the patch reverted, forced alloc_transport() NULL returns leaked counter slots and subsequent connection attempts -- including legitimate connects issued after the forced-fail window had closed -- were all rejected with "Limit the maximum number of connections". With this patch applied, the same connect sequence produces no rejections and the counter cycles cleanly between zero and one on every accept.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31712

HIGH8.3

In the Linux kernel, the following vulnerability has been resolved: ksmbd: require minimum ACE size in smb_check_perm_dacl() Both ACE-walk loops in smb_check_perm_dacl() only guard against an under-sized remaining buffer, not against an ACE whose declared `ace->size` is smaller than the struct it claims to describe: if (offsetof(struct smb_ace, access_req) > aces_size) break; ace_size = le16_to_cpu(ace->size); if (ace_size > aces_size) break; The first check only requires the 4-byte ACE header to be in bounds; it does not require access_req (4 bytes at offset 4) to be readable. An attacker who has set a crafted DACL on a file they own can declare ace->size == 4 with aces_size == 4, pass both checks, and then granted |= le32_to_cpu(ace->access_req); /* upper loop / compare_sids(&sid, &ace->sid); / lower loop / reads access_req at offset 4 (OOB by up to 4 bytes) and ace->sid at offset 8 (OOB by up to CIFS_SID_BASE_SIZE + SID_MAX_SUB_AUTHORITIES 4 bytes). Tighten both loops to require ace_size >= offsetof(struct smb_ace, sid) + CIFS_SID_BASE_SIZE which is the smallest valid on-wire ACE layout (4-byte header + 4-byte access_req + 8-byte sid base with zero sub-auths). Also reject ACEs whose sid.num_subauth exceeds SID_MAX_SUB_AUTHORITIES before letting compare_sids() dereference sub_auth[] entries. parse_sec_desc() already enforces an equivalent check (lines 441-448); smb_check_perm_dacl() simply grew weaker validation over time. Reachability: authenticated SMB client with permission to set an ACL on a file. On a subsequent CREATE against that file, the kernel walks the stored DACL via smb_check_perm_dacl() and triggers the OOB read. Not pre-auth, and the OOB read is not reflected to the attacker, but KASAN reports and kernel state corruption are possible.

Published: 2026-05-01Modified: 2026-05-17

CVSS 3.xHIGH 8.3

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:H

References

CVE-2026-31713

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: fuse: abort on fatal signal during sync init When sync init is used and the server exits for some reason (error, crash) while processing FUSE_INIT, the filesystem creation will hang. The reason is that while all other threads will exit, the mounting thread (or process) will keep the device fd open, which will prevent an abort from happening. This is a regression from the async mount case, where the mount was done first, and the FUSE_INIT processing afterwards, in which case there's no such recursive syscall keeping the fd open.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31714

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid memory leak in f2fs_rename() syzbot reported a f2fs bug as below: BUG: memory leak unreferenced object 0xffff888127f70830 (size 16): comm "syz.0.23", pid 6144, jiffies 4294943712 hex dump (first 16 bytes): 3c af 57 72 5b e6 8f ad 6e 8e fd 33 42 39 03 ff <.Wr[...n..3B9.. backtrace (crc 925f8a80): kmemleak_alloc_recursive include/linux/kmemleak.h:44 [inline] slab_post_alloc_hook mm/slub.c:4520 [inline] slab_alloc_node mm/slub.c:4844 [inline] __do_kmalloc_node mm/slub.c:5237 [inline] __kmalloc_noprof+0x3bd/0x560 mm/slub.c:5250 kmalloc_noprof include/linux/slab.h:954 [inline] fscrypt_setup_filename+0x15e/0x3b0 fs/crypto/fname.c:364 f2fs_setup_filename+0x52/0xb0 fs/f2fs/dir.c:143 f2fs_rename+0x159/0xca0 fs/f2fs/namei.c:961 f2fs_rename2+0xd5/0xf20 fs/f2fs/namei.c:1308 vfs_rename+0x7ff/0x1250 fs/namei.c:6026 filename_renameat2+0x4f4/0x660 fs/namei.c:6144 __do_sys_renameat2 fs/namei.c:6173 [inline] __se_sys_renameat2 fs/namei.c:6168 [inline] __x64_sys_renameat2+0x59/0x80 fs/namei.c:6168 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xe2/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f The root cause is in commit 40b2d55e0452 ("f2fs: fix to create selinux label during whiteout initialization"), we added a call to f2fs_setup_filename() without a matching call to f2fs_free_filename(), fix it.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31715

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: f2fs: fix UAF caused by decrementing sbi->nr_pages[] in f2fs_write_end_io() The xfstests case "generic/107" and syzbot have both reported a NULL pointer dereference. The concurrent scenario that triggers the panic is as follows: F2FS_WB_CP_DATA write callback umount - f2fs_write_checkpoint - f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA) - blk_mq_end_request - bio_endio - f2fs_write_end_io : dec_page_count(sbi, F2FS_WB_CP_DATA) : wake_up(&sbi->cp_wait) - kill_f2fs_super - kill_block_super - f2fs_put_super : iput(sbi->node_inode) : sbi->node_inode = NULL : f2fs_in_warm_node_list - is_node_folio // sbi->node_inode is NULL and panic The root cause is that f2fs_put_super() calls iput(sbi->node_inode) and sets sbi->node_inode to NULL after sbi->nr_pages[F2FS_WB_CP_DATA] is decremented to zero. As a result, f2fs_in_warm_node_list() may dereference a NULL node_inode when checking whether a folio belongs to the node inode, leading to a panic. This patch fixes the issue by calling f2fs_in_warm_node_list() before decrementing sbi->nr_pages[F2FS_WB_CP_DATA], thus preventing the use-after-free condition.

Published: 2026-05-01Modified: 2026-05-17

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31716

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: fs/ntfs3: validate rec->used in journal-replay file record check check_file_record() validates rec->total against the record size but never validates rec->used. The do_action() journal-replay handlers read rec->used from disk and use it to compute memmove lengths: DeleteAttribute: memmove(attr, ..., used - asize - roff) CreateAttribute: memmove(..., attr, used - roff) change_attr_size: memmove(..., used - PtrOffset(rec, next)) When rec->used is smaller than the offset of a validated attribute, or larger than the record size, these subtractions can underflow allowing us to copy huge amounts of memory in to a 4kb buffer, generally considered a bad idea overall. This requires a corrupted filesystem, which isn't a threat model the kernel really needs to worry about, but checking for such an obvious out-of-bounds value is good to keep things robust, especially on journal replay Fix this up by bounding rec->used correctly. This is much like commit b2bc7c44ed17 ("fs/ntfs3: Fix slab-out-of-bounds read in DeleteIndexEntryRoot") which checked different values in this same switch statement.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

References

CVE-2026-31717

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: ksmbd: validate owner of durable handle on reconnect Currently, ksmbd does not verify if the user attempting to reconnect to a durable handle is the same user who originally opened the file. This allows any authenticated user to hijack an orphaned durable handle by predicting or brute-forcing the persistent ID. According to MS-SMB2, the server MUST verify that the SecurityContext of the reconnect request matches the SecurityContext associated with the existing open. Add a durable_owner structure to ksmbd_file to store the original opener's UID, GID, and account name. and catpure the owner information when a file handle becomes orphaned. and implementing ksmbd_vfs_compare_durable_owner() to validate the identity of the requester during SMB2_CREATE (DHnC).

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31718

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix use-after-free in __ksmbd_close_fd() via durable scavenger When a durable file handle survives session disconnect (TCP close without SMB2_LOGOFF), session_fd_check() sets fp->conn = NULL to preserve the handle for later reconnection. However, it did not clean up the byte-range locks on fp->lock_list. Later, when the durable scavenger thread times out and calls __ksmbd_close_fd(NULL, fp), the lock cleanup loop did: spin_lock(&fp->conn->llist_lock); This caused a slab use-after-free because fp->conn was NULL and the original connection object had already been freed by ksmbd_tcp_disconnect(). The root cause is asymmetric cleanup: lock entries (smb_lock->clist) were left dangling on the freed conn->lock_list while fp->conn was nulled out. To fix this issue properly, we need to handle the lifetime of smb_lock->clist across three paths: - Safely skip clist deletion when list is empty and fp->conn is NULL. - Remove the lock from the old connection's lock_list in session_fd_check() - Re-add the lock to the new connection's lock_list in ksmbd_reopen_durable_fd().

Published: 2026-05-01Modified: 2026-05-17

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31719

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: crypto: krb5enc - fix async decrypt skipping hash verification krb5enc_dispatch_decrypt() sets req->base.complete as the skcipher callback, which is the caller's own completion handler. When the skcipher completes asynchronously, this signals "done" to the caller without executing krb5enc_dispatch_decrypt_hash(), completely bypassing the integrity verification (hash check). Compare with the encrypt path which correctly uses krb5enc_encrypt_done as an intermediate callback to chain into the hash computation on async completion. Fix by adding krb5enc_decrypt_done as an intermediate callback that chains into krb5enc_dispatch_decrypt_hash() upon async skcipher completion, matching the encrypt path's callback pattern. Also fix EBUSY/EINPROGRESS handling throughout: remove krb5enc_request_complete() which incorrectly swallowed EINPROGRESS notifications that must be passed up to callers waiting on backlogged requests, and add missing EBUSY checks in krb5enc_encrypt_ahash_done for the dispatch_encrypt return value. Unset MAY_BACKLOG on the async completion path so the user won't see back-to-back EINPROGRESS notifications.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N

References

CVE-2026-31720

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_uac1_legacy: validate control request size f_audio_complete() copies req->length bytes into a 4-byte stack variable: u32 data = 0; memcpy(&data, req->buf, req->length); req->length is derived from the host-controlled USB request path, which can lead to a stack out-of-bounds write. Validate req->actual against the expected payload size for the supported control selectors and decode only the expected amount of data. This avoids copying a host-influenced length into a fixed-size stack object.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31721

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_hid: move list and spinlock inits from bind to alloc There was an issue when you did the following: - setup and bind an hid gadget - open /dev/hidg0 - use the resulting fd in EPOLL_CTL_ADD - unbind the UDC - bind the UDC - use the fd in EPOLL_CTL_DEL When CONFIG_DEBUG_LIST was enabled, a list_del corruption was reported within remove_wait_queue (via ep_remove_wait_queue). After some debugging I found out that the queues, which f_hid registers via poll_wait were the problem. These were initialized using init_waitqueue_head inside hidg_bind. So effectively, the bind function re-initialized the queues while there were still items in them. The solution is to move the initialization from hidg_bind to hidg_alloc to extend their lifetimes to the lifetime of the function instance. Additionally, I found many other possibly problematic init calls in the bind function, which I moved as well.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31722

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_rndis: Fix net_device lifecycle with device_move The net_device is allocated during function instance creation and registered during the bind phase with the gadget device as its sysfs parent. When the function unbinds, the parent device is destroyed, but the net_device survives, resulting in dangling sysfs symlinks: console:/ # ls -l /sys/class/net/usb0 lrwxrwxrwx ... /sys/class/net/usb0 -> /sys/devices/platform/.../gadget.0/net/usb0 console:/ # ls -l /sys/devices/platform/.../gadget.0/net/usb0 ls: .../gadget.0/net/usb0: No such file or directory Use device_move() to reparent the net_device between the gadget device tree and /sys/devices/virtual across bind and unbind cycles. During the final unbind, calling device_move(NULL) moves the net_device to the virtual device tree before the gadget device is destroyed. On rebinding, device_move() reparents the device back under the new gadget, ensuring proper sysfs topology and power management ordering. To maintain compatibility with legacy composite drivers (e.g., multi.c), the borrowed_net flag is used to indicate whether the network device is shared and pre-registered during the legacy driver's bind phase.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31723

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_subset: Fix net_device lifecycle with device_move The net_device is allocated during function instance creation and registered during the bind phase with the gadget device as its sysfs parent. When the function unbinds, the parent device is destroyed, but the net_device survives, resulting in dangling sysfs symlinks: console:/ # ls -l /sys/class/net/usb0 lrwxrwxrwx ... /sys/class/net/usb0 -> /sys/devices/platform/.../gadget.0/net/usb0 console:/ # ls -l /sys/devices/platform/.../gadget.0/net/usb0 ls: .../gadget.0/net/usb0: No such file or directory Use device_move() to reparent the net_device between the gadget device tree and /sys/devices/virtual across bind and unbind cycles. During the final unbind, calling device_move(NULL) moves the net_device to the virtual device tree before the gadget device is destroyed. On rebinding, device_move() reparents the device back under the new gadget, ensuring proper sysfs topology and power management ordering. To maintain compatibility with legacy composite drivers (e.g., multi.c), the bound flag is used to indicate whether the network device is shared and pre-registered during the legacy driver's bind phase.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31724

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_eem: Fix net_device lifecycle with device_move The net_device is allocated during function instance creation and registered during the bind phase with the gadget device as its sysfs parent. When the function unbinds, the parent device is destroyed, but the net_device survives, resulting in dangling sysfs symlinks: console:/ # ls -l /sys/class/net/usb0 lrwxrwxrwx ... /sys/class/net/usb0 -> /sys/devices/platform/.../gadget.0/net/usb0 console:/ # ls -l /sys/devices/platform/.../gadget.0/net/usb0 ls: .../gadget.0/net/usb0: No such file or directory Use device_move() to reparent the net_device between the gadget device tree and /sys/devices/virtual across bind and unbind cycles. During the final unbind, calling device_move(NULL) moves the net_device to the virtual device tree before the gadget device is destroyed. On rebinding, device_move() reparents the device back under the new gadget, ensuring proper sysfs topology and power management ordering. To maintain compatibility with legacy composite drivers (e.g., multi.c), the bound flag is used to indicate whether the network device is shared and pre-registered during the legacy driver's bind phase.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31725

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_ecm: Fix net_device lifecycle with device_move The net_device is allocated during function instance creation and registered during the bind phase with the gadget device as its sysfs parent. When the function unbinds, the parent device is destroyed, but the net_device survives, resulting in dangling sysfs symlinks: console:/ # ls -l /sys/class/net/usb0 lrwxrwxrwx ... /sys/class/net/usb0 -> /sys/devices/platform/.../gadget.0/net/usb0 console:/ # ls -l /sys/devices/platform/.../gadget.0/net/usb0 ls: .../gadget.0/net/usb0: No such file or directory Use device_move() to reparent the net_device between the gadget device tree and /sys/devices/virtual across bind and unbind cycles. During the final unbind, calling device_move(NULL) moves the net_device to the virtual device tree before the gadget device is destroyed. On rebinding, device_move() reparents the device back under the new gadget, ensuring proper sysfs topology and power management ordering. To maintain compatibility with legacy composite drivers (e.g., multi.c), the bound flag is used to indicate whether the network device is shared and pre-registered during the legacy driver's bind phase.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31726

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: uvc: fix NULL pointer dereference during unbind race Commit b81ac4395bbe ("usb: gadget: uvc: allow for application to cleanly shutdown") introduced two stages of synchronization waits totaling 1500ms in uvc_function_unbind() to prevent several types of kernel panics. However, this timing-based approach is insufficient during power management (PM) transitions. When the PM subsystem starts freezing user space processes, the wait_event_interruptible_timeout() is aborted early, which allows the unbind thread to proceed and nullify the gadget pointer (cdev->gadget = NULL): [ 814.123447][ T947] configfs-gadget.g1 gadget.0: uvc: uvc_function_unbind() [ 814.178583][ T3173] PM: suspend entry (deep) [ 814.192487][ T3173] Freezing user space processes [ 814.197668][ T947] configfs-gadget.g1 gadget.0: uvc: uvc_function_unbind no clean disconnect, wait for release When the PM subsystem resumes or aborts the suspend and tasks are restarted, the V4L2 release path is executed and attempts to access the already nullified gadget pointer, triggering a kernel panic: [ 814.292597][ C0] PM: pm_system_irq_wakeup: 479 triggered dhdpcie_host_wake [ 814.386727][ T3173] Restarting tasks ... [ 814.403522][ T4558] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000030 [ 814.404021][ T4558] pc : usb_gadget_deactivate+0x14/0xf4 [ 814.404031][ T4558] lr : usb_function_deactivate+0x54/0x94 [ 814.404078][ T4558] Call trace: [ 814.404080][ T4558] usb_gadget_deactivate+0x14/0xf4 [ 814.404083][ T4558] usb_function_deactivate+0x54/0x94 [ 814.404087][ T4558] uvc_function_disconnect+0x1c/0x5c [ 814.404092][ T4558] uvc_v4l2_release+0x44/0xac [ 814.404095][ T4558] v4l2_release+0xcc/0x130 Address the race condition and NULL pointer dereference by: 1. State Synchronization (flag + mutex) Introduce a 'func_unbound' flag in struct uvc_device. This allows uvc_function_disconnect() to safely skip accessing the nullified cdev->gadget pointer. As suggested by Alan Stern, this flag is protected by a new mutex (uvc->lock) to ensure proper memory ordering and prevent instruction reordering or speculative loads. This mutex is also used to protect 'func_connected' for consistent state management. 2. Explicit Synchronization (completion) Use a completion to synchronize uvc_function_unbind() with the uvc_vdev_release() callback. This prevents Use-After-Free (UAF) by ensuring struct uvc_device is freed after all video device resources are released.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31727

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: u_ether: Fix NULL pointer deref in eth_get_drvinfo Commit ec35c1969650 ("usb: gadget: f_ncm: Fix net_device lifecycle with device_move") reparents the gadget device to /sys/devices/virtual during unbind, clearing the gadget pointer. If the userspace tool queries on the surviving interface during this detached window, this leads to a NULL pointer dereference. Unable to handle kernel NULL pointer dereference Call trace: eth_get_drvinfo+0x50/0x90 ethtool_get_drvinfo+0x5c/0x1f0 __dev_ethtool+0xaec/0x1fe0 dev_ethtool+0x134/0x2e0 dev_ioctl+0x338/0x560 Add a NULL check for dev->gadget in eth_get_drvinfo(). When detached, skip copying the fw_version and bus_info strings, which is natively handled by ethtool_get_drvinfo for empty strings.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31728

MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: u_ether: Fix race between gether_disconnect and eth_stop A race condition between gether_disconnect() and eth_stop() leads to a NULL pointer dereference. Specifically, if eth_stop() is triggered concurrently while gether_disconnect() is tearing down the endpoints, eth_stop() attempts to access the cleared endpoint descriptor, causing the following NPE: Unable to handle kernel NULL pointer dereference Call trace: __dwc3_gadget_ep_enable+0x60/0x788 dwc3_gadget_ep_enable+0x70/0xe4 usb_ep_enable+0x60/0x15c eth_stop+0xb8/0x108 Because eth_stop() crashes while holding the dev->lock, the thread running gether_disconnect() fails to acquire the same lock and spins forever, resulting in a hardlockup: Core - Debugging Information for Hardlockup core(7) Call trace: queued_spin_lock_slowpath+0x94/0x488 _raw_spin_lock+0x64/0x6c gether_disconnect+0x19c/0x1e8 ncm_set_alt+0x68/0x1a0 composite_setup+0x6a0/0xc50 The root cause is that the clearing of dev->port_usb in gether_disconnect() is delayed until the end of the function. Move the clearing of dev->port_usb to the very beginning of gether_disconnect() while holding dev->lock. This cuts off the link immediately, ensuring eth_stop() will see dev->port_usb as NULL and safely bail out.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 4.7

CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31729

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: usb: typec: ucsi: validate connector number in ucsi_notify_common() The connector number extracted from CCI via UCSI_CCI_CONNECTOR() is a 7-bit field (0-127) that is used to index into the connector array in ucsi_connector_change(). However, the array is only allocated for the number of connectors reported by the device (typically 2-4 entries). A malicious or malfunctioning device could report an out-of-range connector number in the CCI, causing an out-of-bounds array access in ucsi_connector_change(). Add a bounds check in ucsi_notify_common(), the central point where CCI is parsed after arriving from hardware, so that bogus connector numbers are rejected before they propagate further.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31730

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: misc: fastrpc: possible double-free of cctx->remote_heap fastrpc_init_create_static_process() may free cctx->remote_heap on the err_map path but does not clear the pointer. Later, fastrpc_rpmsg_remove() frees cctx->remote_heap again if it is non-NULL, which can lead to a double-free if the INIT_CREATE_STATIC ioctl hits the error path and the rpmsg device is subsequently removed/unbound. Clear cctx->remote_heap after freeing it in the error path to prevent the later cleanup from freeing it again. This issue was found by an in-house analysis workflow that extracts AST-based information and runs static checks, with LLM assistance for triage, and was confirmed by manual code review. No hardware testing was performed.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31731

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: thermal: core: Address thermal zone removal races with resume Since thermal_zone_pm_complete() and thermal_zone_device_resume() re-initialize the poll_queue delayed work for the given thermal zone, the cancel_delayed_work_sync() in thermal_zone_device_unregister() may miss some already running work items and the thermal zone may be freed prematurely [1]. There are two failing scenarios that both start with running thermal_pm_notify_complete() right before invoking thermal_zone_device_unregister() for one of the thermal zones. In the first scenario, there is a work item already running for the given thermal zone when thermal_pm_notify_complete() calls thermal_zone_pm_complete() for that thermal zone and it continues to run when thermal_zone_device_unregister() starts. Since the poll_queue delayed work has been re-initialized by thermal_pm_notify_complete(), the running work item will be missed by the cancel_delayed_work_sync() in thermal_zone_device_unregister() and if it continues to run past the freeing of the thermal zone object, a use-after-free will occur. In the second scenario, thermal_zone_device_resume() queued up by thermal_pm_notify_complete() runs right after the thermal_zone_exit() called by thermal_zone_device_unregister() has returned. The poll_queue delayed work is re-initialized by it before cancel_delayed_work_sync() is called by thermal_zone_device_unregister(), so it may continue to run after the freeing of the thermal zone object, which also leads to a use-after-free. Address the first failing scenario by ensuring that no thermal work items will be running when thermal_pm_notify_complete() is called. For this purpose, first move the cancel_delayed_work() call from thermal_zone_pm_complete() to thermal_zone_pm_prepare() to prevent new work from entering the workqueue going forward. Next, switch over to using a dedicated workqueue for thermal events and update the code in thermal_pm_notify() to flush that workqueue after thermal_pm_notify_prepare() has returned which will take care of all leftover thermal work already on the workqueue (that leftover work would do nothing useful anyway because all of the thermal zones have been flagged as suspended). The second failing scenario is addressed by adding a tz->state check to thermal_zone_device_resume() to prevent it from re-initializing the poll_queue delayed work if the thermal zone is going away. Note that the above changes will also facilitate relocating the suspend and resume of thermal zones closer to the suspend and resume of devices, respectively.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31732

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: gpio: Fix resource leaks on errors in gpiochip_add_data_with_key() Since commit aab5c6f20023 ("gpio: set device type for GPIO chips"), `gdev->dev.release` is unset. As a result, the reference count to `gdev->dev` isn't dropped on the error handling paths. Drop the reference on errors. Also reorder the instructions to make the error handling simpler. Now gpiochip_add_data_with_key() roughly looks like: >>> Some memory allocation. Go to ERR ZONE 1 on errors. >>> device_initialize(). gpiodev_release() takes over the responsibility for freeing the resources of `gdev->dev`. The subsequent error handling paths shouldn't go through ERR ZONE 1 again which leads to double free. >>> Some initialization mainly on `gdev`. >>> The rest of initialization. Go to ERR ZONE 2 on errors. >>> Chip registration success and exit. >>> ERR ZONE 2. gpio_device_put() and exit. >>> ERR ZONE 1.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31733

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: sched_ext: Fix stale direct dispatch state in ddsp_dsq_id @p->scx.ddsp_dsq_id can be left set (non-SCX_DSQ_INVALID) triggering a spurious warning in mark_direct_dispatch() when the next wakeup's ops.select_cpu() calls scx_bpf_dsq_insert(), such as: WARNING: kernel/sched/ext.c:1273 at scx_dsq_insert_commit+0xcd/0x140 The root cause is that ddsp_dsq_id was only cleared in dispatch_enqueue(), which is not reached in all paths that consume or cancel a direct dispatch verdict. Fix it by clearing it at the right places: - direct_dispatch(): cache the direct dispatch state in local variables and clear it before dispatch_enqueue() on the synchronous path. For the deferred path, the direct dispatch state must remain set until process_ddsp_deferred_locals() consumes them. - process_ddsp_deferred_locals(): cache the dispatch state in local variables and clear it before calling dispatch_to_local_dsq(), which may migrate the task to another rq. - do_enqueue_task(): clear the dispatch state on the enqueue path (local/global/bypass fallbacks), where the direct dispatch verdict is ignored. - dequeue_task_scx(): clear the dispatch state after dispatch_dequeue() to handle both the deferred dispatch cancellation and the holding_cpu race, covering all cases where a pending direct dispatch is cancelled. - scx_disable_task(): clear the direct dispatch state when transitioning a task out of the current scheduler. Waking tasks may have had the direct dispatch state set by the outgoing scheduler's ops.select_cpu() and then been queued on a wake_list via ttwu_queue_wakelist(), when SCX_OPS_ALLOW_QUEUED_WAKEUP is set. Such tasks are not on the runqueue and are not iterated by scx_bypass(), so their direct dispatch state won't be cleared. Without this clear, any subsequent SCX scheduler that tries to direct dispatch the task will trigger the WARN_ON_ONCE() in mark_direct_dispatch().

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31734

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: sched_ext: Fix is_bpf_migration_disabled() false negative on non-PREEMPT_RCU Since commit 8e4f0b1ebcf2 ("bpf: use rcu_read_lock_dont_migrate() for trampoline.c"), the BPF prolog (__bpf_prog_enter) calls migrate_disable() only when CONFIG_PREEMPT_RCU is enabled, via rcu_read_lock_dont_migrate(). Without CONFIG_PREEMPT_RCU, the prolog never touches migration_disabled, so migration_disabled == 1 always means the task is truly migration-disabled regardless of whether it is the current task. The old unconditional p == current check was a false negative in this case, potentially allowing a migration-disabled task to be dispatched to a remote CPU and triggering scx_error in task_can_run_on_remote_rq(). Only apply the p == current disambiguation when CONFIG_PREEMPT_RCU is enabled, where the ambiguity with the BPF prolog still exists.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31736

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: ethernet: mtk_ppe: avoid NULL deref when gmac0 is disabled If the gmac0 is disabled, the precheck for a valid ingress device will cause a NULL pointer deref and crash the system. This happens because eth->netdev[0] will be NULL but the code will directly try to access netdev_ops. Instead of just checking for the first net_device, it must be checked if any of the mtk_eth net_devices is matching the netdev_ops of the ingress device.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31737

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: ftgmac100: fix ring allocation unwind on open failure ftgmac100_alloc_rings() allocates rx_skbs, tx_skbs, rxdes, txdes, and rx_scratch in stages. On intermediate failures it returned -ENOMEM directly, leaking resources allocated earlier in the function. Rework the failure path to use staged local unwind labels and free allocated resources in reverse order before returning -ENOMEM. This matches common netdev allocation cleanup style.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31738

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: vxlan: validate ND option lengths in vxlan_na_create vxlan_na_create() walks ND options according to option-provided lengths. A malformed option can make the parser advance beyond the computed option span or use a too-short source LLADDR option payload. Validate option lengths against the remaining NS option area before advancing, and only read source LLADDR when the option is large enough for an Ethernet address.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31739

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: crypto: tegra - Add missing CRYPTO_ALG_ASYNC The tegra crypto driver failed to set the CRYPTO_ALG_ASYNC on its asynchronous algorithms, causing the crypto API to select them for users that request only synchronous algorithms. This causes crashes (at least). Fix this by adding the flag like what the other drivers do. Also remove the unnecessary CRYPTO_ALG_TYPE_* flags, since those just get ignored and overridden by the registration function anyway.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31740

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: counter: rz-mtu3-cnt: do not use struct rz_mtu3_channel's dev member The counter driver can use HW channels 1 and 2, while the PWM driver can use HW channels 0, 1, 2, 3, 4, 6, 7. The dev member is assigned both by the counter driver and the PWM driver for channels 1 and 2, to their own struct device instance, overwriting the previous value. The sub-drivers race to assign their own struct device pointer to the same struct rz_mtu3_channel's dev member. The dev member of struct rz_mtu3_channel is used by the counter sub-driver for runtime PM. Depending on the probe order of the counter and PWM sub-drivers, the dev member may point to the wrong struct device instance, causing the counter sub-driver to do runtime PM actions on the wrong device. To fix this, use the parent pointer of the counter, which is assigned during probe to the correct struct device, not the struct device pointer inside the shared struct rz_mtu3_channel.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31741

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: counter: rz-mtu3-cnt: prevent counter from being toggled multiple times Runtime PM counter is incremented / decremented each time the sysfs enable file is written to. If user writes 0 to the sysfs enable file multiple times, runtime PM usage count underflows, generating the following message. rz-mtu3-counter rz-mtu3-counter.0: Runtime PM usage count underflow! At the same time, hardware registers end up being accessed with clocks off in rz_mtu3_terminate_counter() to disable an already disabled channel. If user writes 1 to the sysfs enable file multiple times, runtime PM usage count will be incremented each time, requiring the same number of 0 writes to get it back to 0. If user writes 0 to the sysfs enable file while PWM is in progress, PWM is stopped without counter being the owner of the underlying MTU3 channel. Check against the cached count_is_enabled value and exit if the user is trying to set the same enable value.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31743

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: nvmem: zynqmp_nvmem: Fix buffer size in DMA and memcpy Buffer size used in dma allocation and memcpy is wrong. It can lead to undersized DMA buffer access and possible memory corruption. use correct buffer size in dma_alloc_coherent and memcpy.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31746

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: s390/zcrypt: Fix memory leak with CCA cards used as accelerator Tests showed that there is a memory leak if CCA cards are used as accelerator for clear key RSA requests (ME and CRT). With the last rework for the memory allocation the AP messages are allocated by ap_init_apmsg() but for some reason on two places (ME and CRT) the older allocation was still in place. So the first allocation simple was never freed.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31747

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: comedi: me4000: Fix potential overrun of firmware buffer `me4000_xilinx_download()` loads the firmware that was requested by `request_firmware()`. It is possible for it to overrun the source buffer because it blindly trusts the file format. It reads a data stream length from the first 4 bytes into variable `file_length` and reads the data stream contents of length `file_length` from offset 16 onwards. Add a test to ensure that the supplied firmware is long enough to contain the header and the data stream. On failure, log an error and return `-EINVAL`. Note: The firmware loading was totally broken before commit ac584af59945 ("staging: comedi: me4000: fix firmware downloading"), but that is the most sensible target for this fix.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31748

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: comedi: me_daq: Fix potential overrun of firmware buffer `me2600_xilinx_download()` loads the firmware that was requested by `request_firmware()`. It is possible for it to overrun the source buffer because it blindly trusts the file format. It reads a data stream length from the first 4 bytes into variable `file_length` and reads the data stream contents of length `file_length` from offset 16 onwards. Although it checks that the supplied firmware is at least 16 bytes long, it does not check that it is long enough to contain the data stream. Add a test to ensure that the supplied firmware is long enough to contain the header and the data stream. On failure, log an error and return `-EINVAL`.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31749

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: comedi: ni_atmio16d: Fix invalid clean-up after failed attach If the driver's COMEDI "attach" handler function (`atmio16d_attach()`) returns an error, the COMEDI core will call the driver's "detach" handler function (`atmio16d_detach()`) to clean up. This calls `reset_atmio16d()` unconditionally, but depending on where the error occurred in the attach handler, the device may not have been sufficiently initialized to call `reset_atmio16d()`. It uses `dev->iobase` as the I/O port base address and `dev->private` as the pointer to the COMEDI device's private data structure. `dev->iobase` may still be set to its initial value of 0, which would result in undesired writes to low I/O port addresses. `dev->private` may still be `NULL`, which would result in null pointer dereferences. Fix `atmio16d_detach()` by checking that `dev->private` is valid (non-null) before calling `reset_atmio16d()`. This implies that `dev->iobase` was set correctly since that is set up before `dev->private`.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31751

MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: comedi: dt2815: add hardware detection to prevent crash The dt2815 driver crashes when attached to I/O ports without actual hardware present. This occurs because syzkaller or users can attach the driver to arbitrary I/O addresses via COMEDI_DEVCONFIG ioctl. When no hardware exists at the specified port, inb() operations return 0xff (floating bus), but outb() operations can trigger page faults due to undefined behavior, especially under race conditions: BUG: unable to handle page fault for address: 000000007fffff90 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page RIP: 0010:dt2815_attach+0x6e0/0x1110 Add hardware detection by reading the status register before attempting any write operations. If the read returns 0xff, assume no hardware is present and fail the attach with -ENODEV. This prevents crashes from outb() operations on non-existent hardware.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 4.7

CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31752

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: bridge: br_nd_send: validate ND option lengths br_nd_send() walks ND options according to option-provided lengths. A malformed option can make the parser advance beyond the computed option span or use a too-short source LLADDR option payload. Validate option lengths against the remaining NS option area before advancing, and only read source LLADDR when the option is large enough for an Ethernet address.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31754

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: cdns3: gadget: fix state inconsistency on gadget init failure When cdns3_gadget_start() fails, the DRD hardware is left in gadget mode while software state remains INACTIVE, creating hardware/software state inconsistency. When switching to host mode via sysfs: echo host > /sys/class/usb_role/13180000.usb-role-switch/role The role state is not set to CDNS_ROLE_STATE_ACTIVE due to the error, so cdns_role_stop() skips cleanup because state is still INACTIVE. This violates the DRD controller design specification (Figure22), which requires returning to idle state before switching roles. This leads to a synchronous external abort in xhci_gen_setup() when setting up the host controller: [ 516.440698] configfs-gadget 13180000.usb: failed to start g1: -19 [ 516.442035] cdns-usb3 13180000.usb: Failed to add gadget [ 516.443278] cdns-usb3 13180000.usb: set role 2 has failed ... [ 1301.375722] xhci-hcd xhci-hcd.1.auto: xHCI Host Controller [ 1301.377716] Internal error: synchronous external abort: 96000010 [#1] PREEMPT SMP [ 1301.382485] pc : xhci_gen_setup+0xa4/0x408 [ 1301.393391] backtrace: ... xhci_gen_setup+0xa4/0x408 <-- CRASH xhci_plat_setup+0x44/0x58 usb_add_hcd+0x284/0x678 ... cdns_role_set+0x9c/0xbc <-- Role switch Fix by calling cdns_drd_gadget_off() in the error path to properly clean up the DRD gadget state.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31755

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: cdns3: gadget: fix NULL pointer dereference in ep_queue When the gadget endpoint is disabled or not yet configured, the ep->desc pointer can be NULL. This leads to a NULL pointer dereference when __cdns3_gadget_ep_queue() is called, causing a kernel crash. Add a check to return -ESHUTDOWN if ep->desc is NULL, which is the standard return code for unconfigured endpoints. This prevents potential crashes when ep_queue is called on endpoints that are not ready.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31756

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: dwc2: gadget: Fix spin_lock/unlock mismatch in dwc2_hsotg_udc_stop() dwc2_gadget_exit_clock_gating() internally calls call_gadget() macro, which expects hsotg->lock to be held since it does spin_unlock/spin_lock around the gadget driver callback invocation. However, dwc2_hsotg_udc_stop() calls dwc2_gadget_exit_clock_gating() without holding the lock. This leads to: - spin_unlock on a lock that is not held (undefined behavior) - The lock remaining held after dwc2_gadget_exit_clock_gating() returns, causing a deadlock when spin_lock_irqsave() is called later in the same function. Fix this by acquiring hsotg->lock before calling dwc2_gadget_exit_clock_gating() and releasing it afterwards, which satisfies the locking requirement of the call_gadget() macro.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31757

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: misc: usbio: Fix URB memory leak on submit failure When usb_submit_urb() fails in usbio_probe(), the previously allocated URB is never freed, causing a memory leak. Fix this by jumping to err_free_urb label to properly release the URB on the error path.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31758

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: usb: usbtmc: Flush anchored URBs in usbtmc_release When calling usbtmc_release, pending anchored URBs must be flushed or killed to prevent use-after-free errors (e.g. in the HCD giveback path). Call usbtmc_draw_down() to allow anchored URBs to be completed.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31759

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: usb: ulpi: fix double free in ulpi_register_interface() error path When device_register() fails, ulpi_register() calls put_device() on ulpi->dev. The device release callback ulpi_dev_release() drops the OF node reference and frees ulpi, but the current error path in ulpi_register_interface() then calls kfree(ulpi) again, causing a double free. Let put_device() handle the cleanup through ulpi_dev_release() and avoid freeing ulpi again in ulpi_register_interface().

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31760

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: gpib: lpvo_usb: fix memory leak on disconnect The driver iterates over the registered USB interfaces during GPIB attach and takes a reference to their USB devices until a match is found. These references are never released which leads to a memory leak when devices are disconnected. Fix the leak by dropping the unnecessary references.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31761

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: iio: gyro: mpu3050: Move iio_device_register() to correct location iio_device_register() should be at the end of the probe function to prevent race conditions. Place iio_device_register() at the end of the probe function and place iio_device_unregister() accordingly.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31762

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: iio: gyro: mpu3050: Fix irq resource leak The interrupt handler is setup but only a few lines down if iio_trigger_register() fails the function returns without properly releasing the handler. Add cleanup goto to resolve resource leak. Detected by Smatch: drivers/iio/gyro/mpu3050-core.c:1128 mpu3050_trigger_probe() warn: 'irq' from request_threaded_irq() not released on lines: 1124.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31763

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: iio: gyro: mpu3050: Fix incorrect free_irq() variable The handler for the IRQ part of this driver is mpu3050->trig but, in the teardown free_irq() is called with handler mpu3050. Use correct IRQ handler when calling free_irq().

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31765

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Change AMDGPU_VA_RESERVED_TRAP_SIZE to 64KB Currently, AMDGPU_VA_RESERVED_TRAP_SIZE is hardcoded to 8KB, while KFD_CWSR_TBA_TMA_SIZE is defined as 2 * PAGE_SIZE. On systems with 4K pages, both values match (8KB), so allocation and reserved space are consistent. However, on 64K page-size systems, KFD_CWSR_TBA_TMA_SIZE becomes 128KB, while the reserved trap area remains 8KB. This mismatch causes the kernel to crash when running rocminfo or rccl unit tests. Kernel attempted to read user page (2) - exploit attempt? (uid: 1001) BUG: Kernel NULL pointer dereference on read at 0x00000002 Faulting instruction address: 0xc0000000002c8a64 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries CPU: 34 UID: 1001 PID: 9379 Comm: rocminfo Tainted: G E 6.19.0-rc4-amdgpu-00320-gf23176405700 #56 VOLUNTARY Tainted: [E]=UNSIGNED_MODULE Hardware name: IBM,9105-42A POWER10 (architected) 0x800200 0xf000006 of:IBM,FW1060.30 (ML1060_896) hv:phyp pSeries NIP: c0000000002c8a64 LR: c00000000125dbc8 CTR: c00000000125e730 REGS: c0000001e0957580 TRAP: 0300 Tainted: G E MSR: 8000000000009033 CR: 24008268 XER: 00000036 CFAR: c00000000125dbc4 DAR: 0000000000000002 DSISR: 40000000 IRQMASK: 1 GPR00: c00000000125d908 c0000001e0957820 c0000000016e8100 c00000013d814540 GPR04: 0000000000000002 c00000013d814550 0000000000000045 0000000000000000 GPR08: c00000013444d000 c00000013d814538 c00000013d814538 0000000084002268 GPR12: c00000000125e730 c000007e2ffd5f00 ffffffffffffffff 0000000000020000 GPR16: 0000000000000000 0000000000000002 c00000015f653000 0000000000000000 GPR20: c000000138662400 c00000013d814540 0000000000000000 c00000013d814500 GPR24: 0000000000000000 0000000000000002 c0000001e0957888 c0000001e0957878 GPR28: c00000013d814548 0000000000000000 c00000013d814540 c0000001e0957888 NIP [c0000000002c8a64] __mutex_add_waiter+0x24/0xc0 LR [c00000000125dbc8] __mutex_lock.constprop.0+0x318/0xd00 Call Trace: 0xc0000001e0957890 (unreliable) __mutex_lock.constprop.0+0x58/0xd00 amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x6fc/0xb60 [amdgpu] kfd_process_alloc_gpuvm+0x54/0x1f0 [amdgpu] kfd_process_device_init_cwsr_dgpu+0xa4/0x1a0 [amdgpu] kfd_process_device_init_vm+0xd8/0x2e0 [amdgpu] kfd_ioctl_acquire_vm+0xd0/0x130 [amdgpu] kfd_ioctl+0x514/0x670 [amdgpu] sys_ioctl+0x134/0x180 system_call_exception+0x114/0x300 system_call_vectored_common+0x15c/0x2ec This patch changes AMDGPU_VA_RESERVED_TRAP_SIZE to 64 KB and KFD_CWSR_TBA_TMA_SIZE to the AMD GPU page size. This means we reserve 64 KB for the trap in the address space, but only allocate 8 KB within it. With this approach, the allocation size never exceeds the reserved area. (cherry picked from commit 31b8de5e55666f26ea7ece5f412b83eab3f56dbb)

Published: 2026-05-01Modified: 2026-05-11

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31766

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: validate doorbell_offset in user queue creation amdgpu_userq_get_doorbell_index() passes the user-provided doorbell_offset to amdgpu_doorbell_index_on_bar() without bounds checking. An arbitrarily large doorbell_offset can cause the calculated doorbell index to fall outside the allocated doorbell BO, potentially corrupting kernel doorbell space. Validate that doorbell_offset falls within the doorbell BO before computing the BAR index, using u64 arithmetic to prevent overflow. (cherry picked from commit de1ef4ffd70e1d15f0bf584fd22b1f28cbd5e2ec)

Published: 2026-05-01Modified: 2026-05-11

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:H

References

CVE-2026-31767

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/i915/dsi: Don't do DSC horizontal timing adjustments in command mode Stop adjusting the horizontal timing values based on the compression ratio in command mode. Bspec seems to be telling us to do this only in video mode, and this is also how the Windows driver does things. This should also fix a div-by-zero on some machines because the adjusted htotal ends up being so small that we end up with line_time_us==0 when trying to determine the vtotal value in command mode. Note that this doesn't actually make the display on the Huawei Matebook E work, but at least the kernel no longer explodes when the driver loads. (cherry picked from commit 0b475e91ecc2313207196c6d7fd5c53e1a878525)

Published: 2026-05-01Modified: 2026-05-11

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31768

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: iio: adc: ti-adc161s626: use DMA-safe memory for spi_read() Add a DMA-safe buffer and use it for spi_read() instead of a stack memory. All SPI buffers must be DMA-safe. Since we only need up to 3 bytes, we just use a u8[] instead of be16 and be32 and change the conversion functions appropriately.

Published: 2026-05-01Modified: 2026-05-11

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31769

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: gpib: fix use-after-free in IO ioctl handlers The IBRD, IBWRT, IBCMD, and IBWAIT ioctl handlers use a gpib_descriptor pointer after board->big_gpib_mutex has been released. A concurrent IBCLOSEDEV ioctl can free the descriptor via close_dev_ioctl() during this window, causing a use-after-free. The IO handlers (read_ioctl, write_ioctl, command_ioctl) explicitly release big_gpib_mutex before calling their handler. wait_ioctl() is called with big_gpib_mutex held, but ibwait() releases it internally when wait_mask is non-zero. In all four cases, the descriptor pointer obtained from handle_to_descriptor() becomes unprotected. Fix this by introducing a kernel-only descriptor_busy reference count in struct gpib_descriptor. Each handler atomically increments descriptor_busy under file_priv->descriptors_mutex before releasing the lock, and decrements it when done. close_dev_ioctl() checks descriptor_busy under the same lock and rejects the close with -EBUSY if the count is non-zero. A reference count rather than a simple flag is necessary because multiple handlers can operate on the same descriptor concurrently (e.g. IBRD and IBWAIT on the same handle from different threads). A separate counter is needed because io_in_progress can be cleared from unprivileged userspace via the IBWAIT ioctl (through general_ibstatus() with set_mask containing CMPL), which would allow an attacker to bypass a check based solely on io_in_progress. The new descriptor_busy counter is only modified by the kernel IO paths. The lock ordering is consistent (big_gpib_mutex -> descriptors_mutex) and the handlers only hold descriptors_mutex briefly during the lookup, so there is no deadlock risk and no impact on IO throughput.

Published: 2026-05-01Modified: 2026-05-11

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31770

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: hwmon: (occ) Fix division by zero in occ_show_power_1() In occ_show_power_1() case 1, the accumulator is divided by update_tag without checking for zero. If no samples have been collected yet (e.g. during early boot when the sensor block is included but hasn't been updated), update_tag is zero, causing a kernel divide-by-zero crash. The 2019 fix in commit 211186cae14d ("hwmon: (occ) Fix division by zero issue") only addressed occ_get_powr_avg() used by occ_show_power_2() and occ_show_power_a0(). This separate code path in occ_show_power_1() was missed. Fix this by reusing the existing occ_get_powr_avg() helper, which already handles the zero-sample case and uses mul_u64_u32_div() to multiply before dividing for better precision. Move the helper above occ_show_power_1() so it is visible at the call site. [groeck: Fix alignment problems reported by checkpatch]

Published: 2026-05-01Modified: 2026-05-11

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31772

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_sync: fix stack buffer overflow in hci_le_big_create_sync hci_le_big_create_sync() uses DEFINE_FLEX to allocate a struct hci_cp_le_big_create_sync on the stack with room for 0x11 (17) BIS entries. However, conn->num_bis can hold up to HCI_MAX_ISO_BIS (31) entries — validated against ISO_MAX_NUM_BIS (0x1f) in the caller hci_conn_big_create_sync(). When conn->num_bis is between 18 and 31, the memcpy that copies conn->bis into cp->bis writes up to 14 bytes past the stack buffer, corrupting adjacent stack memory. This is trivially reproducible: binding an ISO socket with bc_num_bis = ISO_MAX_NUM_BIS (31) and calling listen() will eventually trigger hci_le_big_create_sync() from the HCI command sync worker, causing a KASAN-detectable stack-out-of-bounds write: BUG: KASAN: stack-out-of-bounds in hci_le_big_create_sync+0x256/0x3b0 Write of size 31 at addr ffffc90000487b48 by task kworker/u9:0/71 Fix this by changing the DEFINE_FLEX count from the incorrect 0x11 to HCI_MAX_ISO_BIS, which matches the maximum number of BIS entries that conn->bis can actually carry.

Published: 2026-05-01Modified: 2026-05-11

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31773

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: SMP: derive legacy responder STK authentication from MITM state The legacy responder path in smp_random() currently labels the stored STK as authenticated whenever pending_sec_level is BT_SECURITY_HIGH. That reflects what the local service requested, not what the pairing flow actually achieved. For Just Works/Confirm legacy pairing, SMP_FLAG_MITM_AUTH stays clear and the resulting STK should remain unauthenticated even if the local side requested HIGH security. Use the established MITM state when storing the responder STK so the key metadata matches the pairing result. This also keeps the legacy path aligned with the Secure Connections code, which already treats JUST_WORKS/JUST_CFM as unauthenticated.

Published: 2026-05-01Modified: 2026-05-11

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31774

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: io_uring/net: fix slab-out-of-bounds read in io_bundle_nbufs() sqe->len is __u32 but gets stored into sr->len which is int. When userspace passes sqe->len values exceeding INT_MAX (e.g. 0xFFFFFFFF), sr->len overflows to a negative value. This negative value propagates through the bundle recv/send path: 1. io_recv(): sel.val = sr->len (ssize_t gets -1) 2. io_recv_buf_select(): arg.max_len = sel->val (size_t gets 0xFFFFFFFFFFFFFFFF) 3. io_ring_buffers_peek(): buf->len is not clamped because max_len is astronomically large 4. iov[].iov_len = 0xFFFFFFFF flows into io_bundle_nbufs() 5. io_bundle_nbufs(): min_t(int, 0xFFFFFFFF, ret) yields -1, causing ret to increase instead of decrease, creating an infinite loop that reads past the allocated iov[] array This results in a slab-out-of-bounds read in io_bundle_nbufs() from the kmalloc-64 slab, as nbufs increments past the allocated iovec entries. BUG: KASAN: slab-out-of-bounds in io_bundle_nbufs+0x128/0x160 Read of size 8 at addr ffff888100ae05c8 by task exp/145 Call Trace: io_bundle_nbufs+0x128/0x160 io_recv_finish+0x117/0xe20 io_recv+0x2db/0x1160 Fix this by rejecting negative sr->len values early in both io_sendmsg_prep() and io_recvmsg_prep(). Since sqe->len is __u32, any value > INT_MAX indicates overflow and is not a valid length.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31778

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: ALSA: caiaq: fix stack out-of-bounds read in init_card The loop creates a whitespace-stripped copy of the card shortname where `len < sizeof(card->id)` is used for the bounds check. Since sizeof(card->id) is 16 and the local id buffer is also 16 bytes, writing 16 non-space characters fills the entire buffer, overwriting the terminating nullbyte. When this non-null-terminated string is later passed to snd_card_set_id() -> copy_valid_id_string(), the function scans forward with `while (*nid && ...)` and reads past the end of the stack buffer, reading the contents of the stack. A USB device with a product name containing many non-ASCII, non-space characters (e.g. multibyte UTF-8) will reliably trigger this as follows: BUG: KASAN: stack-out-of-bounds in copy_valid_id_string sound/core/init.c:696 [inline] BUG: KASAN: stack-out-of-bounds in snd_card_set_id_no_lock+0x698/0x74c sound/core/init.c:718 The off-by-one has been present since commit bafeee5b1f8d ("ALSA: snd_usb_caiaq: give better shortname") from June 2009 (v2.6.31-rc1), which first introduced this whitespace-stripping loop. The original code never accounted for the null terminator when bounding the copy. Fix this by changing the loop bound to `sizeof(card->id) - 1`, ensuring at least one byte remains as the null terminator.

Published: 2026-05-01Modified: 2026-05-11

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31779

HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: mvm: fix potential out-of-bounds read in iwl_mvm_nd_match_info_handler() The memcpy function assumes the dynamic array notif->matches is at least as large as the number of bytes to copy. Otherwise, results->matches may contain unwanted data. To guarantee safety, extend the validation in one of the checks to ensure sufficient packet length. Found by Linux Verification Center (linuxtesting.org) with SVACE.

Published: 2026-05-01Modified: 2026-05-11

CVSS 3.xHIGH 8.1

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-31780

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: wifi: wilc1000: fix u8 overflow in SSID scan buffer size calculation The variable valuesize is declared as u8 but accumulates the total length of all SSIDs to scan. Each SSID contributes up to 33 bytes (IEEE80211_MAX_SSID_LEN + 1), and with WILC_MAX_NUM_PROBED_SSID (10) SSIDs the total can reach 330, which wraps around to 74 when stored in a u8. This causes kmalloc to allocate only 75 bytes while the subsequent memcpy writes up to 331 bytes into the buffer, resulting in a 256-byte heap buffer overflow. Widen valuesize from u8 to u32 to accommodate the full range.

Published: 2026-05-01Modified: 2026-05-11

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31781

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/ioc32: stop speculation on the drm_compat_ioctl path The drm compat ioctl path takes a user controlled pointer, and then dereferences it into a table of function pointers, the signature method of spectre problems. Fix this up by calling array_index_nospec() on the index to the function pointer list.

Published: 2026-05-01Modified: 2026-05-11

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31782

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: perf/x86: Fix potential bad container_of in intel_pmu_hw_config Auto counter reload may have a group of events with software events present within it. The software event PMU isn't the x86_hybrid_pmu and a container_of operation in intel_pmu_set_acr_caused_constr (via the hybrid helper) could cause out of bound memory reads. Avoid this by guarding the call to intel_pmu_set_acr_caused_constr with an is_x86_event check.

Published: 2026-05-01Modified: 2026-05-11

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31783

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: spi: amlogic: spifc-a4: unregister ECC engine on probe failure and remove() callback aml_sfc_probe() registers the on-host NAND ECC engine, but teardown was missing from both probe unwind and remove-time cleanup. Add a devm cleanup action after successful registration so nand_ecc_unregister_on_host_hw_engine() runs automatically on probe failures and during device removal.

Published: 2026-05-01Modified: 2026-05-11

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31784

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/xe/pxp: Clear restart flag in pxp_start after jumping back If we don't clear the flag we'll keep jumping back at the beginning of the function once we reach the end. (cherry picked from commit 0850ec7bb2459602351639dccf7a68a03c9d1ee0)

Published: 2026-05-01Modified: 2026-05-12

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-31786

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Buffer overflow in drivers/xen/sys-hypervisor.c The build id returned by HYPERVISOR_xen_version(XENVER_build_id) is neither NUL terminated nor a string. The first causes a buffer overflow as sprintf in buildid_show will read and copy till it finds a NUL. 00000000 f4 91 51 f4 dd 38 9e 9d 65 47 52 eb 10 71 db 50 |..Q..8..eGR..q.P| 00000010 b9 a8 01 42 6f 2e 32 |...Bo.2| 00000017 So use a memcpy instead of sprintf to have the correct value: 00000000 f4 91 51 f4 dd 00 9e 9d 65 47 52 eb 10 71 db 50 |..Q.....eGR..q.P| 00000010 b9 a8 01 42 |...B| 00000014 (the above have a hack to embed a zero inside and check it's returned correctly). This is XSA-485 / CVE-2026-31786

Published: 2026-04-30Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31787

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: xen/privcmd: fix double free via VMA splitting privcmd_vm_ops defines .close (privcmd_close), but neither .may_split nor .open. When userspace does a partial munmap() on a privcmd mapping, the kernel splits the VMA via __split_vma(). Since may_split is NULL, the split is allowed. vm_area_dup() copies vm_private_data (a pages array allocated in alloc_empty_pages()) into the new VMA without any fixup, because there is no .open callback. Both VMAs now point to the same pages array. When the unmapped portion is closed, privcmd_close() calls: - xen_unmap_domain_gfn_range() - xen_free_unpopulated_pages() - kvfree(pages) The surviving VMA still holds the dangling pointer. When it is later destroyed, the same sequence runs again, which leads to a double free. Fix this issue by adding a .may_split callback denying the VMA split. This is XSA-487 / CVE-2026-31787

Published: 2026-04-30Modified: 2026-05-06

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-31788

HIGH8.2

In the Linux kernel, the following vulnerability has been resolved: xen/privcmd: restrict usage in unprivileged domU The Xen privcmd driver allows to issue arbitrary hypercalls from user space processes. This is normally no problem, as access is usually limited to root and the hypervisor will deny any hypercalls affecting other domains. In case the guest is booted using secure boot, however, the privcmd driver would be enabling a root user process to modify e.g. kernel memory contents, thus breaking the secure boot feature. The only known case where an unprivileged domU is really needing to use the privcmd driver is the case when it is acting as the device model for another guest. In this case all hypercalls issued via the privcmd driver will target that other guest. Fortunately the privcmd driver can already be locked down to allow only hypercalls targeting a specific domain, but this mode can be activated from user land only today. The target domain can be obtained from Xenstore, so when not running in dom0 restrict the privcmd driver to that target domain from the beginning, resolving the potential problem of breaking secure boot. This is XSA-482 --- V2: - defer reading from Xenstore if Xenstore isn't ready yet (Jan Beulich) - wait in open() if target domain isn't known yet - issue message in case no target domain found (Jan Beulich)

Published: 2026-03-25Modified: 2026-04-24

CVSS 3.xHIGH 8.2

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:H/UI:N/S:C/C:H/I:H/A:H

References

CVE-2026-43004

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: spi: stm32-ospi: Fix resource leak in remove() callback The remove() callback returned early if pm_runtime_resume_and_get() failed, skipping the cleanup of spi controller and other resources. Remove the early return so cleanup completes regardless of PM resume result.

Published: 2026-05-01Modified: 2026-05-12

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43005

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: hwmon: (tps53679) Fix array access with zero-length block read i2c_smbus_read_block_data() can return 0, indicating a zero-length read. When this happens, tps53679_identify_chip() accesses buf[ret - 1] which is buf[-1], reading one byte before the buffer on the stack. Fix by changing the check from "ret < 0" to "ret <= 0", treating a zero-length read as an error (-EIO), which prevents the out-of-bounds array access. Also fix a typo in the adjacent comment: "if present" instead of duplicate "if".

Published: 2026-05-01Modified: 2026-05-12

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-43006

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: io_uring/rsrc: reject zero-length fixed buffer import validate_fixed_range() admits buf_addr at the exact end of the registered region when len is zero, because the check uses strict greater-than (buf_end > imu->ubuf + imu->len). io_import_fixed() then computes offset == imu->len, which causes the bvec skip logic to advance past the last bio_vec entry and read bv_offset from out-of-bounds slab memory. Return early from io_import_fixed() when len is zero. A zero-length import has no data to transfer and should not walk the bvec array at all. BUG: KASAN: slab-out-of-bounds in io_import_reg_buf+0x697/0x7f0 Read of size 4 at addr ffff888002bcc254 by task poc/103 Call Trace: io_import_reg_buf+0x697/0x7f0 io_write_fixed+0xd9/0x250 __io_issue_sqe+0xad/0x710 io_issue_sqe+0x7d/0x1100 io_submit_sqes+0x86a/0x23c0 __do_sys_io_uring_enter+0xa98/0x1590 Allocated by task 103: The buggy address is located 12 bytes to the right of allocated 584-byte region [ffff888002bcc000, ffff888002bcc248)

Published: 2026-05-01Modified: 2026-05-12

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-43007

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: accel/qaic: Handle DBC deactivation if the owner went away When a DBC is released, the device sends a QAIC_TRANS_DEACTIVATE_FROM_DEV transaction to the host over the QAIC_CONTROL MHI channel. QAIC handles this by calling decode_deactivate() to release the resources allocated for that DBC. Since that handling is done in the qaic_manage_ioctl() context, if the user goes away before receiving and handling the deactivation, the host will be out-of-sync with the DBCs available for use, and the DBC resources will not be freed unless the device is removed. If another user loads and requests to activate a network, then the device assigns the same DBC to that network, QAIC will "indefinitely" wait for dbc->in_use = false, leading the user process to hang. As a solution to this, handle QAIC_TRANS_DEACTIVATE_FROM_DEV transactions that are received after the user has gone away.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43010

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: bpf: Reject sleepable kprobe_multi programs at attach time kprobe.multi programs run in atomic/RCU context and cannot sleep. However, bpf_kprobe_multi_link_attach() did not validate whether the program being attached had the sleepable flag set, allowing sleepable helpers such as bpf_copy_from_user() to be invoked from a non-sleepable context. This causes a "sleeping function called from invalid context" splat: BUG: sleeping function called from invalid context at ./include/linux/uaccess.h:169 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1787, name: sudo preempt_count: 1, expected: 0 RCU nest depth: 2, expected: 0 Fix this by rejecting sleepable programs early in bpf_kprobe_multi_link_attach(), before any further processing.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43011

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: net/x25: Fix potential double free of skb When alloc_skb fails in x25_queue_rx_frame it calls kfree_skb(skb) at line 48 and returns 1 (error). This error propagates back through the call chain: x25_queue_rx_frame returns 1 | v x25_state3_machine receives the return value 1 and takes the else branch at line 278, setting queued=0 and returning 0 | v x25_process_rx_frame returns queued=0 | v x25_backlog_rcv at line 452 sees queued=0 and calls kfree_skb(skb) again This would free the same skb twice. Looking at x25_backlog_rcv: net/x25/x25_in.c:x25_backlog_rcv() { ... queued = x25_process_rx_frame(sk, skb); ... if (!queued) kfree_skb(skb); }

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43012

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Fix switchdev mode rollback in case of failure If for some internal reason switchdev mode fails, we rollback to legacy mode, before this patch, rollback will unregister the uplink netdev and leave it unregistered causing the below kernel bug. To fix this, we need to avoid netdev unregister by setting the proper rollback flag 'MLX5_PRIV_FLAGS_SWITCH_LEGACY' to indicate legacy mode. devlink (431) used greatest stack depth: 11048 bytes left mlx5_core 0000:00:03.0: E-Switch: Disable: mode(LEGACY), nvfs(0), \ necvfs(0), active vports(0) mlx5_core 0000:00:03.0: E-Switch: Supported tc chains and prios offload mlx5_core 0000:00:03.0: Loading uplink representor for vport 65535 mlx5_core 0000:00:03.0: mlx5_cmd_out_err:816:(pid 456): \ QUERY_HCA_CAP(0x100) op_mod(0x0) failed, \ status bad parameter(0x3), syndrome (0x3a3846), err(-22) mlx5_core 0000:00:03.0 enp0s3np0 (unregistered): Unloading uplink \ representor for vport 65535 ------------[ cut here ]------------ kernel BUG at net/core/dev.c:12070! Oops: invalid opcode: 0000 [#1] SMP NOPTI CPU: 2 UID: 0 PID: 456 Comm: devlink Not tainted 6.16.0-rc3+ \ #9 PREEMPT(voluntary) RIP: 0010:unregister_netdevice_many_notify+0x123/0xae0 ... Call Trace: [ 90.923094] unregister_netdevice_queue+0xad/0xf0 [ 90.923323] unregister_netdev+0x1c/0x40 [ 90.923522] mlx5e_vport_rep_unload+0x61/0xc6 [ 90.923736] esw_offloads_enable+0x8e6/0x920 [ 90.923947] mlx5_eswitch_enable_locked+0x349/0x430 [ 90.924182] ? is_mp_supported+0x57/0xb0 [ 90.924376] mlx5_devlink_eswitch_mode_set+0x167/0x350 [ 90.924628] devlink_nl_eswitch_set_doit+0x6f/0xf0 [ 90.924862] genl_family_rcv_msg_doit+0xe8/0x140 [ 90.925088] genl_rcv_msg+0x18b/0x290 [ 90.925269] ? __pfx_devlink_nl_pre_doit+0x10/0x10 [ 90.925506] ? __pfx_devlink_nl_eswitch_set_doit+0x10/0x10 [ 90.925766] ? __pfx_devlink_nl_post_doit+0x10/0x10 [ 90.926001] ? __pfx_genl_rcv_msg+0x10/0x10 [ 90.926206] netlink_rcv_skb+0x52/0x100 [ 90.926393] genl_rcv+0x28/0x40 [ 90.926557] netlink_unicast+0x27d/0x3d0 [ 90.926749] netlink_sendmsg+0x1f7/0x430 [ 90.926942] __sys_sendto+0x213/0x220 [ 90.927127] ? __sys_recvmsg+0x6a/0xd0 [ 90.927312] __x64_sys_sendto+0x24/0x30 [ 90.927504] do_syscall_64+0x50/0x1c0 [ 90.927687] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 90.927929] RIP: 0033:0x7f7d0363e047

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43013

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/mlx5: lag: Check for LAG device before creating debugfs __mlx5_lag_dev_add_mdev() may return 0 (success) even when an error occurs that is handled gracefully. Consequently, the initialization flow proceeds to call mlx5_ldev_add_debugfs() even when there is no valid LAG context. mlx5_ldev_add_debugfs() blindly created the debugfs directory and attributes. This exposed interfaces (like the members file) that rely on a valid ldev pointer, leading to potential NULL pointer dereferences if accessed when ldev is NULL. Add a check to verify that mlx5_lag_dev(dev) returns a valid pointer before attempting to create the debugfs entries.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43014

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: macb: properly unregister fixed rate clocks The additional resources allocated with clk_register_fixed_rate() need to be released with clk_unregister_fixed_rate(), otherwise they are lost.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43015

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: macb: fix clk handling on PCI glue driver removal platform_device_unregister() may still want to use the registered clks during runtime resume callback. Note that there is a commit d82d5303c4c5 ("net: macb: fix use after free on rmmod") that addressed the similar problem of clk vs platform device unregistration but just moved the bug to another place. Save the pointers to clks into local variables for reuse after platform device is unregistered. BUG: KASAN: use-after-free in clk_prepare+0x5a/0x60 Read of size 8 at addr ffff888104f85e00 by task modprobe/597 CPU: 2 PID: 597 Comm: modprobe Not tainted 6.1.164+ #114 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.1-0-g3208b098f51a-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack_lvl+0x8d/0xba print_report+0x17f/0x496 kasan_report+0xd9/0x180 clk_prepare+0x5a/0x60 macb_runtime_resume+0x13d/0x410 [macb] pm_generic_runtime_resume+0x97/0xd0 __rpm_callback+0xc8/0x4d0 rpm_callback+0xf6/0x230 rpm_resume+0xeeb/0x1a70 __pm_runtime_resume+0xb4/0x170 bus_remove_device+0x2e3/0x4b0 device_del+0x5b3/0xdc0 platform_device_del+0x4e/0x280 platform_device_unregister+0x11/0x50 pci_device_remove+0xae/0x210 device_remove+0xcb/0x180 device_release_driver_internal+0x529/0x770 driver_detach+0xd4/0x1a0 bus_remove_driver+0x135/0x260 driver_unregister+0x72/0xb0 pci_unregister_driver+0x26/0x220 __do_sys_delete_module+0x32e/0x550 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Allocated by task 519: kasan_save_stack+0x2c/0x50 kasan_set_track+0x21/0x30 __kasan_kmalloc+0x8e/0x90 __clk_register+0x458/0x2890 clk_hw_register+0x1a/0x60 __clk_hw_register_fixed_rate+0x255/0x410 clk_register_fixed_rate+0x3c/0xa0 macb_probe+0x1d8/0x42e [macb_pci] local_pci_probe+0xd7/0x190 pci_device_probe+0x252/0x600 really_probe+0x255/0x7f0 __driver_probe_device+0x1ee/0x330 driver_probe_device+0x4c/0x1f0 __driver_attach+0x1df/0x4e0 bus_for_each_dev+0x15d/0x1f0 bus_add_driver+0x486/0x5e0 driver_register+0x23a/0x3d0 do_one_initcall+0xfd/0x4d0 do_init_module+0x18b/0x5a0 load_module+0x5663/0x7950 __do_sys_finit_module+0x101/0x180 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Freed by task 597: kasan_save_stack+0x2c/0x50 kasan_set_track+0x21/0x30 kasan_save_free_info+0x2a/0x50 __kasan_slab_free+0x106/0x180 __kmem_cache_free+0xbc/0x320 clk_unregister+0x6de/0x8d0 macb_remove+0x73/0xc0 [macb_pci] pci_device_remove+0xae/0x210 device_remove+0xcb/0x180 device_release_driver_internal+0x529/0x770 driver_detach+0xd4/0x1a0 bus_remove_driver+0x135/0x260 driver_unregister+0x72/0xb0 pci_unregister_driver+0x26/0x220 __do_sys_delete_module+0x32e/0x550 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43016

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bpf: sockmap: Fix use-after-free of sk->sk_socket in sk_psock_verdict_data_ready(). syzbot reported use-after-free of AF_UNIX socket's sk->sk_socket in sk_psock_verdict_data_ready(). [0] In unix_stream_sendmsg(), the peer socket's ->sk_data_ready() is called after dropping its unix_state_lock(). Although the sender socket holds the peer's refcount, it does not prevent the peer's sock_orphan(), and the peer's sk_socket might be freed after one RCU grace period. Let's fetch the peer's sk->sk_socket and sk->sk_socket->ops under RCU in sk_psock_verdict_data_ready(). [0]: BUG: KASAN: slab-use-after-free in sk_psock_verdict_data_ready+0xec/0x590 net/core/skmsg.c:1278 Read of size 8 at addr ffff8880594da860 by task syz.4.1842/11013 CPU: 1 UID: 0 PID: 11013 Comm: syz.4.1842 Not tainted syzkaller #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2026 Call Trace: dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xba/0x230 mm/kasan/report.c:482 kasan_report+0x117/0x150 mm/kasan/report.c:595 sk_psock_verdict_data_ready+0xec/0x590 net/core/skmsg.c:1278 unix_stream_sendmsg+0x8a3/0xe80 net/unix/af_unix.c:2482 sock_sendmsg_nosec net/socket.c:721 [inline] __sock_sendmsg net/socket.c:736 [inline] ____sys_sendmsg+0x972/0x9f0 net/socket.c:2585 ___sys_sendmsg+0x2a5/0x360 net/socket.c:2639 __sys_sendmsg net/socket.c:2671 [inline] __do_sys_sendmsg net/socket.c:2676 [inline] __se_sys_sendmsg net/socket.c:2674 [inline] __x64_sys_sendmsg+0x1bd/0x2a0 net/socket.c:2674 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7facf899c819 Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007facf9827028 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007facf8c15fa0 RCX: 00007facf899c819 RDX: 0000000000000000 RSI: 0000200000000500 RDI: 0000000000000004 RBP: 00007facf8a32c91 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007facf8c16038 R14: 00007facf8c15fa0 R15: 00007ffd41b01c78 Allocated by task 11013: kasan_save_stack mm/kasan/common.c:57 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:78 unpoison_slab_object mm/kasan/common.c:340 [inline] __kasan_slab_alloc+0x6c/0x80 mm/kasan/common.c:366 kasan_slab_alloc include/linux/kasan.h:253 [inline] slab_post_alloc_hook mm/slub.c:4538 [inline] slab_alloc_node mm/slub.c:4866 [inline] kmem_cache_alloc_lru_noprof+0x2b8/0x640 mm/slub.c:4885 sock_alloc_inode+0x28/0xc0 net/socket.c:316 alloc_inode+0x6a/0x1b0 fs/inode.c:347 new_inode_pseudo include/linux/fs.h:3003 [inline] sock_alloc net/socket.c:631 [inline] __sock_create+0x12d/0x9d0 net/socket.c:1562 sock_create net/socket.c:1656 [inline] __sys_socketpair+0x1c4/0x560 net/socket.c:1803 __do_sys_socketpair net/socket.c:1856 [inline] __se_sys_socketpair net/socket.c:1853 [inline] __x64_sys_socketpair+0x9b/0xb0 net/socket.c:1853 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f Freed by task 15: kasan_save_stack mm/kasan/common.c:57 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:78 kasan_save_free_info+0x46/0x50 mm/kasan/generic.c:584 poison_slab_object mm/kasan/common.c:253 [inline] __kasan_slab_free+0x5c/0x80 mm/kasan/common.c:285 kasan_slab_free include/linux/kasan.h:235 [inline] slab_free_hook mm/slub.c:2685 [inline] slab_free mm/slub.c:6165 [inline] kmem_cache_free+0x187/0x630 mm/slub.c:6295 rcu_do_batch kernel/rcu/tree.c: ---truncated---

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43017

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: MGMT: validate mesh send advertising payload length mesh_send() currently bounds MGMT_OP_MESH_SEND by total command length, but it never verifies that the bytes supplied for the flexible adv_data[] array actually match the embedded adv_data_len field. MGMT_MESH_SEND_SIZE only covers the fixed header, so a truncated command can still pass the existing 20..50 byte range check and later drive the async mesh send path past the end of the queued command buffer. Keep rejecting zero-length and oversized advertising payloads, but validate adv_data_len explicitly and require the command length to exactly match the flexible array size before queueing the request.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43018

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_event: fix potential UAF in hci_le_remote_conn_param_req_evt hci_conn lookup and field access must be covered by hdev lock in hci_le_remote_conn_param_req_evt, otherwise it's possible it is freed concurrently. Extend the hci_dev_lock critical section to cover all conn usage.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43019

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_conn: fix potential UAF in set_cig_params_sync hci_conn lookup and field access must be covered by hdev lock in set_cig_params_sync, otherwise it's possible it is freed concurrently. Take hdev lock to prevent hci_conn from being deleted or modified concurrently. Just RCU lock is not suitable here, as we also want to avoid "tearing" in the configuration.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43020

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: MGMT: validate LTK enc_size on load Load Long Term Keys stores the user-provided enc_size and later uses it to size fixed-size stack operations when replying to LE LTK requests. An enc_size larger than the 16-byte key buffer can therefore overflow the reply stack buffer. Reject oversized enc_size values while validating the management LTK record so invalid keys never reach the stored key state.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43023

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: SCO: fix race conditions in sco_sock_connect() sco_sock_connect() checks sk_state and sk_type without holding the socket lock. Two concurrent connect() syscalls on the same socket can both pass the check and enter sco_connect(), leading to use-after-free. The buggy scenario involves three participants and was confirmed with additional logging instrumentation: Thread A (connect): HCI disconnect: Thread B (connect): sco_sock_connect(sk) sco_sock_connect(sk) sk_state==BT_OPEN sk_state==BT_OPEN (pass, no lock) (pass, no lock) sco_connect(sk): sco_connect(sk): hci_dev_lock hci_dev_lock hci_connect_sco <- blocked -> hcon1 sco_conn_add->conn1 lock_sock(sk) sco_chan_add: conn1->sk = sk sk->conn = conn1 sk_state=BT_CONNECT release_sock hci_dev_unlock hci_dev_lock sco_conn_del: lock_sock(sk) sco_chan_del: sk->conn=NULL conn1->sk=NULL sk_state= BT_CLOSED SOCK_ZAPPED release_sock hci_dev_unlock (unblocked) hci_connect_sco -> hcon2 sco_conn_add -> conn2 lock_sock(sk) sco_chan_add: sk->conn=conn2 sk_state= BT_CONNECT // zombie sk! release_sock hci_dev_unlock Thread B revives a BT_CLOSED + SOCK_ZAPPED socket back to BT_CONNECT. Subsequent cleanup triggers double sock_put() and use-after-free. Meanwhile conn1 is leaked as it was orphaned when sco_conn_del() cleared the association. Fix this by: - Moving lock_sock() before the sk_state/sk_type checks in sco_sock_connect() to serialize concurrent connect attempts - Fixing the sk_type != SOCK_SEQPACKET check to actually return the error instead of just assigning it - Adding a state re-check in sco_connect() after lock_sock() to catch state changes during the window between the locks - Adding sco_pi(sk)->conn check in sco_chan_add() to prevent double-attach of a socket to multiple connections - Adding hci_conn_drop() on sco_chan_add failure to prevent HCI connection leaks

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43024

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: reject immediate NF_QUEUE verdict nft_queue is always used from userspace nftables to deliver the NF_QUEUE verdict. Immediately emitting an NF_QUEUE verdict is never used by the userspace nft tools, so reject immediate NF_QUEUE verdicts. The arp family does not provide queue support, but such an immediate verdict is still reachable. Globally reject NF_QUEUE immediate verdicts to address this issue.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43025

HIGH7.3

In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: ignore explicit helper on new expectations Use the existing master conntrack helper, anything else is not really supported and it just makes validation more complicated, so just ignore what helper userspace suggests for this expectation. This was uncovered when validating CTA_EXPECT_CLASS via different helper provided by userspace than the existing master conntrack helper: BUG: KASAN: slab-out-of-bounds in nf_ct_expect_related_report+0x2479/0x27c0 Read of size 4 at addr ffff8880043fe408 by task poc/102 Call Trace: nf_ct_expect_related_report+0x2479/0x27c0 ctnetlink_create_expect+0x22b/0x3b0 ctnetlink_new_expect+0x4bd/0x5c0 nfnetlink_rcv_msg+0x67a/0x950 netlink_rcv_skb+0x120/0x350 Allowing to read kernel memory bytes off the expectation boundary. CTA_EXPECT_HELP_NAME is still used to offer the helper name to userspace via netlink dump.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.3

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:H

References

CVE-2026-43026

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: zero expect NAT fields when CTA_EXPECT_NAT absent ctnetlink_alloc_expect() allocates expectations from a non-zeroing slab cache via nf_ct_expect_alloc(). When CTA_EXPECT_NAT is not present in the netlink message, saved_addr and saved_proto are never initialized. Stale data from a previous slab occupant can then be dumped to userspace by ctnetlink_exp_dump_expect(), which checks these fields to decide whether to emit CTA_EXPECT_NAT. The safe sibling nf_ct_expect_init(), used by the packet path, explicitly zeroes these fields. Zero saved_addr, saved_proto and dir in the else branch, guarded by IS_ENABLED(CONFIG_NF_NAT) since these fields only exist when NAT is enabled. Confirmed by priming the expect slab with NAT-bearing expectations, freeing them, creating a new expectation without CTA_EXPECT_NAT, and observing that the ctnetlink dump emits a spurious CTA_EXPECT_NAT containing stale data from the prior allocation.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43027

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_helper: pass helper to expect cleanup nf_conntrack_helper_unregister() calls nf_ct_expect_iterate_destroy() to remove expectations belonging to the helper being unregistered. However, it passes NULL instead of the helper pointer as the data argument, so expect_iter_me() never matches any expectation and all of them survive the cleanup. After unregister returns, nfnl_cthelper_del() frees the helper object immediately. Subsequent expectation dumps or packet-driven init_conntrack() calls then dereference the freed exp->helper, causing a use-after-free. Pass the actual helper pointer so expectations referencing it are properly destroyed before the helper object is freed. BUG: KASAN: slab-use-after-free in string+0x38f/0x430 Read of size 1 at addr ffff888003b14d20 by task poc/103 Call Trace: string+0x38f/0x430 vsnprintf+0x3cc/0x1170 seq_printf+0x17a/0x240 exp_seq_show+0x2e5/0x560 seq_read_iter+0x419/0x1280 proc_reg_read+0x1ac/0x270 vfs_read+0x179/0x930 ksys_read+0xef/0x1c0 Freed by task 103: The buggy address is located 32 bytes inside of freed 192-byte region [ffff888003b14d00, ffff888003b14dc0)

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43028

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: netfilter: x_tables: ensure names are nul-terminated Reject names that lack a \0 character before feeding them to functions that expect c-strings. Fixes tag is the most recent commit that needs this change.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-43029

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: mptcp: fix soft lockup in mptcp_recvmsg() syzbot reported a soft lockup in mptcp_recvmsg() [0]. When receiving data with MSG_PEEK | MSG_WAITALL flags, the skb is not removed from the sk_receive_queue. This causes sk_wait_data() to always find available data and never perform actual waiting, leading to a soft lockup. Fix this by adding a 'last' parameter to track the last peeked skb. This allows sk_wait_data() to make informed waiting decisions and prevent infinite loops when MSG_PEEK is used. [0]: watchdog: BUG: soft lockup - CPU#2 stuck for 156s! [server:1963] Modules linked in: CPU: 2 UID: 0 PID: 1963 Comm: server Not tainted 6.19.0-rc8 #61 PREEMPT(none) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 RIP: 0010:sk_wait_data+0x15/0x190 Code: 80 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 41 56 41 55 41 54 49 89 f4 55 48 89 d5 53 48 89 fb <48> 83 ec 30 65 48 8b 05 17 a4 6b 01 48 89 44 24 28 31 c0 65 48 8b RSP: 0018:ffffc90000603ca0 EFLAGS: 00000246 RAX: 0000000000000000 RBX: ffff888102bf0800 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffffc90000603d18 RDI: ffff888102bf0800 RBP: 0000000000000000 R08: 0000000000000002 R09: 0000000000000101 R10: 0000000000000000 R11: 0000000000000075 R12: ffffc90000603d18 R13: ffff888102bf0800 R14: ffff888102bf0800 R15: 0000000000000000 FS: 00007f6e38b8c4c0(0000) GS:ffff8881b877e000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055aa7bff1680 CR3: 0000000105cbe000 CR4: 00000000000006f0 Call Trace: mptcp_recvmsg+0x547/0x8c0 net/mptcp/protocol.c:2329 inet_recvmsg+0x11f/0x130 net/ipv4/af_inet.c:891 sock_recvmsg+0x94/0xc0 net/socket.c:1100 __sys_recvfrom+0xb2/0x130 net/socket.c:2256 __x64_sys_recvfrom+0x1f/0x30 net/socket.c:2267 do_syscall_64+0x59/0x2d0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e arch/x86/entry/entry_64.S:131 RIP: 0033:0x7f6e386a4a1d Code: 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 8d 05 f1 de 2c 00 41 89 ca 8b 00 85 c0 75 20 45 31 c9 45 31 c0 b8 2d 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 6b f3 c3 66 0f 1f 84 00 00 00 00 00 41 56 41 RSP: 002b:00007ffc3c4bb078 EFLAGS: 00000246 ORIG_RAX: 000000000000002d RAX: ffffffffffffffda RBX: 000000000000861e RCX: 00007f6e386a4a1d RDX: 00000000000003ff RSI: 00007ffc3c4bb150 RDI: 0000000000000004 RBP: 00007ffc3c4bb570 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000103 R11: 0000000000000246 R12: 00005605dbc00be0 R13: 00007ffc3c4bb650 R14: 0000000000000000 R15: 0000000000000000

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43030

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix regsafe() for pointers to packet In case rold->reg->range == BEYOND_PKT_END && rcur->reg->range == N regsafe() may return true which may lead to current state with valid packet range not being explored. Fix the bug.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43031

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: net: xilinx: axienet: Fix BQL accounting for multi-BD TX packets When a TX packet spans multiple buffer descriptors (scatter-gather), axienet_free_tx_chain sums the per-BD actual length from descriptor status into a caller-provided accumulator. That sum is reset on each NAPI poll. If the BDs for a single packet complete across different polls, the earlier bytes are lost and never credited to BQL. This causes BQL to think bytes are permanently in-flight, eventually stalling the TX queue. The SKB pointer is stored only on the last BD of a packet. When that BD completes, use skb->len for the byte count instead of summing per-BD status lengths. This matches netdev_sent_queue(), which debits skb->len, and naturally survives across polls because no partial packet contributes to the accumulator.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43032

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: NFC: pn533: bound the UART receive buffer pn532_receive_buf() appends every incoming byte to dev->recv_skb and only resets the buffer after pn532_uart_rx_is_frame() recognizes a complete frame. A continuous stream of bytes without a valid PN532 frame header therefore keeps growing the skb until skb_put_u8() hits the tail limit. Drop the accumulated partial frame once the fixed receive buffer is full so malformed UART traffic cannot grow the skb past PN532_UART_SKB_BUFF_LEN.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43033

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: crypto: authencesn - Do not place hiseq at end of dst for out-of-place decryption When decrypting data that is not in-place (src != dst), there is no need to save the high-order sequence bits in dst as it could simply be re-copied from the source. However, the data to be hashed need to be rearranged accordingly. Thanks,

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43034

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: bnxt_en: set backing store type from query type bnxt_hwrm_func_backing_store_qcaps_v2() stores resp->type from the firmware response in ctxm->type and later uses that value to index fixed backing-store metadata arrays such as ctx_arr[] and bnxt_bstore_to_trace[]. ctxm->type is fixed by the current backing-store query type and matches the array index of ctx->ctx_arr. Set ctxm->type from the current loop variable instead of depending on resp->type. Also update the loop to advance type from next_valid_type in the for statement, which keeps the control flow simpler for non-valid and unchanged entries.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43035

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: sched: cls_api: fix tc_chain_fill_node to initialize tcm_info to zero to prevent an info-leak When building netlink messages, tc_chain_fill_node() never initializes the tcm_info field of struct tcmsg. Since the allocation is not zeroed, kernel heap memory is leaked to userspace through this 4-byte field. The fix simply zeroes tcm_info alongside the other fields that are already initialized.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43036

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: use skb_header_pointer() for TCPv4 GSO frag_off check Syzbot reported a KMSAN uninit-value warning in gso_features_check() called from netif_skb_features() [1]. gso_features_check() reads iph->frag_off to decide whether to clear mangleid_features. Accessing the IPv4 header via ip_hdr()/inner_ip_hdr() can rely on skb header offsets that are not always safe for direct dereference on packets injected from PF_PACKET paths. Use skb_header_pointer() for the TCPv4 frag_off check so the header read is robust whether data is already linear or needs copying. [1] https://syzkaller.appspot.com/bug?extid=1543a7d954d9c6d00407

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43037

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ip6_tunnel: clear skb2->cb[] in ip4ip6_err() Oskar Kjos reported the following problem. ip4ip6_err() calls icmp_send() on a cloned skb whose cb[] was written by the IPv6 receive path as struct inet6_skb_parm. icmp_send() passes IPCB(skb2) to __ip_options_echo(), which interprets that cb[] region as struct inet_skb_parm (IPv4). The layouts differ: inet6_skb_parm.nhoff at offset 14 overlaps inet_skb_parm.opt.rr, producing a non-zero rr value. __ip_options_echo() then reads optlen from attacker-controlled packet data at sptr[rr+1] and copies that many bytes into dopt->__data, a fixed 40-byte stack buffer (IP_OPTIONS_DATA_FIXED_SIZE). To fix this we clear skb2->cb[], as suggested by Oskar Kjos. Also add minimal IPv4 header validation (version == 4, ihl >= 5).

Published: 2026-05-01Modified: 2026-05-04

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43038

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ipv6: icmp: clear skb2->cb[] in ip6_err_gen_icmpv6_unreach() Sashiko AI-review observed: In ip6_err_gen_icmpv6_unreach(), the skb is an outer IPv4 ICMP error packet where its cb contains an IPv4 inet_skb_parm. When skb is cloned into skb2 and passed to icmp6_send(), it uses IP6CB(skb2). IP6CB interprets the IPv4 inet_skb_parm as an inet6_skb_parm. The cipso offset in inet_skb_parm.opt directly overlaps with dsthao in inet6_skb_parm at offset 18. If an attacker sends a forged ICMPv4 error with a CIPSO IP option, dsthao would be a non-zero offset. Inside icmp6_send(), mip6_addr_swap() is called and uses ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO). This would scan the inner, attacker-controlled IPv6 packet starting at that offset, potentially returning a fake TLV without checking if the remaining packet length can hold the full 18-byte struct ipv6_destopt_hao. Could mip6_addr_swap() then perform a 16-byte swap that extends past the end of the packet data into skb_shared_info? Should the cb array also be cleared in ip6_err_gen_icmpv6_unreach() and ip6ip6_err() to prevent this? This patch implements the first suggestion. I am not sure if ip6ip6_err() needs to be changed. A separate patch would be better anyway.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43040

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: net: ipv6: ndisc: fix ndisc_ra_useropt to initialize nduseropt_padX fields to zero to prevent an info-leak When processing Router Advertisements with user options the kernel builds an RTM_NEWNDUSEROPT netlink message. The nduseroptmsg struct has three padding fields that are never zeroed and can leak kernel data The fix is simple, just zeroes the padding fields.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-43041

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: qrtr: replace qrtr_tx_flow radix_tree with xarray to fix memory leak __radix_tree_create() allocates and links intermediate nodes into the tree one by one. If a subsequent allocation fails, the already-linked nodes remain in the tree with no corresponding leaf entry. These orphaned internal nodes are never reclaimed because radix_tree_for_each_slot() only visits slots containing leaf values. The radix_tree API is deprecated in favor of xarray. As suggested by Matthew Wilcox, migrate qrtr_tx_flow from radix_tree to xarray instead of fixing the radix_tree itself [1]. xarray properly handles cleanup of internal nodes — xa_destroy() frees all internal xarray nodes when the qrtr_node is released, preventing the leak. [1] https://lore.kernel.org/all/20260225071623.41275-1-jiayuan.chen@linux.dev/T/

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43043

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: crypto: af-alg - fix NULL pointer dereference in scatterwalk The AF_ALG interface fails to unmark the end of a Scatter/Gather List (SGL) when chaining a new af_alg_tsgl structure. If a sendmsg() fills an SGL exactly to MAX_SGL_ENTS, the last entry is marked as the end. A subsequent sendmsg() allocates a new SGL and chains it, but fails to clear the end marker on the previous SGL's last data entry. This causes the crypto scatterwalk to hit a premature end, returning NULL on sg_next() and leading to a kernel panic during dereference. Fix this by explicitly unmarking the end of the previous SGL when performing sg_chain() in af_alg_alloc_tsgl().

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43044

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: crypto: caam - fix DMA corruption on long hmac keys When a key longer than block size is supplied, it is copied and then hashed into the real key. The memory allocated for the copy needs to be rounded to DMA cache alignment, as otherwise the hashed key may corrupt neighbouring memory. The rounding was performed, but never actually used for the allocation. Fix this by replacing kmemdup with kmalloc for a larger buffer, followed by memcpy.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43046

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: btrfs: reject root items with drop_progress and zero drop_level [BUG] When recovering relocation at mount time, merge_reloc_root() and btrfs_drop_snapshot() both use BUG_ON(level == 0) to guard against an impossible state: a non-zero drop_progress combined with a zero drop_level in a root_item, which can be triggered: ------------[ cut here ]------------ kernel BUG at fs/btrfs/relocation.c:1545! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI CPU: 1 UID: 0 PID: 283 ... Tainted: 6.18.0+ #16 PREEMPT(voluntary) Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Hardware name: QEMU Ubuntu 24.04 PC v2, BIOS 1.16.3-debian-1.16.3-2 RIP: 0010:merge_reloc_root+0x1266/0x1650 fs/btrfs/relocation.c:1545 Code: ffff0000 00004589 d7e9acfa ffffe8a1 79bafebe 02000000 Call Trace: merge_reloc_roots+0x295/0x890 fs/btrfs/relocation.c:1861 btrfs_recover_relocation+0xd6e/0x11d0 fs/btrfs/relocation.c:4195 btrfs_start_pre_rw_mount+0xa4d/0x1810 fs/btrfs/disk-io.c:3130 open_ctree+0x5824/0x5fe0 fs/btrfs/disk-io.c:3640 btrfs_fill_super fs/btrfs/super.c:987 [inline] btrfs_get_tree_super fs/btrfs/super.c:1951 [inline] btrfs_get_tree_subvol fs/btrfs/super.c:2094 [inline] btrfs_get_tree+0x111c/0x2190 fs/btrfs/super.c:2128 vfs_get_tree+0x9a/0x370 fs/super.c:1758 fc_mount fs/namespace.c:1199 [inline] do_new_mount_fc fs/namespace.c:3642 [inline] do_new_mount fs/namespace.c:3718 [inline] path_mount+0x5b8/0x1ea0 fs/namespace.c:4028 do_mount fs/namespace.c:4041 [inline] __do_sys_mount fs/namespace.c:4229 [inline] __se_sys_mount fs/namespace.c:4206 [inline] __x64_sys_mount+0x282/0x320 fs/namespace.c:4206 ... RIP: 0033:0x7f969c9a8fde Code: 0f1f4000 48c7c2b0 fffffff7 d8648902 b8ffffff ffc3660f ---[ end trace 0000000000000000 ]--- The bug is reproducible on 7.0.0-rc2-next-20260310 with our dynamic metadata fuzzing tool that corrupts btrfs metadata at runtime. [CAUSE] A non-zero drop_progress.objectid means an interrupted btrfs_drop_snapshot() left a resume point on disk, and in that case drop_level must be greater than 0 because the checkpoint is only saved at internal node levels. Although this invariant is enforced when the kernel writes the root item, it is not validated when the root item is read back from disk. That allows on-disk corruption to provide an invalid state with drop_progress.objectid != 0 and drop_level == 0. When relocation recovery later processes such a root item, merge_reloc_root() reads drop_level and hits BUG_ON(level == 0). The same invalid metadata can also trigger the corresponding BUG_ON() in btrfs_drop_snapshot(). [FIX] Fix this by validating the root_item invariant in tree-checker when reading root items from disk: if drop_progress.objectid is non-zero, drop_level must also be non-zero. Reject such malformed metadata with -EUCLEAN before it reaches merge_reloc_root() or btrfs_drop_snapshot() and triggers the BUG_ON. After the fix, the same corruption is correctly rejected by tree-checker and the BUG_ON is no longer triggered.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43047

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: HID: multitouch: Check to ensure report responses match the request It is possible for a malicious (or clumsy) device to respond to a specific report's feature request using a completely different report ID. This can cause confusion in the HID core resulting in nasty side-effects such as OOB writes. Add a check to ensure that the report ID in the response, matches the one that was requested. If it doesn't, omit reporting the raw event and return early.

Published: 2026-05-01Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43048

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: HID: core: Mitigate potential OOB by removing bogus memset() The memset() in hid_report_raw_event() has the good intention of clearing out bogus data by zeroing the area from the end of the incoming data string to the assumed end of the buffer. However, as we have previously seen, doing so can easily result in OOB reads and writes in the subsequent thread of execution. The current suggestion from one of the HID maintainers is to remove the memset() and simply return if the incoming event buffer size is not large enough to fill the associated report. Suggested-by Benjamin Tissoires [bentiss: changed the return value]

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43049

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: HID: logitech-hidpp: Prevent use-after-free on force feedback initialisation failure Presently, if the force feedback initialisation fails when probing the Logitech G920 Driving Force Racing Wheel for Xbox One, an error number will be returned and propagated before the userspace infrastructure (sysfs and /dev/input) has been torn down. If userspace ignores the errors and continues to use its references to these dangling entities, a UAF will promptly follow. We have 2 options; continue to return the error, but ensure that all of the infrastructure is torn down accordingly or continue to treat this condition as a warning by emitting the message but returning success. It is thought that the original author's intention was to emit the warning but keep the device functional, less the force feedback feature, so let's go with that.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43050

HIGH7.0

In the Linux kernel, the following vulnerability has been resolved: atm: lec: fix use-after-free in sock_def_readable() A race condition exists between lec_atm_close() setting priv->lecd to NULL and concurrent access to priv->lecd in send_to_lecd(), lec_handle_bridge(), and lec_atm_send(). When the socket is freed via RCU while another thread is still using it, a use-after-free occurs in sock_def_readable() when accessing the socket's wait queue. The root cause is that lec_atm_close() clears priv->lecd without any synchronization, while callers dereference priv->lecd without any protection against concurrent teardown. Fix this by converting priv->lecd to an RCU-protected pointer: - Mark priv->lecd as __rcu in lec.h - Use rcu_assign_pointer() in lec_atm_close() and lecd_attach() for safe pointer assignment - Use rcu_access_pointer() for NULL checks that do not dereference the pointer in lec_start_xmit(), lec_push(), send_to_lecd() and lecd_attach() - Use rcu_read_lock/rcu_dereference/rcu_read_unlock in send_to_lecd(), lec_handle_bridge() and lec_atm_send() to safely access lecd - Use rcu_assign_pointer() followed by synchronize_rcu() in lec_atm_close() to ensure all readers have completed before proceeding. This is safe since lec_atm_close() is called from vcc_release() which holds lock_sock(), a sleeping lock. - Remove the manual sk_receive_queue drain from lec_atm_close() since vcc_destroy_socket() already drains it after lec_atm_close() returns. v2: Switch from spinlock + sock_hold/put approach to RCU to properly fix the race. The v1 spinlock approach had two issues pointed out by Eric Dumazet: 1. priv->lecd was still accessed directly after releasing the lock instead of using a local copy. 2. The spinlock did not prevent packets being queued after lec_atm_close() drains sk_receive_queue since timer and workqueue paths bypass netif_stop_queue(). Note: Syzbot patch testing was attempted but the test VM terminated unexpectedly with "Connection to localhost closed by remote host", likely due to a QEMU AHCI emulation issue unrelated to this fix. Compile testing with "make W=1 net/atm/lec.o" passes cleanly.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 7.0

CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43051

HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: HID: wacom: fix out-of-bounds read in wacom_intuos_bt_irq The wacom_intuos_bt_irq() function processes Bluetooth HID reports without sufficient bounds checking. A maliciously crafted short report can trigger an out-of-bounds read when copying data into the wacom structure. Specifically, report 0x03 requires at least 22 bytes to safely read the processed data and battery status, while report 0x04 (which falls through to 0x03) requires 32 bytes. Add explicit length checks for these report IDs and log a warning if a short report is received.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 8.1

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-43052

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: check tdls flag in ieee80211_tdls_oper When NL80211_TDLS_ENABLE_LINK is called, the code only checks if the station exists but not whether it is actually a TDLS station. This allows the operation to proceed for non-TDLS stations, causing unintended side effects like modifying channel context and HT protection before failing. Add a check for sta->sta.tdls early in the ENABLE_LINK case, before any side effects occur, to ensure the operation is only allowed for actual TDLS peers.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 7.1

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:H

References

CVE-2026-43054

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: scsi: target: tcm_loop: Drain commands in target_reset handler tcm_loop_target_reset() violates the SCSI EH contract: it returns SUCCESS without draining any in-flight commands. The SCSI EH documentation (scsi_eh.rst) requires that when a reset handler returns SUCCESS the driver has made lower layers "forget about timed out scmds" and is ready for new commands. Every other SCSI LLD (virtio_scsi, mpt3sas, ipr, scsi_debug, mpi3mr) enforces this by draining or completing outstanding commands before returning SUCCESS. Because tcm_loop_target_reset() doesn't drain, the SCSI EH reuses in-flight scsi_cmnd structures for recovery commands (e.g. TUR) while the target core still has async completion work queued for the old se_cmd. The memset in queuecommand zeroes se_lun and lun_ref_active, causing transport_lun_remove_cmd() to skip its percpu_ref_put(). The leaked LUN reference prevents transport_clear_lun_ref() from completing, hanging configfs LUN unlink forever in D-state: INFO: task rm:264 blocked for more than 122 seconds. rm D 0 264 258 0x00004000 Call Trace: __schedule+0x3d0/0x8e0 schedule+0x36/0xf0 transport_clear_lun_ref+0x78/0x90 [target_core_mod] core_tpg_remove_lun+0x28/0xb0 [target_core_mod] target_fabric_port_unlink+0x50/0x60 [target_core_mod] configfs_unlink+0x156/0x1f0 [configfs] vfs_unlink+0x109/0x290 do_unlinkat+0x1d5/0x2d0 Fix this by making tcm_loop_target_reset() actually drain commands: 1. Issue TMR_LUN_RESET via tcm_loop_issue_tmr() to drain all commands that the target core knows about (those not yet CMD_T_COMPLETE). 2. Use blk_mq_tagset_busy_iter() to iterate all started requests and flush_work() on each se_cmd — this drains any deferred completion work for commands that already had CMD_T_COMPLETE set before the TMR (which the TMR skips via __target_check_io_state()). This is the same pattern used by mpi3mr, scsi_debug, and libsas to drain outstanding commands during reset.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43055

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: scsi: target: file: Use kzalloc_flex for aio_cmd The target_core_file doesn't initialize the aio_cmd->iocb for the ki_write_stream. When a write command fd_execute_rw_aio() is executed, we may get a bogus ki_write_stream value, causing unintended write failure status when checking iocb->ki_write_stream > max_write_streams in the block device. Let's just use kzalloc_flex when allocating the aio_cmd and let ki_write_stream=0 to fix this issue.

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43056

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: mana: fix use-after-free in add_adev() error path If auxiliary_device_add() fails, add_adev() jumps to add_fail and calls auxiliary_device_uninit(adev). The auxiliary device has its release callback set to adev_release(), which frees the containing struct mana_adev. Since adev is embedded in struct mana_adev, the subsequent fall-through to init_fail and access to adev->id may result in a use-after-free. Fix this by saving the allocated auxiliary device id in a local variable before calling auxiliary_device_add(), and use that saved id in the cleanup path after auxiliary_device_uninit().

Published: 2026-05-01Modified: 2026-05-07

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43057

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: net: correctly handle tunneled traffic on IPV6_CSUM GSO fallback NETIF_F_IPV6_CSUM only advertises support for checksum offload of packets without IPv6 extension headers. Packets with extension headers must fall back onto software checksumming. Since TSO depends on checksum offload, those must revert to GSO. The below commit introduces that fallback. It always checks network header length. For tunneled packets, the inner header length must be checked instead. Extend the check accordingly. A special case is tunneled packets without inner IP protocol. Such as RFC 6951 SCTP in UDP. Those are not standard IPv6 followed by transport header either, so also must revert to the software GSO path.

Published: 2026-05-01Modified: 2026-05-06

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43067

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ext4: handle wraparound when searching for blocks for indirect mapped blocks Commit 4865c768b563 ("ext4: always allocate blocks only from groups inode can use") restricts what blocks will be allocated for indirect block based files to block numbers that fit within 32-bit block numbers. However, when using a review bot running on the latest Gemini LLM to check this commit when backporting into an LTS based kernel, it raised this concern: If ac->ac_g_ex.fe_group is >= ngroups (for instance, if the goal group was populated via stream allocation from s_mb_last_groups), then start will be >= ngroups. Does this allow allocating blocks beyond the 32-bit limit for indirect block mapped files? The commit message mentions that ext4_mb_scan_groups_linear() takes care to not select unsupported groups. However, its loop uses group = *start, and the very first iteration will call ext4_mb_scan_group() with this unsupported group because next_linear_group() is only called at the end of the iteration. After reviewing the code paths involved and considering the LLM review, I determined that this can happen when there is a file system where some files/directories are extent-mapped and others are indirect-block mapped. To address this, add a safety clamp in ext4_mb_scan_groups().

Published: 2026-05-05Modified: 2026-05-20

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43068

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ext4: avoid allocate block from corrupted group in ext4_mb_find_by_goal() There's issue as follows: ... EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 206 at logical offset 0 with max blocks 1 with error 117 EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 206 at logical offset 0 with max blocks 1 with error 117 EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 206 at logical offset 0 with max blocks 1 with error 117 EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 206 at logical offset 0 with max blocks 1 with error 117 EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 2243 at logical offset 0 with max blocks 1 with error 117 EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 2239 at logical offset 0 with max blocks 1 with error 117 EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost EXT4-fs (mmcblk0p1): error count since last fsck: 1 EXT4-fs (mmcblk0p1): initial error at time 1765597433: ext4_mb_generate_buddy:760 EXT4-fs (mmcblk0p1): last error at time 1765597433: ext4_mb_generate_buddy:760 ... According to the log analysis, blocks are always requested from the corrupted block group. This may happen as follows: ext4_mb_find_by_goal ext4_mb_load_buddy ext4_mb_load_buddy_gfp ext4_mb_init_cache ext4_read_block_bitmap_nowait ext4_wait_block_bitmap ext4_validate_block_bitmap if (!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) return -EFSCORRUPTED; // There's no logs. if (err) return err; // Will return error ext4_lock_group(ac->ac_sb, group); if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) // Unreachable goto out; After commit 9008a58e5dce ("ext4: make the bitmap read routines return real error codes") merged, Commit 163a203ddb36 ("ext4: mark block group as corrupt on block bitmap error") is no real solution for allocating blocks from corrupted block groups. This is because if 'EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)' is true, then 'ext4_mb_load_buddy()' may return an error. This means that the block allocation will fail. Therefore, check block group if corrupted when ext4_mb_load_buddy() returns error.

Published: 2026-05-05Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43074

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: eventpoll: defer struct eventpoll free to RCU grace period In certain situations, ep_free() in eventpoll.c will kfree the epi->ep eventpoll struct while it still being used by another concurrent thread. Defer the kfree() to an RCU callback to prevent UAF.

Published: 2026-05-06Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43075

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ocfs2: fix out-of-bounds write in ocfs2_write_end_inline KASAN reports a use-after-free write of 4086 bytes in ocfs2_write_end_inline, called from ocfs2_write_end_nolock during a copy_file_range splice fallback on a corrupted ocfs2 filesystem mounted on a loop device. The actual bug is an out-of-bounds write past the inode block buffer, not a true use-after-free. The write overflows into an adjacent freed page, which KASAN reports as UAF. The root cause is that ocfs2_try_to_write_inline_data trusts the on-disk id_count field to determine whether a write fits in inline data. On a corrupted filesystem, id_count can exceed the physical maximum inline data capacity, causing writes to overflow the inode block buffer. Call trace (crash path): vfs_copy_file_range (fs/read_write.c:1634) do_splice_direct splice_direct_to_actor iter_file_splice_write ocfs2_file_write_iter generic_perform_write ocfs2_write_end ocfs2_write_end_nolock (fs/ocfs2/aops.c:1949) ocfs2_write_end_inline (fs/ocfs2/aops.c:1915) memcpy_from_folio <-- KASAN: write OOB So add id_count upper bound check in ocfs2_validate_inode_block() to alongside the existing i_size check to fix it.

Published: 2026-05-06Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43076

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ocfs2: validate inline data i_size during inode read When reading an inode from disk, ocfs2_validate_inode_block() performs various sanity checks but does not validate the size of inline data. If the filesystem is corrupted, an inode's i_size can exceed the actual inline data capacity (id_count). This causes ocfs2_dir_foreach_blk_id() to iterate beyond the inline data buffer, triggering a use-after-free when accessing directory entries from freed memory. In the syzbot report: - i_size was 1099511627576 bytes (~1TB) - Actual inline data capacity (id_count) is typically <256 bytes - A garbage rec_len (54648) caused ctx->pos to jump out of bounds - This triggered a UAF in ocfs2_check_dir_entry() Fix by adding a validation check in ocfs2_validate_inode_block() to ensure inodes with inline data have i_size <= id_count. This catches the corruption early during inode read and prevents all downstream code from operating on invalid data.

Published: 2026-05-06Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

References

CVE-2026-43077

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: crypto: algif_aead - Fix minimum RX size check for decryption The check for the minimum receive buffer size did not take the tag size into account during decryption. Fix this by adding the required extra length.

Published: 2026-05-06Modified: 2026-05-20

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43078

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: crypto: af_alg - Fix page reassignment overflow in af_alg_pull_tsgl When page reassignment was added to af_alg_pull_tsgl the original loop wasn't updated so it may try to reassign one more page than necessary. Add the check to the reassignment so that this does not happen. Also update the comment which still refers to the obsolete offset argument.

Published: 2026-05-06Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43084

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: nfnetlink_queue: make hash table per queue Sharing a global hash table among all queues is tempting, but it can cause crash: BUG: KASAN: slab-use-after-free in nfqnl_recv_verdict+0x11ac/0x15e0 [nfnetlink_queue] [..] nfqnl_recv_verdict+0x11ac/0x15e0 [nfnetlink_queue] nfnetlink_rcv_msg+0x46a/0x930 kmem_cache_alloc_node_noprof+0x11e/0x450 struct nf_queue_entry is freed via kfree, but parallel cpu can still encounter such an nf_queue_entry when walking the list. Alternative fix is to free the nf_queue_entry via kfree_rcu() instead, but as we have to alloc/free for each skb this will cause more mem pressure.

Published: 2026-05-06Modified: 2026-05-20

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43090

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xfrm: fix refcount leak in xfrm_migrate_policy_find syzkaller reported a memory leak in xfrm_policy_alloc: BUG: memory leak unreferenced object 0xffff888114d79000 (size 1024): comm "syz.1.17", pid 931 ... xfrm_policy_alloc+0xb3/0x4b0 net/xfrm/xfrm_policy.c:432 The root cause is a double call to xfrm_pol_hold_rcu() in xfrm_migrate_policy_find(). The lookup function already returns a policy with held reference, making the second call redundant. Remove the redundant xfrm_pol_hold_rcu() call to fix the refcount imbalance and prevent the memory leak. Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Published: 2026-05-06Modified: 2026-05-19

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43091

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: xfrm: Wait for RCU readers during policy netns exit xfrm_policy_fini() frees the policy_bydst hash tables after flushing the policy work items and deleting all policies, but it does not wait for concurrent RCU readers to leave their read-side critical sections first. The policy_bydst tables are published via rcu_assign_pointer() and are looked up through rcu_dereference_check(), so netns teardown must also wait for an RCU grace period before freeing the table memory. Fix this by adding synchronize_rcu() before freeing the policy hash tables.

Published: 2026-05-06Modified: 2026-05-19

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43092

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xsk: validate MTU against usable frame size on bind AF_XDP bind currently accepts zero-copy pool configurations without verifying that the device MTU fits into the usable frame space provided by the UMEM chunk. This becomes a problem since we started to respect tailroom which is subtracted from chunk_size (among with headroom). 2k chunk size might not provide enough space for standard 1500 MTU, so let us catch such settings at bind time. Furthermore, validate whether underlying HW will be able to satisfy configured MTU wrt XSK's frame size multiplied by supported Rx buffer chain length (that is exposed via net_device::xdp_zc_max_segs).

Published: 2026-05-06Modified: 2026-05-19

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43093

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: xsk: tighten UMEM headroom validation to account for tailroom and min frame The current headroom validation in xdp_umem_reg() could leave us with insufficient space dedicated to even receive minimum-sized ethernet frame. Furthermore if multi-buffer would come to play then skb_shared_info stored at the end of XSK frame would be corrupted. HW typically works with 128-aligned sizes so let us provide this value as bare minimum. Multi-buffer setting is known later in the configuration process so besides accounting for 128 bytes, let us also take care of tailroom space upfront.

Published: 2026-05-06Modified: 2026-05-19

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43094

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ixgbevf: add missing negotiate_features op to Hyper-V ops table Commit a7075f501bd3 ("ixgbevf: fix mailbox API compatibility by negotiating supported features") added the .negotiate_features callback to ixgbe_mac_operations and populated it in ixgbevf_mac_ops, but forgot to add it to ixgbevf_hv_mac_ops. This leaves the function pointer NULL on Hyper-V VMs. During probe, ixgbevf_negotiate_api() calls ixgbevf_set_features(), which unconditionally dereferences hw->mac.ops.negotiate_features(). On Hyper-V this results in a NULL pointer dereference: BUG: kernel NULL pointer dereference, address: 0000000000000000 [...] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine [...] Workqueue: events work_for_cpu_fn RIP: 0010:0x0 [...] Call Trace: ixgbevf_negotiate_api+0x66/0x160 [ixgbevf] ixgbevf_sw_init+0xe4/0x1f0 [ixgbevf] ixgbevf_probe+0x20f/0x4a0 [ixgbevf] local_pci_probe+0x50/0xa0 work_for_cpu_fn+0x1a/0x30 [...] Add ixgbevf_hv_negotiate_features_vf() that returns -EOPNOTSUPP and wire it into ixgbevf_hv_mac_ops. The caller already handles -EOPNOTSUPP gracefully.

Published: 2026-05-06Modified: 2026-05-19

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43098

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: nfc: s3fwrn5: allocate rx skb before consuming bytes s3fwrn82_uart_read() reports the number of accepted bytes to the serdev core. The current code consumes bytes into recv_skb and may already deliver a complete frame before allocating a fresh receive buffer. If that alloc_skb() fails, the callback returns 0 even though it has already consumed bytes, and it leaves recv_skb as NULL for the next receive callback. That breaks the receive_buf() accounting contract and can also lead to a NULL dereference on the next skb_put_u8(). Allocate the receive skb lazily before consuming the next byte instead. If allocation fails, return the number of bytes already accepted.

Published: 2026-05-06Modified: 2026-05-14

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43099

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: ipv4: icmp: fix null-ptr-deref in icmp_build_probe() ipv6_stub->ipv6_dev_find() may return ERR_PTR(-EAFNOSUPPORT) when the IPv6 stack is not active (CONFIG_IPV6=m and not loaded), and passing this error pointer to dev_hold() will cause a kernel crash with null-ptr-deref. Instead, silently discard the request. RFC 8335 does not appear to define a specific response for the case where an IPv6 interface identifier is syntactically valid but the implementation cannot perform the lookup at runtime, and silently dropping the request may safer than misreporting "No Such Interface".

Published: 2026-05-06Modified: 2026-05-11

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43100

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: bridge: guard local VLAN-0 FDB helpers against NULL vlan group When CONFIG_BRIDGE_VLAN_FILTERING is not set, br_vlan_group() and nbp_vlan_group() return NULL (br_private.h stub definitions). The BR_BOOLOPT_FDB_LOCAL_VLAN_0 toggle code is compiled unconditionally and reaches br_fdb_delete_locals_per_vlan_port() and br_fdb_insert_locals_per_vlan_port(), where the NULL vlan group pointer is dereferenced via list_for_each_entry(v, &vg->vlan_list, vlist). The observed crash is in the delete path, triggered when creating a bridge with IFLA_BR_MULTI_BOOLOPT containing BR_BOOLOPT_FDB_LOCAL_VLAN_0 via RTM_NEWLINK. The insert helper has the same bug pattern. Oops: general protection fault, probably for non-canonical address 0xdffffc0000000056: 0000 [#1] KASAN NOPTI KASAN: null-ptr-deref in range [0x00000000000002b0-0x00000000000002b7] RIP: 0010:br_fdb_delete_locals_per_vlan+0x2b9/0x310 Call Trace: br_fdb_toggle_local_vlan_0+0x452/0x4c0 br_toggle_fdb_local_vlan_0+0x31/0x80 net/bridge/br.c:276 br_boolopt_toggle net/bridge/br.c:313 br_boolopt_multi_toggle net/bridge/br.c:364 br_changelink net/bridge/br_netlink.c:1542 br_dev_newlink net/bridge/br_netlink.c:1575 Add NULL checks for the vlan group pointer in both helpers, returning early when there are no VLANs to iterate. This matches the existing pattern used by other bridge FDB functions such as br_fdb_add() and br_fdb_delete().

Published: 2026-05-06Modified: 2026-05-11

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43101

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: ipv6: ioam: fix potential NULL dereferences in __ioam6_fill_trace_data() We need to check __in6_dev_get() for possible NULL value, as suggested by Yiming Qian. Also add skb_dst_dev_rcu() instead of skb_dst_dev(), and two missing READ_ONCE(). Note that @dev can't be NULL.

Published: 2026-05-06Modified: 2026-05-11

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43102

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: airoha: Fix memory leak in airoha_qdma_rx_process() If an error occurs on the subsequents buffers belonging to the non-linear part of the skb (e.g. due to an error in the payload length reported by the NIC or if we consumed all the available fragments for the skb), the page_pool fragment will not be linked to the skb so it will not return to the pool in the airoha_qdma_rx_process() error path. Fix the memory leak partially reverting commit 'd6d2b0e1538d ("net: airoha: Fix page recycling in airoha_qdma_rx_process()")' and always running page_pool_put_full_page routine in the airoha_qdma_rx_process() error path.

Published: 2026-05-06Modified: 2026-05-11

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43103

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: lapbether: handle NETDEV_PRE_TYPE_CHANGE lapbeth_data_transmit() expects the underlying device type to be ARPHRD_ETHER. Returning NOTIFY_BAD from lapbeth_device_event() makes sure bonding driver can not break this expectation.

Published: 2026-05-06Modified: 2026-05-11

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43104

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/vc4: Fix a memory leak in hang state error path When vc4_save_hang_state() encounters an early return condition, it returns without freeing the previously allocated `kernel_state`, leaking memory. Add the missing kfree() calls by consolidating the early return paths into a single place.

Published: 2026-05-06Modified: 2026-05-11

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43105

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/vc4: Fix memory leak of BO array in hang state The hang state's BO array is allocated separately with kzalloc() in vc4_save_hang_state() but never freed in vc4_free_hang_state(). Add the missing kfree() for the BO array before freeing the hang state struct.

Published: 2026-05-06Modified: 2026-05-11

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43107

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xfrm: account XFRMA_IF_ID in aevent size calculation xfrm_get_ae() allocates the reply skb with xfrm_aevent_msgsize(), then build_aevent() appends attributes including XFRMA_IF_ID when x->if_id is set. xfrm_aevent_msgsize() does not include space for XFRMA_IF_ID. For states with if_id, build_aevent() can fail with -EMSGSIZE and hit BUG_ON(err < 0) in xfrm_get_ae(), turning a malformed netlink interaction into a kernel panic. Account XFRMA_IF_ID in the size calculation unconditionally and replace the BUG_ON with normal error unwinding.

Published: 2026-05-06Modified: 2026-05-11

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43108

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: soc: qcom: pd-mapper: Fix element length in servreg_loc_pfr_req_ei It looks element length declared in servreg_loc_pfr_req_ei for reason not matching servreg_loc_pfr_req's reason field due which we could observe decoding error on PD crash. qmi_decode_string_elem: String len 81 >= Max Len 65 Fix this by matching with servreg_loc_pfr_req's reason field.

Published: 2026-05-06Modified: 2026-05-11

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43109

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: x86: shadow stacks: proper error handling for mmap lock 김영민 reports that shstk_pop_sigframe() doesn't check for errors from mmap_read_lock_killable(), which is a silly oversight, and also shows that we haven't marked those functions with "__must_check", which would have immediately caught it. So let's fix both issues.

Published: 2026-05-06Modified: 2026-05-17

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43110

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: wifi: brcmfmac: validate bsscfg indices in IF events brcmf_fweh_handle_if_event() validates the firmware-provided interface index before it touches drvr->iflist[], but it still uses the raw bsscfgidx field as an array index without a matching range check. Reject IF events whose bsscfg index does not fit in drvr->iflist[] before indexing the interface array. [add missing wifi prefix]

Published: 2026-05-06Modified: 2026-05-08

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43111

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: HID: roccat: fix use-after-free in roccat_report_event roccat_report_event() iterates over the device->readers list without holding the readers_lock. This allows a concurrent roccat_release() to remove and free a reader while it's still being accessed, leading to a use-after-free. Protect the readers list traversal with the readers_lock mutex.

Published: 2026-05-06Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43112

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: fs/smb/client: fix out-of-bounds read in cifs_sanitize_prepath When cifs_sanitize_prepath is called with an empty string or a string containing only delimiters (e.g., "/"), the current logic attempts to check *(cursor2 - 1) before cursor2 has advanced. This results in an out-of-bounds read. This patch adds an early exit check after stripping prepended delimiters. If no path content remains, the function returns NULL. The bug was identified via manual audit and verified using a standalone test case compiled with AddressSanitizer, which triggered a SEGV on affected inputs.

Published: 2026-05-06Modified: 2026-05-08

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

References

CVE-2026-43113

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: wifi: wl1251: validate packet IDs before indexing tx_frames wl1251_tx_packet_cb() uses the firmware completion ID directly to index the fixed 16-entry wl->tx_frames[] array. The ID is a raw u8 from the completion block, and the callback does not currently verify that it fits the array before dereferencing it. Reject completion IDs that fall outside wl->tx_frames[] and keep the existing NULL check in the same guard. This keeps the fix local to the trust boundary and avoids touching the rest of the completion flow.

Published: 2026-05-06Modified: 2026-05-08

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43114

CRITICAL9.4

In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_set_pipapo_avx2: don't return non-matching entry on expiry New test case fails unexpectedly when avx2 matching functions are used. The test first loads a ranomly generated pipapo set with 'ipv4 . port' key, i.e. nft -f foo. This works. Then, it reloads the set after a flush: (echo flush set t s; cat foo) | nft -f - This is expected to work, because its the same set after all and it was already loaded once. But with avx2, this fails: nft reports a clashing element. The reported clash is of following form: We successfully re-inserted a . b c . d Then we try to insert a . d avx2 finds the already existing a . d, which (due to 'flush set') is marked as invalid in the new generation. It skips the element and moves to next. Due to incorrect masking, the skip-step finds the next matching element only considering the first field, i.e. we return the already reinserted "a . b", even though the last field is different and the entry should not have been matched. No such error is reported for the generic c implementation (no avx2) or when the last field has to use the 'nft_pipapo_avx2_lookup_slow' fallback. Bisection points to 7711f4bb4b36 ("netfilter: nft_set_pipapo: fix range overlap detection") but that fix merely uncovers this bug. Before this commit, the wrong element is returned, but erronously reported as a full, identical duplicate. The root-cause is too early return in the avx2 match functions. When we process the last field, we should continue to process data until the entire input size has been consumed to make sure no stale bits remain in the map.

Published: 2026-05-06Modified: 2026-05-08

CVSS 3.xCRITICAL 9.4

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:L

References

CVE-2026-43116

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: ensure safe access to master conntrack Holding reference on the expectation is not sufficient, the master conntrack object can just go away, making exp->master invalid. To access exp->master safely: - Grab the nf_conntrack_expect_lock, this gets serialized with clean_from_lists() which also holds this lock when the master conntrack goes away. - Hold reference on master conntrack via nf_conntrack_find_get(). Not so easy since the master tuple to look up for the master conntrack is not available in the existing problematic paths. This patch goes for extending the nf_conntrack_expect_lock section to address this issue for simplicity, in the cases that are described below this is just slightly extending the lock section. The add expectation command already holds a reference to the master conntrack from ctnetlink_create_expect(). However, the delete expectation command needs to grab the spinlock before looking up for the expectation. Expand the existing spinlock section to address this to cover the expectation lookup. Note that, the nf_ct_expect_iterate_net() calls already grabs the spinlock while iterating over the expectation table, which is correct. The get expectation command needs to grab the spinlock to ensure master conntrack does not go away. This also expands the existing spinlock section to cover the expectation lookup too. I needed to move the netlink skb allocation out of the spinlock to keep it GFP_KERNEL. For the expectation events, the IPEXP_DESTROY event is already delivered under the spinlock, just move the delivery of IPEXP_NEW under the spinlock too because the master conntrack event cache is reached through exp->master. While at it, add lockdep notations to help identify what codepaths need to grab the spinlock.

Published: 2026-05-06Modified: 2026-05-08

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43117

CRITICAL9.1

In the Linux kernel, the following vulnerability has been resolved: btrfs: tracepoints: get correct superblock from dentry in event btrfs_sync_file() If overlay is used on top of btrfs, dentry->d_sb translates to overlay's super block and fsid assignment will lead to a crash. Use file_inode(file)->i_sb to always get btrfs_sb.

Published: 2026-05-06Modified: 2026-05-08

CVSS 3.xCRITICAL 9.1

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H

References

CVE-2026-43118

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: btrfs: fix zero size inode with non-zero size after log replay When logging that an inode exists, as part of logging a new name or logging new dir entries for a directory, we always set the generation of the logged inode item to 0. This is to signal during log replay (in overwrite_item()), that we should not set the i_size since we only logged that an inode exists, so the i_size of the inode in the subvolume tree must be preserved (as when we log new names or that an inode exists, we don't log extents). This works fine except when we have already logged an inode in full mode or it's the first time we are logging an inode created in a past transaction, that inode has a new i_size of 0 and then we log a new name for the inode (due to a new hardlink or a rename), in which case we log an i_size of 0 for the inode and a generation of 0, which causes the log replay code to not update the inode's i_size to 0 (in overwrite_item()). An example scenario: mkdir /mnt/dir xfs_io -f -c "pwrite 0 64K" /mnt/dir/foo sync xfs_io -c "truncate 0" -c "fsync" /mnt/dir/foo ln /mnt/dir/foo /mnt/dir/bar xfs_io -c "fsync" /mnt/dir After log replay the file remains with a size of 64K. This is because when we first log the inode, when we fsync file foo, we log its current i_size of 0, and then when we create a hard link we log again the inode in exists mode (LOG_INODE_EXISTS) but we set a generation of 0 for the inode item we add to the log tree, so during log replay overwrite_item() sees that the generation is 0 and i_size is 0 so we skip updating the inode's i_size from 64K to 0. Fix this by making sure at fill_inode_item() we always log the real generation of the inode if it was logged in the current transaction with the i_size we logged before. Also if an inode created in a previous transaction is logged in exists mode only, make sure we log the i_size stored in the inode item located from the commit root, so that if we log multiple times that the inode exists we get the correct i_size. A test case for fstests will follow soon.

Published: 2026-05-06Modified: 2026-05-08

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43119

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_sync: annotate data-races around hdev->req_status __hci_cmd_sync_sk() sets hdev->req_status under hdev->req_lock: hdev->req_status = HCI_REQ_PEND; However, several other functions read or write hdev->req_status without holding any lock: - hci_send_cmd_sync() reads req_status in hci_cmd_work (workqueue) - hci_cmd_sync_complete() reads/writes from HCI event completion - hci_cmd_sync_cancel() / hci_cmd_sync_cancel_sync() read/write - hci_abort_conn() reads in connection abort path Since __hci_cmd_sync_sk() runs on hdev->req_workqueue while hci_send_cmd_sync() runs on hdev->workqueue, these are different workqueues that can execute concurrently on different CPUs. The plain C accesses constitute a data race. Add READ_ONCE()/WRITE_ONCE() annotations on all concurrent accesses to hdev->req_status to prevent potential compiler optimizations that could affect correctness (e.g., load fusing in the wait_event condition or store reordering).

Published: 2026-05-06Modified: 2026-05-12

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43120

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: RDMA/irdma: Fix double free related to rereg_user_mr If IB_MR_REREG_TRANS is set during rereg_user_mr, the umem will be released and a new one will be allocated in irdma_rereg_mr_trans. If any step of irdma_rereg_mr_trans fails after the new umem is allocated, it releases the umem, but does not set iwmr->region to NULL. The problem is that this failure is propagated to the user, who will then call ibv_dereg_mr (as they should). Then, the dereg_mr path will see a non-NULL umem and attempt to call ib_umem_release again. Fix this by setting iwmr->region to NULL after ib_umem_release. Fixed: 5ac388db27c4 ("RDMA/irdma: Add support to re-register a memory region")

Published: 2026-05-06Modified: 2026-05-12

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43323

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: sched/fair: Fix zero_vruntime tracking fix John reported that stress-ng-yield could make his machine unhappy and managed to bisect it to commit b3d99f43c72b ("sched/fair: Fix zero_vruntime tracking"). The combination of yield and that commit was specific enough to hypothesize the following scenario: Suppose we have 2 runnable tasks, both doing yield. Then one will be eligible and one will not be, because the average position must be in between these two entities. Therefore, the runnable task will be eligible, and be promoted a full slice (all the tasks do is yield after all). This causes it to jump over the other task and now the other task is eligible and current is no longer. So we schedule. Since we are runnable, there is no {de,en}queue. All we have is the __{en,de}queue_entity() from {put_prev,set_next}_task(). But per the fingered commit, those two no longer move zero_vruntime. All that moves zero_vruntime are tick and full {de,en}queue. This means, that if the two tasks playing leapfrog can reach the critical speed to reach the overflow point inside one tick's worth of time, we're up a creek. Additionally, when multiple cgroups are involved, there is no guarantee the tick will in fact hit every cgroup in a timely manner. Statistically speaking it will, but that same statistics does not rule out the possibility of one cgroup not getting a tick for a significant amount of time -- however unlikely. Therefore, just like with the yield() case, force an update at the end of every slice. This ensures the update is never more than a single slice behind and the whole thing is within 2 lag bounds as per the comment on entity_key().

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43324

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: USB: dummy-hcd: Fix interrupt synchronization error This fixes an error in synchronization in the dummy-hcd driver. The error has a somewhat involved history. The synchronization mechanism was introduced by commit 7dbd8f4cabd9 ("USB: dummy-hcd: Fix erroneous synchronization change"), which added an emulated "interrupts enabled" flag together with code emulating synchronize_irq() (it waits until all current handler callbacks have returned). But the emulated interrupt-disable occurred too late, after the driver containing the handler callback routines had been told that it was unbound and no more callbacks would occur. Commit 4a5d797a9f9c ("usb: gadget: dummy_hcd: fix gpf in gadget_setup") tried to fix this by moving the synchronize_irq() emulation code from dummy_stop() to dummy_pullup(), which runs before the unbind callback. There still were races, though, because the emulated interrupt-disable still occurred too late. It couldn't be moved to dummy_pullup(), because that routine can be called for reasons other than an impending unbind. Therefore commits 7dc0c55e9f30 ("USB: UDC core: Add udc_async_callbacks gadget op") and 04145a03db9d ("USB: UDC: Implement udc_async_callbacks in dummy-hcd") added an API allowing the UDC core to tell dummy-hcd exactly when emulated interrupts and their callbacks should be disabled. That brings us to the current state of things, which is still wrong because the emulated synchronize_irq() occurs before the emulated interrupt-disable! That's no good, beause it means that more emulated interrupts can occur after the synchronize_irq() emulation has run, leading to the possibility that a callback handler may be running when the gadget driver is unbound. To fix this, we have to move the synchronize_irq() emulation code yet again, to the dummy_udc_async_callbacks() routine, which takes care of enabling and disabling emulated interrupt requests. The synchronization will now run immediately after emulated interrupts are disabled, which is where it belongs.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43325

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: mvm: don't send a 6E related command when not supported MCC_ALLOWED_AP_TYPE_CMD is related to 6E support. Do not send it if the device doesn't support 6E. Apparently, the firmware is mistakenly advertising support for this command even on AX201 which does not support 6E and then the firmware crashes.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43327

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: USB: dummy-hcd: Fix locking/synchronization error Syzbot testing was able to provoke an addressing exception and crash in the usb_gadget_udc_reset() routine in drivers/usb/gadgets/udc/core.c, resulting from the fact that the routine was called with a second ("driver") argument of NULL. The bad caller was set_link_state() in dummy_hcd.c, and the problem arose because of a race between a USB reset and driver unbind. These sorts of races were not supposed to be possible; commit 7dbd8f4cabd9 ("USB: dummy-hcd: Fix erroneous synchronization change"), along with a few followup commits, was written specifically to prevent them. As it turns out, there are (at least) two errors remaining in the code. Another patch will address the second error; this one is concerned with the first. The error responsible for the syzbot crash occurred because the stop_activity() routine will sometimes drop and then re-acquire the dum->lock spinlock. A call to stop_activity() occurs in set_link_state() when handling an emulated USB reset, after the test of dum->ints_enabled and before the increment of dum->callback_usage. This allowed another thread (doing a driver unbind) to sneak in and grab the spinlock, and then clear dum->ints_enabled and dum->driver. Normally this other thread would have to wait for dum->callback_usage to go down to 0 before it would clear dum->driver, but in this case it didn't have to wait since dum->callback_usage had not yet been incremented. The fix is to increment dum->callback_usage _before_ calling stop_activity() instead of after. Then the thread doing the unbind will not clear dum->driver until after the call to usb_gadget_udc_reset() safely returns and dum->callback_usage has been decremented again.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43328

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: cpufreq: governor: fix double free in cpufreq_dbs_governor_init() error path When kobject_init_and_add() fails, cpufreq_dbs_governor_init() calls kobject_put(&dbs_data->attr_set.kobj). The kobject release callback cpufreq_dbs_data_release() calls gov->exit(dbs_data) and kfree(dbs_data), but the current error path then calls gov->exit(dbs_data) and kfree(dbs_data) again, causing a double free. Keep the direct kfree(dbs_data) for the gov->init() failure path, but after kobject_init_and_add() has been called, let kobject_put() handle the cleanup through cpufreq_dbs_data_release().

Published: 2026-05-08Modified: 2026-05-18

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43329

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: flowtable: strictly check for maximum number of actions The maximum number of flowtable hardware offload actions in IPv6 is: * ethernet mangling (4 payload actions, 2 for each ethernet address) * SNAT (4 payload actions) * DNAT (4 payload actions) * Double VLAN (4 vlan actions, 2 for popping vlan, and 2 for pushing) for QinQ. * Redirect (1 action) Which makes 17, while the maximum is 16. But act_ct supports for tunnels actions too. Note that payload action operates at 32-bit word level, so mangling an IPv6 address takes 4 payload actions. Update flow_action_entry_next() calls to check for the maximum number of supported actions. While at it, rise the maximum number of actions per flow from 16 to 24 so this works fine with IPv6 setups.

Published: 2026-05-08Modified: 2026-05-18

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43330

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: crypto: caam - fix overflow on long hmac keys When a key longer than block size is supplied, it is copied and then hashed into the real key. The memory allocated for the copy needs to be rounded to DMA cache alignment, as otherwise the hashed key may corrupt neighbouring memory. The copying is performed using kmemdup, however this leads to an overflow: reading more bytes (aligned_len - keylen) from the keylen source buffer. Fix this by replacing kmemdup with kmalloc, followed by memcpy.

Published: 2026-05-08Modified: 2026-05-18

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43331

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: x86/kexec: Disable KCOV instrumentation after load_segments() The load_segments() function changes segment registers, invalidating GS base (which KCOV relies on for per-cpu data). When CONFIG_KCOV is enabled, any subsequent instrumented C code call (e.g. native_gdt_invalidate()) begins crashing the kernel in an endless loop. To reproduce the problem, it's sufficient to do kexec on a KCOV-instrumented kernel: $ kexec -l /boot/otherKernel $ kexec -e The real-world context for this problem is enabling crash dump collection in syzkaller. For this, the tool loads a panic kernel before fuzzing and then calls makedumpfile after the panic. This workflow requires both CONFIG_KEXEC and CONFIG_KCOV to be enabled simultaneously. Adding safeguards directly to the KCOV fast-path (__sanitizer_cov_trace_pc()) is also undesirable as it would introduce an extra performance overhead. Disabling instrumentation for the individual functions would be too fragile, so disable KCOV instrumentation for the entire machine_kexec_64.c and physaddr.c. If coverage-guided fuzzing ever needs these components in the future, other approaches should be considered. The problem is not relevant for 32 bit kernels as CONFIG_KCOV is not supported there. [ bp: Space out comment for better readability. ]

Published: 2026-05-08Modified: 2026-05-18

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43332

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: thermal: core: Fix thermal zone device registration error path If thermal_zone_device_register_with_trips() fails after registering a thermal zone device, it needs to wait for the tz->removal completion like thermal_zone_device_unregister(), in case user space has managed to take a reference to the thermal zone device's kobject, in which case thermal_release() may not be called by the error path itself and tz may be freed prematurely. Add the missing wait_for_completion() call to the thermal zone device registration error path.

Published: 2026-05-08Modified: 2026-05-18

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43333

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: bpf: reject direct access to nullable PTR_TO_BUF pointers check_mem_access() matches PTR_TO_BUF via base_type() which strips PTR_MAYBE_NULL, allowing direct dereference without a null check. Map iterator ctx->key and ctx->value are PTR_TO_BUF | PTR_MAYBE_NULL. On stop callbacks these are NULL, causing a kernel NULL dereference. Add a type_may_be_null() guard to the PTR_TO_BUF branch, matching the existing PTR_TO_BTF_ID pattern.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43334

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: SMP: force responder MITM requirements before building the pairing response smp_cmd_pairing_req() currently builds the pairing response from the initiator auth_req before enforcing the local BT_SECURITY_HIGH requirement. If the initiator omits SMP_AUTH_MITM, the response can also omit it even though the local side still requires MITM. tk_request() then sees an auth value without SMP_AUTH_MITM and may select JUST_CFM, making method selection inconsistent with the pairing policy the responder already enforces. When the local side requires HIGH security, first verify that MITM can be achieved from the IO capabilities and then force SMP_AUTH_MITM in the response in both rsp.auth_req and auth. This keeps the responder auth bits and later method selection aligned.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xHIGH 8.8

CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43336

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: lib/crypto: chacha: Zeroize permuted_state before it leaves scope Since the ChaCha permutation is invertible, the local variable 'permuted_state' is sufficient to compute the original 'state', and thus the key, even after the permutation has been done. While the kernel is quite inconsistent about zeroizing secrets on the stack (and some prominent userspace crypto libraries don't bother at all since it's not guaranteed to work anyway), the kernel does try to do it as a best practice, especially in cases involving the RNG. Thus, explicitly zeroize 'permuted_state' before it goes out of scope.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

References

CVE-2026-43337

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix NULL pointer dereference in dcn401_init_hw() dcn401_init_hw() assumes that update_bw_bounding_box() is valid when entering the update path. However, the existing condition: ((!fams2_enable && update_bw_bounding_box) || freq_changed) does not guarantee this, as the freq_changed branch can evaluate to true independently of the callback pointer. This can result in calling update_bw_bounding_box() when it is NULL. Fix this by separating the update condition from the pointer checks and ensuring the callback, dc->clk_mgr, and bw_params are validated before use. Fixes the below: ../dc/hwss/dcn401/dcn401_hwseq.c:367 dcn401_init_hw() error: we previously assumed 'dc->res_pool->funcs->update_bw_bounding_box' could be null (see line 362) (cherry picked from commit 86117c5ab42f21562fedb0a64bffea3ee5fcd477)

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43338

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: btrfs: reserve enough transaction items for qgroup ioctls Currently our qgroup ioctls don't reserve any space, they just do a transaction join, which does not reserve any space, neither for the quota tree updates nor for the delayed refs generated when updating the quota tree. The quota root uses the global block reserve, which is fine most of the time since we don't expect a lot of updates to the quota root, or to be too close to -ENOSPC such that other critical metadata updates need to resort to the global reserve. However this is not optimal, as not reserving proper space may result in a transaction abort due to not reserving space for delayed refs and then abusing the use of the global block reserve. For example, the following reproducer (which is unlikely to model any real world use case, but just to illustrate the problem), triggers such a transaction abort due to -ENOSPC when running delayed refs: $ cat test.sh #!/bin/bash DEV=/dev/nullb0 MNT=/mnt/nullb0 umount $DEV &> /dev/null # Limit device to 1G so that it's much faster to reproduce the issue. mkfs.btrfs -f -b 1G $DEV mount -o commit=600 $DEV $MNT fallocate -l 800M $MNT/filler btrfs quota enable $MNT for ((i = 1; i <= 400000; i++)); do btrfs qgroup create 1/$i $MNT done umount $MNT When running this, we can see in dmesg/syslog that a transaction abort happened: [436.490] BTRFS error (device nullb0): failed to run delayed ref for logical 30408704 num_bytes 16384 type 176 action 1 ref_mod 1: -28 [436.493] ------------[ cut here ]------------ [436.494] BTRFS: Transaction aborted (error -28) [436.495] WARNING: fs/btrfs/extent-tree.c:2247 at btrfs_run_delayed_refs+0xd9/0x110 [btrfs], CPU#4: umount/2495372 [436.497] Modules linked in: btrfs loop (...) [436.508] CPU: 4 UID: 0 PID: 2495372 Comm: umount Tainted: G W 6.19.0-rc8-btrfs-next-225+ #1 PREEMPT(full) [436.510] Tainted: [W]=WARN [436.511] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014 [436.513] RIP: 0010:btrfs_run_delayed_refs+0xdf/0x110 [btrfs] [436.514] Code: 0f 82 ea (...) [436.518] RSP: 0018:ffffd511850b7d78 EFLAGS: 00010292 [436.519] RAX: 00000000ffffffe4 RBX: ffff8f120dad37e0 RCX: 0000000002040001 [436.520] RDX: 0000000000000002 RSI: 00000000ffffffe4 RDI: ffffffffc090fd80 [436.522] RBP: 0000000000000000 R08: 0000000000000001 R09: ffffffffc04d1867 [436.523] R10: ffff8f18dc1fffa8 R11: 0000000000000003 R12: ffff8f173aa89400 [436.524] R13: 0000000000000000 R14: ffff8f173aa89400 R15: 0000000000000000 [436.526] FS: 00007fe59045d840(0000) GS:ffff8f192e22e000(0000) knlGS:0000000000000000 [436.527] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [436.528] CR2: 00007fe5905ff2b0 CR3: 000000060710a002 CR4: 0000000000370ef0 [436.530] Call Trace: [436.530] [436.530] btrfs_commit_transaction+0x73/0xc00 [btrfs] [436.531] ? btrfs_attach_transaction_barrier+0x1e/0x70 [btrfs] [436.532] sync_filesystem+0x7a/0x90 [436.533] generic_shutdown_super+0x28/0x180 [436.533] kill_anon_super+0x12/0x40 [436.534] btrfs_kill_super+0x12/0x20 [btrfs] [436.534] deactivate_locked_super+0x2f/0xb0 [436.534] cleanup_mnt+0xea/0x180 [436.535] task_work_run+0x58/0xa0 [436.535] exit_to_user_mode_loop+0xed/0x480 [436.536] ? __x64_sys_umount+0x68/0x80 [436.536] do_syscall_64+0x2a5/0xf20 [436.537] entry_SYSCALL_64_after_hwframe+0x76/0x7e [436.537] RIP: 0033:0x7fe5906b6217 [436.538] Code: 0d 00 f7 (...) [436.540] RSP: 002b:00007ffcd87a61f8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 [436.541] RAX: 0000000000000000 RBX: 00005618b9ecadc8 RCX: 00007fe5906b6217 [436.541] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 00005618b9ecb100 [436.542] RBP: 0000000000000000 R08: 00007ffcd87a4fe0 R09: 00000000ffffffff [436.544] R10: 0000000000000103 R11: ---truncated---

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43339

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ipv6: prevent possible UaF in addrconf_permanent_addr() The mentioned helper try to warn the user about an exceptional condition, but the message is delivered too late, accessing the ipv6 after its possible deletion. Reorder the statement to avoid the possible UaF; while at it, place the warning outside the idev->lock as it needs no protection.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xHIGH 7.8

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43340

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: comedi: Reinit dev->spinlock between attachments to low-level drivers `struct comedi_device` is the main controlling structure for a COMEDI device created by the COMEDI subsystem. It contains a member `spinlock` containing a spin-lock that is initialized by the COMEDI subsystem, but is reserved for use by a low-level driver attached to the COMEDI device (at least since commit 25436dc9d84f ("Staging: comedi: remove RT code")). Some COMEDI devices (those created on initialization of the COMEDI subsystem when the "comedi.comedi_num_legacy_minors" parameter is non-zero) can be attached to different low-level drivers over their lifetime using the `COMEDI_DEVCONFIG` ioctl command. This can result in inconsistent lock states being reported when there is a mismatch in the spin-lock locking levels used by each low-level driver to which the COMEDI device has been attached. Fix it by reinitializing `dev->spinlock` before calling the low-level driver's `attach` function pointer if `CONFIG_LOCKDEP` is enabled.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43341

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: net/ipv6: ioam6: prevent schema length wraparound in trace fill ioam6_fill_trace_data() stores the schema contribution to the trace length in a u8. With bit 22 enabled and the largest schema payload, sclen becomes 1 + 1020 / 4, wraps from 256 to 0, and bypasses the remaining-space check. __ioam6_fill_trace_data() then positions the write cursor without reserving the schema area but still copies the 4-byte schema header and the full schema payload, overrunning the trace buffer. Keep sclen in an unsigned int so the remaining-space check and the write cursor calculation both see the full schema length.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xCRITICAL 9.8

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

CVE-2026-43342

MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_rndis: Protect RNDIS options with mutex The class/subclass/protocol options are suspectible to race conditions as they can be accessed concurrently through configfs. Use existing mutex to protect these options. This issue was identified during code inspection.

Published: 2026-05-08Modified: 2026-05-18

CVSS 3.xMEDIUM 4.7

CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43343

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_subset: Fix unbalanced refcnt in geth_free geth_alloc() increments the reference count, but geth_free() fails to decrement it. This prevents the configuration of attributes via configfs after unlinking the function. Decrement the reference count in geth_free() to ensure proper cleanup.

Published: 2026-05-08Modified: 2026-05-18

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43345

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: net: ipa: fix event ring index not programmed for IPA v5.0+ For IPA v5.0+, the event ring index field moved from CH_C_CNTXT_0 to CH_C_CNTXT_1. The v5.0 register definition intended to define this field in the CH_C_CNTXT_1 fmask array but used the old identifier of ERINDEX instead of CH_ERINDEX. Without a valid event ring, GSI channels could never signal transfer completions. This caused gsi_channel_trans_quiesce() to block forever in wait_for_completion(). At least for IPA v5.2 this resolves an issue seen where runtime suspend, system suspend, and remoteproc stop all hanged forever. It also meant the IPA data path was completely non functional.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43346

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ice: ptp: don't WARN when controlling PF is unavailable In VFIO passthrough setups, it is possible to pass through only a PF which doesn't own the source timer. In that case the PTP controlling PF (adapter->ctrl_pf) is never initialized in the VM, so ice_get_ctrl_ptp() returns NULL and triggers WARN_ON() in ice_ptp_setup_pf(). Since this is an expected behavior in that configuration, replace WARN_ON() with an informational message and return -EOPNOTSUPP.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43347

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: arm64: dts: qcom: monaco: Reserve full Gunyah metadata region We observe spurious "Synchronous External Abort" exceptions (ESR=0x96000010) and kernel crashes on Monaco-based platforms. These faults are caused by the kernel inadvertently accessing hypervisor-owned memory that is not properly marked as reserved. >From boot log, The Qualcomm hypervisor reports the memory range at 0x91a80000 of size 0x80000 (512 KiB) as hypervisor-owned: qhee_hyp_assign_remove_memory: 0x91a80000/0x80000 -> ret 0 However, the EFI memory map provided by firmware only reserves the subrange 0x91a40000–0x91a87fff (288 KiB). The remaining portion (0x91a88000–0x91afffff) is incorrectly reported as conventional memory (from efi debug): efi: 0x000091a40000-0x000091a87fff [Reserved...] efi: 0x000091a88000-0x0000938fffff [Conventional...] As a result, the allocator may hand out PFNs inside the hypervisor owned region, causing fatal aborts when the kernel accesses those addresses. Add a reserved-memory carveout for the Gunyah hypervisor metadata at 0x91a80000 (512 KiB) and mark it as no-map so Linux does not map or allocate from this area. For the record: Hyp version: gunyah-e78adb36e debug (2025-11-17 05:38:05 UTC) UEFI Ver: 6.0.260122.BOOT.MXF.1.0.c1-00449-KODIAKLA-1

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43349

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid uninit-value access in f2fs_sanity_check_node_footer syzbot reported a f2fs bug as below: BUG: KMSAN: uninit-value in f2fs_sanity_check_node_footer+0x374/0xa20 fs/f2fs/node.c:1520 f2fs_sanity_check_node_footer+0x374/0xa20 fs/f2fs/node.c:1520 f2fs_finish_read_bio+0xe1e/0x1d60 fs/f2fs/data.c:177 f2fs_read_end_io+0x6ab/0x2220 fs/f2fs/data.c:-1 bio_endio+0x1006/0x1160 block/bio.c:1792 submit_bio_noacct+0x533/0x2960 block/blk-core.c:891 submit_bio+0x57a/0x620 block/blk-core.c:926 blk_crypto_submit_bio include/linux/blk-crypto.h:203 [inline] f2fs_submit_read_bio+0x12c/0x360 fs/f2fs/data.c:557 f2fs_submit_page_bio+0xee2/0x1450 fs/f2fs/data.c:775 read_node_folio+0x384/0x4b0 fs/f2fs/node.c:1481 __get_node_folio+0x5db/0x15d0 fs/f2fs/node.c:1576 f2fs_get_inode_folio+0x40/0x50 fs/f2fs/node.c:1623 do_read_inode fs/f2fs/inode.c:425 [inline] f2fs_iget+0x1209/0x9380 fs/f2fs/inode.c:596 f2fs_fill_super+0x8f5a/0xb2e0 fs/f2fs/super.c:5184 get_tree_bdev_flags+0x6e6/0x920 fs/super.c:1694 get_tree_bdev+0x38/0x50 fs/super.c:1717 f2fs_get_tree+0x35/0x40 fs/f2fs/super.c:5436 vfs_get_tree+0xb3/0x5d0 fs/super.c:1754 fc_mount fs/namespace.c:1193 [inline] do_new_mount_fc fs/namespace.c:3763 [inline] do_new_mount+0x885/0x1dd0 fs/namespace.c:3839 path_mount+0x7a2/0x20b0 fs/namespace.c:4159 do_mount fs/namespace.c:4172 [inline] __do_sys_mount fs/namespace.c:4361 [inline] __se_sys_mount+0x704/0x7f0 fs/namespace.c:4338 __x64_sys_mount+0xe4/0x150 fs/namespace.c:4338 x64_sys_call+0x39f0/0x3ea0 arch/x86/include/generated/asm/syscalls_64.h:166 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x134/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f The root cause is: in f2fs_finish_read_bio(), we may access uninit data in folio if we failed to read the data from device into folio, let's add a check condition to avoid such issue.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43350

HIGH7.6

In the Linux kernel, the following vulnerability has been resolved: smb: client: require a full NFS mode SID before reading mode bits parse_dacl() treats an ACE SID matching sid_unix_NFS_mode as an NFS mode SID and reads sid.sub_auth[2] to recover the mode bits. That assumes the ACE carries three subauthorities, but compare_sids() only compares min(a, b) subauthorities. A malicious server can return an ACE with num_subauth = 2 and sub_auth[] = {88, 3}, which still matches sid_unix_NFS_mode and then drives the sub_auth[2] read four bytes past the end of the ACE. Require num_subauth >= 3 before treating the ACE as an NFS mode SID. This keeps the fix local to the special-SID mode path without changing compare_sids() semantics for the rest of cifsacl.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xHIGH 7.6

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:H

References

CVE-2026-43364

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ublk: fix NULL pointer dereference in ublk_ctrl_set_size() ublk_ctrl_set_size() unconditionally dereferences ub->ub_disk via set_capacity_and_notify() without checking if it is NULL. ub->ub_disk is NULL before UBLK_CMD_START_DEV completes (it is only assigned in ublk_ctrl_start_dev()) and after UBLK_CMD_STOP_DEV runs (ublk_detach_disk() sets it to NULL). Since the UBLK_CMD_UPDATE_SIZE handler performs no state validation, a user can trigger a NULL pointer dereference by sending UPDATE_SIZE to a device that has been added but not yet started, or one that has been stopped. Fix this by checking ub->ub_disk under ub->mutex before dereferencing it, and returning -ENODEV if the disk is not available.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43371

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: macb: Shuffle the tx ring before enabling tx Quanyang observed that when using an NFS rootfs on an AMD ZynqMp board, the rootfs may take an extended time to recover after a suspend. Upon investigation, it was determined that the issue originates from a problem in the macb driver. According to the Zynq UltraScale TRM [1], when transmit is disabled, the transmit buffer queue pointer resets to point to the address specified by the transmit buffer queue base address register. In the current implementation, the code merely resets `queue->tx_head` and `queue->tx_tail` to '0'. This approach presents several issues: - Packets already queued in the tx ring are silently lost, leading to memory leaks since the associated skbs cannot be released. - Concurrent write access to `queue->tx_head` and `queue->tx_tail` may occur from `macb_tx_poll()` or `macb_start_xmit()` when these values are reset to '0'. - The transmission may become stuck on a packet that has already been sent out, with its 'TX_USED' bit set, but has not yet been processed. However, due to the manipulation of 'queue->tx_head' and 'queue->tx_tail', `macb_tx_poll()` incorrectly assumes there are no packets to handle because `queue->tx_head == queue->tx_tail`. This issue is only resolved when a new packet is placed at this position. This is the root cause of the prolonged recovery time observed for the NFS root filesystem. To resolve this issue, shuffle the tx ring and tx skb array so that the first unsent packet is positioned at the start of the tx ring. Additionally, ensure that updates to `queue->tx_head` and `queue->tx_tail` are properly protected with the appropriate lock. [1] https://docs.amd.com/v/u/en-US/ug1085-zynq-ultrascale-trm

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xMEDIUM 5.5

CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

CVE-2026-43377

HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: ksmbd: Don't log keys in SMB3 signing and encryption key generation When KSMBD_DEBUG_AUTH logging is enabled, generate_smb3signingkey() and generate_smb3encryptionkey() log the session, signing, encryption, and decryption key bytes. Remove the logs to avoid exposing credentials.

Published: 2026-05-08Modified: 2026-05-15

CVSS 3.xHIGH 8.1

CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N

References

GHSA-m38g-vww2-mvgx

HIGH7.5

Talos Linux has a local privilege escalation from untrusted workloads

Published: 2026-05-07

CVSS 3.xHIGH 7.5

CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:C/C:H/I:H/A:N

References

Package update kernel-image-pine in branch p11

Closed issues (538)

Уязвимость функции acpi_processor_errata_piix4() ядра операционной системы Linux, позволяющая нарушителю вызвать повреждение памяти

Уязвимость функции icmp_tag_validation() ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость компонента ksmbd ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость компонента ksmbd ядра операционной системы Linux, позволяющая нарушителю получить несанкционированный доступ к защищаемой информации

Уязвимость подсистемы управления памятью mm/mseal ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость компонента NFSv4.0 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость компонента sunrpc ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость компонента BPF ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании или раскрыть защищаемую информацию

Уязвимость компонента NFSD ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость модуля управления памятью (MMU) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость функции nd_async_device_register() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость функции svc_export_put() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость функции move_pages_huge_pmd() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость модуля для реализации AEAD-алгоритмов algif_aead ядра операционной системы Linux, позволяющая нарушителю повысить свои привилегии

Уязвимость функции tc_chain_fill_node() ядра операционных систем Linux, позволяющая нарушителю получить несанкционированный доступ к конфиденциальной информации

Уязвимость функции gso_features_check() ядра операционных систем Linux, позволяющая нарушителю получить несанкционированный доступ к конфиденциальной информации

Уязвимость функции pn532_receive_buf() ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость функции mptcp_recvmsg() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость функции ctnetlink_alloc_expect() ядра операционных систем Linux, позволяющая нарушителю раскрыть конфиденциальную информацию

Уязвимость функции hci_cmd_sync_queue_once() ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость функции nft_queue() ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость функции bnxt_hwrm_func_backing_store_qcaps_v2() ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость функции regsafe() ядра операционных систем Linux, позволяющая нарушителю раскрыть конфиденциальную информацию или вызвать отказ в обслуживании

Уязвимость модуля crypto/authencesn.c ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость функции set_cig_params_sync() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость функции hci_le_remote_conn_param_req_evt() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость модуля net/core/skmsg.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость модуля net/bluetooth/mgmt.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость модуля drivers/net/ethernet/cadence/macb_pci.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Уязвимость функции rxgk_verify_response() компонента rxrpc операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

In the Linux kernel, the following vulnerability has been resolved: drm/vmwgfx: Don't overwrite KMS surface dirty tracker We were overwriting the surface's dirty tracker here causing a memory leak.

In the Linux kernel, the following vulnerability has been resolved: ksmbd: use volume UUID in FS_OBJECT_ID_INFORMATION Use sb->s_uuid for a proper volume identifier as the primary choice. For filesystems that do not provide a UUID, fall back to stfs.f_fsid obtained from vfs_statfs().

In the Linux kernel, the following vulnerability has been resolved: net/x25: Fix overflow when accumulating packets Add a check to ensure that `x25_sock.fraglen` does not overflow. The `fraglen` also needs to be resetted when purging `fragment_queue` in `x25_clear_queues()`.

In the Linux kernel, the following vulnerability has been resolved: ext4: reject mount if bigalloc with s_first_data_block != 0 bigalloc with s_first_data_block != 0 is not supported, reject mounting it.