Все бюллетени/sisyphus_loongarch64/ALT-PU-2026-10455-1
ALT-PU-2026-10455-1

Обновление пакета kernel-image-6.12 в ветке sisyphus_loongarch64

Версия6.12.94-alt1.port.la64
Задание#0
Опубликовано2026-07-02
Макс. серьёзностьCRITICAL
Серьёзность:

Закрытые проблемы (857)

BDU:2026-01057
MEDIUM4.7

Уязвимость функций rt6_uncached_list_del() и rt_del_uncached_list() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-01-29Изменено: 2026-05-14
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0НИЗКАЯ 3.8
CVSS:2.0/AV:L/AC:H/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-03486
MEDIUM5.5

Уязвимость функции xchk_xfile_*_descr() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-03-23Изменено: 2026-05-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-04164
MEDIUM4.7

Уязвимость функции ptype_seq_next() и ptype_seq_show() модуля net/core/net-procfs.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-03-29Изменено: 2026-05-14
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0НИЗКАЯ 3.8
CVSS:2.0/AV:L/AC:H/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-04243
MEDIUM5.5

Уязвимость модуля fs/btrfs/inode.c ядра операционной системы Linux, позволяющая нарушителю получить доступ на чтение и изменение данных

Опубликовано: 2026-03-30Изменено: 2026-05-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-04311
MEDIUM5.5

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

Опубликовано: 2026-03-31Изменено: 2026-07-05
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:A/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
CVSS 2.0СРЕДНЯЯ 5.2
CVSS:2.0/AV:A/AC:L/Au:S/C:P/I:P/A:P
Ссылки
BDU:2026-04645
MEDIUM5.5

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

Опубликовано: 2026-04-05Изменено: 2026-05-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-04784
MEDIUM5.5

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

Опубликовано: 2026-04-06Изменено: 2026-04-07
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-04852
HIGH7.5

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

Опубликовано: 2026-04-07Изменено: 2026-06-03
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0ВЫСОКАЯ 7.8
CVSS:2.0/AV:N/AC:L/Au:N/C:N/I:N/A:C
Ссылки
BDU:2026-04924
HIGH7.8

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

Опубликовано: 2026-04-08Изменено: 2026-05-14
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
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

Опубликовано: 2026-04-08Изменено: 2026-05-14
CVSS 3.xВЫСОКАЯ 7.0
CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.0
CVSS:2.0/AV:L/AC:H/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-04926
MEDIUM5.3

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

Опубликовано: 2026-04-08Изменено: 2026-05-14
CVSS 3.xСРЕДНЯЯ 5.3
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
CVSS 2.0СРЕДНЯЯ 5.0
CVSS:2.0/AV:N/AC:L/Au:N/C:N/I:N/A:P
Ссылки
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

Опубликовано: 2026-04-12Изменено: 2026-05-14
CVSS 3.xВЫСОКАЯ 7.0
CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.0
CVSS:2.0/AV:L/AC:H/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-05258
HIGH7.0

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

Опубликовано: 2026-04-13Изменено: 2026-06-18
CVSS 3.xВЫСОКАЯ 7.0
CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.0
CVSS:2.0/AV:L/AC:H/Au:S/C:C/I:C/A:C
Ссылки
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

Опубликовано: 2026-04-13Изменено: 2026-05-05
CVSS 3.xВЫСОКАЯ 7.0
CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.0
CVSS:2.0/AV:L/AC:H/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-05764
MEDIUM5.5

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

Опубликовано: 2026-04-23Изменено: 2026-05-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-05765
MEDIUM4.4

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

Опубликовано: 2026-04-23Изменено: 2026-05-14
CVSS 3.xСРЕДНЯЯ 4.4
CVSS:3.x/AV:L/AC:L/PR:H/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-05766
MEDIUM5.5

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

Опубликовано: 2026-04-23Изменено: 2026-05-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-05768
MEDIUM4.7

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

Опубликовано: 2026-04-23Изменено: 2026-05-26
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0НИЗКАЯ 3.8
CVSS:2.0/AV:L/AC:H/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-06123
HIGH7.8

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

Опубликовано: 2026-04-29Изменено: 2026-06-16
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-06439
HIGH8.8

Уязвимость компонента xfrm ядра операционной системы Linux, позволяющая нарушителю повысить свои привилегии до уровня root

Опубликовано: 2026-05-07Изменено: 2026-07-05
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-06493
MEDIUM5.5

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

Опубликовано: 2026-05-11Изменено: 2026-05-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-06494
MEDIUM5.5

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

Опубликовано: 2026-05-11Изменено: 2026-05-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-06495
HIGH8.4

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

Опубликовано: 2026-05-11Изменено: 2026-05-26
CVSS 3.xВЫСОКАЯ 8.4
CVSS:3.x/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0ВЫСОКАЯ 7.2
CVSS:2.0/AV:L/AC:L/Au:N/C:C/I:C/A:C
Ссылки
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

Опубликовано: 2026-05-11Изменено: 2026-05-26
CVSS 3.xВЫСОКАЯ 7.0
CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.0
CVSS:2.0/AV:L/AC:H/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-06498
MEDIUM5.5

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

Опубликовано: 2026-05-11Изменено: 2026-05-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-06499
HIGH7.3

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

Опубликовано: 2026-05-11Изменено: 2026-05-14
CVSS 3.xВЫСОКАЯ 7.3
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:H
CVSS 2.0СРЕДНЯЯ 6.4
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:P/A:C
Ссылки
BDU:2026-06501
HIGH8.4

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

Опубликовано: 2026-05-11Изменено: 2026-05-26
CVSS 3.xВЫСОКАЯ 8.4
CVSS:3.x/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0ВЫСОКАЯ 7.2
CVSS:2.0/AV:L/AC:L/Au:N/C:C/I:C/A:C
Ссылки
BDU:2026-06503
HIGH7.1

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

Опубликовано: 2026-05-11Изменено: 2026-05-26
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
CVSS 2.0СРЕДНЯЯ 6.2
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:N/A:C
Ссылки
BDU:2026-06505
HIGH7.8

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

Опубликовано: 2026-05-11Изменено: 2026-05-26
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-06506
HIGH7.8

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

Опубликовано: 2026-05-11Изменено: 2026-05-26
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-06507
HIGH7.8

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

Опубликовано: 2026-05-11Изменено: 2026-05-14
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-06508
HIGH8.8

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

Опубликовано: 2026-05-11Изменено: 2026-05-14
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0ВЫСОКАЯ 8.3
CVSS:2.0/AV:A/AC:L/Au:N/C:C/I:C/A:C
Ссылки
BDU:2026-06509
HIGH7.8

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

Опубликовано: 2026-05-11Изменено: 2026-05-14
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-06510
MEDIUM5.5

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

Опубликовано: 2026-05-11Изменено: 2026-05-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-06511
HIGH7.8

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

Опубликовано: 2026-05-11Изменено: 2026-05-26
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-06785
HIGH7.8

Уязвимость функции skb_try_coalesce() ядра операционной системы Linux, позволяющая нарушителю повысить свои привилегии

Опубликовано: 2026-05-13Изменено: 2026-07-05
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-06912
HIGH7.8

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

Опубликовано: 2026-05-17Изменено: 2026-07-05
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-07273
HIGH7.8

Уязвимость реализации сетевого протокола RDS ядра операционной системы Linux, позволяющая нарушителю повысить свои привилегии и вызвать отказ в обслуживании

Опубликовано: 2026-05-24Изменено: 2026-07-05
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0
CVSS:2.0/AV:L/AC:M/Au:N/C:C/I:C/A:C
Ссылки
BDU:2026-07574
HIGH8.8

Уязвимость функции cifs_get_spnego_key() инструмента cifs.upcall пакета cifs-utils ядра операционных систем Linux, позволяющая нарушителю повысить свои привилегии до уровня root и выполнить произвольный код

Опубликовано: 2026-05-31Изменено: 2026-07-05
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-07832
CRITICAL9.8

Уязвимость функции ip4ip6_err() модуля net/ipv6/ip6_tunnel.c ядра операционной системы Linux, позволяющая нарушителю выполнить произвольный код

Опубликовано: 2026-06-04Изменено: 2026-06-18
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0КРИТИЧЕСКАЯ 10.0
CVSS:2.0/AV:N/AC:L/Au:N/C:C/I:C/A:C
Ссылки
BDU:2026-07834
HIGH7.8

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

Опубликовано: 2026-06-04Изменено: 2026-06-18
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-07835
HIGH8.0

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

Опубликовано: 2026-06-04Изменено: 2026-06-18
CVSS 3.xВЫСОКАЯ 8.0
CVSS:3.x/AV:A/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0ВЫСОКАЯ 7.7
CVSS:2.0/AV:A/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-07836
HIGH7.8

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

Опубликовано: 2026-06-04Изменено: 2026-06-18
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-07837
HIGH7.8

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

Опубликовано: 2026-06-04Изменено: 2026-06-18
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-08413
HIGH8.2

Уязвимость функции mlx5e_reset_txqsq_cc_pc() драйвера mlx5e ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-06-16Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 8.2
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:H
CVSS 2.0ВЫСОКАЯ 8.5
CVSS:2.0/AV:N/AC:L/Au:N/C:N/I:P/A:C
Ссылки
BDU:2026-08414
HIGH7.8

Уязвимость функции bond_setup_by_slave() компонента bonding driver ядра операционных систем Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-06-16Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-08415
HIGH8.8

Уязвимость функции may_see_all_namespaces() подсистемы nsfs ядра операционных систем Linux, позволяющая нарушителю раскрыть защищаемую информацию

Опубликовано: 2026-06-16Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-08522
HIGH7.1

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

Опубликовано: 2026-06-21
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:H
CVSS 2.0ВЫСОКАЯ 7.5
CVSS:2.0/AV:N/AC:L/Au:S/C:N/I:P/A:C
Ссылки
BDU:2026-08738
HIGH7.8

Уязвимость модуля drivers/hid/hid-multitouch.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-08740
HIGH7.5

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

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0ВЫСОКАЯ 7.8
CVSS:2.0/AV:N/AC:L/Au:N/C:N/I:N/A:C
Ссылки
BDU:2026-08741
MEDIUM5.5

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

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-08742
HIGH7.1

Уязвимость модуля drivers/crypto/ccp/sev-dev.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
CVSS 2.0СРЕДНЯЯ 6.2
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:N/A:C
Ссылки
BDU:2026-08745
MEDIUM5.5

Уязвимость функции __radix_tree_create() модуля net/qrtr/af_qrtr.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-08746
MEDIUM5.5

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

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-08747
HIGH7.8

Уязвимость модуля drivers/hid/hid-logitech-hidpp.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-08748
MEDIUM5.5

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

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-08749
HIGH7.1

Уязвимость функции ieee80211_tdls_oper() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.2
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:C/A:C
Ссылки
BDU:2026-08750
HIGH8.1

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

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
CVSS 2.0ВЫСОКАЯ 7.8
CVSS:2.0/AV:A/AC:L/Au:N/C:C/I:N/A:C
Ссылки
BDU:2026-08751
HIGH7.8

Уязвимость модуля drivers/crypto/caam/caamhash.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-08752
HIGH7.1

Уязвимость функции fix ndisc_ra_useropt() модуля net/ipv6/ndisc.c ядра операционной системы Linux, позволяющая нарушителю раскрыть защищаемую информацию

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
CVSS 2.0СРЕДНЯЯ 6.2
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:N/A:C
Ссылки
BDU:2026-08753
MEDIUM5.5

Уязвимость функции f2fs_rename() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:C
Ссылки
BDU:2026-08754
CRITICAL9.8

Уязвимость функции ip6_err_gen_icmpv6_unreach() модуля net/ipv6/icmp.c ядра операционной системы Linux, позволяющая нарушителю получить несанкционированный доступ к защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0КРИТИЧЕСКАЯ 10.0
CVSS:2.0/AV:N/AC:L/Au:N/C:C/I:C/A:C
Ссылки
BDU:2026-08755
HIGH7.1

Уязвимость модуля drivers/crypto/ccp/sev-dev.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
CVSS 2.0СРЕДНЯЯ 6.2
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:N/A:C
Ссылки
BDU:2026-08756
HIGH7.1

Уязвимость модуля drivers/crypto/ccp/sev-dev.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
CVSS 2.0СРЕДНЯЯ 6.2
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:N/A:C
Ссылки
BDU:2026-08757
HIGH7.8

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

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-08758
HIGH7.8

Уязвимость модуля drivers/net/wireless/virtual/virt_wifi.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-06-24Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-08759
CRITICAL9.1

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

Опубликовано: 2026-06-25Изменено: 2026-07-06
CVSS 3.xКРИТИЧЕСКАЯ 9.1
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.4
CVSS:2.0/AV:N/AC:L/Au:N/C:C/I:N/A:C
Ссылки
BDU:2026-08760
CRITICAL9.4

Уязвимость функции eui64_mt6() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-06-25Изменено: 2026-07-06
CVSS 3.xКРИТИЧЕСКАЯ 9.4
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.7
CVSS:2.0/AV:N/AC:L/Au:N/C:C/I:P/A:C
Ссылки
BDU:2026-08794
HIGH7.8

Уязвимость функции ip6fl_seq_show() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-06-25Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-08799
HIGH7.8

Уязвимость модуля net/batman-adv/bat_iv_ogm.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслудивании

Опубликовано: 2026-06-25Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-08879
HIGH8.8

Уязвимость сетевого компонента skbuff ядра операционных систем Linux, позволяющая нарушителю повысить свои привилегии

Опубликовано: 2026-06-28Изменено: 2026-07-06
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-08889
HIGH7.8

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

Опубликовано: 2026-06-28Изменено: 2026-06-29
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
BDU:2026-08901
CRITICAL9.1

Уязвимость функции nft_inner_parse_l2l3() модуля net/netfilter/nft_inner.c ядра операционной системы Linux, позволяющая нарушителю получить несанкционированный доступ к защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-06-28
CVSS 3.xКРИТИЧЕСКАЯ 9.1
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
CVSS 2.0КРИТИЧЕСКАЯ 9.4
CVSS:2.0/AV:N/AC:L/Au:N/C:C/I:C/A:N
Ссылки
BDU:2026-09090
HIGH7.8

Уязвимость функции cache fuse_add_dirent_to_cache() модуля fs/fuse/readdir.c ядра операционной системы Linux, позволяющая нарушителю получить несанкционированный доступ к защищаемой информации и повысить свои привилегии

Опубликовано: 2026-07-01
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:C
Ссылки
CVE-2025-71269
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: btrfs: do not free data reservation in fallback from inline due to -ENOSPC If we fail to create an inline extent due to -ENOSPC, we will attempt to go through the normal COW path, reserve an extent, create an ordered extent, etc. However we were always freeing the reserved qgroup data, which is wrong since we will use data. Fix this by freeing the reserved qgroup data in __cow_file_range_inline() only if we are not doing the fallback (ret is <= 0).

Опубликовано: 2026-03-18Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23004
MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: dst: fix races in rt6_uncached_list_del() and rt_del_uncached_list() syzbot was able to crash the kernel in rt6_uncached_list_flush_dev() in an interesting way [1] Crash happens in list_del_init()/INIT_LIST_HEAD() while writing list->prev, while the prior write on list->next went well. static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); // This went well WRITE_ONCE(list->prev, list); // Crash, @list has been freed. } Issue here is that rt6_uncached_list_del() did not attempt to lock ul->lock, as list_empty(&rt->dst.rt_uncached) returned true because the WRITE_ONCE(list->next, list) happened on the other CPU. We might use list_del_init_careful() and list_empty_careful(), or make sure rt6_uncached_list_del() always grabs the spinlock whenever rt->dst.rt_uncached_list has been set. A similar fix is neeed for IPv4. [1] BUG: KASAN: slab-use-after-free in INIT_LIST_HEAD include/linux/list.h:46 [inline] BUG: KASAN: slab-use-after-free in list_del_init include/linux/list.h:296 [inline] BUG: KASAN: slab-use-after-free in rt6_uncached_list_flush_dev net/ipv6/route.c:191 [inline] BUG: KASAN: slab-use-after-free in rt6_disable_ip+0x633/0x730 net/ipv6/route.c:5020 Write of size 8 at addr ffff8880294cfa78 by task kworker/u8:14/3450 CPU: 0 UID: 0 PID: 3450 Comm: kworker/u8:14 Tainted: G L syzkaller #0 PREEMPT_{RT,(full)} Tainted: [L]=SOFTLOCKUP Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/25/2025 Workqueue: netns cleanup_net Call Trace: dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xca/0x240 mm/kasan/report.c:482 kasan_report+0x118/0x150 mm/kasan/report.c:595 INIT_LIST_HEAD include/linux/list.h:46 [inline] list_del_init include/linux/list.h:296 [inline] rt6_uncached_list_flush_dev net/ipv6/route.c:191 [inline] rt6_disable_ip+0x633/0x730 net/ipv6/route.c:5020 addrconf_ifdown+0x143/0x18a0 net/ipv6/addrconf.c:3853 addrconf_notify+0x1bc/0x1050 net/ipv6/addrconf.c:-1 notifier_call_chain+0x19d/0x3a0 kernel/notifier.c:85 call_netdevice_notifiers_extack net/core/dev.c:2268 [inline] call_netdevice_notifiers net/core/dev.c:2282 [inline] netif_close_many+0x29c/0x410 net/core/dev.c:1785 unregister_netdevice_many_notify+0xb50/0x2330 net/core/dev.c:12353 ops_exit_rtnl_list net/core/net_namespace.c:187 [inline] ops_undo_list+0x3dc/0x990 net/core/net_namespace.c:248 cleanup_net+0x4de/0x7b0 net/core/net_namespace.c:696 process_one_work kernel/workqueue.c:3257 [inline] process_scheduled_works+0xad1/0x1770 kernel/workqueue.c:3340 worker_thread+0x8a0/0xda0 kernel/workqueue.c:3421 kthread+0x711/0x8a0 kernel/kthread.c:463 ret_from_fork+0x510/0xa50 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246 Allocated by task 803: 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:4953 [inline] slab_alloc_node mm/slub.c:5263 [inline] kmem_cache_alloc_noprof+0x18d/0x6c0 mm/slub.c:5270 dst_alloc+0x105/0x170 net/core/dst.c:89 ip6_dst_alloc net/ipv6/route.c:342 [inline] icmp6_dst_alloc+0x75/0x460 net/ipv6/route.c:3333 mld_sendpack+0x683/0xe60 net/ipv6/mcast.c:1844 mld_send_cr net/ipv6/mcast.c:2154 [inline] mld_ifc_work+0x83e/0xd60 net/ipv6/mcast.c:2693 process_one_work kernel/workqueue.c:3257 [inline] process_scheduled_works+0xad1/0x1770 kernel/workqueue.c:3340 worker_thread+0x8a0/0xda0 kernel/workqueue.c:3421 kthread+0x711/0x8a0 kernel/kthread.c:463 ret_from_fork+0x510/0xa50 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entr ---truncated---

Опубликовано: 2026-01-25Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23245
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net/sched: act_gate: snapshot parameters with RCU on replace The gate action can be replaced while the hrtimer callback or dump path is walking the schedule list. Convert the parameters to an RCU-protected snapshot and swap updates under tcf_lock, freeing the previous snapshot via call_rcu(). When REPLACE omits the entry list, preserve the existing schedule so the effective state is unchanged.

Опубликовано: 2026-03-18Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-23252
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xfs: get rid of the xchk_xfile_*_descr calls The xchk_xfile_*_descr macros call kasprintf, which can fail to allocate memory if the formatted string is larger than 16 bytes (or whatever the nofail guarantees are nowadays). Some of them could easily exceed that, and Jiaming Zhang found a few places where that can happen with syzbot. The descriptions are debugging aids and aren't required to be unique, so let's just pass in static strings and eliminate this path to failure. Note this patch touches a number of commits, most of which were merged between 6.6 and 6.14.

Опубликовано: 2026-03-18Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23255
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: add proper RCU protection to /proc/net/ptype Yin Fengwei reported an RCU stall in ptype_seq_show() and provided a patch. Real issue is that ptype_seq_next() and ptype_seq_show() violate RCU rules. ptype_seq_show() runs under rcu_read_lock(), and reads pt->dev to get device name without any barrier. At the same time, concurrent writers can remove a packet_type structure (which is correctly freed after an RCU grace period) and clear pt->dev without an RCU grace period. Define ptype_iter_state to carry a dev pointer along seq_net_private: struct ptype_iter_state { struct seq_net_private p; struct net_device *dev; // added in this patch }; We need to record the device pointer in ptype_get_idx() and ptype_seq_next() so that ptype_seq_show() is safe against concurrent pt->dev changes. We also need to add full RCU protection in ptype_seq_next(). (Missing READ_ONCE() when reading list.next values) Many thanks to Dong Chenchen for providing a repro.

Опубликовано: 2026-03-18Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23274
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: xt_IDLETIMER: reject rev0 reuse of ALARM timer labels IDLETIMER revision 0 rules reuse existing timers by label and always call mod_timer() on timer->timer. If the label was created first by revision 1 with XT_IDLETIMER_ALARM, the object uses alarm timer semantics and timer->timer is never initialized. Reusing that object from revision 0 causes mod_timer() on an uninitialized timer_list, triggering debugobjects warnings and possible panic when panic_on_warn=1. Fix this by rejecting revision 0 rule insertion when an existing timer with the same label is of ALARM type.

Опубликовано: 2026-03-20Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-23276
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: add xmit recursion limit to tunnel xmit functions Tunnel xmit functions (iptunnel_xmit, ip6tunnel_xmit) lack their own recursion limit. When a bond device in broadcast mode has GRE tap interfaces as slaves, and those GRE tunnels route back through the bond, multicast/broadcast traffic triggers infinite recursion between bond_xmit_broadcast() and ip_tunnel_xmit()/ip6_tnl_xmit(), causing kernel stack overflow. The existing XMIT_RECURSION_LIMIT (8) in the no-qdisc path is not sufficient because tunnel recursion involves route lookups and full IP output, consuming much more stack per level. Use a lower limit of 4 (IP_TUNNEL_RECURSION_LIMIT) to prevent overflow. Add recursion detection using dev_xmit_recursion helpers directly in iptunnel_xmit() and ip6tunnel_xmit() to cover all IPv4/IPv6 tunnel paths including UDP encapsulated tunnels (VXLAN, Geneve, etc.). Move dev_xmit_recursion helpers from net/core/dev.h to public header include/linux/netdevice.h so they can be used by tunnel code. BUG: KASAN: stack-out-of-bounds in blake2s.constprop.0+0xe7/0x160 Write of size 32 at addr ffff88810033fed0 by task kworker/0:1/11 Workqueue: mld mld_ifc_work Call Trace: __build_flow_key.constprop.0 (net/ipv4/route.c:515) ip_rt_update_pmtu (net/ipv4/route.c:1073) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:84) ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) ip_finish_output2 (net/ipv4/ip_output.c:237) ip_output (net/ipv4/ip_output.c:438) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) ip_finish_output2 (net/ipv4/ip_output.c:237) ip_output (net/ipv4/ip_output.c:438) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86) ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) mld_sendpack mld_ifc_work process_one_work worker_thread

Опубликовано: 2026-03-20Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23277
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/sched: teql: fix NULL pointer dereference in iptunnel_xmit on TEQL slave xmit teql_master_xmit() calls netdev_start_xmit(skb, slave) to transmit through slave devices, but does not update skb->dev to the slave device beforehand. When a gretap tunnel is a TEQL slave, the transmit path reaches iptunnel_xmit() which saves dev = skb->dev (still pointing to teql0 master) and later calls iptunnel_xmit_stats(dev, pkt_len). This function does: get_cpu_ptr(dev->tstats) Since teql_master_setup() does not set dev->pcpu_stat_type to NETDEV_PCPU_STAT_TSTATS, the core network stack never allocates tstats for teql0, so dev->tstats is NULL. get_cpu_ptr(NULL) computes NULL + __per_cpu_offset[cpu], resulting in a page fault. BUG: unable to handle page fault for address: ffff8880e6659018 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 68bc067 P4D 68bc067 PUD 0 Oops: Oops: 0002 [#1] SMP KASAN PTI RIP: 0010:iptunnel_xmit (./include/net/ip_tunnels.h:664 net/ipv4/ip_tunnel_core.c:89) Call Trace: ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) __gre_xmit (net/ipv4/ip_gre.c:478) gre_tap_xmit (net/ipv4/ip_gre.c:779) teql_master_xmit (net/sched/sch_teql.c:319) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) neigh_direct_output (net/core/neighbour.c:1660) ip_finish_output2 (net/ipv4/ip_output.c:237) __ip_finish_output.part.0 (net/ipv4/ip_output.c:315) ip_mc_output (net/ipv4/ip_output.c:369) ip_send_skb (net/ipv4/ip_output.c:1508) udp_send_skb (net/ipv4/udp.c:1195) udp_sendmsg (net/ipv4/udp.c:1485) inet_sendmsg (net/ipv4/af_inet.c:859) __sys_sendto (net/socket.c:2206) Fix this by setting skb->dev = slave before calling netdev_start_xmit(), so that tunnel xmit functions see the correct slave device with properly allocated tstats.

Опубликовано: 2026-03-20Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23278
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: always walk all pending catchall elements During transaction processing we might have more than one catchall element: 1 live catchall element and 1 pending element that is coming as part of the new batch. If the map holding the catchall elements is also going away, its required to toggle all catchall elements and not just the first viable candidate. Otherwise, we get: WARNING: ./include/net/netfilter/nf_tables.h:1281 at nft_data_release+0xb7/0xe0 [nf_tables], CPU#2: nft/1404 RIP: 0010:nft_data_release+0xb7/0xe0 [nf_tables] [..] __nft_set_elem_destroy+0x106/0x380 [nf_tables] nf_tables_abort_release+0x348/0x8d0 [nf_tables] nf_tables_abort+0xcf2/0x3ac0 [nf_tables] nfnetlink_rcv_batch+0x9c9/0x20e0 [..]

Опубликовано: 2026-03-20Изменено: 2026-07-04
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-23281
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: wifi: libertas: fix use-after-free in lbs_free_adapter() The lbs_free_adapter() function uses timer_delete() (non-synchronous) for both command_timer and tx_lockup_timer before the structure is freed. This is incorrect because timer_delete() does not wait for any running timer callback to complete. If a timer callback is executing when lbs_free_adapter() is called, the callback will access freed memory since lbs_cfg_free() frees the containing structure immediately after lbs_free_adapter() returns. Both timer callbacks (lbs_cmd_timeout_handler and lbs_tx_lockup_handler) access priv->driver_lock, priv->cur_cmd, priv->dev, and other fields, which would all be use-after-free violations. Use timer_delete_sync() instead to ensure any running timer callback has completed before returning. This bug was introduced in commit 8f641d93c38a ("libertas: detect TX lockups and reset hardware") where del_timer() was used instead of del_timer_sync() in the cleanup path. The command_timer has had the same issue since the driver was first written.

Опубликовано: 2026-03-25Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-23302
MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: net: annotate data-races around sk->sk_{data_ready,write_space} skmsg (and probably other layers) are changing these pointers while other cpus might read them concurrently. Add corresponding READ_ONCE()/WRITE_ONCE() annotations for UDP, TCP and AF_UNIX.

Опубликовано: 2026-03-25Изменено: 2026-07-04
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23321
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mptcp: pm: in-kernel: always mark signal+subflow endp as used Syzkaller managed to find a combination of actions that was generating this warning: msk->pm.local_addr_used == 0 WARNING: net/mptcp/pm_kernel.c:1071 at __mark_subflow_endp_available net/mptcp/pm_kernel.c:1071 [inline], CPU#1: syz.2.17/961 WARNING: net/mptcp/pm_kernel.c:1071 at mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_kernel.c:1103 [inline], CPU#1: syz.2.17/961 WARNING: net/mptcp/pm_kernel.c:1071 at mptcp_pm_nl_del_addr_doit+0x81d/0x8f0 net/mptcp/pm_kernel.c:1210, CPU#1: syz.2.17/961 Modules linked in: CPU: 1 UID: 0 PID: 961 Comm: syz.2.17 Not tainted 6.19.0-08368-gfafda3b4b06b #22 PREEMPT(full) Hardware name: QEMU Ubuntu 25.10 PC v2 (i440FX + PIIX, + 10.1 machine, 1996), BIOS 1.17.0-debian-1.17.0-1build1 04/01/2014 RIP: 0010:__mark_subflow_endp_available net/mptcp/pm_kernel.c:1071 [inline] RIP: 0010:mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_kernel.c:1103 [inline] RIP: 0010:mptcp_pm_nl_del_addr_doit+0x81d/0x8f0 net/mptcp/pm_kernel.c:1210 Code: 89 c5 e8 46 30 6f fe e9 21 fd ff ff 49 83 ed 80 e8 38 30 6f fe 4c 89 ef be 03 00 00 00 e8 db 49 df fe eb ac e8 24 30 6f fe 90 <0f> 0b 90 e9 1d ff ff ff e8 16 30 6f fe eb 05 e8 0f 30 6f fe e8 9a RSP: 0018:ffffc90001663880 EFLAGS: 00010293 RAX: ffffffff82de1a6c RBX: 0000000000000000 RCX: ffff88800722b500 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff8880158b22d0 R08: 0000000000010425 R09: ffffffffffffffff R10: ffffffff82de18ba R11: 0000000000000000 R12: ffff88800641a640 R13: ffff8880158b1880 R14: ffff88801ec3c900 R15: ffff88800641a650 FS: 00005555722c3500(0000) GS:ffff8880f909d000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f66346e0f60 CR3: 000000001607c000 CR4: 0000000000350ef0 Call Trace: genl_family_rcv_msg_doit+0x117/0x180 net/netlink/genetlink.c:1115 genl_family_rcv_msg net/netlink/genetlink.c:1195 [inline] genl_rcv_msg+0x3a8/0x3f0 net/netlink/genetlink.c:1210 netlink_rcv_skb+0x16d/0x240 net/netlink/af_netlink.c:2550 genl_rcv+0x28/0x40 net/netlink/genetlink.c:1219 netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline] netlink_unicast+0x3e9/0x4c0 net/netlink/af_netlink.c:1344 netlink_sendmsg+0x4aa/0x5b0 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:727 [inline] __sock_sendmsg+0xc9/0xf0 net/socket.c:742 ____sys_sendmsg+0x272/0x3b0 net/socket.c:2592 ___sys_sendmsg+0x2de/0x320 net/socket.c:2646 __sys_sendmsg net/socket.c:2678 [inline] __do_sys_sendmsg net/socket.c:2683 [inline] __se_sys_sendmsg net/socket.c:2681 [inline] __x64_sys_sendmsg+0x110/0x1a0 net/socket.c:2681 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x143/0x440 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f66346f826d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 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:00007ffc83d8bdc8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f6634985fa0 RCX: 00007f66346f826d RDX: 00000000040000b0 RSI: 0000200000000740 RDI: 0000000000000007 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f6634985fa8 R13: 00007f6634985fac R14: 0000000000000000 R15: 0000000000001770 The actions that caused that seem to be: - Set the MPTCP subflows limit to 0 - Create an MPTCP endpoint with both the 'signal' and 'subflow' flags - Create a new MPTCP connection from a different address: an ADD_ADDR linked to the MPTCP endpoint will be sent ('signal' flag), but no subflows is initiated ('subflow' flag) - Remove the MPTCP endpoint ---truncated---

Опубликовано: 2026-03-25Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23330
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: nfc: nci: complete pending data exchange on device close In nci_close_device(), complete any pending data exchange before closing. The data exchange callback (e.g. rawsock_data_exchange_complete) holds a socket reference. NIPA occasionally hits this leak: unreferenced object 0xff1100000f435000 (size 2048): comm "nci_dev", pid 3954, jiffies 4295441245 hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 27 00 01 40 00 00 00 00 00 00 00 00 00 00 00 00 '..@............ backtrace (crc ec2b3c5): __kmalloc_noprof+0x4db/0x730 sk_prot_alloc.isra.0+0xe4/0x1d0 sk_alloc+0x36/0x760 rawsock_create+0xd1/0x540 nfc_sock_create+0x11f/0x280 __sock_create+0x22d/0x630 __sys_socket+0x115/0x1d0 __x64_sys_socket+0x72/0xd0 do_syscall_64+0x117/0xfc0 entry_SYSCALL_64_after_hwframe+0x4b/0x53

Опубликовано: 2026-03-25Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23364
HIGH7.4

In the Linux kernel, the following vulnerability has been resolved: ksmbd: Compare MACs in constant time To prevent timing attacks, MAC comparisons need to be constant-time. Replace the memcmp() with the correct function, crypto_memneq().

Опубликовано: 2026-03-25Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.4
CVSS:3.x/CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:N
Ссылки
CVE-2026-23368
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: phy: register phy led_triggers during probe to avoid AB-BA deadlock There is an AB-BA deadlock when both LEDS_TRIGGER_NETDEV and LED_TRIGGER_PHY are enabled: [ 1362.049207] [<8054e4b8>] led_trigger_register+0x5c/0x1fc <-- Trying to get lock "triggers_list_lock" via down_write(&triggers_list_lock); [ 1362.054536] [<80662830>] phy_led_triggers_register+0xd0/0x234 [ 1362.060329] [<8065e200>] phy_attach_direct+0x33c/0x40c [ 1362.065489] [<80651fc4>] phylink_fwnode_phy_connect+0x15c/0x23c [ 1362.071480] [<8066ee18>] mtk_open+0x7c/0xba0 [ 1362.075849] [<806d714c>] __dev_open+0x280/0x2b0 [ 1362.080384] [<806d7668>] __dev_change_flags+0x244/0x24c [ 1362.085598] [<806d7698>] dev_change_flags+0x28/0x78 [ 1362.090528] [<807150e4>] dev_ioctl+0x4c0/0x654 <-- Hold lock "rtnl_mutex" by calling rtnl_lock(); [ 1362.094985] [<80694360>] sock_ioctl+0x2f4/0x4e0 [ 1362.099567] [<802e9c4c>] sys_ioctl+0x32c/0xd8c [ 1362.104022] [<80014504>] syscall_common+0x34/0x58 Here LED_TRIGGER_PHY is registering LED triggers during phy_attach while holding RTNL and then taking triggers_list_lock. [ 1362.191101] [<806c2640>] register_netdevice_notifier+0x60/0x168 <-- Trying to get lock "rtnl_mutex" via rtnl_lock(); [ 1362.197073] [<805504ac>] netdev_trig_activate+0x194/0x1e4 [ 1362.202490] [<8054e28c>] led_trigger_set+0x1d4/0x360 <-- Hold lock "triggers_list_lock" by down_read(&triggers_list_lock); [ 1362.207511] [<8054eb38>] led_trigger_write+0xd8/0x14c [ 1362.212566] [<80381d98>] sysfs_kf_bin_write+0x80/0xbc [ 1362.217688] [<8037fcd8>] kernfs_fop_write_iter+0x17c/0x28c [ 1362.223174] [<802cbd70>] vfs_write+0x21c/0x3c4 [ 1362.227712] [<802cc0c4>] ksys_write+0x78/0x12c [ 1362.232164] [<80014504>] syscall_common+0x34/0x58 Here LEDS_TRIGGER_NETDEV is being enabled on an LED. It first takes triggers_list_lock and then RTNL. A classical AB-BA deadlock. phy_led_triggers_registers() does not require the RTNL, it does not make any calls into the network stack which require protection. There is also no requirement the PHY has been attached to a MAC, the triggers only make use of phydev state. This allows the call to phy_led_triggers_registers() to be placed elsewhere. PHY probe() and release() don't hold RTNL, so solving the AB-BA deadlock.

Опубликовано: 2026-03-25Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23374
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: blktrace: fix __this_cpu_read/write in preemptible context tracing_record_cmdline() internally uses __this_cpu_read() and __this_cpu_write() on the per-CPU variable trace_cmdline_save, and trace_save_cmdline() explicitly asserts preemption is disabled via lockdep_assert_preemption_disabled(). These operations are only safe when preemption is off, as they were designed to be called from the scheduler context (probe_wakeup_sched_switch() / probe_wakeup()). __blk_add_trace() was calling tracing_record_cmdline(current) early in the blk_tracer path, before ring buffer reservation, from process context where preemption is fully enabled. This triggers the following using blktests/blktrace/002: blktrace/002 (blktrace ftrace corruption with sysfs trace) [failed] runtime 0.367s ... 0.437s something found in dmesg: [ 81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33 [ 81.239580] null_blk: disk nullb1 created [ 81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516 [ 81.362842] caller is tracing_record_cmdline+0x10/0x40 [ 81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G N 7.0.0-rc1lblk+ #84 PREEMPT(full) [ 81.362877] Tainted: [N]=TEST [ 81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 [ 81.362881] Call Trace: [ 81.362884] [ 81.362886] dump_stack_lvl+0x8d/0xb0 ... (See '/mnt/sda/blktests/results/nodev/blktrace/002.dmesg' for the entire message) [ 81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33 [ 81.239580] null_blk: disk nullb1 created [ 81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516 [ 81.362842] caller is tracing_record_cmdline+0x10/0x40 [ 81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G N 7.0.0-rc1lblk+ #84 PREEMPT(full) [ 81.362877] Tainted: [N]=TEST [ 81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 [ 81.362881] Call Trace: [ 81.362884] [ 81.362886] dump_stack_lvl+0x8d/0xb0 [ 81.362895] check_preemption_disabled+0xce/0xe0 [ 81.362902] tracing_record_cmdline+0x10/0x40 [ 81.362923] __blk_add_trace+0x307/0x5d0 [ 81.362934] ? lock_acquire+0xe0/0x300 [ 81.362940] ? iov_iter_extract_pages+0x101/0xa30 [ 81.362959] blk_add_trace_bio+0x106/0x1e0 [ 81.362968] submit_bio_noacct_nocheck+0x24b/0x3a0 [ 81.362979] ? lockdep_init_map_type+0x58/0x260 [ 81.362988] submit_bio_wait+0x56/0x90 [ 81.363009] __blkdev_direct_IO_simple+0x16c/0x250 [ 81.363026] ? __pfx_submit_bio_wait_endio+0x10/0x10 [ 81.363038] ? rcu_read_lock_any_held+0x73/0xa0 [ 81.363051] blkdev_read_iter+0xc1/0x140 [ 81.363059] vfs_read+0x20b/0x330 [ 81.363083] ksys_read+0x67/0xe0 [ 81.363090] do_syscall_64+0xbf/0xf00 [ 81.363102] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 81.363106] RIP: 0033:0x7f281906029d [ 81.363111] Code: 31 c0 e9 c6 fe ff ff 50 48 8d 3d 66 63 0a 00 e8 59 ff 01 00 66 0f 1f 84 00 00 00 00 00 80 3d 41 33 0e 00 00 74 17 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 5b c3 66 2e 0f 1f 84 00 00 00 00 00 48 83 ec [ 81.363113] RSP: 002b:00007ffca127dd48 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [ 81.363120] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f281906029d [ 81.363122] RDX: 0000000000001000 RSI: 0000559f8bfae000 RDI: 0000000000000000 [ 81.363123] RBP: 0000000000001000 R08: 0000002863a10a81 R09: 00007f281915f000 [ 81.363124] R10: 00007f2818f77b60 R11: 0000000000000246 R12: 0000559f8bfae000 [ 81.363126] R13: 0000000000000000 R14: 0000000000000000 R15: 000000000000000a [ 81.363142] The same BUG fires from blk_add_trace_plug(), blk_add_trace_unplug(), and blk_add_trace_rq() paths as well. The purpose of tracin ---truncated---

Опубликовано: 2026-03-25Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23375
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mm: thp: deny THP for files on anonymous inodes file_thp_enabled() incorrectly allows THP for files on anonymous inodes (e.g. guest_memfd and secretmem). These files are created via alloc_file_pseudo(), which does not call get_write_access() and leaves inode->i_writecount at 0. Combined with S_ISREG(inode->i_mode) being true, they appear as read-only regular files when CONFIG_READ_ONLY_THP_FOR_FS is enabled, making them eligible for THP collapse. Anonymous inodes can never pass the inode_is_open_for_write() check since their i_writecount is never incremented through the normal VFS open path. The right thing to do is to exclude them from THP eligibility altogether, since CONFIG_READ_ONLY_THP_FOR_FS was designed for real filesystem files (e.g. shared libraries), not for pseudo-filesystem inodes. For guest_memfd, this allows khugepaged and MADV_COLLAPSE to create large folios in the page cache via the collapse path, but the guest_memfd fault handler does not support large folios. This triggers WARN_ON_ONCE(folio_test_large(folio)) in kvm_gmem_fault_user_mapping(). For secretmem, collapse_file() tries to copy page contents through the direct map, but secretmem pages are removed from the direct map. This can result in a kernel crash: BUG: unable to handle page fault for address: ffff88810284d000 RIP: 0010:memcpy_orig+0x16/0x130 Call Trace: collapse_file hpage_collapse_scan_file madvise_collapse Secretmem is not affected by the crash on upstream as the memory failure recovery handles the failed copy gracefully, but it still triggers confusing false memory failure reports: Memory failure: 0x106d96f: recovery action for clean unevictable LRU page: Recovered Check IS_ANON_FILE(inode) in file_thp_enabled() to deny THP for all anonymous inode files.

Опубликовано: 2026-03-25Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23386
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: gve: fix incorrect buffer cleanup in gve_tx_clean_pending_packets for QPL In DQ-QPL mode, gve_tx_clean_pending_packets() incorrectly uses the RDA buffer cleanup path. It iterates num_bufs times and attempts to unmap entries in the dma array. This leads to two issues: 1. The dma array shares storage with tx_qpl_buf_ids (union). Interpreting buffer IDs as DMA addresses results in attempting to unmap incorrect memory locations. 2. num_bufs in QPL mode (counting 2K chunks) can significantly exceed the size of the dma array, causing out-of-bounds access warnings (trace below is how we noticed this issue). UBSAN: array-index-out-of-bounds in drivers/net/ethernet/drivers/net/ethernet/google/gve/gve_tx_dqo.c:178:5 index 18 is out of range for type 'dma_addr_t[18]' (aka 'unsigned long long[18]') Workqueue: gve gve_service_task [gve] Call Trace: dump_stack_lvl+0x33/0xa0 __ubsan_handle_out_of_bounds+0xdc/0x110 gve_tx_stop_ring_dqo+0x182/0x200 [gve] gve_close+0x1be/0x450 [gve] gve_reset+0x99/0x120 [gve] gve_service_task+0x61/0x100 [gve] process_scheduled_works+0x1e9/0x380 Fix this by properly checking for QPL mode and delegating to gve_free_tx_qpl_bufs() to reclaim the buffers.

Опубликовано: 2026-03-25Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-03-25Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-03-25Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-03-25Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-03-25Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-03-25Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-03-26Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-03-26Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-03-26Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-03-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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 ]---

Опубликовано: 2026-04-01Изменено: 2026-07-08
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-02Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-02Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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]

Опубликовано: 2026-04-02Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-02Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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] ? __pfx__raw_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] ? __pfx__raw_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] ? __pfx__raw_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---

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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] ? __pfx__raw_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---

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23442
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ipv6: add NULL checks for idev in SRv6 paths __in6_dev_get() can return NULL when the device has no IPv6 configuration (e.g. MTU < IPV6_MIN_MTU or after NETDEV_UNREGISTER). Add NULL checks for idev returned by __in6_dev_get() in both seg6_hmac_validate_skb() and ipv6_srh_rcv() to prevent potential NULL pointer dereferences.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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---

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-23452
MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: PM: runtime: Fix a race condition related to device removal The following code in pm_runtime_work() may dereference the dev->parent pointer after the parent device has been freed: /* Maybe the parent is now able to suspend. */ if (parent && !parent->power.ignore_children) { spin_unlock(&dev->power.lock); spin_lock(&parent->power.lock); rpm_idle(parent, RPM_ASYNC); spin_unlock(&parent->power.lock); spin_lock(&dev->power.lock); } Fix this by inserting a flush_work() call in pm_runtime_remove(). Without this patch blktest block/001 triggers the following complaint sporadically: BUG: KASAN: slab-use-after-free in lock_acquire+0x70/0x160 Read of size 1 at addr ffff88812bef7198 by task kworker/u553:1/3081 Workqueue: pm pm_runtime_work Call Trace: dump_stack_lvl+0x61/0x80 print_address_description.constprop.0+0x8b/0x310 print_report+0xfd/0x1d7 kasan_report+0xd8/0x1d0 __kasan_check_byte+0x42/0x60 lock_acquire.part.0+0x38/0x230 lock_acquire+0x70/0x160 _raw_spin_lock+0x36/0x50 rpm_suspend+0xc6a/0xfe0 rpm_idle+0x578/0x770 pm_runtime_work+0xee/0x120 process_one_work+0xde3/0x1410 worker_thread+0x5eb/0xfe0 kthread+0x37b/0x480 ret_from_fork+0x6cb/0x920 ret_from_fork_asm+0x11/0x20 Allocated by task 4314: kasan_save_stack+0x2a/0x50 kasan_save_track+0x18/0x40 kasan_save_alloc_info+0x3d/0x50 __kasan_kmalloc+0xa0/0xb0 __kmalloc_noprof+0x311/0x990 scsi_alloc_target+0x122/0xb60 [scsi_mod] __scsi_scan_target+0x101/0x460 [scsi_mod] scsi_scan_channel+0x179/0x1c0 [scsi_mod] scsi_scan_host_selected+0x259/0x2d0 [scsi_mod] store_scan+0x2d2/0x390 [scsi_mod] dev_attr_store+0x43/0x80 sysfs_kf_write+0xde/0x140 kernfs_fop_write_iter+0x3ef/0x670 vfs_write+0x506/0x1470 ksys_write+0xfd/0x230 __x64_sys_write+0x76/0xc0 x64_sys_call+0x213/0x1810 do_syscall_64+0xee/0xfc0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 Freed by task 4314: kasan_save_stack+0x2a/0x50 kasan_save_track+0x18/0x40 kasan_save_free_info+0x3f/0x50 __kasan_slab_free+0x67/0x80 kfree+0x225/0x6c0 scsi_target_dev_release+0x3d/0x60 [scsi_mod] device_release+0xa3/0x220 kobject_cleanup+0x105/0x3a0 kobject_put+0x72/0xd0 put_device+0x17/0x20 scsi_device_dev_release+0xacf/0x12c0 [scsi_mod] device_release+0xa3/0x220 kobject_cleanup+0x105/0x3a0 kobject_put+0x72/0xd0 put_device+0x17/0x20 scsi_device_put+0x7f/0xc0 [scsi_mod] sdev_store_delete+0xa5/0x120 [scsi_mod] dev_attr_store+0x43/0x80 sysfs_kf_write+0xde/0x140 kernfs_fop_write_iter+0x3ef/0x670 vfs_write+0x506/0x1470 ksys_write+0xfd/0x230 __x64_sys_write+0x76/0xc0 x64_sys_call+0x213/0x1810

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23454
HIGH7.0

In the Linux kernel, the following vulnerability has been resolved: net: mana: fix use-after-free in mana_hwc_destroy_channel() by reordering teardown A potential race condition exists in mana_hwc_destroy_channel() where hwc->caller_ctx is freed before the HWC's Completion Queue (CQ) and Event Queue (EQ) are destroyed. This allows an in-flight CQ interrupt handler to dereference freed memory, leading to a use-after-free or NULL pointer dereference in mana_hwc_handle_resp(). mana_smc_teardown_hwc() signals the hardware to stop but does not synchronize against IRQ handlers already executing on other CPUs. The IRQ synchronization only happens in mana_hwc_destroy_cq() via mana_gd_destroy_eq() -> mana_gd_deregister_irq(). Since this runs after kfree(hwc->caller_ctx), a concurrent mana_hwc_rx_event_handler() can dereference freed caller_ctx (and rxq->msg_buf) in mana_hwc_handle_resp(). Fix this by reordering teardown to reverse-of-creation order: destroy the TX/RX work queues and CQ/EQ before freeing hwc->caller_ctx. This ensures all in-flight interrupt handlers complete before the memory they access is freed.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.0
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-23455
CRITICAL9.1

In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_h323: check for zero length in DecodeQ931() In DecodeQ931(), the UserUserIE code path reads a 16-bit length from the packet, then decrements it by 1 to skip the protocol discriminator byte before passing it to DecodeH323_UserInformation(). If the encoded length is 0, the decrement wraps to -1, which is then passed as a large value to the decoder, leading to an out-of-bounds read. Add a check to ensure len is positive after the decrement.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-23456
HIGH8.2

In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_h323: fix OOB read in decode_int() CONS case In decode_int(), the CONS case calls get_bits(bs, 2) to read a length value, then calls get_uint(bs, len) without checking that len bytes remain in the buffer. The existing boundary check only validates the 2 bits for get_bits(), not the subsequent 1-4 bytes that get_uint() reads. This allows a malformed H.323/RAS packet to cause a 1-4 byte slab-out-of-bounds read. Add a boundary check for len bytes after get_bits() and before get_uint().

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.2
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H
Ссылки
CVE-2026-23457
HIGH8.6

In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_sip: fix Content-Length u32 truncation in sip_help_tcp() sip_help_tcp() parses the SIP Content-Length header with simple_strtoul(), which returns unsigned long, but stores the result in unsigned int clen. On 64-bit systems, values exceeding UINT_MAX are silently truncated before computing the SIP message boundary. For example, Content-Length 4294967328 (2^32 + 32) is truncated to 32, causing the parser to miscalculate where the current message ends. The loop then treats trailing data in the TCP segment as a second SIP message and processes it through the SDP parser. Fix this by changing clen to unsigned long to match the return type of simple_strtoul(), and reject Content-Length values that exceed the remaining TCP payload length.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.6
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H
Ссылки
CVE-2026-23458
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: fix use-after-free in ctnetlink_dump_exp_ct() ctnetlink_dump_exp_ct() stores a conntrack pointer in cb->data for the netlink dump callback ctnetlink_exp_ct_dump_table(), but drops the conntrack reference immediately after netlink_dump_start(). When the dump spans multiple rounds, the second recvmsg() triggers the dump callback which dereferences the now-freed conntrack via nfct_help(ct), leading to a use-after-free on ct->ext. The bug is that the netlink_dump_control has no .start or .done callbacks to manage the conntrack reference across dump rounds. Other dump functions in the same file (e.g. ctnetlink_get_conntrack) properly use .start/.done callbacks for this purpose. Fix this by adding .start and .done callbacks that hold and release the conntrack reference for the duration of the dump, and move the nfct_help() call after the cb->args[0] early-return check in the dump callback to avoid dereferencing ct->ext unnecessarily. BUG: KASAN: slab-use-after-free in ctnetlink_exp_ct_dump_table+0x4f/0x2e0 Read of size 8 at addr ffff88810597ebf0 by task ctnetlink_poc/133 CPU: 1 UID: 0 PID: 133 Comm: ctnetlink_poc Not tainted 7.0.0-rc2+ #3 PREEMPTLAZY Call Trace: ctnetlink_exp_ct_dump_table+0x4f/0x2e0 netlink_dump+0x333/0x880 netlink_recvmsg+0x3e2/0x4b0 ? aa_sk_perm+0x184/0x450 sock_recvmsg+0xde/0xf0 Allocated by task 133: kmem_cache_alloc_noprof+0x134/0x440 __nf_conntrack_alloc+0xa8/0x2b0 ctnetlink_create_conntrack+0xa1/0x900 ctnetlink_new_conntrack+0x3cf/0x7d0 nfnetlink_rcv_msg+0x48e/0x510 netlink_rcv_skb+0xc9/0x1f0 nfnetlink_rcv+0xdb/0x220 netlink_unicast+0x3ec/0x590 netlink_sendmsg+0x397/0x690 __sys_sendmsg+0xf4/0x180 Freed by task 0: slab_free_after_rcu_debug+0xad/0x1e0 rcu_core+0x5c3/0x9c0

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-23460
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/rose: fix NULL pointer dereference in rose_transmit_link on reconnect syzkaller reported a bug [1], and the reproducer is available at [2]. ROSE sockets use four sk->sk_state values: TCP_CLOSE, TCP_LISTEN, TCP_SYN_SENT, and TCP_ESTABLISHED. rose_connect() already rejects calls for TCP_ESTABLISHED (-EISCONN) and TCP_CLOSE with SS_CONNECTING (-ECONNREFUSED), but lacks a check for TCP_SYN_SENT. When rose_connect() is called a second time while the first connection attempt is still in progress (TCP_SYN_SENT), it overwrites rose->neighbour via rose_get_neigh(). If that returns NULL, the socket is left with rose->state == ROSE_STATE_1 but rose->neighbour == NULL. When the socket is subsequently closed, rose_release() sees ROSE_STATE_1 and calls rose_write_internal() -> rose_transmit_link(skb, NULL), causing a NULL pointer dereference. Per connect(2), a second connect() while a connection is already in progress should return -EALREADY. Add this missing check for TCP_SYN_SENT to complete the state validation in rose_connect(). [1] https://syzkaller.appspot.com/bug?extid=d00f90e0af54102fb271 [2] https://gist.github.com/mrpre/9e6779e0d13e2c66779b1653fef80516

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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---

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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().

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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)

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-23468
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Limit BO list entry count to prevent resource exhaustion Userspace can pass an arbitrary number of BO list entries via the bo_number field. Although the previous multiplication overflow check prevents out-of-bounds allocation, a large number of entries could still cause excessive memory allocation (up to potentially gigabytes) and unnecessarily long list processing times. Introduce a hard limit of 128k entries per BO list, which is more than sufficient for any realistic use case (e.g., a single list containing all buffers in a large scene). This prevents memory exhaustion attacks and ensures predictable performance. Return -EINVAL if the requested entry count exceeds the limit (cherry picked from commit 688b87d39e0aa8135105b40dc167d74b5ada5332)

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23470
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/imagination: Fix deadlock in soft reset sequence The soft reset sequence is currently executed from the threaded IRQ handler, hence it cannot call disable_irq() which internally waits for IRQ handlers, i.e. itself, to complete. Use disable_irq_nosync() during a soft reset instead.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23474
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mtd: Avoid boot crash in RedBoot partition table parser Given CONFIG_FORTIFY_SOURCE=y and a recent compiler, commit 439a1bcac648 ("fortify: Use __builtin_dynamic_object_size() when available") produces the warning below and an oops. Searching for RedBoot partition table in 50000000.flash at offset 0x7e0000 ------------[ cut here ]------------ WARNING: lib/string_helpers.c:1035 at 0xc029e04c, CPU#0: swapper/0/1 memcmp: detected buffer overflow: 15 byte read of buffer size 14 Modules linked in: CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.19.0 #1 NONE As Kees said, "'names' is pointing to the final 'namelen' many bytes of the allocation ... 'namelen' could be basically any length at all. This fortify warning looks legit to me -- this code used to be reading beyond the end of the allocation." Since the size of the dynamic allocation is calculated with strlen() we can use strcmp() instead of memcmp() and remain within bounds.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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).

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-31391
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: crypto: atmel-sha204a - Fix OOM ->tfm_count leak If memory allocation fails, decrement ->tfm_count to avoid blocking future reads.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-31392
HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: smb: client: fix krb5 mount with username option Customer reported that some of their krb5 mounts were failing against a single server as the client was trying to mount the shares with wrong credentials. It turned out the client was reusing SMB session from first mount to try mounting the other shares, even though a different username= option had been specified to the other mounts. By using username mount option along with sec=krb5 to search for principals from keytab is supported by cifs.upcall(8) since cifs-utils-4.8. So fix this by matching username mount option in match_session() even with Kerberos. For example, the second mount below should fail with -ENOKEY as there is no 'foobar' principal in keytab (/etc/krb5.keytab). The client ends up reusing SMB session from first mount to perform the second one, which is wrong. ``` $ ktutil ktutil: add_entry -password -p testuser -k 1 -e aes256-cts Password for testuser@ZELDA.TEST: ktutil: write_kt /etc/krb5.keytab ktutil: quit $ klist -ke Keytab name: FILE:/etc/krb5.keytab KVNO Principal ---- ---------------------------------------------------------------- 1 testuser@ZELDA.TEST (aes256-cts-hmac-sha1-96) $ mount.cifs //w22-root2/scratch /mnt/1 -o sec=krb5,username=testuser $ mount.cifs //w22-root2/scratch /mnt/2 -o sec=krb5,username=foobar $ mount -t cifs | grep -Po 'username=\K\w+' testuser testuser ```

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:H/UI:N/S:C/C:H/I:H/A:L
Ссылки
CVE-2026-31393
HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Validate L2CAP_INFO_RSP payload length before access l2cap_information_rsp() checks that cmd_len covers the fixed l2cap_info_rsp header (type + result, 4 bytes) but then reads rsp->data without verifying that the payload is present: - L2CAP_IT_FEAT_MASK calls get_unaligned_le32(rsp->data), which reads 4 bytes past the header (needs cmd_len >= 8). - L2CAP_IT_FIXED_CHAN reads rsp->data[0], 1 byte past the header (needs cmd_len >= 5). A truncated L2CAP_INFO_RSP with result == L2CAP_IR_SUCCESS triggers an out-of-bounds read of adjacent skb data. Guard each data access with the required payload length check. If the payload is too short, skip the read and let the state machine complete with safe defaults (feat_mask and remote_fixed_chan remain zero from kzalloc), so the info timer cleanup and l2cap_conn_start() still run and the connection is not stalled.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
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]

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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---

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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().

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-07-08
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-31405
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: media: dvb-net: fix OOB access in ULE extension header tables The ule_mandatory_ext_handlers[] and ule_optional_ext_handlers[] tables in handle_one_ule_extension() are declared with 255 elements (valid indices 0-254), but the index htype is derived from network-controlled data as (ule_sndu_type & 0x00FF), giving a range of 0-255. When htype equals 255, an out-of-bounds read occurs on the function pointer table, and the OOB value may be called as a function pointer. Add a bounds check on htype against the array size before either table is accessed. Out-of-range values now cause the SNDU to be discarded.

Опубликовано: 2026-04-06Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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().

Опубликовано: 2026-04-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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().

Опубликовано: 2026-04-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-31412
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_mass_storage: Fix potential integer overflow in check_command_size_in_blocks() The `check_command_size_in_blocks()` function calculates the data size in bytes by left shifting `common->data_size_from_cmnd` by the block size (`common->curlun->blkbits`). However, it does not validate whether this shift operation will cause an integer overflow. Initially, the block size is set up in `fsg_lun_open()` , and the `common->data_size_from_cmnd` is set up in `do_scsi_command()`. During initialization, there is no integer overflow check for the interaction between two variables. So if a malicious USB host sends a SCSI READ or WRITE command requesting a large amount of data (`common->data_size_from_cmnd`), the left shift operation can wrap around. This results in a truncated data size, which can bypass boundary checks and potentially lead to memory corruption or out-of-bounds accesses. Fix this by using the check_shl_overflow() macro to safely perform the shift and catch any overflows.

Опубликовано: 2026-04-10Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-12Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-13Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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: `32*2048 + 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---

Опубликовано: 2026-04-13Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-13Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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()`.

Опубликовано: 2026-04-13Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-13Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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 ==================================================================

Опубликовано: 2026-04-13Изменено: 2026-07-08
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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)

Опубликовано: 2026-04-13Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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) [...] =======================================================================

Опубликовано: 2026-04-13Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-13Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-13Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-13Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-04-13Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.0
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-13Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-13Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-20Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-31430
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: X.509: Fix out-of-bounds access when parsing extensions Leo reports an out-of-bounds access when parsing a certificate with empty Basic Constraints or Key Usage extension because the first byte of the extension is read before checking its length. Fix it. The bug can be triggered by an unprivileged user by submitting a specially crafted certificate to the kernel through the keyrings(7) API. Leo has demonstrated this with a proof-of-concept program responsibly disclosed off-list.

Опубликовано: 2026-04-20Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-07-01
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-31432
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix OOB write in QUERY_INFO for compound requests When a compound request such as READ + QUERY_INFO(Security) is received, and the first command (READ) consumes most of the response buffer, ksmbd could write beyond the allocated buffer while building a security descriptor. The root cause was that smb2_get_info_sec() checked buffer space using ppntsd_size from xattr, while build_sec_desc() often synthesized a significantly larger descriptor from POSIX ACLs. This patch introduces smb_acl_sec_desc_scratch_len() to accurately compute the final descriptor size beforehand, performs proper buffer checking with smb2_calc_max_out_buf_len(), and uses exact-sized allocation + iov pinning.

Опубликовано: 2026-04-22Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-31433
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix potencial OOB in get_file_all_info() for compound requests When a compound request consists of QUERY_DIRECTORY + QUERY_INFO (FILE_ALL_INFORMATION) and the first command consumes nearly the entire max_trans_size, get_file_all_info() would blindly call smbConvertToUTF16() with PATH_MAX, causing out-of-bounds write beyond the response buffer. In get_file_all_info(), there was a missing validation check for the client-provided OutputBufferLength before copying the filename into FileName field of the smb2_file_all_info structure. If the filename length exceeds the available buffer space, it could lead to potential buffer overflows or memory corruption during smbConvertToUTF16 conversion. This calculating the actual free buffer size using smb2_calc_max_out_buf_len() and returning -EINVAL if the buffer is insufficient and updating smbConvertToUTF16 to use the actual filename length (clamped by PATH_MAX) to ensure a safe copy operation.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Ссылки
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]

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.4
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-07-04
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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().

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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)

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
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]

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-30
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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().

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.2
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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)

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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).

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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().

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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".

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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)

Опубликовано: 2026-04-22Изменено: 2026-06-30
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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").

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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[].

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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---

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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---

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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/

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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().

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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]

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-22Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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

Опубликовано: 2026-04-23Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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]

Опубликовано: 2026-04-23Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-23Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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)

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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 --

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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).

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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().

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
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[].

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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)

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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().

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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---

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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().

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-30
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.6
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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").

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-30
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
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 $

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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]

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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---

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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)

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
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().

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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)

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-24Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-25Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-25Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-25Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-25Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-25Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-25Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-25Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-25Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-25Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-25Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-04-25Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-25Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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)`.

Опубликовано: 2026-04-25Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.4
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:H
Ссылки
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

Опубликовано: 2026-04-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-04-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-07-02
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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 ? __pfx__raw_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

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 8.3
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Ссылки
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().

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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().

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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`.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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`.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-07-04
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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().

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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().

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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)

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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)

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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]

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-04-30Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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

Опубликовано: 2026-04-30Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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)

Опубликовано: 2026-03-25Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.2
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:H/UI:N/S:C/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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); }

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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---

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.3
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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)

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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,

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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).

Опубликовано: 2026-05-01Изменено: 2026-07-07
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-30
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
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/

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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().

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.0
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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().

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-01Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43058
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: media: vidtv: fix pass-by-value structs causing MSAN warnings vidtv_ts_null_write_into() and vidtv_ts_pcr_write_into() take their argument structs by value, causing MSAN to report uninit-value warnings. While only vidtv_ts_null_write_into() has triggered a report so far, both functions share the same issue. Fix by passing both structs by const pointer instead, avoiding the stack copy of the struct along with its MSAN shadow and origin metadata. The functions do not modify the structs, which is enforced by the const qualifier.

Опубликовано: 2026-05-02Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43059
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: MGMT: Fix list corruption and UAF in command complete handlers Commit 302a1f674c00 ("Bluetooth: MGMT: Fix possible UAFs") introduced mgmt_pending_valid(), which not only validates the pending command but also unlinks it from the pending list if it is valid. This change in semantics requires updates to several completion handlers to avoid list corruption and memory safety issues. This patch addresses two left-over issues from the aforementioned rework: 1. In mgmt_add_adv_patterns_monitor_complete(), mgmt_pending_remove() is replaced with mgmt_pending_free() in the success path. Since mgmt_pending_valid() already unlinks the command at the beginning of the function, calling mgmt_pending_remove() leads to a double list_del() and subsequent list corruption/kernel panic. 2. In set_mesh_complete(), the use of mgmt_pending_foreach() in the error path is removed. Since the current command is already unlinked by mgmt_pending_valid(), this foreach loop would incorrectly target other pending mesh commands, potentially freeing them while they are still being processed concurrently (leading to UAFs). The redundant mgmt_cmd_status() is also simplified to use cmd->opcode directly.

Опубликовано: 2026-05-05Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43060
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_ct: drop pending enqueued packets on removal Packets sitting in nfqueue might hold a reference to: - templates that specify the conntrack zone, because a percpu area is used and module removal is possible. - conntrack timeout policies and helper, where object removal leave a stale reference. Since these objects can just go away, drop enqueued packets to avoid stale reference to them. If there is a need for finer grain removal, this logic can be revisited to make selective packet drop upon dependencies.

Опубликовано: 2026-05-05Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43061
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: serial: 8250: Fix TX deadlock when using DMA `dmaengine_terminate_async` does not guarantee that the `__dma_tx_complete` callback will run. The callback is currently the only place where `dma->tx_running` gets cleared. If the transaction is canceled and the callback never runs, then `dma->tx_running` will never get cleared and we will never schedule new TX DMA transactions again. This change makes it so we clear `dma->tx_running` after we terminate the DMA transaction. This is "safe" because `serial8250_tx_dma_flush` is holding the UART port lock. The first thing the callback does is also grab the UART port lock, so access to `dma->tx_running` is serialized.

Опубликовано: 2026-05-05Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43062
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix type confusion in l2cap_ecred_reconf_rsp() l2cap_ecred_reconf_rsp() casts the incoming data to struct l2cap_ecred_conn_rsp (the ECRED *connection* response, 8 bytes with result at offset 6) instead of struct l2cap_ecred_reconf_rsp (2 bytes with result at offset 0). This causes two problems: - The sizeof(*rsp) length check requires 8 bytes instead of the correct 2, so valid L2CAP_ECRED_RECONF_RSP packets are rejected with -EPROTO. - rsp->result reads from offset 6 instead of offset 0, returning wrong data when the packet is large enough to pass the check. Fix by using the correct type. Also pass the already byte-swapped result variable to BT_DBG instead of the raw __le16 field.

Опубликовано: 2026-05-05Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:L
Ссылки
CVE-2026-43063
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: xfs: don't irele after failing to iget in xfs_attri_recover_work xlog_recovery_iget* never set @ip to a valid pointer if they return an error, so this irele will walk off a dangling pointer. Fix that.

Опубликовано: 2026-05-05Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43064
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Fix not releasing workqueue on .release() The workqueue associated with an DSA/IAA device is not released when the object is freed.

Опубликовано: 2026-05-05Изменено: 2026-06-19
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43065
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ext4: always drain queued discard work in ext4_mb_release() While reviewing recent ext4 patch[1], Sashiko raised the following concern[2]: > If the filesystem is initially mounted with the discard option, > deleting files will populate sbi->s_discard_list and queue > s_discard_work. If it is then remounted with nodiscard, the > EXT4_MOUNT_DISCARD flag is cleared, but the pending s_discard_work is > neither cancelled nor flushed. [1] https://lore.kernel.org/r/20260319094545.19291-1-qiang.zhang@linux.dev/ [2] https://sashiko.dev/#/patchset/20260319094545.19291-1-qiang.zhang%40linux.dev The concern was valid, but it had nothing to do with the patch[1]. One of the problems with Sashiko in its current (early) form is that it will detect pre-existing issues and report it as a problem with the patch that it is reviewing. In practice, it would be hard to hit deliberately (unless you are a malicious syzkaller fuzzer), since it would involve mounting the file system with -o discard, and then deleting a large number of files, remounting the file system with -o nodiscard, and then immediately unmounting the file system before the queued discard work has a change to drain on its own. Fix it because it's a real bug, and to avoid Sashiko from raising this concern when analyzing future patches to mballoc.c.

Опубликовано: 2026-05-05Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43066
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ext4: fix iloc.bh leak in ext4_fc_replay_inode() error paths During code review, Joseph found that ext4_fc_replay_inode() calls ext4_get_fc_inode_loc() to get the inode location, which holds a reference to iloc.bh that must be released via brelse(). However, several error paths jump to the 'out' label without releasing iloc.bh: - ext4_handle_dirty_metadata() failure - sync_dirty_buffer() failure - ext4_mark_inode_used() failure - ext4_iget() failure Fix this by introducing an 'out_brelse' label placed just before the existing 'out' label to ensure iloc.bh is always released. Additionally, make ext4_fc_replay_inode() propagate errors properly instead of always returning 0.

Опубликовано: 2026-05-05Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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().

Опубликовано: 2026-05-05Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-05Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43069
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_ll: Fix firmware leak on error path Smatch reports: drivers/bluetooth/hci_ll.c:587 download_firmware() warn: 'fw' from request_firmware() not released on lines: 544. In download_firmware(), if request_firmware() succeeds but the returned firmware content is invalid (no data or zero size), the function returns without releasing the firmware, resulting in a resource leak. Fix this by calling release_firmware() before returning when request_firmware() succeeded but the firmware content is invalid.

Опубликовано: 2026-05-05Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43071
CRITICAL9.1

In the Linux kernel, the following vulnerability has been resolved: dcache: Limit the minimal number of bucket to two There is an OOB read problem on dentry_hashtable when user sets 'dhash_entries=1': BUG: unable to handle page fault for address: ffff888b30b774b0 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page Oops: Oops: 0000 [#1] SMP PTI RIP: 0010:__d_lookup+0x56/0x120 Call Trace: d_lookup.cold+0x16/0x5d lookup_dcache+0x27/0xf0 lookup_one_qstr_excl+0x2a/0x180 start_dirop+0x55/0xa0 simple_start_creating+0x8d/0xa0 debugfs_start_creating+0x8c/0x180 debugfs_create_dir+0x1d/0x1c0 pinctrl_init+0x6d/0x140 do_one_initcall+0x6d/0x3d0 kernel_init_freeable+0x39f/0x460 kernel_init+0x2a/0x260 There will be only one bucket in dentry_hashtable when dhash_entries is set as one, and d_hash_shift is calculated as 32 by dcache_init(). Then, following process will access more than one buckets(which memory region is not allocated) in dentry_hashtable: d_lookup b = d_hash(hash) dentry_hashtable + ((u32)hashlen >> d_hash_shift) // The C standard defines the behavior of right shift amounts // exceeding the bit width of the operand as undefined. The // result of '(u32)hashlen >> d_hash_shift' becomes 'hashlen', // so 'b' will point to an unallocated memory region. hlist_bl_for_each_entry_rcu(b) hlist_bl_first_rcu(head) h->first // read OOB! Fix it by limiting the minimal number of dentry_hashtable bucket to two, so that 'd_hash_shift' won't exceeds the bit width of type u32.

Опубликовано: 2026-05-05Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-43072
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/vc4: platform_get_irq_byname() returns an int platform_get_irq_byname() will return a negative value if an error happens, so it should be checked and not just passed directly into devm_request_threaded_irq() hoping all will be ok.

Опубликовано: 2026-05-05Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43073
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: x86-64: rename misleadingly named '__copy_user_nocache()' function This function was a masterclass in bad naming, for various historical reasons. It claimed to be a non-cached user copy. It is literally _neither_ of those things. It's a specialty memory copy routine that uses non-temporal stores for the destination (but not the source), and that does exception handling for both source and destination accesses. Also note that while it works for unaligned targets, any unaligned parts (whether at beginning or end) will not use non-temporal stores, since only words and quadwords can be non-temporal on x86. The exception handling means that it _can_ be used for user space accesses, but not on its own - it needs all the normal "start user space access" logic around it. But typically the user space access would be the source, not the non-temporal destination. That was the original intention of this, where the destination was some fragile persistent memory target that needed non-temporal stores in order to catch machine check exceptions synchronously and deal with them gracefully. Thus that non-descriptive name: one use case was to copy from user space into a non-cached kernel buffer. However, the existing users are a mix of that intended use-case, and a couple of random drivers that just did this as a performance tweak. Some of those random drivers then actively misused the user copying version (with STAC/CLAC and all) to do kernel copies without ever even caring about the exception handling, _just_ for the non-temporal destination. Rename it as a first small step to actually make it halfway sane, and change the prototype to be more normal: it doesn't take a user pointer unless the caller has done the proper conversion, and the argument size is the full size_t (it still won't actually copy more than 4GB in one go, but there's also no reason to silently truncate the size argument in the caller). Finally, use this now sanely named function in the NTB code, which mis-used a user copy version (with STAC/CLAC and all) of this interface despite it not actually being a user copy at all.

Опубликовано: 2026-05-05Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43079
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: perf/x86/intel/uncore: Skip discovery table for offline dies This warning can be triggered if NUMA is disabled and the system boots with fewer CPUs than the number of CPUs in die 0. WARNING: CPU: 9 PID: 7257 at uncore.c:1157 uncore_pci_pmu_register+0x136/0x160 [intel_uncore] Currently, the discovery table continues to be parsed even if all CPUs in the associated die are offline. This can lead to an array overflow at "pmu->boxes[die] = box" in uncore_pci_pmu_register(), which may trigger the warning above or cause other issues.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43080
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: l2tp: Drop large packets with UDP encap syzbot reported a WARN on my patch series [1]. The actual issue is an overflow of 16-bit UDP length field, and it exists in the upstream code. My series added a debug WARN with an overflow check that exposed the issue, that's why syzbot tripped on my patches, rather than on upstream code. syzbot's repro: r0 = socket$pppl2tp(0x18, 0x1, 0x1) r1 = socket$inet6_udp(0xa, 0x2, 0x0) connect$inet6(r1, &(0x7f00000000c0)={0xa, 0x0, 0x0, @loopback, 0xfffffffc}, 0x1c) connect$pppl2tp(r0, &(0x7f0000000240)=@pppol2tpin6={0x18, 0x1, {0x0, r1, 0x4, 0x0, 0x0, 0x0, {0xa, 0x4e22, 0xffff, @ipv4={'\x00', '\xff\xff', @empty}}}}, 0x32) writev(r0, &(0x7f0000000080)=[{&(0x7f0000000000)="ee", 0x34000}], 0x1) It basically sends an oversized (0x34000 bytes) PPPoL2TP packet with UDP encapsulation, and l2tp_xmit_core doesn't check for overflows when it assigns the UDP length field. The value gets trimmed to 16 bites. Add an overflow check that drops oversized packets and avoids sending packets with trimmed UDP length to the wire. syzbot's stack trace (with my patch applied): len >= 65536u WARNING: ./include/linux/udp.h:38 at udp_set_len_short include/linux/udp.h:38 [inline], CPU#1: syz.0.17/5957 WARNING: ./include/linux/udp.h:38 at l2tp_xmit_core net/l2tp/l2tp_core.c:1293 [inline], CPU#1: syz.0.17/5957 WARNING: ./include/linux/udp.h:38 at l2tp_xmit_skb+0x1204/0x18d0 net/l2tp/l2tp_core.c:1327, CPU#1: syz.0.17/5957 Modules linked in: CPU: 1 UID: 0 PID: 5957 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 RIP: 0010:udp_set_len_short include/linux/udp.h:38 [inline] RIP: 0010:l2tp_xmit_core net/l2tp/l2tp_core.c:1293 [inline] RIP: 0010:l2tp_xmit_skb+0x1204/0x18d0 net/l2tp/l2tp_core.c:1327 Code: 0f 0b 90 e9 21 f9 ff ff e8 e9 05 ec f6 90 0f 0b 90 e9 8d f9 ff ff e8 db 05 ec f6 90 0f 0b 90 e9 cc f9 ff ff e8 cd 05 ec f6 90 <0f> 0b 90 e9 de fa ff ff 44 89 f1 80 e1 07 80 c1 03 38 c1 0f 8c 4f RSP: 0018:ffffc90003d67878 EFLAGS: 00010293 RAX: ffffffff8ad985e3 RBX: ffff8881a6400090 RCX: ffff8881697f0000 RDX: 0000000000000000 RSI: 0000000000034010 RDI: 000000000000ffff RBP: dffffc0000000000 R08: 0000000000000003 R09: 0000000000000004 R10: dffffc0000000000 R11: fffff520007acf00 R12: ffff8881baf20900 R13: 0000000000034010 R14: ffff8881a640008e R15: ffff8881760f7000 FS: 000055557e81f500(0000) GS:ffff8882a9467000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000200000033000 CR3: 00000001612f4000 CR4: 00000000000006f0 Call Trace: pppol2tp_sendmsg+0x40a/0x5f0 net/l2tp/l2tp_ppp.c:302 sock_sendmsg_nosec net/socket.c:727 [inline] __sock_sendmsg net/socket.c:742 [inline] sock_write_iter+0x503/0x550 net/socket.c:1195 do_iter_readv_writev+0x619/0x8c0 fs/read_write.c:-1 vfs_writev+0x33c/0x990 fs/read_write.c:1059 do_writev+0x154/0x2e0 fs/read_write.c:1105 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: 0033:0x7f636479c629 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:00007ffffd4241c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000014 RAX: ffffffffffffffda RBX: 00007f6364a15fa0 RCX: 00007f636479c629 RDX: 0000000000000001 RSI: 0000200000000080 RDI: 0000000000000003 RBP: 00007f6364832b39 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f6364a15fac R14: 00007f6364a15fa0 R15: 00007f6364a15fa0 [1]: https://lore.kernel.org/all/20260226201600.222044-1-alice.kernel@fastmail.im/

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43081
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: ipa: fix GENERIC_CMD register field masks for IPA v5.0+ Fix the field masks to match the hardware layout documented in downstream GSI (GSI_V3_0_EE_n_GSI_EE_GENERIC_CMD_*). Notably this fixes a WARN I was seeing when I tried to send "stop" to the MPSS remoteproc while IPA was up.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43082
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: txgbe: leave space for null terminators on property_entry Lists of struct property_entry are supposed to be terminated with an empty property, this driver currently seems to be allocating exactly the amount of entry used. Change the struct definition to leave an extra element for all property_entry.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43085
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: nfnetlink_log: initialize nfgenmsg in NLMSG_DONE terminator When batching multiple NFLOG messages (inst->qlen > 1), __nfulnl_send() appends an NLMSG_DONE terminator with sizeof(struct nfgenmsg) payload via nlmsg_put(), but never initializes the nfgenmsg bytes. The nlmsg_put() helper only zeroes alignment padding after the payload, not the payload itself, so four bytes of stale kernel heap data are leaked to userspace in the NLMSG_DONE message body. Use nfnl_msg_put() to build the NLMSG_DONE terminator, which initializes the nfgenmsg payload via nfnl_fill_hdr(), consistent with how __build_packet_message() already constructs NFULNL_MSG_PACKET headers.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43086
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ipvs: fix NULL deref in ip_vs_add_service error path When ip_vs_bind_scheduler() succeeds in ip_vs_add_service(), the local variable sched is set to NULL. If ip_vs_start_estimator() subsequently fails, the out_err cleanup calls ip_vs_unbind_scheduler(svc, sched) with sched == NULL. ip_vs_unbind_scheduler() passes the cur_sched NULL check (because svc->scheduler was set by the successful bind) but then dereferences the NULL sched parameter at sched->done_service, causing a kernel panic at offset 0x30 from NULL. Oops: general protection fault, [..] [#1] PREEMPT SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037] RIP: 0010:ip_vs_unbind_scheduler (net/netfilter/ipvs/ip_vs_sched.c:69) Call Trace: ip_vs_add_service.isra.0 (net/netfilter/ipvs/ip_vs_ctl.c:1500) do_ip_vs_set_ctl (net/netfilter/ipvs/ip_vs_ctl.c:2809) nf_setsockopt (net/netfilter/nf_sockopt.c:102) [..] Fix by simply not clearing the local sched variable after a successful bind. ip_vs_unbind_scheduler() already detects whether a scheduler is installed via svc->scheduler, and keeping sched non-NULL ensures the error path passes the correct pointer to both ip_vs_unbind_scheduler() and ip_vs_scheduler_put(). While the bug is older, the problem popups in more recent kernels (6.2), when the new error path is taken after the ip_vs_start_estimator() call.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43088
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: af_key: zero aligned sockaddr tail in PF_KEY exports PF_KEY export paths use `pfkey_sockaddr_size()` when reserving sockaddr payload space, so IPv6 addresses occupy 32 bytes on the wire. However, `pfkey_sockaddr_fill()` initializes only the first 28 bytes of `struct sockaddr_in6`, leaving the final 4 aligned bytes uninitialized. Not every PF_KEY message is affected. The state and policy dump builders already zero the whole message buffer before filling the sockaddr payloads. Keep the fix to the export paths that still append aligned sockaddr payloads with plain `skb_put()`: - `SADB_ACQUIRE` - `SADB_X_NAT_T_NEW_MAPPING` - `SADB_X_MIGRATE` Fix those paths by clearing only the aligned sockaddr tail after `pfkey_sockaddr_fill()`.

Опубликовано: 2026-05-06Изменено: 2026-06-19
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43089
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xfrm_user: fix info leak in build_mapping() struct xfrm_usersa_id has a one-byte padding hole after the proto field, which ends up never getting set to zero before copying out to userspace. Fix that up by zeroing out the whole structure before setting individual variables.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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).

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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".

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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]

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-07-08
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-30
CVSS 3.xКРИТИЧЕСКАЯ 9.4
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:L
Ссылки
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.

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
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).

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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")

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43252
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mptcp: pm: in-kernel: always set ID as avail when rm endp Syzkaller managed to find a combination of actions that was generating this warning: WARNING: net/mptcp/pm_kernel.c:1074 at __mark_subflow_endp_available net/mptcp/pm_kernel.c:1074 [inline], CPU#1: syz.7.48/2535 WARNING: net/mptcp/pm_kernel.c:1074 at mptcp_pm_nl_fullmesh net/mptcp/pm_kernel.c:1446 [inline], CPU#1: syz.7.48/2535 WARNING: net/mptcp/pm_kernel.c:1074 at mptcp_pm_nl_set_flags_all net/mptcp/pm_kernel.c:1474 [inline], CPU#1: syz.7.48/2535 WARNING: net/mptcp/pm_kernel.c:1074 at mptcp_pm_nl_set_flags+0x5de/0x640 net/mptcp/pm_kernel.c:1538, CPU#1: syz.7.48/2535 Modules linked in: CPU: 1 UID: 0 PID: 2535 Comm: syz.7.48 Not tainted 6.18.0-03987-gea5f5e676cf5 #17 PREEMPT(voluntary) Hardware name: QEMU Ubuntu 25.10 PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014 RIP: 0010:__mark_subflow_endp_available net/mptcp/pm_kernel.c:1074 [inline] RIP: 0010:mptcp_pm_nl_fullmesh net/mptcp/pm_kernel.c:1446 [inline] RIP: 0010:mptcp_pm_nl_set_flags_all net/mptcp/pm_kernel.c:1474 [inline] RIP: 0010:mptcp_pm_nl_set_flags+0x5de/0x640 net/mptcp/pm_kernel.c:1538 Code: 89 c7 e8 c5 8c 73 fe e9 f7 fd ff ff 49 83 ef 80 e8 b7 8c 73 fe 4c 89 ff be 03 00 00 00 e8 4a 29 e3 fe eb ac e8 a3 8c 73 fe 90 <0f> 0b 90 e9 3d ff ff ff e8 95 8c 73 fe b8 a1 ff ff ff eb 1a e8 89 RSP: 0018:ffffc9001535b820 EFLAGS: 00010287 netdevsim0: tun_chr_ioctl cmd 1074025677 RAX: ffffffff82da294d RBX: 0000000000000001 RCX: 0000000000080000 RDX: ffffc900096d0000 RSI: 00000000000006d6 RDI: 00000000000006d7 netdevsim0: linktype set to 823 RBP: ffff88802cdb2240 R08: 00000000000104ae R09: ffffffffffffffff R10: ffffffff82da27d4 R11: 0000000000000000 R12: 0000000000000000 R13: ffff88801246d8c0 R14: ffffc9001535b8b8 R15: ffff88802cdb1800 FS: 00007fc6ac5a76c0(0000) GS:ffff8880f90c8000(0000) knlGS:0000000000000000 netlink: 'syz.3.50': attribute type 5 has an invalid length. CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 netlink: 1232 bytes leftover after parsing attributes in process `syz.3.50'. CR2: 0000200000010000 CR3: 0000000025b1a000 CR4: 0000000000350ef0 Call Trace: mptcp_pm_set_flags net/mptcp/pm_netlink.c:277 [inline] mptcp_pm_nl_set_flags_doit+0x1d7/0x210 net/mptcp/pm_netlink.c:282 genl_family_rcv_msg_doit+0x117/0x180 net/netlink/genetlink.c:1115 genl_family_rcv_msg net/netlink/genetlink.c:1195 [inline] genl_rcv_msg+0x3a8/0x3f0 net/netlink/genetlink.c:1210 netlink_rcv_skb+0x16d/0x240 net/netlink/af_netlink.c:2550 genl_rcv+0x28/0x40 net/netlink/genetlink.c:1219 netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline] netlink_unicast+0x3e9/0x4c0 net/netlink/af_netlink.c:1344 netlink_sendmsg+0x4ab/0x5b0 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:718 [inline] __sock_sendmsg+0xc9/0xf0 net/socket.c:733 ____sys_sendmsg+0x272/0x3b0 net/socket.c:2608 ___sys_sendmsg+0x2de/0x320 net/socket.c:2662 __sys_sendmsg net/socket.c:2694 [inline] __do_sys_sendmsg net/socket.c:2699 [inline] __se_sys_sendmsg net/socket.c:2697 [inline] __x64_sys_sendmsg+0x110/0x1a0 net/socket.c:2697 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xed/0x360 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fc6adb66f6d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 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:00007fc6ac5a6ff8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007fc6addf5fa0 RCX: 00007fc6adb66f6d RDX: 0000000000048084 RSI: 00002000000002c0 RDI: 000000000000000e RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000 ---truncated---

Опубликовано: 2026-05-06Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43284
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: xfrm: esp: avoid in-place decrypt on shared skb frags MSG_SPLICE_PAGES can attach pages from a pipe directly to an skb. TCP marks such skbs with SKBFL_SHARED_FRAG after skb_splice_from_iter(), so later paths that may modify packet data can first make a private copy. The IPv4/IPv6 datagram append paths did not set this flag when splicing pages into UDP skbs. That leaves an ESP-in-UDP packet made from shared pipe pages looking like an ordinary uncloned nonlinear skb. ESP input then takes the no-COW fast path for uncloned skbs without a frag_list and decrypts in place over data that is not owned privately by the skb. Mark IPv4/IPv6 datagram splice frags with SKBFL_SHARED_FRAG, matching TCP. Also make ESP input fall back to skb_cow_data() when the flag is present, so ESP does not decrypt externally backed frags in place. Private nonlinear skb frags still use the existing fast path. This intentionally does not change ESP output. In esp_output_head(), the path that appends the ESP trailer to existing skb tailroom without calling skb_cow_data() is not reachable for nonlinear skbs: skb_tailroom() returns zero when skb->data_len is nonzero, while ESP tailen is positive. Thus ESP output will either use the separate destination-frag path or fall back to skb_cow_data().

Опубликовано: 2026-05-08Изменено: 2026-07-01
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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().

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-07-07
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Ссылки
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---

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-19
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.6
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:H
Ссылки
CVE-2026-43354
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: iio: proximity: hx9023s: Protect against division by zero in set_samp_freq Avoid division by zero when sampling frequency is unspecified.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43357
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: iio: gyro: mpu3050-core: fix pm_runtime error handling The return value of pm_runtime_get_sync() is not checked, allowing the driver to access hardware that may fail to resume. The device usage count is also unconditionally incremented. Use pm_runtime_resume_and_get() which propagates errors and avoids incrementing the usage count on failure. In preenable, add pm_runtime_put_autosuspend() on set_8khz_samplerate() failure since postdisable does not run when preenable fails.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43359
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: btrfs: fix transaction abort on set received ioctl due to item overflow If the set received ioctl fails due to an item overflow when attempting to add the BTRFS_UUID_KEY_RECEIVED_SUBVOL we have to abort the transaction since we did some metadata updates before. This means that if a user calls this ioctl with the same received UUID field for a lot of subvolumes, we will hit the overflow, trigger the transaction abort and turn the filesystem into RO mode. A malicious user could exploit this, and this ioctl does not even requires that a user has admin privileges (CAP_SYS_ADMIN), only that he/she owns the subvolume. Fix this by doing an early check for item overflow before starting a transaction. This is also race safe because we are holding the subvol_sem semaphore in exclusive (write) mode. A test case for fstests will follow soon.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43360
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: btrfs: fix transaction abort on file creation due to name hash collision If we attempt to create several files with names that result in the same hash, we have to pack them in same dir item and that has a limit inherent to the leaf size. However if we reach that limit, we trigger a transaction abort and turns the filesystem into RO mode. This allows for a malicious user to disrupt a system, without the need to have administration privileges/capabilities. Reproducer: $ cat exploit-hash-collisions.sh #!/bin/bash DEV=/dev/sdi MNT=/mnt/sdi # Use smallest node size to make the test faster and require fewer file # names that result in hash collision. mkfs.btrfs -f --nodesize 4K $DEV mount $DEV $MNT # List of names that result in the same crc32c hash for btrfs. declare -a names=( 'foobar' '%a8tYkxfGMLWRGr55QSeQc4PBNH9PCLIvR6jZnkDtUUru1t@RouaUe_L:@xGkbO3nCwvLNYeK9vhE628gss:T$yZjZ5l-Nbd6CbC$M=hqE-ujhJICXyIxBvYrIU9-TDC' 'AQci3EUB%shMsg-N%frgU:02ByLs=IPJU0OpgiWit5nexSyxZDncY6WB:=zKZuk5Zy0DD$Ua78%MelgBuMqaHGyKsJUFf9s=UW80PcJmKctb46KveLSiUtNmqrMiL9-Y0I_l5Fnam04CGIg=8@U:Z' 'CvVqJpJzueKcuA$wqwePfyu7VxuWNN3ho$p0zi2H8QFYK$7YlEqOhhb%:hHgjhIjW5vnqWHKNP4' 'ET:vk@rFU4tsvMB0$C_p=xQHaYZjvoF%-BTc%wkFW8yaDAPcCYoR%x$FH5O:' 'HwTon%v7SGSP4FE08jBwwiu5aot2CFKXHTeEAa@38fUcNGOWvE@Mz6WBeDH_VooaZ6AgsXPkVGwy9l@@ZbNXabUU9csiWrrOp0MWUdfi$EZ3w9GkIqtz7I_eOsByOkBOO' 'Ij%2VlFGXSuPvxJGf5UWy6O@1svxGha%b@=%wjkq:CIgE6u7eJOjmQY5qTtxE2Rjbis9@us' 'KBkjG5%9R8K9sOG8UTnAYjxLNAvBmvV5vz3IiZaPmKuLYO03-6asI9lJ_j4@6Xo$KZicaLWJ3Pv8XEwVeUPMwbHYWwbx0pYvNlGMO9F:ZhHAwyctnGy%_eujl%WPd4U2BI7qooOSr85J-C2V$LfY' 'NcRfDfuUQ2=zP8K3CCF5dFcpfiOm6mwenShsAb_F%n6GAGC7fT2JFFn:c35X-3aYwoq7jNX5$ZJ6hI3wnZs$7KgGi7wjulffhHNUxAT0fRRLF39vJ@NvaEMxsMO' 'Oj42AQAEzRoTxa5OuSKIr=A_lwGMy132v4g3Pdq1GvUG9874YseIFQ6QU' 'Ono7avN5GjC:_6dBJ_' 'WHmN2gnmaN-9dVDy4aWo:yNGFzz8qsJyJhWEWcud7$QzN2D9R0efIWWEdu5kwWr73NZm4=@CoCDxrrZnRITr-kGtU_cfW2:%2_am' 'WiFnuTEhAG9FEC6zopQmj-A-$LDQ0T3WULz%ox3UZAPybSV6v1Z$b4L_XBi4M4BMBtJZpz93r9xafpB77r:lbwvitWRyo$odnAUYlYMmU4RvgnNd--e=I5hiEjGLETTtaScWlQp8mYsBovZwM2k' 'XKyH=OsOAF3p%uziGF_ZVr$ivrvhVgD@1u%5RtrV-gl_vqAwHkK@x7YwlxX3qT6WKKQ%PR56NrUBU2dOAOAdzr2=5nJuKPM-T-$ZpQfCL7phxQbUcb:BZOTPaFExc-qK-gDRCDW2' 'd3uUR6OFEwZr%ns1XH_@tbxA@cCPmbBRLdyh7p6V45H$P2$F%w0RqrD3M0g8aGvWpoTFMiBdOTJXjD:JF7=h9a_43xBywYAP%r$SPZi%zDg%ql-KvkdUCtF9OLaQlxmd' 'ePTpbnit%hyNm@WELlpKzNZYOzOTf8EQ$sEfkMy1VOfIUu3coyvIr13-Y7Sv5v-Ivax2Go_GQRFMU1b3362nktT9WOJf3SpT%z8sZmM3gvYQBDgmKI%%RM-G7hyrhgYflOw%z::ZRcv5O:lDCFm' 'evqk743Y@dvZAiG5J05L_ROFV@$2%rVWJ2%3nxV72-W7$e$-SK3tuSHA2mBt$qloC5jwNx33GmQUjD%akhBPu=VJ5g$xhlZiaFtTrjeeM5x7dt4cHpX0cZkmfImndYzGmvwQG:$euFYmXn$_2rA9mKZ' 'gkgUtnihWXsZQTEkrMAWIxir09k3t7jk_IK25t1:cy1XWN0GGqC%FrySdcmU7M8MuPO_ppkLw3=Dfr0UuBAL4%GFk2$Ma10V1jDRGJje%Xx9EV2ERaWKtjpwiZwh0gCSJsj5UL7CR8RtW5opCVFKGGy8Cky' 'hNgsG_8lNRik3PvphqPm0yEH3P%%fYG:kQLY=6O-61Wa6nrV_WVGR6TLB09vHOv%g4VQRP8Gzx7VXUY1qvZyS' 'isA7JVzN12xCxVPJZ_qoLm-pTBuhjjHMvV7o=F:EaClfYNyFGlsfw-Kf%uxdqW-kwk1sPl2vhbjyHU1A6$hz' 'kiJ_fgcdZFDiOptjgH5PN9-PSyLO4fbk_:u5_2tz35lV_iXiJ6cx7pwjTtKy-XGaQ5IefmpJ4N_ZqGsqCsKuqOOBgf9LkUdffHet@Wu' 'lvwtxyhE9:%Q3UxeHiViUyNzJsy:fm38pg_b6s25JvdhOAT=1s0$pG25x=LZ2rlHTszj=gN6M4zHZYr_qrB49i=pA--@WqWLIuX7o1S_SfS@2FSiUZN' 'rC24cw3UBDZ=5qJBUMs9e$=S4Y94ni%Z8639vnrGp=0Hv4z3dNFL0fBLmQ40=EYIY:Z=SLc@QLMSt2zsss2ZXrP7j4=' 'uwGl2s-fFrf@GqS=DQqq2I0LJSsOmM%xzTjS:lzXguE3wChdMoHYtLRKPvfaPOZF2fER@j53evbKa7R%A7r4%YEkD=kicJe@SFiGtXHbKe4gCgPAYbnVn' 'UG37U6KKua2bgc:IHzRs7BnB6FD:2Mt5Cc5NdlsW%$1tyvnfz7S27FvNkroXwAW:mBZLA1@qa9WnDbHCDmQmfPMC9z-Eq6QT0jhhPpqyymaD:R02ghwYo%yx7SAaaq-:x33LYpei$5g8DMl3C' 'y2vjek0FE1PDJC0qpfnN:x8k2wCFZ9xiUF2ege=JnP98R%wxjKkdfEiLWvQzmnW' '8-HCSgH5B%K7P8_jaVtQhBXpBk:pE-$P7ts58U0J@iR9YZntMPl7j$s62yAJO@_9eanFPS54b=UTw$94C-t=HLxT8n6o9P=QnIxq-f1=Ne2dvhe6WbjEQtc' 'YPPh:IFt2mtR6XWSmjHptXL_hbSYu8bMw-JP8@PNyaFkdNFsk$M=xfL6LDKCDM-mSyGA_2MBwZ8Dr4=R1D%7-mC ---truncated---

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43361
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: btrfs: fix transaction abort when snapshotting received subvolumes Currently a user can trigger a transaction abort by snapshotting a previously received snapshot a bunch of times until we reach a BTRFS_UUID_KEY_RECEIVED_SUBVOL item overflow (the maximum item size we can store in a leaf). This is very likely not common in practice, but if it happens, it turns the filesystem into RO mode. The snapshot, send and set_received_subvol and subvol_setflags (used by receive) don't require CAP_SYS_ADMIN, just inode_owner_or_capable(). A malicious user could use this to turn a filesystem into RO mode and disrupt a system. Reproducer script: $ cat test.sh #!/bin/bash DEV=/dev/sdi MNT=/mnt/sdi # Use smallest node size to make the test faster. mkfs.btrfs -f --nodesize 4K $DEV mount $DEV $MNT # Create a subvolume and set it to RO so that it can be used for send. btrfs subvolume create $MNT/sv touch $MNT/sv/foo btrfs property set $MNT/sv ro true # Send and receive the subvolume into snaps/sv. mkdir $MNT/snaps btrfs send $MNT/sv | btrfs receive $MNT/snaps # Now snapshot the received subvolume, which has a received_uuid, a # lot of times to trigger the leaf overflow. total=500 for ((i = 1; i <= $total; i++)); do echo -ne "\rCreating snapshot $i/$total" btrfs subvolume snapshot -r $MNT/snaps/sv $MNT/snaps/sv_$i > /dev/null done echo umount $MNT When running the test: $ ./test.sh (...) Create subvolume '/mnt/sdi/sv' At subvol /mnt/sdi/sv At subvol sv Creating snapshot 496/500ERROR: Could not create subvolume: Value too large for defined data type Creating snapshot 497/500ERROR: Could not create subvolume: Read-only file system Creating snapshot 498/500ERROR: Could not create subvolume: Read-only file system Creating snapshot 499/500ERROR: Could not create subvolume: Read-only file system Creating snapshot 500/500ERROR: Could not create subvolume: Read-only file system And in dmesg/syslog: $ dmesg (...) [251067.627338] BTRFS warning (device sdi): insert uuid item failed -75 (0x4628b21c4ac8d898, 0x2598bee2b1515c91) type 252! [251067.629212] ------------[ cut here ]------------ [251067.630033] BTRFS: Transaction aborted (error -75) [251067.630871] WARNING: fs/btrfs/transaction.c:1907 at create_pending_snapshot.cold+0x52/0x465 [btrfs], CPU#10: btrfs/615235 [251067.632851] Modules linked in: btrfs dm_zero (...) [251067.644071] CPU: 10 UID: 0 PID: 615235 Comm: btrfs Tainted: G W 6.19.0-rc8-btrfs-next-225+ #1 PREEMPT(full) [251067.646165] Tainted: [W]=WARN [251067.646733] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014 [251067.648735] RIP: 0010:create_pending_snapshot.cold+0x55/0x465 [btrfs] [251067.649984] Code: f0 48 0f (...) [251067.653313] RSP: 0018:ffffce644908fae8 EFLAGS: 00010292 [251067.653987] RAX: 00000000ffffff01 RBX: ffff8e5639e63a80 RCX: 00000000ffffffd3 [251067.655042] RDX: ffff8e53faa76b00 RSI: 00000000ffffffb5 RDI: ffffffffc0919750 [251067.656077] RBP: ffffce644908fbd8 R08: 0000000000000000 R09: ffffce644908f820 [251067.657068] R10: ffff8e5adc1fffa8 R11: 0000000000000003 R12: ffff8e53c0431bd0 [251067.658050] R13: ffff8e5414593600 R14: ffff8e55efafd000 R15: 00000000ffffffb5 [251067.659019] FS: 00007f2a4944b3c0(0000) GS:ffff8e5b27dae000(0000) knlGS:0000000000000000 [251067.660115] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [251067.660943] CR2: 00007ffc5aa57898 CR3: 00000005813a2003 CR4: 0000000000370ef0 [251067.661972] Call Trace: [251067.662292] [251067.662653] create_pending_snapshots+0x97/0xc0 [btrfs] [251067.663413] btrfs_commit_transaction+0x26e/0xc00 [btrfs] [251067.664257] ? btrfs_qgroup_convert_reserved_meta+0x35/0x390 [btrfs] [251067.665238] ? _raw_spin_unlock+0x15/0x30 [251067.665837] ? record_root_ ---truncated---

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43362
HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: smb: client: fix in-place encryption corruption in SMB2_write() SMB2_write() places write payload in iov[1..n] as part of rq_iov. smb3_init_transform_rq() pointer-shares rq_iov, so crypt_message() encrypts iov[1] in-place, replacing the original plaintext with ciphertext. On a replayable error, the retry sends the same iov[1] which now contains ciphertext instead of the original data, resulting in corruption. The corruption is most likely to be observed when connections are unstable, as reconnects trigger write retries that re-send the already-encrypted data. This affects SFU mknod, MF symlinks, etc. On kernels before 6.10 (prior to the netfs conversion), sync writes also used this path and were similarly affected. The async write path wasn't unaffected as it uses rq_iter which gets deep-copied. Fix by moving the write payload into rq_iter via iov_iter_kvec(), so smb3_init_transform_rq() deep-copies it before encryption.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:H
Ссылки
CVE-2026-43363
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: x86/apic: Disable x2apic on resume if the kernel expects so When resuming from s2ram, firmware may re-enable x2apic mode, which may have been disabled by the kernel during boot either because it doesn't support IRQ remapping or for other reasons. This causes the kernel to continue using the xapic interface, while the hardware is in x2apic mode, which causes hangs. This happens on defconfig + bare metal + s2ram. Fix this in lapic_resume() by disabling x2apic if the kernel expects it to be disabled, i.e. when x2apic_mode = 0. The ACPI v6.6 spec, Section 16.3 [1] says firmware restores either the pre-sleep configuration or initial boot configuration for each CPU, including MSR state: When executing from the power-on reset vector as a result of waking from an S2 or S3 sleep state, the platform firmware performs only the hardware initialization required to restore the system to either the state the platform was in prior to the initial operating system boot, or to the pre-sleep configuration state. In multiprocessor systems, non-boot processors should be placed in the same state as prior to the initial operating system boot. (further ahead) If this is an S2 or S3 wake, then the platform runtime firmware restores minimum context of the system before jumping to the waking vector. This includes: CPU configuration. Platform runtime firmware restores the pre-sleep configuration or initial boot configuration of each CPU (MSR, MTRR, firmware update, SMBase, and so on). Interrupts must be disabled (for IA-32 processors, disabled by CLI instruction). (and other things) So at least as per the spec, re-enablement of x2apic by the firmware is allowed if "x2apic on" is a part of the initial boot configuration. [1] https://uefi.org/specs/ACPI/6.6/16_Waking_and_Sleeping.html#initialization [ bp: Massage. ]

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43365
HIGH8.2

In the Linux kernel, the following vulnerability has been resolved: xfs: fix undersized l_iclog_roundoff values If the superblock doesn't list a log stripe unit, we set the incore log roundoff value to 512. This leads to corrupt logs and unmountable filesystems in generic/617 on a disk with 4k physical sectors... XFS (sda1): Mounting V5 Filesystem ff3121ca-26e6-4b77-b742-aaff9a449e1c XFS (sda1): Torn write (CRC failure) detected at log block 0x318e. Truncating head block from 0x3197. XFS (sda1): failed to locate log tail XFS (sda1): log mount/recovery failed: error -74 XFS (sda1): log mount failed XFS (sda1): Mounting V5 Filesystem ff3121ca-26e6-4b77-b742-aaff9a449e1c XFS (sda1): Ending clean mount ...on the current xfsprogs for-next which has a broken mkfs. xfs_info shows this... meta-data=/dev/sda1 isize=512 agcount=4, agsize=644992 blks = sectsz=4096 attr=2, projid32bit=1 = crc=1 finobt=1, sparse=1, rmapbt=1 = reflink=1 bigtime=1 inobtcount=1 nrext64=1 = exchange=1 metadir=1 data = bsize=4096 blocks=2579968, imaxpct=25 = sunit=0 swidth=0 blks naming =version 2 bsize=4096 ascii-ci=0, ftype=1, parent=1 log =internal log bsize=4096 blocks=16384, version=2 = sectsz=4096 sunit=0 blks, lazy-count=1 realtime =none extsz=4096 blocks=0, rtextents=0 = rgcount=0 rgsize=268435456 extents = zoned=0 start=0 reserved=0 ...observe that the log section has sectsz=4096 sunit=0, which means that the roundoff factor is 512, not 4096 as you'd expect. We should fix mkfs not to generate broken filesystems, but anyone can fuzz the ondisk superblock so we should be more cautious. I think the inadequate logic predates commit a6a65fef5ef8d0, but that's clearly going to require a different backport.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.2
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:H
Ссылки
CVE-2026-43366
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: io_uring/kbuf: check if target buffer list is still legacy on recycle There's a gap between when the buffer was grabbed and when it potentially gets recycled, where if the list is empty, someone could've upgraded it to a ring provided type. This can happen if the request is forced via io-wq. The legacy recycling is missing checking if the buffer_list still exists, and if it's of the correct type. Add those checks.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43368
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: drm/i915: Fix potential overflow of shmem scatterlist length When a scatterlists table of a GEM shmem object of size 4 GB or more is populated with pages allocated from a folio, unsigned int .length attribute of a scatterlist may get overflowed if total byte length of pages allocated to that single scatterlist happens to reach or cross the 4GB limit. As a consequence, users of the object may suffer from hitting unexpected, premature end of the object's backing pages. [278.780187] ------------[ cut here ]------------ [278.780377] WARNING: CPU: 1 PID: 2326 at drivers/gpu/drm/i915/i915_mm.c:55 remap_sg+0x199/0x1d0 [i915] ... [278.780654] CPU: 1 UID: 0 PID: 2326 Comm: gem_mmap_offset Tainted: G S U 6.17.0-rc1-CI_DRM_16981-ged823aaa0607+ #1 PREEMPT(voluntary) [278.780656] Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER [278.780658] Hardware name: Intel Corporation Meteor Lake Client Platform/MTL-P LP5x T3 RVP, BIOS MTLPFWI1.R00.3471.D91.2401310918 01/31/2024 [278.780659] RIP: 0010:remap_sg+0x199/0x1d0 [i915] ... [278.780786] Call Trace: [278.780787] [278.780788] ? __apply_to_page_range+0x3e6/0x910 [278.780795] ? __pfx_remap_sg+0x10/0x10 [i915] [278.780906] apply_to_page_range+0x14/0x30 [278.780908] remap_io_sg+0x14d/0x260 [i915] [278.781013] vm_fault_cpu+0xd2/0x330 [i915] [278.781137] __do_fault+0x3a/0x1b0 [278.781140] do_fault+0x322/0x640 [278.781143] __handle_mm_fault+0x938/0xfd0 [278.781150] handle_mm_fault+0x12c/0x300 [278.781152] ? lock_mm_and_find_vma+0x4b/0x760 [278.781155] do_user_addr_fault+0x2d6/0x8e0 [278.781160] exc_page_fault+0x96/0x2c0 [278.781165] asm_exc_page_fault+0x27/0x30 ... That issue was apprehended by the author of a change that introduced it, and potential risk even annotated with a comment, but then never addressed. When adding folio pages to a scatterlist table, take care of byte length of any single scatterlist not exceeding max_segment. (cherry picked from commit 06249b4e691a75694c014a61708c007fb5755f60)

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43370
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix use-after-free race in VM acquire Replace non-atomic vm->process_info assignment with cmpxchg() to prevent race when parent/child processes sharing a drm_file both try to acquire the same VM after fork(). (cherry picked from commit c7c573275ec20db05be769288a3e3bb2250ec618)

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
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

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43372
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: dsa: microchip: Fix error path in PTP IRQ setup If request_threaded_irq() fails during the PTP message IRQ setup, the newly created IRQ mapping is never disposed. Indeed, the ksz_ptp_irq_setup()'s error path only frees the mappings that were successfully set up. Dispose the newly created mapping if the associated request_threaded_irq() fails at setup.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43373
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: net: ncsi: fix skb leak in error paths Early return paths in NCSI RX and AEN handlers fail to release the received skb, resulting in a memory leak. Specifically, ncsi_aen_handler() returns on invalid AEN packets without consuming the skb. Similarly, ncsi_rcv_rsp() exits early when failing to resolve the NCSI device, response handler, or request, leaving the skb unfreed.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43374
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: nexthop: fix percpu use-after-free in remove_nh_grp_entry When removing a nexthop from a group, remove_nh_grp_entry() publishes the new group via rcu_assign_pointer() then immediately frees the removed entry's percpu stats with free_percpu(). However, the synchronize_net() grace period in the caller remove_nexthop_from_groups() runs after the free. RCU readers that entered before the publish still see the old group and can dereference the freed stats via nh_grp_entry_stats_inc() -> get_cpu_ptr(nhge->stats), causing a use-after-free on percpu memory. Fix by deferring the free_percpu() until after synchronize_net() in the caller. Removed entries are chained via nh_list onto a local deferred free list. After the grace period completes and all RCU readers have finished, the percpu stats are safely freed.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43376
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix use-after-free by using call_rcu() for oplock_info ksmbd currently frees oplock_info immediately using kfree(), even though it is accessed under RCU read-side critical sections in places like opinfo_get() and proc_show_files(). Since there is no RCU grace period delay between nullifying the pointer and freeing the memory, a reader can still access oplock_info structure after it has been freed. This can leads to a use-after-free especially in opinfo_get() where atomic_inc_not_zero() is called on already freed memory. Fix this by switching to deferred freeing using call_rcu().

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
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.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
Ссылки
CVE-2026-43378
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: smb: server: fix use-after-free in smb2_open() The opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is dereferenced after rcu_read_unlock(), creating a use-after-free window.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43379
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix use-after-free in smb_lazy_parent_lease_break_close() opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is being accessed after rcu_read_unlock() has been called. This creates a race condition where the memory could be freed by a concurrent writer between the unlock and the subsequent pointer dereferences (opinfo->is_lease, etc.), leading to a use-after-free.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43380
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: hwmon: (pmbus/q54sj108a2) fix stack overflow in debugfs read The q54sj108a2_debugfs_read function suffers from a stack buffer overflow due to incorrect arguments passed to bin2hex(). The function currently passes 'data' as the destination and 'data_char' as the source. Because bin2hex() converts each input byte into two hex characters, a 32-byte block read results in 64 bytes of output. Since 'data' is only 34 bytes (I2C_SMBUS_BLOCK_MAX + 2), this writes 30 bytes past the end of the buffer onto the stack. Additionally, the arguments were swapped: it was reading from the zero-initialized 'data_char' and writing to 'data', resulting in all-zero output regardless of the actual I2C read. Fix this by: 1. Expanding 'data_char' to 66 bytes to safely hold the hex output. 2. Correcting the bin2hex() argument order and using the actual read count. 3. Using a pointer to select the correct output buffer for the final simple_read_from_buffer call.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-43381
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: nouveau/dpcd: return EBUSY for aux xfer if the device is asleep If we have runtime suspended, and userspace wants to use /dev/drm_dp_* then just tell it the device is busy instead of crashing in the GSP code. WARNING: CPU: 2 PID: 565741 at drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c:164 r535_gsp_msgq_wait+0x9a/0xb0 [nouveau] CPU: 2 UID: 0 PID: 565741 Comm: fwupd Not tainted 6.18.10-200.fc43.x86_64 #1 PREEMPT(lazy) Hardware name: LENOVO 20QTS0PQ00/20QTS0PQ00, BIOS N2OET65W (1.52 ) 08/05/2024 RIP: 0010:r535_gsp_msgq_wait+0x9a/0xb0 [nouveau] This is a simple fix to get backported. We should probably engineer a proper power domain solution to wake up devices and keep them awake while fw updates are happening.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43382
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: batman-adv: Avoid double-rtnl_lock ELP metric worker batadv_v_elp_get_throughput() might be called when the RTNL lock is already held. This could be problematic when the work queue item is cancelled via cancel_delayed_work_sync() in batadv_v_elp_iface_disable(). In this case, an rtnl_lock() would cause a deadlock. To avoid this, rtnl_trylock() was used in this function to skip the retrieval of the ethtool information in case the RTNL lock was already held. But for cfg80211 interfaces, batadv_get_real_netdev() was called - which also uses rtnl_lock(). The approach for __ethtool_get_link_ksettings() must also be used instead and the lockless version __batadv_get_real_netdev() has to be called.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43383
CRITICAL9.4

In the Linux kernel, the following vulnerability has been resolved: net/tcp-md5: Fix MAC comparison to be constant-time To prevent timing attacks, MACs need to be compared in constant time. Use the appropriate helper function for this.

Опубликовано: 2026-05-08Изменено: 2026-06-19
CVSS 3.xКРИТИЧЕСКАЯ 9.4
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H
Ссылки
CVE-2026-43384
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: net/tcp-ao: Fix MAC comparison to be constant-time To prevent timing attacks, MACs need to be compared in constant time. Use the appropriate helper function for this.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43386
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: staging: rtl8723bs: fix potential out-of-bounds read in rtw_restruct_wmm_ie The current code checks 'i + 5 < in_len' at the end of the if statement. However, it accesses 'in_ie[i + 5]' before that check, which can lead to an out-of-bounds read. Move the length check to the beginning of the conditional to ensure the index is within bounds before accessing the array.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-43387
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: staging: rtl8723bs: properly validate the data in rtw_get_ie_ex() Just like in commit 154828bf9559 ("staging: rtl8723bs: fix out-of-bounds read in rtw_get_ie() parser"), we don't trust the data in the frame so we should check the length better before acting on it

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43392
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: sched_ext: Fix starvation of scx_enable() under fair-class saturation During scx_enable(), the READY -> ENABLED task switching loop changes the calling thread's sched_class from fair to ext. Since fair has higher priority than ext, saturating fair-class workloads can indefinitely starve the enable thread, hanging the system. This was introduced when the enable path switched from preempt_disable() to scx_bypass() which doesn't protect against fair-class starvation. Note that the original preempt_disable() protection wasn't complete either - in partial switch modes, the calling thread could still be starved after preempt_enable() as it may have been switched to ext class. Fix it by offloading the enable body to a dedicated system-wide RT (SCHED_FIFO) kthread which cannot be starved by either fair or ext class tasks. scx_enable() lazily creates the kthread on first use and passes the ops pointer through a struct scx_enable_cmd containing the kthread_work, then synchronously waits for completion. The workfn runs on a different kthread from sch->helper (which runs disable_work), so it can safely flush disable_work on the error path without deadlock.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43393
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: btrfs: fix chunk map leak in btrfs_map_block() after btrfs_chunk_map_num_copies() Fix a chunk map leak in btrfs_map_block(): if we return early with -EINVAL, we're not freeing the chunk map that we've just looked up.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43394
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: nfsd: Fix cred ref leak in nfsd_nl_listener_set_doit(). nfsd_nl_listener_set_doit() uses get_current_cred() without put_cred(). As we can see from other callers, svc_xprt_create_from_sa() does not require the extra refcount. nfsd_nl_listener_set_doit() is always in the process context, sendmsg(), and current->cred does not go away. Let's use current_cred() in nfsd_nl_listener_set_doit().

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43395
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/xe/sync: Cleanup partially initialized sync on parse failure xe_sync_entry_parse() can allocate references (syncobj, fence, chain fence, or user fence) before hitting a later failure path. Several of those paths returned directly, leaving partially initialized state and leaking refs. Route these error paths through a common free_sync label and call xe_sync_entry_cleanup(sync) before returning the error. (cherry picked from commit f939bdd9207a5d1fc55cced5459858480686ce22)

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43397
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/bridge: samsung-dsim: Fix memory leak in error path In samsung_dsim_host_attach(), drm_bridge_add() is called to add the bridge. However, if samsung_dsim_register_te_irq() or pdata->host_ops->attach() fails afterwards, the function returns without removing the bridge, causing a memory leak. Fix this by adding proper error handling with goto labels to ensure drm_bridge_remove() is called in all error paths. Also ensure that samsung_dsim_unregister_te_irq() is called if the attach operation fails after the TE IRQ has been registered. samsung_dsim_unregister_te_irq() function is moved without changes to be before samsung_dsim_host_attach() to avoid forward declaration.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43403
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: nsfs: tighten permission checks for ns iteration ioctls Even privileged services should not necessarily be able to see other privileged service's namespaces so they can't leak information to each other. Use may_see_all_namespaces() helper that centralizes this policy until the nstree adapts.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Ссылки
CVE-2026-43405
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: libceph: Use u32 for non-negative values in ceph_monmap_decode() This patch fixes unnecessary implicit conversions that change signedness of blob_len and num_mon in ceph_monmap_decode(). Currently blob_len and num_mon are (signed) int variables. They are used to hold values that are always non-negative and get assigned in ceph_decode_32_safe(), which is meant to assign u32 values. Both variables are subsequently used as unsigned values, and the value of num_mon is further assigned to monmap->num_mon, which is of type u32. Therefore, both variables should be of type u32. This is especially relevant for num_mon. If the value read from the incoming message is very large, it is interpreted as a negative value, and the check for num_mon > CEPH_MAX_MON does not catch it. This leads to the attempt to allocate a very large chunk of memory for monmap, which will most likely fail. In this case, an unnecessary attempt to allocate memory is performed, and -ENOMEM is returned instead of -EINVAL.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43406
CRITICAL9.1

In the Linux kernel, the following vulnerability has been resolved: libceph: prevent potential out-of-bounds reads in process_message_header() If the message frame is (maliciously) corrupted in a way that the length of the control segment ends up being less than the size of the message header or a different frame is made to look like a message frame, out-of-bounds reads may ensue in process_message_header(). Perform an explicit bounds check before decoding the message header.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-43407
CRITICAL9.1

In the Linux kernel, the following vulnerability has been resolved: libceph: Fix potential out-of-bounds access in ceph_handle_auth_reply() This patch fixes an out-of-bounds access in ceph_handle_auth_reply() that can be triggered by a message of type CEPH_MSG_AUTH_REPLY. In ceph_handle_auth_reply(), the value of the payload_len field of such a message is stored in a variable of type int. A value greater than INT_MAX leads to an integer overflow and is interpreted as a negative value. This leads to decrementing the pointer address by this value and subsequently accessing it because ceph_decode_need() only checks that the memory access does not exceed the end address of the allocation. This patch fixes the issue by changing the data type of payload_len to u32. Additionally, the data type of result_msg_len is changed to u32, as it is also a variable holding a non-negative length. Also, an additional layer of sanity checks is introduced, ensuring that directly after reading it from the message, payload_len and result_msg_len are not greater than the overall segment length. BUG: KASAN: slab-out-of-bounds in ceph_handle_auth_reply+0x642/0x7a0 [libceph] Read of size 4 at addr ffff88811404df14 by task kworker/20:1/262 CPU: 20 UID: 0 PID: 262 Comm: kworker/20:1 Not tainted 6.19.2 #5 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 Workqueue: ceph-msgr ceph_con_workfn [libceph] Call Trace: dump_stack_lvl+0x76/0xa0 print_report+0xd1/0x620 ? __pfx__raw_spin_lock_irqsave+0x10/0x10 ? kasan_complete_mode_report_info+0x72/0x210 kasan_report+0xe7/0x130 ? ceph_handle_auth_reply+0x642/0x7a0 [libceph] ? ceph_handle_auth_reply+0x642/0x7a0 [libceph] __asan_report_load_n_noabort+0xf/0x20 ceph_handle_auth_reply+0x642/0x7a0 [libceph] mon_dispatch+0x973/0x23d0 [libceph] ? apparmor_socket_recvmsg+0x6b/0xa0 ? __pfx_mon_dispatch+0x10/0x10 [libceph] ? __kasan_check_write+0x14/0x30i ? mutex_unlock+0x7f/0xd0 ? __pfx_mutex_unlock+0x10/0x10 ? __pfx_do_recvmsg+0x10/0x10 [libceph] ceph_con_process_message+0x1f1/0x650 [libceph] process_message+0x1e/0x450 [libceph] ceph_con_v2_try_read+0x2e48/0x6c80 [libceph] ? __pfx_ceph_con_v2_try_read+0x10/0x10 [libceph] ? save_fpregs_to_fpstate+0xb0/0x230 ? raw_spin_rq_unlock+0x17/0xa0 ? finish_task_switch.isra.0+0x13b/0x760 ? __switch_to+0x385/0xda0 ? __kasan_check_write+0x14/0x30 ? mutex_lock+0x8d/0xe0 ? __pfx_mutex_lock+0x10/0x10 ceph_con_workfn+0x248/0x10c0 [libceph] process_one_work+0x629/0xf80 ? __kasan_check_write+0x14/0x30 worker_thread+0x87f/0x1570 ? __pfx__raw_spin_lock_irqsave+0x10/0x10 ? __pfx_try_to_wake_up+0x10/0x10 ? kasan_print_address_stack_frame+0x1f7/0x280 ? __pfx_worker_thread+0x10/0x10 kthread+0x396/0x830 ? __pfx__raw_spin_lock_irq+0x10/0x10 ? __pfx_kthread+0x10/0x10 ? __kasan_check_write+0x14/0x30 ? recalc_sigpending+0x180/0x210 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x3f7/0x610 ? __pfx_ret_from_fork+0x10/0x10 ? __switch_to+0x385/0xda0 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 [ idryomov: replace if statements with ceph_decode_need() for payload_len and result_msg_len ]

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-43408
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ceph: add a bunch of missing ceph_path_info initializers ceph_mdsc_build_path() must be called with a zero-initialized ceph_path_info parameter, or else the following ceph_mdsc_free_path_info() may crash. Example crash (on Linux 6.18.12): virt_to_cache: Object is not a Slab page! WARNING: CPU: 184 PID: 2871736 at mm/slub.c:6732 kmem_cache_free+0x316/0x400 [...] Call Trace: [...] ceph_open+0x13d/0x3e0 do_dentry_open+0x134/0x480 vfs_open+0x2a/0xe0 path_openat+0x9a3/0x1160 [...] cache_from_obj: Wrong slab cache. names_cache but object is from ceph_inode_info WARNING: CPU: 184 PID: 2871736 at mm/slub.c:6746 kmem_cache_free+0x2dd/0x400 [...] kernel BUG at mm/slub.c:634! Oops: invalid opcode: 0000 [#1] SMP NOPTI RIP: 0010:__slab_free+0x1a4/0x350 Some of the ceph_mdsc_build_path() callers had initializers, but others had not, even though they were all added by commit 15f519e9f883 ("ceph: fix race condition validating r_parent before applying state"). The ones without initializer are suspectible to random crashes. (I can imagine it could even be possible to exploit this bug to elevate privileges.) Unfortunately, these Ceph functions are undocumented and its semantics can only be derived from the code. I see that ceph_mdsc_build_path() initializes the structure only on success, but not on error. Calling ceph_mdsc_free_path_info() after a failed ceph_mdsc_build_path() call does not even make sense, but that's what all callers do, and for it to be safe, the structure must be zero-initialized. The least intrusive approach to fix this is therefore to add initializers everywhere.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43409
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: kprobes: avoid crash when rmmod/insmod after ftrace killed After we hit ftrace is killed by some errors, the kernel crash if we remove modules in which kprobe probes. BUG: unable to handle page fault for address: fffffbfff805000d PGD 817fcc067 P4D 817fcc067 PUD 817fc8067 PMD 101555067 PTE 0 Oops: Oops: 0000 [#1] SMP KASAN PTI CPU: 4 UID: 0 PID: 2012 Comm: rmmod Tainted: G W OE Tainted: [W]=WARN, [O]=OOT_MODULE, [E]=UNSIGNED_MODULE RIP: 0010:kprobes_module_callback+0x89/0x790 RSP: 0018:ffff88812e157d30 EFLAGS: 00010a02 RAX: 1ffffffff805000d RBX: dffffc0000000000 RCX: ffffffff86a8de90 RDX: ffffed1025c2af9b RSI: 0000000000000008 RDI: ffffffffc0280068 RBP: 0000000000000000 R08: 0000000000000001 R09: ffffed1025c2af9a R10: ffff88812e157cd7 R11: 205d323130325420 R12: 0000000000000002 R13: ffffffffc0290488 R14: 0000000000000002 R15: ffffffffc0280040 FS: 00007fbc450dd740(0000) GS:ffff888420331000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffbfff805000d CR3: 000000010f624000 CR4: 00000000000006f0 Call Trace: notifier_call_chain+0xc6/0x280 blocking_notifier_call_chain+0x60/0x90 __do_sys_delete_module.constprop.0+0x32a/0x4e0 do_syscall_64+0x5d/0xfa0 entry_SYSCALL_64_after_hwframe+0x76/0x7e This is because the kprobe on ftrace does not correctly handles the kprobe_ftrace_disabled flag set by ftrace_kill(). To prevent this error, check kprobe_ftrace_disabled in __disarm_kprobe_ftrace() and skip all ftrace related operations.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43411
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: tipc: fix divide-by-zero in tipc_sk_filter_connect() A user can set conn_timeout to any value via setsockopt(TIPC_CONN_TIMEOUT), including values less than 4. When a SYN is rejected with TIPC_ERR_OVERLOAD and the retry path in tipc_sk_filter_connect() executes: delay %= (tsk->conn_timeout / 4); If conn_timeout is in the range [0, 3], the integer division yields 0, and the modulo operation triggers a divide-by-zero exception, causing a kernel oops/panic. Fix this by clamping conn_timeout to a minimum of 4 at the point of use in tipc_sk_filter_connect(). Oops: divide error: 0000 [#1] SMP KASAN NOPTI CPU: 0 UID: 0 PID: 119 Comm: poc-F144 Not tainted 7.0.0-rc2+ RIP: 0010:tipc_sk_filter_rcv (net/tipc/socket.c:2236 net/tipc/socket.c:2362) Call Trace: tipc_sk_backlog_rcv (include/linux/instrumented.h:82 include/linux/atomic/atomic-instrumented.h:32 include/net/sock.h:2357 net/tipc/socket.c:2406) __release_sock (include/net/sock.h:1185 net/core/sock.c:3213) release_sock (net/core/sock.c:3797) tipc_connect (net/tipc/socket.c:2570) __sys_connect (include/linux/file.h:62 include/linux/file.h:83 net/socket.c:2098)

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43412
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ASoC: qcom: qdsp6: Fix q6apm remove ordering during ADSP stop and start During ADSP stop and start, the kernel crashes due to the order in which ASoC components are removed. On ADSP stop, the q6apm-audio .remove callback unloads topology and removes PCM runtimes during ASoC teardown. This deletes the RTDs that contain the q6apm DAI components before their removal pass runs, leaving those components still linked to the card and causing crashes on the next rebind. Fix this by ensuring that all dependent (child) components are removed first, and the q6apm component is removed last. [ 48.105720] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000d0 [ 48.114763] Mem abort info: [ 48.117650] ESR = 0x0000000096000004 [ 48.121526] EC = 0x25: DABT (current EL), IL = 32 bits [ 48.127010] SET = 0, FnV = 0 [ 48.130172] EA = 0, S1PTW = 0 [ 48.133415] FSC = 0x04: level 0 translation fault [ 48.138446] Data abort info: [ 48.141422] ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 [ 48.147079] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 48.152354] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 48.157859] user pgtable: 4k pages, 48-bit VAs, pgdp=00000001173cf000 [ 48.164517] [00000000000000d0] pgd=0000000000000000, p4d=0000000000000000 [ 48.171530] Internal error: Oops: 0000000096000004 [#1] SMP [ 48.177348] Modules linked in: q6prm_clocks q6apm_lpass_dais q6apm_dai snd_q6dsp_common q6prm snd_q6apm 8021q garp mrp stp llc snd_soc_hdmi_codec apr pdr_interface phy_qcom_edp fastrpc qcom_pd_mapper rpmsg_ctrl qrtr_smd rpmsg_char qcom_pdr_msg qcom_iris v4l2_mem2mem videobuf2_dma_contig ath11k_pci msm ubwc_config at24 ath11k videobuf2_memops mac80211 ocmem videobuf2_v4l2 libarc4 drm_gpuvm mhi qrtr videodev drm_exec snd_soc_sc8280xp gpu_sched videobuf2_common nvmem_qcom_spmi_sdam snd_soc_qcom_sdw drm_dp_aux_bus qcom_q6v5_pas qcom_spmi_temp_alarm snd_soc_qcom_common rtc_pm8xxx qcom_pon drm_display_helper cec qcom_pil_info qcom_stats soundwire_bus drm_client_lib mc dispcc0_sa8775p videocc_sa8775p qcom_q6v5 camcc_sa8775p snd_soc_dmic phy_qcom_sgmii_eth snd_soc_max98357a i2c_qcom_geni snd_soc_core dwmac_qcom_ethqos llcc_qcom icc_bwmon qcom_sysmon snd_compress qcom_refgen_regulator coresight_stm stmmac_platform snd_pcm_dmaengine qcom_common coresight_tmc stmmac coresight_replicator qcom_glink_smem coresight_cti stm_core [ 48.177444] coresight_funnel snd_pcm ufs_qcom phy_qcom_qmp_usb gpi phy_qcom_snps_femto_v2 coresight phy_qcom_qmp_ufs qcom_wdt gpucc_sa8775p pcs_xpcs mdt_loader qcom_ice icc_osm_l3 qmi_helpers snd_timer snd soundcore display_connector qcom_rng nvmem_reboot_mode drm_kms_helper phy_qcom_qmp_pcie sha256 cfg80211 rfkill socinfo fuse drm backlight ipv6 [ 48.301059] CPU: 2 UID: 0 PID: 293 Comm: kworker/u32:2 Not tainted 6.19.0-rc6-dirty #10 PREEMPT [ 48.310081] Hardware name: Qualcomm Technologies, Inc. Lemans EVK (DT) [ 48.316782] Workqueue: pdr_notifier_wq pdr_notifier_work [pdr_interface] [ 48.323672] pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 48.330825] pc : mutex_lock+0xc/0x54 [ 48.334514] lr : soc_dapm_shutdown_dapm+0x44/0x174 [snd_soc_core] [ 48.340794] sp : ffff800084ddb7b0 [ 48.344207] x29: ffff800084ddb7b0 x28: ffff00009cd9cf30 x27: ffff00009cd9cc00 [ 48.351544] x26: ffff000099610190 x25: ffffa31d2f19c810 x24: ffffa31d2f185098 [ 48.358869] x23: ffff800084ddb7f8 x22: 0000000000000000 x21: 00000000000000d0 [ 48.366198] x20: ffff00009ba6c338 x19: ffff00009ba6c338 x18: 00000000ffffffff [ 48.373528] x17: 000000040044ffff x16: ffffa31d4ae6dca8 x15: 072007740775076f [ 48.380853] x14: 0765076d07690774 x13: 00313a323a656369 x12: 767265733a637673 [ 48.388182] x11: 00000000000003f9 x10: ffffa31d4c7dea98 x9 : 0000000000000001 [ 48.395519] x8 : ffff00009a2aadc0 x7 : 0000000000000003 x6 : 0000000000000000 [ 48.402854] x5 : 0000000000000 ---truncated---

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43413
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: scsi: hisi_sas: Fix NULL pointer exception during user_scan() user_scan() invokes updated sas_user_scan() for channel 0, and if successful, iteratively scans remaining channels (1 to shost->max_channel) via scsi_scan_host_selected() in commit 37c4e72b0651 ("scsi: Fix sas_user_scan() to handle wildcard and multi-channel scans"). However, hisi_sas supports only one channel, and the current value of max_channel is 1. sas_user_scan() for channel 1 will trigger the following NULL pointer exception: [ 441.554662] Unable to handle kernel NULL pointer dereference at virtual address 00000000000008b0 [ 441.554699] Mem abort info: [ 441.554710] ESR = 0x0000000096000004 [ 441.554718] EC = 0x25: DABT (current EL), IL = 32 bits [ 441.554723] SET = 0, FnV = 0 [ 441.554726] EA = 0, S1PTW = 0 [ 441.554730] FSC = 0x04: level 0 translation fault [ 441.554735] Data abort info: [ 441.554737] ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 [ 441.554742] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 441.554747] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 441.554752] user pgtable: 4k pages, 48-bit VAs, pgdp=00000828377a6000 [ 441.554757] [00000000000008b0] pgd=0000000000000000, p4d=0000000000000000 [ 441.554769] Internal error: Oops: 0000000096000004 [#1] SMP [ 441.629589] Modules linked in: arm_spe_pmu arm_smmuv3_pmu tpm_tis_spi hisi_uncore_sllc_pmu hisi_uncore_pa_pmu hisi_uncore_l3c_pmu hisi_uncore_hha_pmu hisi_uncore_ddrc_pmu hisi_uncore_cpa_pmu hns3_pmu hisi_ptt hisi_pcie_pmu tpm_tis_core spidev spi_hisi_sfc_v3xx hisi_uncore_pmu spi_dw_mmio fuse hclge hclge_common hisi_sec2 hisi_hpre hisi_zip hisi_qm hns3 hisi_sas_v3_hw sm3_ce sbsa_gwdt hnae3 hisi_sas_main uacce hisi_dma i2c_hisi dm_mirror dm_region_hash dm_log dm_mod [ 441.670819] CPU: 46 UID: 0 PID: 6994 Comm: bash Kdump: loaded Not tainted 7.0.0-rc2+ #84 PREEMPT [ 441.691327] pstate: 81400009 (Nzcv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) [ 441.698277] pc : sas_find_dev_by_rphy+0x44/0x118 [ 441.702896] lr : sas_find_dev_by_rphy+0x3c/0x118 [ 441.707502] sp : ffff80009abbba40 [ 441.710805] x29: ffff80009abbba40 x28: ffff082819a40008 x27: ffff082810c37c08 [ 441.717930] x26: ffff082810c37c28 x25: ffff082819a40290 x24: ffff082810c37c00 [ 441.725054] x23: 0000000000000000 x22: 0000000000000001 x21: ffff082819a40000 [ 441.732179] x20: ffff082819a40290 x19: 0000000000000000 x18: 0000000000000020 [ 441.739304] x17: 0000000000000000 x16: ffffb5dad6bda690 x15: 00000000ffffffff [ 441.746428] x14: ffff082814c3b26c x13: 00000000ffffffff x12: ffff082814c3b26a [ 441.753553] x11: 00000000000000c0 x10: 000000000000003a x9 : ffffb5dad5ea94f4 [ 441.760678] x8 : 000000000000003a x7 : ffff80009abbbab0 x6 : 0000000000000030 [ 441.767802] x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000 [ 441.774926] x2 : ffff08280f35a300 x1 : ffffb5dad7127180 x0 : 0000000000000000 [ 441.782053] Call trace: [ 441.784488] sas_find_dev_by_rphy+0x44/0x118 (P) [ 441.789095] sas_target_alloc+0x24/0xb0 [ 441.792920] scsi_alloc_target+0x290/0x330 [ 441.797010] __scsi_scan_target+0x88/0x258 [ 441.801096] scsi_scan_channel+0x74/0xb8 [ 441.805008] scsi_scan_host_selected+0x170/0x188 [ 441.809615] sas_user_scan+0xfc/0x148 [ 441.813267] store_scan+0x10c/0x180 [ 441.816743] dev_attr_store+0x20/0x40 [ 441.820398] sysfs_kf_write+0x84/0xa8 [ 441.824054] kernfs_fop_write_iter+0x130/0x1c8 [ 441.828487] vfs_write+0x2c0/0x370 [ 441.831880] ksys_write+0x74/0x118 [ 441.835271] __arm64_sys_write+0x24/0x38 [ 441.839182] invoke_syscall+0x50/0x120 [ 441.842919] el0_svc_common.constprop.0+0xc8/0xf0 [ 441.847611] do_el0_svc+0x24/0x38 [ 441.850913] el0_svc+0x38/0x158 [ 441.854043] el0t_64_sync_handler+0xa0/0xe8 [ 441.858214] el0t_64_sync+0x1ac/0x1b0 [ 441.861865] Code: aa1303e0 97ff70a8 34ffff80 d10a4273 (f9445a75) [ 441.867946] ---[ end trace 0000000000000000 ]--- Therefore ---truncated---

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43415
MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: core: Fix SError in ufshcd_rtc_work() during UFS suspend In __ufshcd_wl_suspend(), cancel_delayed_work_sync() is called to cancel the UFS RTC work, but it is placed after ufshcd_vops_suspend(hba, pm_op, POST_CHANGE). This creates a race condition where ufshcd_rtc_work() can still be running while ufshcd_vops_suspend() is executing. When UFSHCD_CAP_CLK_GATING is not supported, the condition !hba->clk_gating.active_reqs is always true, causing ufshcd_update_rtc() to be executed. Since ufshcd_vops_suspend() typically performs clock gating operations, executing ufshcd_update_rtc() at that moment triggers an SError. The kernel panic trace is as follows: Kernel panic - not syncing: Asynchronous SError Interrupt Call trace: dump_backtrace+0xec/0x128 show_stack+0x18/0x28 dump_stack_lvl+0x40/0xa0 dump_stack+0x18/0x24 panic+0x148/0x374 nmi_panic+0x3c/0x8c arm64_serror_panic+0x64/0x8c do_serror+0xc4/0xc8 el1h_64_error_handler+0x34/0x4c el1h_64_error+0x68/0x6c el1_interrupt+0x20/0x58 el1h_64_irq_handler+0x18/0x24 el1h_64_irq+0x68/0x6c ktime_get+0xc4/0x12c ufshcd_mcq_sq_stop+0x4c/0xec ufshcd_mcq_sq_cleanup+0x64/0x1dc ufshcd_clear_cmd+0x38/0x134 ufshcd_issue_dev_cmd+0x298/0x4d0 ufshcd_exec_dev_cmd+0x1a4/0x1c4 ufshcd_query_attr+0xbc/0x19c ufshcd_rtc_work+0x10c/0x1c8 process_scheduled_works+0x1c4/0x45c worker_thread+0x32c/0x3e8 kthread+0x120/0x1d8 ret_from_fork+0x10/0x20 Fix this by moving cancel_delayed_work_sync() before the call to ufshcd_vops_suspend(hba, pm_op, PRE_CHANGE), ensuring the UFS RTC work is fully completed or cancelled at that point.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43419
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ceph: fix memory leaks in ceph_mdsc_build_path() Add __putname() calls to error code paths that did not free the "path" pointer obtained by __getname(). If ownership of this pointer is not passed to the caller via path_info.path, the function must free it before returning.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43420
MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: ceph: fix i_nlink underrun during async unlink During async unlink, we drop the `i_nlink` counter before we receive the completion (that will eventually update the `i_nlink`) because "we assume that the unlink will succeed". That is not a bad idea, but it races against deletions by other clients (or against the completion of our own unlink) and can lead to an underrun which emits a WARNING like this one: WARNING: CPU: 85 PID: 25093 at fs/inode.c:407 drop_nlink+0x50/0x68 Modules linked in: CPU: 85 UID: 3221252029 PID: 25093 Comm: php-cgi8.1 Not tainted 6.14.11-cm4all1-ampere #655 Hardware name: Supermicro ARS-110M-NR/R12SPD-A, BIOS 1.1b 10/17/2023 pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : drop_nlink+0x50/0x68 lr : ceph_unlink+0x6c4/0x720 sp : ffff80012173bc90 x29: ffff80012173bc90 x28: ffff086d0a45aaf8 x27: ffff0871d0eb5680 x26: ffff087f2a64a718 x25: 0000020000000180 x24: 0000000061c88647 x23: 0000000000000002 x22: ffff07ff9236d800 x21: 0000000000001203 x20: ffff07ff9237b000 x19: ffff088b8296afc0 x18: 00000000f3c93365 x17: 0000000000070000 x16: ffff08faffcbdfe8 x15: ffff08faffcbdfec x14: 0000000000000000 x13: 45445f65645f3037 x12: 34385f6369706f74 x11: 0000a2653104bb20 x10: ffffd85f26d73290 x9 : ffffd85f25664f94 x8 : 00000000000000c0 x7 : 0000000000000000 x6 : 0000000000000002 x5 : 0000000000000081 x4 : 0000000000000481 x3 : 0000000000000000 x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff08727d3f91e8 Call trace: drop_nlink+0x50/0x68 (P) vfs_unlink+0xb0/0x2e8 do_unlinkat+0x204/0x288 __arm64_sys_unlinkat+0x3c/0x80 invoke_syscall.constprop.0+0x54/0xe8 do_el0_svc+0xa4/0xc8 el0_svc+0x18/0x58 el0t_64_sync_handler+0x104/0x130 el0t_64_sync+0x154/0x158 In ceph_unlink(), a call to ceph_mdsc_submit_request() submits the CEPH_MDS_OP_UNLINK to the MDS, but does not wait for completion. Meanwhile, between this call and the following drop_nlink() call, a worker thread may process a CEPH_CAP_OP_IMPORT, CEPH_CAP_OP_GRANT or just a CEPH_MSG_CLIENT_REPLY (the latter of which could be our own completion). These will lead to a set_nlink() call, updating the `i_nlink` counter to the value received from the MDS. If that new `i_nlink` value happens to be zero, it is illegal to decrement it further. But that is exactly what ceph_unlink() will do then. The WARNING can be reproduced this way: 1. Force async unlink; only the async code path is affected. Having no real clue about Ceph internals, I was unable to find out why the MDS wouldn't give me the "Fxr" capabilities, so I patched get_caps_for_async_unlink() to always succeed. (Note that the WARNING dump above was found on an unpatched kernel, without this kludge - this is not a theoretical bug.) 2. Add a sleep call after ceph_mdsc_submit_request() so the unlink completion gets handled by a worker thread before drop_nlink() is called. This guarantees that the `i_nlink` is already zero before drop_nlink() runs. The solution is to skip the counter decrement when it is already zero, but doing so without a lock is still racy (TOCTOU). Since ceph_fill_inode() and handle_cap_grant() both hold the `ceph_inode_info.i_ceph_lock` spinlock while set_nlink() runs, this seems like the proper lock to protect the `i_nlink` updates. I found prior art in NFS and SMB (using `inode.i_lock`) and AFS (using `afs_vnode.cb_lock`). All three have the zero check as well.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43421
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_ncm: Fix net_device lifecycle with device_move The network device outlived its parent gadget device during disconnection, resulting in dangling sysfs links and null pointer dereference problems. A prior attempt to solve this by removing SET_NETDEV_DEV entirely [1] was reverted due to power management ordering concerns and a NO-CARRIER regression. A subsequent attempt to defer net_device allocation to bind [2] broke 1:1 mapping between function instance and network device, making it impossible for configfs to report the resolved interface name. This results in a regression where the DHCP server fails on pmOS. Use device_move to reparent the net_device between the gadget device and /sys/devices/virtual/ across bind/unbind cycles. This preserves the network interface across USB reconnection, allowing the DHCP server to retain their binding. Introduce gether_attach_gadget()/gether_detach_gadget() helpers and use __free(detach_gadget) macro to undo attachment on bind failure. The bind_count ensures device_move executes only on the first bind. [1] https://lore.kernel.org/lkml/f2a4f9847617a0929d62025748384092e5f35cce.camel@crapouillou.net/ [2] https://lore.kernel.org/linux-usb/795ea759-7eaf-4f78-81f4-01ffbf2d7961@ixit.cz/

Опубликовано: 2026-05-08Изменено: 2026-06-19
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43424
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_tcm: Fix NULL pointer dereferences in nexus handling The `tpg->tpg_nexus` pointer in the USB Target driver is dynamically managed and tied to userspace configuration via ConfigFS. It can be NULL if the USB host sends requests before the nexus is fully established or immediately after it is dropped. Currently, functions like `bot_submit_command()` and the data transfer paths retrieve `tv_nexus = tpg->tpg_nexus` and immediately dereference `tv_nexus->tvn_se_sess` without any validation. If a malicious or misconfigured USB host sends a BOT (Bulk-Only Transport) command during this race window, it triggers a NULL pointer dereference, leading to a kernel panic (local DoS). This exposes an inconsistent API usage within the module, as peer functions like `usbg_submit_command()` and `bot_send_bad_response()` correctly implement a NULL check for `tv_nexus` before proceeding. Fix this by bringing consistency to the nexus handling. Add the missing `if (!tv_nexus)` checks to the vulnerable BOT command and request processing paths, aborting the command gracefully with an error instead of crashing the system.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43425
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: image: mdc800: kill download URB on timeout mdc800_device_read() submits download_urb and waits for completion. If the timeout fires and the device has not responded, the function returns without killing the URB, leaving it active. A subsequent read() resubmits the same URB while it is still in-flight, triggering the WARN in usb_submit_urb(): "URB submitted while active" Check the return value of wait_event_timeout() and kill the URB if it indicates timeout, ensuring the URB is complete before its status is inspected or the URB is resubmitted. Similar to - commit 372c93131998 ("USB: yurex: fix control-URB timeout handling") - commit b98d5000c505 ("media: rc: iguanair: handle timeouts")

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43426
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: usb: renesas_usbhs: fix use-after-free in ISR during device removal In usbhs_remove(), the driver frees resources (including the pipe array) while the interrupt handler (usbhs_interrupt) is still registered. If an interrupt fires after usbhs_pipe_remove() but before the driver is fully unbound, the ISR may access freed memory, causing a use-after-free. Fix this by calling devm_free_irq() before freeing resources. This ensures the interrupt handler is both disabled and synchronized (waits for any running ISR to complete) before usbhs_pipe_remove() is called.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43427
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: usb: class: cdc-wdm: fix reordering issue in read code path Quoting the bug report: Due to compiler optimization or CPU out-of-order execution, the desc->length update can be reordered before the memmove. If this happens, wdm_read() can see the new length and call copy_to_user() on uninitialized memory. This also violates LKMM data race rules [1]. Fix it by using WRITE_ONCE and memory barriers.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-43428
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: USB: core: Limit the length of unkillable synchronous timeouts The usb_control_msg(), usb_bulk_msg(), and usb_interrupt_msg() APIs in usbcore allow unlimited timeout durations. And since they use uninterruptible waits, this leaves open the possibility of hanging a task for an indefinitely long time, with no way to kill it short of unplugging the target device. To prevent this sort of problem, enforce a maximum limit on the length of these unkillable timeouts. The limit chosen here, somewhat arbitrarily, is 60 seconds. On many systems (although not all) this is short enough to avoid triggering the kernel's hung-task detector. In addition, clear up the ambiguity of negative timeout values by treating them the same as 0, i.e., using the maximum allowed timeout.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43429
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: USB: usbtmc: Use usb_bulk_msg_killable() with user-specified timeouts The usbtmc driver accepts timeout values specified by the user in an ioctl command, and uses these timeouts for some usb_bulk_msg() calls. Since the user can specify arbitrarily long timeouts and usb_bulk_msg() uses unkillable waits, call usb_bulk_msg_killable() instead to avoid the possibility of the user hanging a kernel thread indefinitely.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43430
MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: usb: yurex: fix race in probe The bbu member of the descriptor must be set to the value standing for uninitialized values before the URB whose completion handler sets bbu is submitted. Otherwise there is a window during which probing can overwrite already retrieved data.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43432
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: xhci: Fix memory leak in xhci_disable_slot() xhci_alloc_command() allocates a command structure and, when the second argument is true, also allocates a completion structure. Currently, the error handling path in xhci_disable_slot() only frees the command structure using kfree(), causing the completion structure to leak. Use xhci_free_command() instead of kfree(). xhci_free_command() correctly frees both the command structure and the associated completion structure. Since the command structure is allocated with zero-initialization, command->in_ctx is NULL and will not be erroneously freed by xhci_free_command(). This bug was found using an experimental static analysis tool we are developing. The tool is based on the LLVM framework and is specifically designed to detect memory management issues. It is currently under active development and not yet publicly available, but we plan to open-source it after our research is published. The bug was originally detected on v6.13-rc1 using our static analysis tool, and we have verified that the issue persists in the latest mainline kernel. We performed build testing on x86_64 with allyesconfig using GCC=11.4.0. Since triggering these error paths in xhci_disable_slot() requires specific hardware conditions or abnormal state, we were unable to construct a test case to reliably trigger these specific error paths at runtime.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43436
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ALSA: usb-audio: Check endpoint numbers at parsing Scarlett2 mixer interfaces The Scarlett2 mixer quirk in USB-audio driver may hit a NULL dereference when a malformed USB descriptor is passed, since it assumes the presence of an endpoint in the parsed interface in scarlett2_find_fc_interface(), as reported by fuzzer. For avoiding the NULL dereference, just add the sanity check of bNumEndpoints and skip the invalid interface.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43437
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ALSA: pcm: fix use-after-free on linked stream runtime in snd_pcm_drain() In the drain loop, the local variable 'runtime' is reassigned to a linked stream's runtime (runtime = s->runtime at line 2157). After releasing the stream lock at line 2169, the code accesses runtime->no_period_wakeup, runtime->rate, and runtime->buffer_size (lines 2170-2178) — all referencing the linked stream's runtime without any lock or refcount protecting its lifetime. A concurrent close() on the linked stream's fd triggers snd_pcm_release_substream() → snd_pcm_drop() → pcm_release_private() → snd_pcm_unlink() → snd_pcm_detach_substream() → kfree(runtime). No synchronization prevents kfree(runtime) from completing while the drain path dereferences the stale pointer. Fix by caching the needed runtime fields (no_period_wakeup, rate, buffer_size) into local variables while still holding the stream lock, and using the cached values after the lock is released.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43438
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: sched_ext: Remove redundant css_put() in scx_cgroup_init() The iterator css_for_each_descendant_pre() walks the cgroup hierarchy under cgroup_lock(). It does not increment the reference counts on yielded css structs. According to the cgroup documentation, css_put() should only be used to release a reference obtained via css_get() or css_tryget_online(). Since the iterator does not use either of these to acquire a reference, calling css_put() in the error path of scx_cgroup_init() causes a refcount underflow. Remove the unbalanced css_put() to prevent a potential Use-After-Free (UAF) vulnerability.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43439
MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: cgroup: fix race between task migration and iteration When a task is migrated out of a css_set, cgroup_migrate_add_task() first moves it from cset->tasks to cset->mg_tasks via: list_move_tail(&task->cg_list, &cset->mg_tasks); If a css_task_iter currently has it->task_pos pointing to this task, css_set_move_task() calls css_task_iter_skip() to keep the iterator valid. However, since the task has already been moved to ->mg_tasks, the iterator is advanced relative to the mg_tasks list instead of the original tasks list. As a result, remaining tasks on cset->tasks, as well as tasks queued on cset->mg_tasks, can be skipped by iteration. Fix this by calling css_set_skip_task_iters() before unlinking task->cg_list from cset->tasks. This advances all active iterators to the next task on cset->tasks, so iteration continues correctly even when a task is concurrently being migrated. This race is hard to hit in practice without instrumentation, but it can be reproduced by artificially slowing down cgroup_procs_show(). For example, on an Android device a temporary /sys/kernel/cgroup/cgroup_test knob can be added to inject a delay into cgroup_procs_show(), and then: 1) Spawn three long-running tasks (PIDs 101, 102, 103). 2) Create a test cgroup and move the tasks into it. 3) Enable a large delay via /sys/kernel/cgroup/cgroup_test. 4) In one shell, read cgroup.procs from the test cgroup. 5) Within the delay window, in another shell migrate PID 102 by writing it to a different cgroup.procs file. Under this setup, cgroup.procs can intermittently show only PID 101 while skipping PID 103. Once the migration completes, reading the file again shows all tasks as expected. Note that this change does not allow removing the existing css_set_skip_task_iters() call in css_set_move_task(). The new call in cgroup_migrate_add_task() only handles iterators that are racing with migration while the task is still on cset->tasks. Iterators may also start after the task has been moved to cset->mg_tasks. If we dropped css_set_skip_task_iters() from css_set_move_task(), such iterators could keep task_pos pointing to a migrating task, causing css_task_iter_advance() to malfunction on the destination css_set, up to and including crashes or infinite loops. The race window between migration and iteration is very small, and css_task_iter is not on a hot path. In the worst case, when an iterator is positioned on the first thread of the migrating process, cgroup_migrate_add_task() may have to skip multiple tasks via css_set_skip_task_iters(). However, this only happens when migration and iteration actually race, so the performance impact is negligible compared to the correctness fix provided here.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43441
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: net: bonding: Fix nd_tbl NULL dereference when IPv6 is disabled When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never initialized because inet6_init() exits before ndisc_init() is called which initializes it. If bonding ARP/NS validation is enabled, an IPv6 NS/NA packet received on a slave can reach bond_validate_na(), which calls bond_has_this_ip6(). That path calls ipv6_chk_addr() and can crash in __ipv6_chk_addr_and_flags(). BUG: kernel NULL pointer dereference, address: 00000000000005d8 Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:__ipv6_chk_addr_and_flags+0x69/0x170 Call Trace: ipv6_chk_addr+0x1f/0x30 bond_validate_na+0x12e/0x1d0 [bonding] ? __pfx_bond_handle_frame+0x10/0x10 [bonding] bond_rcv_validate+0x1a0/0x450 [bonding] bond_handle_frame+0x5e/0x290 [bonding] ? srso_alias_return_thunk+0x5/0xfbef5 __netif_receive_skb_core.constprop.0+0x3e8/0xe50 ? srso_alias_return_thunk+0x5/0xfbef5 ? update_cfs_rq_load_avg+0x1a/0x240 ? srso_alias_return_thunk+0x5/0xfbef5 ? __enqueue_entity+0x5e/0x240 __netif_receive_skb_one_core+0x39/0xa0 process_backlog+0x9c/0x150 __napi_poll+0x30/0x200 ? srso_alias_return_thunk+0x5/0xfbef5 net_rx_action+0x338/0x3b0 handle_softirqs+0xc9/0x2a0 do_softirq+0x42/0x60 __local_bh_enable_ip+0x62/0x70 __dev_queue_xmit+0x2d3/0x1000 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? packet_parse_headers+0x10a/0x1a0 packet_sendmsg+0x10da/0x1700 ? kick_pool+0x5f/0x140 ? srso_alias_return_thunk+0x5/0xfbef5 ? __queue_work+0x12d/0x4f0 __sys_sendto+0x1f3/0x220 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x101/0xf80 ? exc_page_fault+0x6e/0x170 ? srso_alias_return_thunk+0x5/0xfbef5 entry_SYSCALL_64_after_hwframe+0x77/0x7f Fix this by checking ipv6_mod_enabled() before dispatching IPv6 packets to bond_na_rcv(). If IPv6 is disabled, return early from bond_rcv_validate() and avoid the path to ipv6_chk_addr().

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43444
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: Unreserve bo if queue update failed Error handling path should unreserve bo then return failed. (cherry picked from commit c24afed7de9ecce341825d8ab55a43a254348b33)

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43445
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: e1000/e1000e: Fix leak in DMA error cleanup If an error is encountered while mapping TX buffers, the driver should unmap any buffers already mapped for that skb. Because count is incremented after a successful mapping, it will always match the correct number of unmappings needed when dma_error is reached. Decrementing count before the while loop in dma_error causes an off-by-one error. If any mapping was successful before an unsuccessful mapping, exactly one DMA mapping would leak. In these commits, a faulty while condition caused an infinite loop in dma_error: Commit 03b1320dfcee ("e1000e: remove use of skb_dma_map from e1000e driver") Commit 602c0554d7b0 ("e1000: remove use of skb_dma_map from e1000 driver") Commit c1fa347f20f1 ("e1000/e1000e/igb/igbvf/ixgb/ixgbe: Fix tests of unsigned in *_tx_map()") fixed the infinite loop, but introduced the off-by-one error. This issue may still exist in the igbvf driver, but I did not address it in this patch.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43448
MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: nvme-pci: Fix race bug in nvme_poll_irqdisable() In the following scenario, pdev can be disabled between (1) and (3) by (2). This sets pdev->msix_enabled = 0. Then, pci_irq_vector() will return MSI-X IRQ(>15) for (1) whereas return INTx IRQ(<=15) for (2). This causes IRQ warning because it tries to enable INTx IRQ that has never been disabled before. To fix this, save IRQ number into a local variable and ensure disable_irq() and enable_irq() operate on the same IRQ number. Even if pci_free_irq_vectors() frees the IRQ concurrently, disable_irq() and enable_irq() on a stale IRQ number is still valid and safe, and the depth accounting reamins balanced. task 1: nvme_poll_irqdisable() disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)) ...(1) enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)) ...(3) task 2: nvme_reset_work() nvme_dev_disable() pdev->msix_enable = 0; ...(2) crash log: ------------[ cut here ]------------ Unbalanced enable for IRQ 10 WARNING: kernel/irq/manage.c:753 at __enable_irq+0x102/0x190 kernel/irq/manage.c:753, CPU#1: kworker/1:0H/26 Modules linked in: CPU: 1 UID: 0 PID: 26 Comm: kworker/1:0H Not tainted 6.19.0-dirty #9 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 Workqueue: kblockd blk_mq_timeout_work RIP: 0010:__enable_irq+0x107/0x190 kernel/irq/manage.c:753 Code: ff df 48 89 fa 48 c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 79 48 8d 3d 2e 7a 3f 05 41 8b 74 24 2c <67> 48 0f b9 3a e8 ef b9 21 00 5b 41 5c 5d e9 46 54 66 03 e8 e1 b9 RSP: 0018:ffffc900001bf550 EFLAGS: 00010046 RAX: 0000000000000007 RBX: 0000000000000000 RCX: ffffffffb20c0e90 RDX: 0000000000000000 RSI: 000000000000000a RDI: ffffffffb74b88f0 RBP: ffffc900001bf560 R08: ffff88800197cf00 R09: 0000000000000001 R10: 0000000000000003 R11: 0000000000000003 R12: ffff8880012a6000 R13: 1ffff92000037eae R14: 000000000000000a R15: 0000000000000293 FS: 0000000000000000(0000) GS:ffff8880b49f7000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000555da4a25fa8 CR3: 00000000208e8000 CR4: 00000000000006f0 Call Trace: enable_irq+0x121/0x1e0 kernel/irq/manage.c:797 nvme_poll_irqdisable+0x162/0x1c0 drivers/nvme/host/pci.c:1494 nvme_timeout+0x965/0x14b0 drivers/nvme/host/pci.c:1744 blk_mq_rq_timed_out block/blk-mq.c:1653 [inline] blk_mq_handle_expired+0x227/0x2d0 block/blk-mq.c:1721 bt_iter+0x2fc/0x3a0 block/blk-mq-tag.c:292 __sbitmap_for_each_set include/linux/sbitmap.h:269 [inline] sbitmap_for_each_set include/linux/sbitmap.h:290 [inline] bt_for_each block/blk-mq-tag.c:324 [inline] blk_mq_queue_tag_busy_iter+0x969/0x1e80 block/blk-mq-tag.c:536 blk_mq_timeout_work+0x627/0x870 block/blk-mq.c:1763 process_one_work+0x956/0x1aa0 kernel/workqueue.c:3257 process_scheduled_works kernel/workqueue.c:3340 [inline] worker_thread+0x65c/0xe60 kernel/workqueue.c:3421 kthread+0x41a/0x930 kernel/kthread.c:463 ret_from_fork+0x6f8/0x8c0 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246 irq event stamp: 74478 hardirqs last enabled at (74477): [] __raw_spin_unlock_irq include/linux/spinlock_api_smp.h:159 [inline] hardirqs last enabled at (74477): [] _raw_spin_unlock_irq+0x2c/0x60 kernel/locking/spinlock.c:202 hardirqs last disabled at (74478): [] __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:108 [inline] hardirqs last disabled at (74478): [] _raw_spin_lock_irqsave+0x85/0xa0 kernel/locking/spinlock.c:162 softirqs last enabled at (74304): [] __do_softirq kernel/softirq.c:656 [inline] softirqs last enabled at (74304): [] invoke_softirq kernel/softirq.c:496 [inline] softirqs last enabled at (74304): [] __irq_exit_rcu+0xdc/0x120 ---truncated---

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43449
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: nvme-pci: Fix slab-out-of-bounds in nvme_dbbuf_set dev->online_queues is a count incremented in nvme_init_queue. Thus, valid indices are 0 through dev->online_queues − 1. This patch fixes the loop condition to ensure the index stays within the valid range. Index 0 is excluded because it is the admin queue. KASAN splat: ================================================================== BUG: KASAN: slab-out-of-bounds in nvme_dbbuf_free drivers/nvme/host/pci.c:377 [inline] BUG: KASAN: slab-out-of-bounds in nvme_dbbuf_set+0x39c/0x400 drivers/nvme/host/pci.c:404 Read of size 2 at addr ffff88800592a574 by task kworker/u8:5/74 CPU: 0 UID: 0 PID: 74 Comm: kworker/u8:5 Not tainted 6.19.0-dirty #10 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 Workqueue: nvme-reset-wq nvme_reset_work Call Trace: __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0xea/0x150 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xce/0x5d0 mm/kasan/report.c:482 kasan_report+0xdc/0x110 mm/kasan/report.c:595 __asan_report_load2_noabort+0x18/0x20 mm/kasan/report_generic.c:379 nvme_dbbuf_free drivers/nvme/host/pci.c:377 [inline] nvme_dbbuf_set+0x39c/0x400 drivers/nvme/host/pci.c:404 nvme_reset_work+0x36b/0x8c0 drivers/nvme/host/pci.c:3252 process_one_work+0x956/0x1aa0 kernel/workqueue.c:3257 process_scheduled_works kernel/workqueue.c:3340 [inline] worker_thread+0x65c/0xe60 kernel/workqueue.c:3421 kthread+0x41a/0x930 kernel/kthread.c:463 ret_from_fork+0x6f8/0x8c0 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246 Allocated by task 34 on cpu 1 at 4.241550s: kasan_save_stack+0x2c/0x60 mm/kasan/common.c:57 kasan_save_track+0x1c/0x70 mm/kasan/common.c:78 kasan_save_alloc_info+0x3c/0x50 mm/kasan/generic.c:570 poison_kmalloc_redzone mm/kasan/common.c:398 [inline] __kasan_kmalloc+0xb5/0xc0 mm/kasan/common.c:415 kasan_kmalloc include/linux/kasan.h:263 [inline] __do_kmalloc_node mm/slub.c:5657 [inline] __kmalloc_node_noprof+0x2bf/0x8d0 mm/slub.c:5663 kmalloc_array_node_noprof include/linux/slab.h:1075 [inline] nvme_pci_alloc_dev drivers/nvme/host/pci.c:3479 [inline] nvme_probe+0x2f1/0x1820 drivers/nvme/host/pci.c:3534 local_pci_probe+0xef/0x1c0 drivers/pci/pci-driver.c:324 pci_call_probe drivers/pci/pci-driver.c:392 [inline] __pci_device_probe drivers/pci/pci-driver.c:417 [inline] pci_device_probe+0x743/0x920 drivers/pci/pci-driver.c:451 call_driver_probe drivers/base/dd.c:583 [inline] really_probe+0x29b/0xb70 drivers/base/dd.c:661 __driver_probe_device+0x3b0/0x4a0 drivers/base/dd.c:803 driver_probe_device+0x56/0x1f0 drivers/base/dd.c:833 __driver_attach_async_helper+0x155/0x340 drivers/base/dd.c:1159 async_run_entry_fn+0xa6/0x4b0 kernel/async.c:129 process_one_work+0x956/0x1aa0 kernel/workqueue.c:3257 process_scheduled_works kernel/workqueue.c:3340 [inline] worker_thread+0x65c/0xe60 kernel/workqueue.c:3421 kthread+0x41a/0x930 kernel/kthread.c:463 ret_from_fork+0x6f8/0x8c0 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246 The buggy address belongs to the object at ffff88800592a000 which belongs to the cache kmalloc-2k of size 2048 The buggy address is located 244 bytes to the right of allocated 1152-byte region [ffff88800592a000, ffff88800592a480) The buggy address belongs to the physical page: page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x5928 head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 anon flags: 0xfffffc0000040(head|node=0|zone=1|lastcpupid=0x1fffff) page_type: f5(slab) raw: 000fffffc0000040 ffff888001042000 0000000000000000 dead000000000001 raw: 0000000000000000 0000000000080008 00000000f5000000 0000000000000000 head: 000fffffc0000040 ffff888001042000 00000 ---truncated---

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-43450
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: netfilter: nfnetlink_cthelper: fix OOB read in nfnl_cthelper_dump_table() nfnl_cthelper_dump_table() has a 'goto restart' that jumps to a label inside the for loop body. When the "last" helper saved in cb->args[1] is deleted between dump rounds, every entry fails the (cur != last) check, so cb->args[1] is never cleared. The for loop finishes with cb->args[0] == nf_ct_helper_hsize, and the 'goto restart' jumps back into the loop body bypassing the bounds check, causing an 8-byte out-of-bounds read on nf_ct_helper_hash[nf_ct_helper_hsize]. The 'goto restart' block was meant to re-traverse the current bucket when "last" is no longer found, but it was placed after the for loop instead of inside it. Move the block into the for loop body so that the restart only occurs while cb->args[0] is still within bounds. BUG: KASAN: slab-out-of-bounds in nfnl_cthelper_dump_table+0x9f/0x1b0 Read of size 8 at addr ffff888104ca3000 by task poc_cthelper/131 Call Trace: nfnl_cthelper_dump_table+0x9f/0x1b0 netlink_dump+0x333/0x880 netlink_recvmsg+0x3e2/0x4b0 sock_recvmsg+0xde/0xf0 __sys_recvfrom+0x150/0x200 __x64_sys_recvfrom+0x76/0x90 do_syscall_64+0xc3/0x6e0 Allocated by task 1: __kvmalloc_node_noprof+0x21b/0x700 nf_ct_alloc_hashtable+0x65/0xd0 nf_conntrack_helper_init+0x21/0x60 nf_conntrack_init_start+0x18d/0x300 nf_conntrack_standalone_init+0x12/0xc0

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-43451
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: nfnetlink_queue: fix entry leak in bridge verdict error path nfqnl_recv_verdict() calls find_dequeue_entry() to remove the queue entry from the queue data structures, taking ownership of the entry. For PF_BRIDGE packets, it then calls nfqa_parse_bridge() to parse VLAN attributes. If nfqa_parse_bridge() returns an error (e.g. NFQA_VLAN present but NFQA_VLAN_TCI missing), the function returns immediately without freeing the dequeued entry or its sk_buff. This leaks the nf_queue_entry, its associated sk_buff, and all held references (net_device refcounts, struct net refcount). Repeated triggering exhausts kernel memory. Fix this by dropping the entry via nfqnl_reinject() with NF_DROP verdict on the error path, consistent with other error handling in this file.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43452
HIGH8.2

In the Linux kernel, the following vulnerability has been resolved: netfilter: x_tables: guard option walkers against 1-byte tail reads When the last byte of options is a non-single-byte option kind, walkers that advance with i += op[i + 1] ? : 1 can read op[i + 1] past the end of the option area. Add an explicit i == optlen - 1 check before dereferencing op[i + 1] in xt_tcpudp and xt_dccp option walkers.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.2
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H
Ссылки
CVE-2026-43453
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_set_pipapo: fix stack out-of-bounds read in pipapo_drop() pipapo_drop() passes rulemap[i + 1].n to pipapo_unmap() as the to_offset argument on every iteration, including the last one where i == m->field_count - 1. This reads one element past the end of the stack-allocated rulemap array (declared as rulemap[NFT_PIPAPO_MAX_FIELDS] with NFT_PIPAPO_MAX_FIELDS == 16). Although pipapo_unmap() returns early when is_last is true without using the to_offset value, the argument is evaluated at the call site before the function body executes, making this a genuine out-of-bounds stack read confirmed by KASAN: BUG: KASAN: stack-out-of-bounds in pipapo_drop+0x50c/0x57c [nf_tables] Read of size 4 at addr ffff8000810e71a4 This frame has 1 object: [32, 160) 'rulemap' The buggy address is at offset 164 -- exactly 4 bytes past the end of the rulemap array. Pass 0 instead of rulemap[i + 1].n on the last iteration to avoid the out-of-bounds read.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-43455
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mctp: route: hold key->lock in mctp_flow_prepare_output() mctp_flow_prepare_output() checks key->dev and may call mctp_dev_set_key(), but it does not hold key->lock while doing so. mctp_dev_set_key() and mctp_dev_release_key() are annotated with __must_hold(&key->lock), so key->dev access is intended to be serialized by key->lock. The mctp_sendmsg() transmit path reaches mctp_flow_prepare_output() via mctp_local_output() -> mctp_dst_output() without holding key->lock, so the check-and-set sequence is racy. Example interleaving: CPU0 CPU1 ---- ---- mctp_flow_prepare_output(key, devA) if (!key->dev) // sees NULL mctp_flow_prepare_output( key, devB) if (!key->dev) // still NULL mctp_dev_set_key(devB, key) mctp_dev_hold(devB) key->dev = devB mctp_dev_set_key(devA, key) mctp_dev_hold(devA) key->dev = devA // overwrites devB Now both devA and devB references were acquired, but only the final key->dev value is tracked for release. One reference can be lost, causing a resource leak as mctp_dev_release_key() would only decrease the reference on one dev. Fix by taking key->lock around the key->dev check and mctp_dev_set_key() call.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43456
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bonding: fix type confusion in bond_setup_by_slave() kernel BUG at net/core/skbuff.c:2306! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI RIP: 0010:pskb_expand_head+0xa08/0xfe0 net/core/skbuff.c:2306 RSP: 0018:ffffc90004aff760 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff88807e3c8780 RCX: ffffffff89593e0e RDX: ffff88807b7c4900 RSI: ffffffff89594747 RDI: ffff88807b7c4900 RBP: 0000000000000820 R08: 0000000000000005 R09: 0000000000000000 R10: 00000000961a63e0 R11: 0000000000000000 R12: ffff88807e3c8780 R13: 00000000961a6560 R14: dffffc0000000000 R15: 00000000961a63e0 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe1a0ed8df0 CR3: 000000002d816000 CR4: 00000000003526f0 Call Trace: ipgre_header+0xdd/0x540 net/ipv4/ip_gre.c:900 dev_hard_header include/linux/netdevice.h:3439 [inline] packet_snd net/packet/af_packet.c:3028 [inline] packet_sendmsg+0x3ae5/0x53c0 net/packet/af_packet.c:3108 sock_sendmsg_nosec net/socket.c:727 [inline] __sock_sendmsg net/socket.c:742 [inline] ____sys_sendmsg+0xa54/0xc30 net/socket.c:2592 ___sys_sendmsg+0x190/0x1e0 net/socket.c:2646 __sys_sendmsg+0x170/0x220 net/socket.c:2678 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x106/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fe1a0e6c1a9 When a non-Ethernet device (e.g. GRE tunnel) is enslaved to a bond, bond_setup_by_slave() directly copies the slave's header_ops to the bond device: bond_dev->header_ops = slave_dev->header_ops; This causes a type confusion when dev_hard_header() is later called on the bond device. Functions like ipgre_header(), ip6gre_header(),all use netdev_priv(dev) to access their device-specific private data. When called with the bond device, netdev_priv() returns the bond's private data (struct bonding) instead of the expected type (e.g. struct ip_tunnel), leading to garbage values being read and kernel crashes. Fix this by introducing bond_header_ops with wrapper functions that delegate to the active slave's header_ops using the slave's own device. This ensures netdev_priv() in the slave's header functions always receives the correct device. The fix is placed in the bonding driver rather than individual device drivers, as the root cause is bond blindly inheriting header_ops from the slave without considering that these callbacks expect a specific netdev_priv() layout. The type confusion can be observed by adding a printk in ipgre_header() and running the following commands: ip link add dummy0 type dummy ip addr add 10.0.0.1/24 dev dummy0 ip link set dummy0 up ip link add gre1 type gre local 10.0.0.1 ip link add bond1 type bond mode active-backup ip link set gre1 master bond1 ip link set gre1 up ip link set bond1 up ip addr add fe80::1/64 dev bond1

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43457
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mctp: i2c: fix skb memory leak in receive path When 'midev->allow_rx' is false, the newly allocated skb isn't consumed by netif_rx(), it needs to free the skb directly.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43458
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: serial: caif: hold tty->link reference in ldisc_open and ser_release A reproducer triggers a KASAN slab-use-after-free in pty_write_room() when caif_serial's TX path calls tty_write_room(). The faulting access is on tty->link->port. Hold an extra kref on tty->link for the lifetime of the caif_serial line discipline: get it in ldisc_open() and drop it in ser_release(), and also drop it on the ldisc_open() error path. With this change applied, the reproducer no longer triggers the UAF in my testing.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43459
HIGH7.3

In the Linux kernel, the following vulnerability has been resolved: ASoC: soc-core: flush delayed work before removing DAIs and widgets When a sound card is unbound while a PCM stream is open, a use-after-free can occur in snd_soc_dapm_stream_event(), called from the close_delayed_work workqueue handler. During unbind, snd_soc_unbind_card() flushes delayed work and then calls soc_cleanup_card_resources(). Inside cleanup, snd_card_disconnect_sync() releases all PCM file descriptors, and the resulting PCM close path can call snd_soc_dapm_stream_stop() which schedules new delayed work with a pmdown_time timer delay. Since this happens after the flush in snd_soc_unbind_card(), the new work is not caught. soc_remove_link_components() then frees DAPM widgets before this work fires, leading to the use-after-free. The existing flush in soc_free_pcm_runtime() also cannot help as it runs after soc_remove_link_components() has already freed the widgets. Add a flush in soc_cleanup_card_resources() after snd_card_disconnect_sync() (after which no new PCM closes can schedule further delayed work) and before soc_remove_link_dais() and soc_remove_link_components() (which tear down the structures the delayed work accesses).

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.3
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43466
HIGH8.2

In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Fix DMA FIFO desync on error CQE SQ recovery In case of a TX error CQE, a recovery flow is triggered, mlx5e_reset_txqsq_cc_pc() resets dma_fifo_cc to 0 but not dma_fifo_pc, desyncing the DMA FIFO producer and consumer. After recovery, the producer pushes new DMA entries at the old dma_fifo_pc, while the consumer reads from position 0. This causes us to unmap stale DMA addresses from before the recovery. The DMA FIFO is a purely software construct with no HW counterpart. At the point of reset, all WQEs have been flushed so dma_fifo_cc is already equal to dma_fifo_pc. There is no need to reset either counter, similar to how skb_fifo pc/cc are untouched. Remove the 'dma_fifo_cc = 0' reset. This fixes the following WARNING: WARNING: CPU: 0 PID: 0 at drivers/iommu/dma-iommu.c:1240 iommu_dma_unmap_page+0x79/0x90 Modules linked in: mlx5_vdpa vringh vdpa bonding mlx5_ib mlx5_vfio_pci ipip mlx5_fwctl tunnel4 mlx5_core ib_ipoib geneve ip6_gre ip_gre gre nf_tables ip6_tunnel rdma_ucm ib_uverbs ib_umad vfio_pci vfio_pci_core act_mirred act_skbedit act_vlan vhost_net vhost tap ip6table_mangle ip6table_nat ip6table_filter ip6_tables iptable_mangle cls_matchall nfnetlink_cttimeout act_gact cls_flower sch_ingress vhost_iotlb iptable_raw tunnel6 vfio_iommu_type1 vfio openvswitch nsh rpcsec_gss_krb5 auth_rpcgss oid_registry xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink iptable_nat nf_nat xt_addrtype br_netfilter overlay zram zsmalloc rpcrdma ib_iser libiscsi scsi_transport_iscsi rdma_cm iw_cm ib_cm ib_core fuse [last unloaded: nf_tables] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.13.0-rc5_for_upstream_min_debug_2024_12_30_21_33 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:iommu_dma_unmap_page+0x79/0x90 Code: 2b 4d 3b 21 72 26 4d 3b 61 08 73 20 49 89 d8 44 89 f9 5b 4c 89 f2 4c 89 e6 48 89 ef 5d 41 5c 41 5d 41 5e 41 5f e9 c7 ae 9e ff <0f> 0b 5b 5d 41 5c 41 5d 41 5e 41 5f c3 66 2e 0f 1f 84 00 00 00 00 Call Trace: ? __warn+0x7d/0x110 ? iommu_dma_unmap_page+0x79/0x90 ? report_bug+0x16d/0x180 ? handle_bug+0x4f/0x90 ? exc_invalid_op+0x14/0x70 ? asm_exc_invalid_op+0x16/0x20 ? iommu_dma_unmap_page+0x79/0x90 ? iommu_dma_unmap_page+0x2e/0x90 dma_unmap_page_attrs+0x10d/0x1b0 mlx5e_tx_wi_dma_unmap+0xbe/0x120 [mlx5_core] mlx5e_poll_tx_cq+0x16d/0x690 [mlx5_core] mlx5e_napi_poll+0x8b/0xac0 [mlx5_core] __napi_poll+0x24/0x190 net_rx_action+0x32a/0x3b0 ? mlx5_eq_comp_int+0x7e/0x270 [mlx5_core] ? notifier_call_chain+0x35/0xa0 handle_softirqs+0xc9/0x270 irq_exit_rcu+0x71/0xd0 common_interrupt+0x7f/0xa0 asm_common_interrupt+0x22/0x40

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.2
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:H
Ссылки
CVE-2026-43467
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Fix crash when moving to switchdev mode When moving to switchdev mode when the device doesn't support IPsec, we try to clean up the IPsec resources anyway which causes the crash below, fix that by correctly checking for IPsec support before trying to clean up its resources. [27642.515799] WARNING: arch/x86/mm/fault.c:1276 at do_user_addr_fault+0x18a/0x680, CPU#4: devlink/6490 [27642.517159] Modules linked in: xt_conntrack xt_MASQUERADE ip6table_nat ip6table_filter ip6_tables iptable_nat nf_nat xt_addrtype rpcsec_gss_krb5 auth_rpcgss oid_registry overlay mlx5_fwctl nfnetlink zram zsmalloc mlx5_ib fuse rpcrdma rdma_ucm ib_uverbs ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm mlx5_core ib_core [27642.521358] CPU: 4 UID: 0 PID: 6490 Comm: devlink Not tainted 6.19.0-rc5_for_upstream_min_debug_2026_01_14_16_47 #1 NONE [27642.522923] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 [27642.524528] RIP: 0010:do_user_addr_fault+0x18a/0x680 [27642.525362] Code: ff 0f 84 75 03 00 00 48 89 ee 4c 89 e7 e8 5e b9 22 00 49 89 c0 48 85 c0 0f 84 a8 02 00 00 f7 c3 60 80 00 00 74 22 31 c9 eb ae <0f> 0b 48 83 c4 10 48 89 ea 48 89 de 4c 89 f7 5b 5d 41 5c 41 5d 41 [27642.528166] RSP: 0018:ffff88810770f6b8 EFLAGS: 00010046 [27642.529038] RAX: 0000000000000000 RBX: 0000000000000002 RCX: ffff88810b980f00 [27642.530158] RDX: 00000000000000a0 RSI: 0000000000000002 RDI: ffff88810770f728 [27642.531270] RBP: 00000000000000a0 R08: 0000000000000000 R09: 0000000000000000 [27642.532383] R10: 0000000000000000 R11: 0000000000000000 R12: ffff888103f3c4c0 [27642.533499] R13: 0000000000000000 R14: ffff88810770f728 R15: 0000000000000000 [27642.534614] FS: 00007f197c741740(0000) GS:ffff88856a94c000(0000) knlGS:0000000000000000 [27642.535915] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [27642.536858] CR2: 00000000000000a0 CR3: 000000011334c003 CR4: 0000000000172eb0 [27642.537982] Call Trace: [27642.538466] [27642.538907] exc_page_fault+0x76/0x140 [27642.539583] asm_exc_page_fault+0x22/0x30 [27642.540282] RIP: 0010:_raw_spin_lock_irqsave+0x10/0x30 [27642.541134] Code: 07 85 c0 75 11 ba ff 00 00 00 f0 0f b1 17 75 06 b8 01 00 00 00 c3 31 c0 c3 90 0f 1f 44 00 00 53 9c 5b fa 31 c0 ba 01 00 00 00 0f b1 17 75 05 48 89 d8 5b c3 89 c6 e8 7e 02 00 00 48 89 d8 5b [27642.543936] RSP: 0018:ffff88810770f7d8 EFLAGS: 00010046 [27642.544803] RAX: 0000000000000000 RBX: 0000000000000202 RCX: ffff888113ad96d8 [27642.545916] RDX: 0000000000000001 RSI: ffff88810770f818 RDI: 00000000000000a0 [27642.547027] RBP: 0000000000000098 R08: 0000000000000400 R09: ffff88810b980f00 [27642.548140] R10: 0000000000000001 R11: ffff888101845a80 R12: 00000000000000a8 [27642.549263] R13: ffffffffa02a9060 R14: 00000000000000a0 R15: ffff8881130d8a40 [27642.550379] complete_all+0x20/0x90 [27642.551010] mlx5e_ipsec_disable_events+0xb6/0xf0 [mlx5_core] [27642.552022] mlx5e_nic_disable+0x12d/0x220 [mlx5_core] [27642.552929] mlx5e_detach_netdev+0x66/0xf0 [mlx5_core] [27642.553822] mlx5e_netdev_change_profile+0x5b/0x120 [mlx5_core] [27642.554821] mlx5e_vport_rep_load+0x419/0x590 [mlx5_core] [27642.555757] ? xa_load+0x53/0x90 [27642.556361] __esw_offloads_load_rep+0x54/0x70 [mlx5_core] [27642.557328] mlx5_esw_offloads_rep_load+0x45/0xd0 [mlx5_core] [27642.558320] esw_offloads_enable+0xb4b/0xc90 [mlx5_core] [27642.559247] mlx5_eswitch_enable_locked+0x34e/0x4f0 [mlx5_core] [27642.560257] ? mlx5_rescan_drivers_locked+0x222/0x2d0 [mlx5_core] [27642.561284] mlx5_devlink_eswitch_mode_set+0x5ac/0x9c0 [mlx5_core] [27642.562334] ? devlink_rate_set_ops_supported+0x21/0x3a0 [27642.563220] devlink_nl_eswitch_set_doit+0x67/0xe0 [27642.564026] genl_family_rcv_msg_doit+0xe0/0x130 [27642.564816] genl_rcv_msg+0x183/0x290 [27642.565466] ? __devlink_nl_pre_doit.isra.0+0x160/0x160 [27642.566329] ? d ---truncated---

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43468
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Fix deadlock between devlink lock and esw->wq esw->work_queue executes esw_functions_changed_event_handler -> esw_vfs_changed_event_handler and acquires the devlink lock. .eswitch_mode_set (acquires devlink lock in devlink_nl_pre_doit) -> mlx5_devlink_eswitch_mode_set -> mlx5_eswitch_disable_locked -> mlx5_eswitch_event_handler_unregister -> flush_workqueue deadlocks when esw_vfs_changed_event_handler executes. Fix that by no longer flushing the work to avoid the deadlock, and using a generation counter to keep track of work relevance. This avoids an old handler manipulating an esw that has undergone one or more mode changes: - the counter is incremented in mlx5_eswitch_event_handler_unregister. - the counter is read and passed to the ephemeral mlx5_host_work struct. - the work handler takes the devlink lock and bails out if the current generation is different than the one it was scheduled to operate on. - mlx5_eswitch_cleanup does the final draining before destroying the wq. No longer flushing the workqueue has the side effect of maybe no longer cancelling pending vport_change_handler work items, but that's ok since those are disabled elsewhere: - mlx5_eswitch_disable_locked disables the vport eq notifier. - mlx5_esw_vport_disable disarms the HW EQ notification and marks vport->enabled under state_lock to false to prevent pending vport handler from doing anything. - mlx5_eswitch_cleanup destroys the workqueue and makes sure all events are disabled/finished.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43469
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: xprtrdma: Decrement re_receiving on the early exit paths In the event that rpcrdma_post_recvs() fails to create a work request (due to memory allocation failure, say) or otherwise exits early, we should decrement ep->re_receiving before returning. Otherwise we will hang in rpcrdma_xprt_drain() as re_receiving will never reach zero and the completion will never be triggered. On a system with high memory pressure, this can appear as the following hung task: INFO: task kworker/u385:17:8393 blocked for more than 122 seconds. Tainted: G S E 6.19.0 #3 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:kworker/u385:17 state:D stack:0 pid:8393 tgid:8393 ppid:2 task_flags:0x4248060 flags:0x00080000 Workqueue: xprtiod xprt_autoclose [sunrpc] Call Trace: __schedule+0x48b/0x18b0 ? ib_post_send_mad+0x247/0xae0 [ib_core] schedule+0x27/0xf0 schedule_timeout+0x104/0x110 __wait_for_common+0x98/0x180 ? __pfx_schedule_timeout+0x10/0x10 wait_for_completion+0x24/0x40 rpcrdma_xprt_disconnect+0x444/0x460 [rpcrdma] xprt_rdma_close+0x12/0x40 [rpcrdma] xprt_autoclose+0x5f/0x120 [sunrpc] process_one_work+0x191/0x3e0 worker_thread+0x2e3/0x420 ? __pfx_worker_thread+0x10/0x10 kthread+0x10d/0x230 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x273/0x2b0 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43470
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: nfs: return EISDIR on nfs3_proc_create if d_alias is a dir If we found an alias through nfs3_do_create/nfs_add_or_obtain /d_splice_alias which happens to be a dir dentry, we don't return any error, and simply forget about this alias, but the original dentry we were adding and passed as parameter remains negative. This later causes an oops on nfs_atomic_open_v23/finish_open since we supply a negative dentry to do_dentry_open. This has been observed running lustre-racer, where dirs and files are created/removed concurrently with the same name and O_EXCL is not used to open files (frequent file redirection). While d_splice_alias typically returns a directory alias or NULL, we explicitly check d_is_dir() to ensure that we don't attempt to perform file operations (like finish_open) on a directory inode, which triggers the observed oops.

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43471
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: core: Fix possible NULL pointer dereference in ufshcd_add_command_trace() The kernel log indicates a crash in ufshcd_add_command_trace, due to a NULL pointer dereference when accessing hwq->id. This can happen if ufshcd_mcq_req_to_hwq() returns NULL. This patch adds a NULL check for hwq before accessing its id field to prevent a kernel crash. Kernel log excerpt: [] notify_die+0x4c/0x8c [] __die+0x60/0xb0 [] die+0x4c/0xe0 [] die_kernel_fault+0x74/0x88 [] __do_kernel_fault+0x314/0x318 [] do_page_fault+0xa4/0x5f8 [] do_translation_fault+0x34/0x54 [] do_mem_abort+0x50/0xa8 [] el1_abort+0x3c/0x64 [] el1h_64_sync_handler+0x44/0xcc [] el1h_64_sync+0x80/0x88 [] ufshcd_add_command_trace+0x23c/0x320 [] ufshcd_compl_one_cqe+0xa4/0x404 [] ufshcd_mcq_poll_cqe_lock+0xac/0x104 [] ufs_mtk_mcq_intr+0x54/0x74 [ufs_mediatek_mod] [] __handle_irq_event_percpu+0xc8/0x348 [] handle_irq_event+0x3c/0xa8 [] handle_fasteoi_irq+0xf8/0x294 [] generic_handle_domain_irq+0x54/0x80 [] gic_handle_irq+0x1d4/0x330 [] call_on_irq_stack+0x44/0x68 [] do_interrupt_handler+0x78/0xd8 [] el1_interrupt+0x48/0xa8 [] el1h_64_irq_handler+0x14/0x24 [] el1h_64_irq+0x80/0x88 [] arch_local_irq_enable+0x4/0x1c [] cpuidle_enter+0x34/0x54 [] do_idle+0x1dc/0x2f8 [] cpu_startup_entry+0x30/0x3c [] secondary_start_kernel+0x134/0x1ac [] __secondary_switched+0xc4/0xcc

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43472
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: unshare: fix unshare_fs() handling There's an unpleasant corner case in unshare(2), when we have a CLONE_NEWNS in flags and current->fs hadn't been shared at all; in that case copy_mnt_ns() gets passed current->fs instead of a private copy, which causes interesting warts in proof of correctness] > I guess if private means fs->users == 1, the condition could still be true. Unfortunately, it's worse than just a convoluted proof of correctness. Consider the case when we have CLONE_NEWCGROUP in addition to CLONE_NEWNS (and current->fs->users == 1). We pass current->fs to copy_mnt_ns(), all right. Suppose it succeeds and flips current->fs->{pwd,root} to corresponding locations in the new namespace. Now we proceed to copy_cgroup_ns(), which fails (e.g. with -ENOMEM). We call put_mnt_ns() on the namespace created by copy_mnt_ns(), it's destroyed and its mount tree is dissolved, but... current->fs->root and current->fs->pwd are both left pointing to now detached mounts. They are pinning those, so it's not a UAF, but it leaves the calling process with unshare(2) failing with -ENOMEM _and_ leaving it with pwd and root on detached isolated mounts. The last part is clearly a bug. There is other fun related to that mess (races with pivot_root(), including the one between pivot_root() and fork(), of all things), but this one is easy to isolate and fix - treat CLONE_NEWNS as "allocate a new fs_struct even if it hadn't been shared in the first place". Sure, we could go for something like "if both CLONE_NEWNS *and* one of the things that might end up failing after copy_mnt_ns() call in create_new_namespaces() are set, force allocation of new fs_struct", but let's keep it simple - the cost of copy_fs_struct() is trivial. Another benefit is that copy_mnt_ns() with CLONE_NEWNS *always* gets a freshly allocated fs_struct, yet to be attached to anything. That seriously simplifies the analysis... FWIW, that bug had been there since the introduction of unshare(2) ;-/

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43473
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: scsi: mpi3mr: Add NULL checks when resetting request and reply queues The driver encountered a crash during resource cleanup when the reply and request queues were NULL due to freed memory. This issue occurred when the creation of reply or request queues failed, and the driver freed the memory first, but attempted to mem set the content of the freed memory, leading to a system crash. Add NULL pointer checks for reply and request queues before accessing the reply/request memory during cleanup

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43475
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: scsi: storvsc: Fix scheduling while atomic on PREEMPT_RT This resolves the follow splat and lock-up when running with PREEMPT_RT enabled on Hyper-V: [ 415.140818] BUG: scheduling while atomic: stress-ng-iomix/1048/0x00000002 [ 415.140822] INFO: lockdep is turned off. [ 415.140823] Modules linked in: intel_rapl_msr intel_rapl_common intel_uncore_frequency_common intel_pmc_core pmt_telemetry pmt_discovery pmt_class intel_pmc_ssram_telemetry intel_vsec ghash_clmulni_intel aesni_intel rapl binfmt_misc nls_ascii nls_cp437 vfat fat snd_pcm hyperv_drm snd_timer drm_client_lib drm_shmem_helper snd sg soundcore drm_kms_helper pcspkr hv_balloon hv_utils evdev joydev drm configfs efi_pstore nfnetlink vsock_loopback vmw_vsock_virtio_transport_common hv_sock vmw_vsock_vmci_transport vsock vmw_vmci efivarfs autofs4 ext4 crc16 mbcache jbd2 sr_mod sd_mod cdrom hv_storvsc serio_raw hid_generic scsi_transport_fc hid_hyperv scsi_mod hid hv_netvsc hyperv_keyboard scsi_common [ 415.140846] Preemption disabled at: [ 415.140847] [] storvsc_queuecommand+0x2e1/0xbe0 [hv_storvsc] [ 415.140854] CPU: 8 UID: 0 PID: 1048 Comm: stress-ng-iomix Not tainted 6.19.0-rc7 #30 PREEMPT_{RT,(full)} [ 415.140856] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 09/04/2024 [ 415.140857] Call Trace: [ 415.140861] [ 415.140861] ? storvsc_queuecommand+0x2e1/0xbe0 [hv_storvsc] [ 415.140863] dump_stack_lvl+0x91/0xb0 [ 415.140870] __schedule_bug+0x9c/0xc0 [ 415.140875] __schedule+0xdf6/0x1300 [ 415.140877] ? rtlock_slowlock_locked+0x56c/0x1980 [ 415.140879] ? rcu_is_watching+0x12/0x60 [ 415.140883] schedule_rtlock+0x21/0x40 [ 415.140885] rtlock_slowlock_locked+0x502/0x1980 [ 415.140891] rt_spin_lock+0x89/0x1e0 [ 415.140893] hv_ringbuffer_write+0x87/0x2a0 [ 415.140899] vmbus_sendpacket_mpb_desc+0xb6/0xe0 [ 415.140900] ? rcu_is_watching+0x12/0x60 [ 415.140902] storvsc_queuecommand+0x669/0xbe0 [hv_storvsc] [ 415.140904] ? HARDIRQ_verbose+0x10/0x10 [ 415.140908] ? __rq_qos_issue+0x28/0x40 [ 415.140911] scsi_queue_rq+0x760/0xd80 [scsi_mod] [ 415.140926] __blk_mq_issue_directly+0x4a/0xc0 [ 415.140928] blk_mq_issue_direct+0x87/0x2b0 [ 415.140931] blk_mq_dispatch_queue_requests+0x120/0x440 [ 415.140933] blk_mq_flush_plug_list+0x7a/0x1a0 [ 415.140935] __blk_flush_plug+0xf4/0x150 [ 415.140940] __submit_bio+0x2b2/0x5c0 [ 415.140944] ? submit_bio_noacct_nocheck+0x272/0x360 [ 415.140946] submit_bio_noacct_nocheck+0x272/0x360 [ 415.140951] ext4_read_bh_lock+0x3e/0x60 [ext4] [ 415.140995] ext4_block_write_begin+0x396/0x650 [ext4] [ 415.141018] ? __pfx_ext4_da_get_block_prep+0x10/0x10 [ext4] [ 415.141038] ext4_da_write_begin+0x1c4/0x350 [ext4] [ 415.141060] generic_perform_write+0x14e/0x2c0 [ 415.141065] ext4_buffered_write_iter+0x6b/0x120 [ext4] [ 415.141083] vfs_write+0x2ca/0x570 [ 415.141087] ksys_write+0x76/0xf0 [ 415.141089] do_syscall_64+0x99/0x1490 [ 415.141093] ? rcu_is_watching+0x12/0x60 [ 415.141095] ? finish_task_switch.isra.0+0xdf/0x3d0 [ 415.141097] ? rcu_is_watching+0x12/0x60 [ 415.141098] ? lock_release+0x1f0/0x2a0 [ 415.141100] ? rcu_is_watching+0x12/0x60 [ 415.141101] ? finish_task_switch.isra.0+0xe4/0x3d0 [ 415.141103] ? rcu_is_watching+0x12/0x60 [ 415.141104] ? __schedule+0xb34/0x1300 [ 415.141106] ? hrtimer_try_to_cancel+0x1d/0x170 [ 415.141109] ? do_nanosleep+0x8b/0x160 [ 415.141111] ? hrtimer_nanosleep+0x89/0x100 [ 415.141114] ? __pfx_hrtimer_wakeup+0x10/0x10 [ 415.141116] ? xfd_validate_state+0x26/0x90 [ 415.141118] ? rcu_is_watching+0x12/0x60 [ 415.141120] ? do_syscall_64+0x1e0/0x1490 [ 415.141121] ? do_syscall_64+0x1e0/0x1490 [ 415.141123] ? rcu_is_watching+0x12/0x60 [ 415.141124] ? do_syscall_64+0x1e0/0x1490 [ 415.141125] ? do_syscall_64+0x1e0/0x1490 [ 415.141127] ? irqentry_exit+0x140/0 ---truncated---

Опубликовано: 2026-05-08Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43476
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: iio: chemical: sps30_i2c: fix buffer size in sps30_i2c_read_meas() sizeof(num) evaluates to sizeof(size_t) (8 bytes on 64-bit) instead of the intended __be32 element size (4 bytes). Use sizeof(*meas) to correctly match the buffer element type.

Опубликовано: 2026-05-13Изменено: 2026-06-26
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43480
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ASoC: amd: acp3x-rt5682-max9836: Add missing error check for clock acquisition The acp3x_5682_init() function did not check the return value of clk_get(), which could lead to dereferencing error pointers in rt5682_clk_enable(). Fix this by: 1. Changing clk_get() to the device-managed devm_clk_get(). 2. Adding proper IS_ERR() checks for both clock acquisitions.

Опубликовано: 2026-05-13Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43482
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: sched_ext: Disable preemption between scx_claim_exit() and kicking helper work scx_claim_exit() atomically sets exit_kind, which prevents scx_error() from triggering further error handling. After claiming exit, the caller must kick the helper kthread work which initiates bypass mode and teardown. If the calling task gets preempted between claiming exit and kicking the helper work, and the BPF scheduler fails to schedule it back (since error handling is now disabled), the helper work is never queued, bypass mode never activates, tasks stop being dispatched, and the system wedges. Disable preemption across scx_claim_exit() and the subsequent work kicking in all callers - scx_disable() and scx_vexit(). Add lockdep_assert_preemption_disabled() to scx_claim_exit() to enforce the requirement.

Опубликовано: 2026-05-13Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43483
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: KVM: SVM: Set/clear CR8 write interception when AVIC is (de)activated Explicitly set/clear CR8 write interception when AVIC is (de)activated to fix a bug where KVM leaves the interception enabled after AVIC is activated. E.g. if KVM emulates INIT=>WFS while AVIC is deactivated, CR8 will remain intercepted in perpetuity. On its own, the dangling CR8 intercept is "just" a performance issue, but combined with the TPR sync bug fixed by commit d02e48830e3f ("KVM: SVM: Sync TPR from LAPIC into VMCB::V_TPR even if AVIC is active"), the danging intercept is fatal to Windows guests as the TPR seen by hardware gets wildly out of sync with reality. Note, VMX isn't affected by the bug as TPR_THRESHOLD is explicitly ignored when Virtual Interrupt Delivery is enabled, i.e. when APICv is active in KVM's world. I.e. there's no need to trigger update_cr8_intercept(), this is firmly an SVM implementation flaw/detail. WARN if KVM gets a CR8 write #VMEXIT while AVIC is active, as KVM should never enter the guest with AVIC enabled and CR8 writes intercepted. [Squash fix to avic_deactivate_vmcb. - Paolo]

Опубликовано: 2026-05-13Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43484
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mmc: core: Avoid bitfield RMW for claim/retune flags Move claimed and retune control flags out of the bitfield word to avoid unrelated RMW side effects in asynchronous contexts. The host->claimed bit shared a word with retune flags. Writes to claimed in __mmc_claim_host() or retune_now in mmc_mq_queue_rq() can overwrite other bits when concurrent updates happen in other contexts, triggering spurious WARN_ON(!host->claimed). Convert claimed, can_retune, retune_now and retune_paused to bool to remove shared-word coupling.

Опубликовано: 2026-05-13Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43486
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: arm64: contpte: fix set_access_flags() no-op check for SMMU/ATS faults contpte_ptep_set_access_flags() compared the gathered ptep_get() value against the requested entry to detect no-ops. ptep_get() ORs AF/dirty from all sub-PTEs in the CONT block, so a dirty sibling can make the target appear already-dirty. When the gathered value matches entry, the function returns 0 even though the target sub-PTE still has PTE_RDONLY set in hardware. For a CPU with FEAT_HAFDBS this gathered view is fine, since hardware may set AF/dirty on any sub-PTE and CPU TLB behavior is effectively gathered across the CONT range. But page-table walkers that evaluate each descriptor individually (e.g. a CPU without DBM support, or an SMMU without HTTU, or with HA/HD disabled in CD.TCR) can keep faulting on the unchanged target sub-PTE, causing an infinite fault loop. Gathering can therefore cause false no-ops when only a sibling has been updated: - write faults: target still has PTE_RDONLY (needs PTE_RDONLY cleared) - read faults: target still lacks PTE_AF Fix by checking each sub-PTE against the requested AF/dirty/write state (the same bits consumed by __ptep_set_access_flags()), using raw per-PTE values rather than the gathered ptep_get() view, before returning no-op. Keep using the raw target PTE for the write-bit unfold decision. Per Arm ARM (DDI 0487) D8.7.1 ("The Contiguous bit"), any sub-PTE in a CONT range may become the effective cached translation and software must maintain consistent attributes across the range.

Опубликовано: 2026-05-13Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43487
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ata: libata-core: Disable LPM on ST1000DM010-2EP102 According to a user report, the ST1000DM010-2EP102 has problems with LPM, causing random system freezes. The drive belongs to the same BarraCuda family as the ST2000DM008-2FR102 which has the same issue.

Опубликовано: 2026-05-13Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43488
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: xhci: Prevent interrupt storm on host controller error (HCE) The xHCI controller reports a Host Controller Error (HCE) in UAS Storage Device plug/unplug scenarios on Android devices. HCE is checked in xhci_irq() function and causes an interrupt storm (since the interrupt isn’t cleared), leading to severe system-level faults. When the xHC controller reports HCE in the interrupt handler, the driver only logs a warning and assumes xHC activity will stop as stated in xHCI specification. An interrupt storm does however continue on some hosts even after HCE, and only ceases after manually disabling xHC interrupt and stopping the controller by calling xhci_halt(). Add xhci_halt() to xhci_irq() function where STS_HCE status is checked, mirroring the existing error handling pattern used for STS_FATAL errors. This only fixes the interrupt storm. Proper HCE recovery requires resetting and re-initializing the xHC.

Опубликовано: 2026-05-13Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43490
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: ksmbd: validate inherited ACE SID length smb_inherit_dacl() walks the parent directory DACL loaded from the security descriptor xattr. It verifies that each ACE contains the fixed SID header before using it, but does not verify that the variable-length SID described by sid.num_subauth is fully contained in the ACE. A malformed inheritable ACE can advertise more subauthorities than are present in the ACE. compare_sids() may then read past the ACE. smb_set_ace() also clamps the copied destination SID, but used the unchecked source SID count to compute the inherited ACE size. That could advance the temporary inherited ACE buffer pointer and nt_size accounting past the allocated buffer. Fix this by validating the parent ACE SID count and SID length before using the SID during inheritance. Compute the inherited ACE size from the copied SID so the size matches the bounded destination SID. Reject the inherited DACL if size accumulation would overflow smb_acl.size or the security descriptor allocation size.

Опубликовано: 2026-05-15Изменено: 2026-06-26
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43491
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: qrtr: ns: Limit the maximum server registration per node Current code does no bound checking on the number of servers added per node. A malicious client can flood NEW_SERVER messages and exhaust memory. Fix this issue by limiting the maximum number of server registrations to 256 per node. If the NEW_SERVER message is received for an old port, then don't restrict it as it will get replaced. While at it, also rate limit the error messages in the failure path of qrtr_ns_worker(). Note that the limit of 256 is chosen based on the current platform requirements. If requirement changes in the future, this limit can be increased.

Опубликовано: 2026-05-19Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43492
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: lib/crypto: mpi: Fix integer underflow in mpi_read_raw_from_sgl() Yiming reports an integer underflow in mpi_read_raw_from_sgl() when subtracting "lzeros" from the unsigned "nbytes". For this to happen, the scatterlist "sgl" needs to occupy more bytes than the "nbytes" parameter and the first "nbytes + 1" bytes of the scatterlist must be zero. Under these conditions, the while loop iterating over the scatterlist will count more zeroes than "nbytes", subtract the number of zeroes from "nbytes" and cause the underflow. When commit 2d4d1eea540b ("lib/mpi: Add mpi sgl helpers") originally introduced the bug, it couldn't be triggered because all callers of mpi_read_raw_from_sgl() passed a scatterlist whose length was equal to "nbytes". However since commit 63ba4d67594a ("KEYS: asymmetric: Use new crypto interface without scatterlists"), the underflow can now actually be triggered. When invoking a KEYCTL_PKEY_ENCRYPT system call with a larger "out_len" than "in_len" and filling the "in" buffer with zeroes, crypto_akcipher_sync_prep() will create an all-zero scatterlist used for both the "src" and "dst" member of struct akcipher_request and thereby fulfil the conditions to trigger the bug: sys_keyctl() keyctl_pkey_e_d_s() asymmetric_key_eds_op() software_key_eds_op() crypto_akcipher_sync_encrypt() crypto_akcipher_sync_prep() crypto_akcipher_encrypt() rsa_enc() mpi_read_raw_from_sgl() To the user this will be visible as a DoS as the kernel spins forever, causing soft lockup splats as a side effect. Fix it.

Опубликовано: 2026-05-19Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43493
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: crypto: pcrypt - Fix handling of MAY_BACKLOG requests MAY_BACKLOG requests can return EBUSY. Handle them by checking for that value and filtering out EINPROGRESS notifications.

Опубликовано: 2026-05-19Изменено: 2026-06-26
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43494
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net/rds: reset op_nents when zerocopy page pin fails When iov_iter_get_pages2() fails in rds_message_zcopy_from_user(), the pinned pages are released with put_page(), and rm->data.op_mmp_znotifier is cleared. But we fail to properly clear rm->data.op_nents. Later when rds_message_purge() is called from rds_sendmsg() the cleanup loop iterates over the incorrectly non zero number of op_nents and frees them again. Fix this by properly resetting op_nents when it should be in rds_message_zcopy_from_user().

Опубликовано: 2026-05-21Изменено: 2026-06-30
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43495
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: net: wwan: t7xx: validate port_count against message length in t7xx_port_enum_msg_handler t7xx_port_enum_msg_handler() uses the modem-supplied port_count field as a loop bound over port_msg->data[] without checking that the message buffer contains sufficient data. A modem sending port_count=65535 in a 12-byte buffer triggers a slab-out-of-bounds read of up to 262140 bytes. Add a sizeof(*port_msg) check before accessing the port message header fields to guard against undersized messages. Add a struct_size() check after extracting port_count and before the loop. In t7xx_parse_host_rt_data(), guard the rt_feature header read with a remaining-buffer check before accessing data_len, validate feat_data_len against the actual remaining buffer to prevent OOB reads and signed integer overflow on offset. Pass msg_len from both call sites: skb->len at the DPMAIF path after skb_pull(), and the validated feat_data_len at the handshake path.

Опубликовано: 2026-05-21Изменено: 2026-06-26
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43496
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/sched: sch_red: Replace direct dequeue call with peek and qdisc_dequeue_peeked When red qdisc has children (eg qfq qdisc) whose peek() callback is qdisc_peek_dequeued(), we could get a kernel panic. When the parent of such qdiscs (eg illustrated in patch #3 as tbf) wants to retrieve an skb from its child (red in this case), it will do the following: 1a. do a peek() - and when sensing there's an skb the child can offer, then - the child in this case(red) calls its child's (qfq) peek. qfq does the right thing and will return the gso_skb queue packet. Note: if there wasnt a gso_skb entry then qfq will store it there. 1b. invoke a dequeue() on the child (red). And herein lies the problem. - red will call the child's dequeue() which will essentially just try to grab something of qfq's queue. [ 78.667668][ T363] KASAN: null-ptr-deref in range [0x0000000000000048-0x000000000000004f] [ 78.667927][ T363] CPU: 1 UID: 0 PID: 363 Comm: ping Not tainted 7.1.0-rc1-00033-g46f74a3f7d57-dirty #790 PREEMPT(full) [ 78.668263][ T363] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 78.668486][ T363] RIP: 0010:qfq_dequeue+0x446/0xc90 [sch_qfq] [ 78.668718][ T363] Code: 54 c0 e8 dd 90 00 f1 48 c7 c7 e0 03 54 c0 48 89 de e8 ce 90 00 f1 48 8d 7b 48 b8 ff ff 37 00 48 89 fa 48 c1 e0 2a 48 c1 ea 03 <80> 3c 02 00 74 05 e8 ef a1 e1 f1 48 8b 7b 48 48 8d 54 24 58 48 8d [ 78.669312][ T363] RSP: 0018:ffff88810de573e0 EFLAGS: 00010216 [ 78.669533][ T363] RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 78.669790][ T363] RDX: 0000000000000009 RSI: 0000000000000004 RDI: 0000000000000048 [ 78.670044][ T363] RBP: ffff888110dc4000 R08: ffffffffb1b0885a R09: fffffbfff6ba9078 [ 78.670297][ T363] R10: 0000000000000003 R11: ffff888110e31c80 R12: 0000001880000000 [ 78.670560][ T363] R13: ffff888110dc4150 R14: ffff888110dc42b8 R15: 0000000000000200 [ 78.670814][ T363] FS: 00007f66a8f09c40(0000) GS:ffff888163428000(0000) knlGS:0000000000000000 [ 78.671110][ T363] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 78.671324][ T363] CR2: 000055db4c6a30a8 CR3: 000000010da67000 CR4: 0000000000750ef0 [ 78.671585][ T363] PKRU: 55555554 [ 78.671713][ T363] Call Trace: [ 78.671843][ T363] [ 78.671936][ T363] ? __pfx_qfq_dequeue+0x10/0x10 [sch_qfq] [ 78.672148][ T363] ? __pfx__printk+0x10/0x10 [ 78.672322][ T363] ? srso_alias_return_thunk+0x5/0xfbef5 [ 78.672496][ T363] ? lockdep_hardirqs_on_prepare+0xa8/0x1a0 [ 78.672706][ T363] ? srso_alias_return_thunk+0x5/0xfbef5 [ 78.672875][ T363] ? trace_hardirqs_on+0x19/0x1a0 [ 78.673047][ T363] red_dequeue+0x65/0x270 [sch_red] [ 78.673217][ T363] ? srso_alias_return_thunk+0x5/0xfbef5 [ 78.673385][ T363] tbf_dequeue.cold+0xb0/0x70c [sch_tbf] [ 78.673566][ T363] __qdisc_run+0x169/0x1900 The right thing to do in #1b is to grab the skb off gso_skb queue. This patchset fixes that issue by changing #1b to use qdisc_dequeue_peeked() method instead.

Опубликовано: 2026-05-21Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-43497
HIGH7.3

In the Linux kernel, the following vulnerability has been resolved: fbdev: udlfb: add vm_ops to dlfb_ops_mmap to prevent use-after-free dlfb_ops_mmap() uses remap_pfn_range() to map vmalloc framebuffer pages to userspace but sets no vm_ops on the VMA. This means the kernel cannot track active mmaps. When dlfb_realloc_framebuffer() replaces the backing buffer via FBIOPUT_VSCREENINFO, existing mmap PTEs are not invalidated. On USB disconnect, dlfb_ops_destroy() calls vfree() on the old pages while userspace PTEs still reference them, resulting in a use-after-free: the process retains read/write access to freed kernel pages. Add vm_operations_struct with open/close callbacks that maintain an atomic mmap_count on struct dlfb_data. In dlfb_realloc_framebuffer(), check mmap_count and return -EBUSY if the buffer is currently mapped, preventing buffer replacement while userspace holds stale PTEs. Tested with PoC using dummy_hcd + raw_gadget USB device emulation.

Опубликовано: 2026-05-21Изменено: 2026-06-26
CVSS 3.xВЫСОКАЯ 7.3
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43499
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: rtmutex: Use waiter::task instead of current in remove_waiter() remove_waiter() is used by the slowlock paths, but it is also used for proxy-lock rollback in rt_mutex_start_proxy_lock() when invoked from futex_requeue(). In the latter case waiter::task is not current, but remove_waiter() operates on current for the dequeue operation. That results in several problems: 1) the rbtree dequeue happens without waiter::task::pi_lock being held 2) the waiter task's pi_blocked_on state is not cleared, which leaves a dangling pointer primed for UAF around. 3) rt_mutex_adjust_prio_chain() operates on the wrong top priority waiter task Use waiter::task instead of current in all related operations in remove_waiter() to cure those problems. [ tglx: Fixup rt_mutex_adjust_prio_chain(), add a comment and amend the changelog ]

Опубликовано: 2026-05-21Изменено: 2026-07-08
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43501
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ipv6: rpl: reserve mac_len headroom when recompressed SRH grows ipv6_rpl_srh_rcv() decompresses an RFC 6554 Source Routing Header, swaps the next segment into ipv6_hdr->daddr, recompresses, then pulls the old header and pushes the new one plus the IPv6 header back. The recompressed header can be larger than the received one when the swap reduces the common-prefix length the segments share with daddr (CmprI=0, CmprE>0, seg[0][0] != daddr[0] gives the maximum +8 bytes). pskb_expand_head() was gated on segments_left == 0, so on earlier segments the push consumed unchecked headroom. Once skb_push() leaves fewer than skb->mac_len bytes in front of data, skb_mac_header_rebuild()'s call to: skb_set_mac_header(skb, -skb->mac_len); will store (data - head) - mac_len into the u16 mac_header field, which wraps to ~65530, and the following memmove() writes mac_len bytes ~64KiB past skb->head. A single AF_INET6/SOCK_RAW/IPV6_HDRINCL packet over lo with a two segment type-3 SRH (CmprI=0, CmprE=15) reaches headroom 8 after one pass; KASAN reports a 14-byte OOB write in ipv6_rthdr_rcv. Fix this by expanding the head whenever the remaining room is less than the push size plus mac_len, and request that much extra so the rebuilt MAC header fits afterwards.

Опубликовано: 2026-05-21Изменено: 2026-07-02
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43502
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net/rds: handle zerocopy send cleanup before the message is queued A zerocopy send can fail after user pages have been pinned but before the message is attached to the sending socket. The purge path currently infers zerocopy state from rm->m_rs, so an unqueued message can be cleaned up as if it owned normal payload pages. However, zerocopy ownership is really determined by the presence of op_mmp_znotifier, regardless of whether the message has reached the socket queue. Capture op_mmp_znotifier up front in rds_message_purge() and use it as the cleanup discriminator. If the message is already associated with a socket, keep the existing completion path. Otherwise, drop the pinned page accounting directly and release the notifier before putting the payload pages. This keeps early send failure cleanup consistent with the zerocopy lifetime rules without changing the normal queued completion path.

Опубликовано: 2026-05-21Изменено: 2026-06-26
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-43503
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: net: skbuff: propagate shared-frag marker through frag-transfer helpers Two frag-transfer helpers (__pskb_copy_fclone() and skb_shift()) fail to propagate the SKBFL_SHARED_FRAG bit in skb_shinfo()->flags when moving frags from source to destination. __pskb_copy_fclone() defers the rest of the shinfo metadata to skb_copy_header() after copying frag descriptors, but that helper only carries over gso_{size,segs, type} and never touches skb_shinfo()->flags; skb_shift() moves frag descriptors directly and leaves flags untouched. As a result, the destination skb keeps a reference to the same externally-owned or page-cache-backed pages while reporting skb_has_shared_frag() as false. The mismatch is harmful in any in-place writer that uses skb_has_shared_frag() to decide whether shared pages must be detoured through skb_cow_data(). ESP input is one such writer (esp4.c, esp6.c), and a single nft 'dup to ' rule -- or any other nf_dup_ipv4() / xt_TEE caller -- is enough to land a pskb_copy()'d skb in esp_input() with the marker stripped, letting an unprivileged user write into the page cache of a root-owned read-only file via authencesn-ESN stray writes. Set SKBFL_SHARED_FRAG on the destination whenever frag descriptors were actually moved from the source. skb_copy() and skb_copy_expand() share skb_copy_header() too but linearize all paged data into freshly allocated head storage and emerge with nr_frags == 0, so skb_has_shared_frag() returns false on its own; they need no change. The same omission exists in skb_gro_receive() and skb_gro_receive_list(). The former moves the incoming skb's frag descriptors into the accumulator's last sub-skb via two paths (a direct frag-move loop and the head_frag + memcpy path); the latter chains the incoming skb whole onto p's frag_list. Downstream skb_segment() reads only skb_shinfo(p)->flags, and skb_segment_list() reuses each sub-skb's shinfo as the nskb -- both p and lp must carry the marker. The same omission also exists in tcp_clone_payload(), which builds an MTU probe skb by moving frag descriptors from skbs on sk_write_queue into a freshly allocated nskb. The helper falls into the same family and warrants the same fix for consistency; no TCP TX-side in-place writer is currently known to reach a user page through this gap, but a future consumer depending on the marker would regress silently. The same omission exists in skb_segment(): the per-iteration flag merge takes only head_skb's flag, and the inner switch that rebinds frag_skb to list_skb on head_skb-frags exhaustion does not fold the new frag_skb's flag into nskb. Fold frag_skb's flag at both sites so segments drawing frags from frag_list members carry the marker.

Опубликовано: 2026-05-23Изменено: 2026-07-02
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Ссылки
CVE-2026-45834
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix null-ptr-deref in l2cap_sock_state_change_cb() Add the same NULL guard already present in l2cap_sock_resume_cb() and l2cap_sock_ready_cb().

Опубликовано: 2026-05-26Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45835
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix null-ptr-deref in l2cap_sock_new_connection_cb() Add the same NULL guard already present in l2cap_sock_resume_cb() and l2cap_sock_ready_cb().

Опубликовано: 2026-05-26Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45836
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix null-ptr-deref in l2cap_sock_get_sndtimeo_cb() Add the same NULL guard already present in l2cap_sock_resume_cb() and l2cap_sock_ready_cb().

Опубликовано: 2026-05-26Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45837
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix use-after-free in arena_vm_close on fork arena_vm_open() only bumps vml->mmap_count but never registers the child VMA in arena->vma_list. The vml->vma always points at the parent VMA, so after parent munmap the pointer dangles. If the child then calls bpf_arena_free_pages(), zap_pages() reads the stale vml->vma triggering use-after-free. Fix this by preventing the arena VMA from being inherited across fork with VM_DONTCOPY, and preventing VMA splits via the may_split callback. Also reject mremap with a .mremap callback returning -EINVAL. A same-size mremap(MREMAP_FIXED) on the full arena VMA reaches copy_vma() through the following path: check_prep_vma() - returns 0 early: new_len == old_len skips VM_DONTEXPAND check prep_move_vma() - vm_start == old_addr and vm_end == old_addr + old_len so may_split is never called move_vma() copy_vma_and_data() copy_vma() vm_area_dup() - copies vm_private_data (vml pointer) vm_ops->open() - bumps vml->mmap_count vm_ops->mremap() - returns -EINVAL, rollback unmaps new VMA The refcount ensures the rollback's arena_vm_close does not free the vml shared with the original VMA.

Опубликовано: 2026-05-27Изменено: 2026-06-26
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-45838
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: bpf: fix end-of-list detection in cgroup_storage_get_next_key() list_next_entry() never returns NULL -- when the current element is the last entry it wraps to the list head via container_of(). The subsequent NULL check is therefore dead code and get_next_key() never returns -ENOENT for the last element, instead reading storage->key from a bogus pointer that aliases internal map fields and copying the result to userspace. Replace it with list_entry_is_head() so the function correctly returns -ENOENT when there are no more entries.

Опубликовано: 2026-05-27Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45839
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bpf: reject negative CO-RE accessor indices in bpf_core_parse_spec() CO-RE accessor strings are colon-separated indices that describe a path from a root BTF type to a target field, e.g. "0:1:2" walks through nested struct members. bpf_core_parse_spec() parses each component with sscanf("%d"), so negative values like -1 are silently accepted. The subsequent bounds checks (access_idx >= btf_vlen(t)) only guard the upper bound and always pass for negative values because C integer promotion converts the __u16 btf_vlen result to int, making the comparison (int)(-1) >= (int)(N) false for any positive N. When -1 reaches btf_member_bit_offset() it gets cast to u32 0xffffffff, producing an out-of-bounds read far past the members array. A crafted BPF program with a negative CO-RE accessor on any struct that exists in vmlinux BTF (e.g. task_struct) crashes the kernel deterministically during BPF_PROG_LOAD on any system with CONFIG_DEBUG_INFO_BTF=y (default on major distributions). The bug is reachable with CAP_BPF: BUG: unable to handle page fault for address: ffffed11818b6626 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page Oops: Oops: 0000 [#1] SMP KASAN NOPTI CPU: 0 UID: 0 PID: 85 Comm: poc Not tainted 7.0.0-rc6 #18 PREEMPT(full) RIP: 0010:bpf_core_parse_spec (tools/lib/bpf/relo_core.c:354) RAX: 00000000ffffffff Call Trace: bpf_core_calc_relo_insn (tools/lib/bpf/relo_core.c:1321) bpf_core_apply (kernel/bpf/btf.c:9507) check_core_relo (kernel/bpf/verifier.c:19475) bpf_check (kernel/bpf/verifier.c:26031) bpf_prog_load (kernel/bpf/syscall.c:3089) __sys_bpf (kernel/bpf/syscall.c:6228) CO-RE accessor indices are inherently non-negative (struct member index, array element index, or enumerator index), so reject them immediately after parsing.

Опубликовано: 2026-05-27Изменено: 2026-06-26
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-45840
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: openvswitch: cap upcall PID array size and pre-size vport replies The vport netlink reply helpers allocate a fixed-size skb with nlmsg_new(NLMSG_DEFAULT_SIZE, ...) but serialize the full upcall PID array via ovs_vport_get_upcall_portids(). Since ovs_vport_set_upcall_portids() accepts any non-zero multiple of sizeof(u32) with no upper bound, a CAP_NET_ADMIN user can install a PID array large enough to overflow the reply buffer, causing nla_put() to fail with -EMSGSIZE and hitting BUG_ON(err < 0). On systems with unprivileged user namespaces enabled (e.g., Ubuntu default), this is reachable via unshare -Urn since OVS vport mutation operations use GENL_UNS_ADMIN_PERM. kernel BUG at net/openvswitch/datapath.c:2414! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI CPU: 1 UID: 0 PID: 65 Comm: poc Not tainted 7.0.0-rc7-00195-geb216e422044 #1 RIP: 0010:ovs_vport_cmd_set+0x34c/0x400 Call Trace: genl_family_rcv_msg_doit (net/netlink/genetlink.c:1116) genl_rcv_msg (net/netlink/genetlink.c:1194) netlink_rcv_skb (net/netlink/af_netlink.c:2550) genl_rcv (net/netlink/genetlink.c:1219) netlink_unicast (net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) __sys_sendto (net/socket.c:2206) __x64_sys_sendto (net/socket.c:2209) do_syscall_64 (arch/x86/entry/syscall_64.c:63) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Kernel panic - not syncing: Fatal exception Reject attempts to set more PIDs than nr_cpu_ids in ovs_vport_set_upcall_portids(), and pre-compute the worst-case reply size in ovs_vport_cmd_msg_size() based on that bound, similar to the existing ovs_dp_cmd_msg_size(). nr_cpu_ids matches the cap already used by the per-CPU dispatch configuration on the datapath side (ovs_dp_cmd_fill_info() serialises at most nr_cpu_ids PIDs), so the two sides stay consistent.

Опубликовано: 2026-05-27Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45841
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: nfnetlink_osf: fix divide-by-zero in OSF_WSS_MODULO nf_osf_match_one() computes ctx->window % f->wss.val in the OSF_WSS_MODULO branch with no guard for f->wss.val == 0. A CAP_NET_ADMIN user can add such a fingerprint via nfnetlink; a subsequent matching TCP SYN divides by zero and panics the kernel. Reject the bogus fingerprint in nfnl_osf_add_callback() above the per-option for-loop. f->wss is per-fingerprint, not per-option, so the check must run regardless of f->opt_num (including 0). Also reject wss.wc >= OSF_WSS_MAX; nf_osf_match_one() already treats that as "should not happen". Crash: Oops: divide error: 0000 [#1] SMP KASAN NOPTI RIP: 0010:nf_osf_match_one (net/netfilter/nfnetlink_osf.c:98) Call Trace: nf_osf_match (net/netfilter/nfnetlink_osf.c:220) xt_osf_match_packet (net/netfilter/xt_osf.c:32) ipt_do_table (net/ipv4/netfilter/ip_tables.c:348) nf_hook_slow (net/netfilter/core.c:622) ip_local_deliver (net/ipv4/ip_input.c:265) ip_rcv (include/linux/skbuff.h:1162) __netif_receive_skb_one_core (net/core/dev.c:6181) process_backlog (net/core/dev.c:6642) __napi_poll (net/core/dev.c:7710) net_rx_action (net/core/dev.c:7945) handle_softirqs (kernel/softirq.c:622)

Опубликовано: 2026-05-27Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45842
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: slip: reject VJ receive packets on instances with no rstate array slhc_init() accepts rslots == 0 as a valid configuration, with the documented meaning of 'no receive compression'. In that case the allocation loop in slhc_init() is skipped, so comp->rstate stays NULL and comp->rslot_limit stays 0 (from the kzalloc of struct slcompress). The receive helpers do not defend against that configuration. slhc_uncompress() dereferences comp->rstate[x] when the VJ header carries an explicit connection ID, and slhc_remember() later assigns cs = &comp->rstate[...] after only comparing the packet's slot number to comp->rslot_limit. Because rslot_limit is 0, slot 0 passes the range check, and the code dereferences a NULL rstate. The configuration is reachable in-tree through PPP. PPPIOCSMAXCID stores its argument in a signed int, and (val >> 16) uses arithmetic shift. Passing 0xffff0000 therefore sign-extends to -1, so val2 + 1 is 0 and ppp_generic.c ends up calling slhc_init(0, 1). Because /dev/ppp open is gated by ns_capable(CAP_NET_ADMIN), the whole path is reachable from an unprivileged user namespace. Once the malformed VJ state is installed, any inbound VJ-compressed or VJ-uncompressed frame that selects slot 0 crashes the kernel in softirq context: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:slhc_uncompress (drivers/net/slip/slhc.c:519) Call Trace: ppp_receive_nonmp_frame (drivers/net/ppp/ppp_generic.c:2466) ppp_input (drivers/net/ppp/ppp_generic.c:2359) ppp_async_process (drivers/net/ppp/ppp_async.c:492) tasklet_action_common (kernel/softirq.c:926) handle_softirqs (kernel/softirq.c:623) run_ksoftirqd (kernel/softirq.c:1055) smpboot_thread_fn (kernel/smpboot.c:160) kthread (kernel/kthread.c:436) ret_from_fork (arch/x86/kernel/process.c:164) Reject the receive side on such instances instead of touching rstate. slhc_uncompress() falls through to its existing 'bad' label, which bumps sls_i_error and enters the toss state. slhc_remember() mirrors that with an explicit sls_i_error increment followed by slhc_toss(); the sls_i_runt counter is not used here because a missing rstate is an internal configuration state, not a runt packet. The transmit path is unaffected: the only in-tree caller that picks rslots from userspace (ppp_generic.c) still supplies tslots >= 1, and slip.c always calls slhc_init(16, 16), so comp->tstate remains valid and slhc_compress() continues to work.

Опубликовано: 2026-05-27Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45843
HIGH8.2

In the Linux kernel, the following vulnerability has been resolved: slip: bound decode() reads against the compressed packet length slhc_uncompress() parses a VJ-compressed TCP header by advancing a pointer through the packet via decode() and pull16(). Neither helper bounds-checks against isize, and decode() masks its return with & 0xffff so it can never return the -1 that callers test for -- those error paths are dead code. A short compressed frame whose change byte requests optional fields lets decode() read past the end of the packet. The over-read bytes are folded into the cached cstate and reflected into subsequent reconstructed packets. Make decode() and pull16() take the packet end pointer and return -1 when exhausted. Add a bounds check before the TCP-checksum read. The existing == -1 tests now do what they were always meant to.

Опубликовано: 2026-05-27Изменено: 2026-06-26
CVSS 3.xВЫСОКАЯ 8.2
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
Ссылки
CVE-2026-45844
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: arp_tables: fix IEEE1394 ARP payload parsing Weiming Shi says: "arp_packet_match() unconditionally parses the ARP payload assuming two hardware addresses are present (source and target). However, IPv4-over-IEEE1394 ARP (RFC 2734) omits the target hardware address field, and arp_hdr_len() already accounts for this by returning a shorter length for ARPHRD_IEEE1394 devices. As a result, on IEEE1394 interfaces arp_packet_match() advances past a nonexistent target hardware address and reads the wrong bytes for both the target device address comparison and the target IP address. This causes arptables rules to match against garbage data, leading to incorrect filtering decisions: packets that should be accepted may be dropped and vice versa. The ARP stack in net/ipv4/arp.c (arp_create and arp_process) already handles this correctly by skipping the target hardware address for ARPHRD_IEEE1394. Apply the same pattern to arp_packet_match()." Mangle the original patch to always return 0 (no match) in case user matches on the target hardware address which is never present in IEEE1394. Note that this returns 0 (no match) for either normal and inverse match because matching in the target hardware address in ARPHRD_IEEE1394 has never been supported by arptables. This is intentional, matching on the target hardware address should never evaluate true for ARPHRD_IEEE1394. Moreover, adjust arpt_mangle to drop the packet too as AI suggests: In arpt_mangle, the logic assumes a standard ARP layout. Because IEEE1394 (FireWire) omits the target hardware address, the linear pointer arithmetic miscalculates the offset for the target IP address. This causes mangling operations to write to the wrong location, leading to packet corruption. To ensure safety, this patch drops packets (NF_DROP) when mangling is requested for these fields on IEEE1394 devices, as the current implementation cannot correctly map the FireWire ARP payload. This omits both mangling target hardware and IP address. Even if IP address mangling should be possible in IEEE1394, this would require to adjust arpt_mangle offset calculation, which has never been supported. Based on patch from Weiming Shi .

Опубликовано: 2026-05-27Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45845
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/sched: taprio: fix NULL pointer dereference in class dump When a TAPRIO child qdisc is deleted via RTM_DELQDISC, taprio_graft() is called with new == NULL and stores NULL into q->qdiscs[cl - 1]. Subsequent RTM_GETTCLASS dump operations walk all classes via taprio_walk() and call taprio_dump_class(), which calls taprio_leaf() returning the NULL pointer, then dereferences it to read child->handle, causing a kernel NULL pointer dereference. The bug is reachable with namespace-scoped CAP_NET_ADMIN on any kernel with CONFIG_NET_SCH_TAPRIO enabled. On systems with unprivileged user namespaces enabled, an unprivileged local user can trigger a kernel panic by creating a taprio qdisc inside a new network namespace, grafting an explicit child qdisc, deleting it, and requesting a class dump. The RTM_GETTCLASS dump itself requires no capability. Oops: general protection fault, probably for non-canonical address 0xdffffc0000000007: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f] RIP: 0010:taprio_dump_class (net/sched/sch_taprio.c:2478) Call Trace: tc_fill_tclass (net/sched/sch_api.c:1966) qdisc_class_dump (net/sched/sch_api.c:2326) taprio_walk (net/sched/sch_taprio.c:2514) tc_dump_tclass_qdisc (net/sched/sch_api.c:2352) tc_dump_tclass_root (net/sched/sch_api.c:2370) tc_dump_tclass (net/sched/sch_api.c:2431) rtnl_dumpit (net/core/rtnetlink.c:6864) netlink_dump (net/netlink/af_netlink.c:2325) rtnetlink_rcv_msg (net/core/rtnetlink.c:6959) netlink_rcv_skb (net/netlink/af_netlink.c:2550) Fix this by substituting &noop_qdisc when new is NULL in taprio_graft(), a common pattern used by other qdiscs (e.g., multiq_graft()) to ensure the q->qdiscs[] slots are never NULL. This makes control-plane dump paths safe without requiring individual NULL checks. Since the data-plane paths (taprio_enqueue and taprio_dequeue_from_txq) previously had explicit NULL guards that would drop/skip the packet cleanly, update those checks to test for &noop_qdisc instead. Without this, packets would reach taprio_enqueue_one() which increments the root qdisc's qlen and backlog before calling the child's enqueue; noop_qdisc drops the packet but those counters are never rolled back, permanently inflating the root qdisc's statistics. After this change *old can be a valid qdisc, NULL, or &noop_qdisc. Only call qdisc_put(*old) in the first case to avoid decreasing noop_qdisc's refcount, which was never increased.

Опубликовано: 2026-05-27Изменено: 2026-06-26
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45846
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: bareudp: fix NULL pointer dereference in bareudp_fill_metadata_dst() bareudp_fill_metadata_dst() passes bareudp->sock to udp_tunnel6_dst_lookup() in the IPv6 path without a NULL check. The socket is only created in bareudp_open() and NULLed in bareudp_stop(), so calling this function while the device is down triggers a NULL dereference via sock->sk. BUG: kernel NULL pointer dereference, address: 0000000000000018 RIP: 0010:udp_tunnel6_dst_lookup (net/ipv6/ip6_udp_tunnel.c:160) Call Trace: bareudp_fill_metadata_dst (drivers/net/bareudp.c:532) do_execute_actions (net/openvswitch/actions.c:901) ovs_execute_actions (net/openvswitch/actions.c:1589) ovs_packet_cmd_execute (net/openvswitch/datapath.c:700) genl_family_rcv_msg_doit (net/netlink/genetlink.c:1114) genl_rcv_msg (net/netlink/genetlink.c:1209) netlink_rcv_skb (net/netlink/af_netlink.c:2550) Add a NULL check returning -ESHUTDOWN, consistent with the xmit paths in the same driver.

Опубликовано: 2026-05-27Изменено: 2026-06-25
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45850
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ipvs: skip ipv6 extension headers for csum checks Protocol checksum validation fails for IPv6 if there are extension headers before the protocol header. iph->len already contains its offset, so use it to fix the problem.

Опубликовано: 2026-05-27Изменено: 2026-06-25
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45924
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ksmbd: call ksmbd_vfs_kern_path_end_removing() on some error paths There are two places where ksmbd_vfs_kern_path_end_removing() needs to be called in order to balance what the corresponding successful call to ksmbd_vfs_kern_path_start_removing() has done, i.e. drop inode locks and put the taken references. Otherwise there might be potential deadlocks and unbalanced locks which are caught like: BUG: workqueue leaked lock or atomic: kworker/5:21/0x00000000/7596 last function: handle_ksmbd_work 2 locks held by kworker/5:21/7596: #0: ffff8881051ae448 (sb_writers#3){.+.+}-{0:0}, at: ksmbd_vfs_kern_path_locked+0x142/0x660 #1: ffff888130e966c0 (&type->i_mutex_dir_key#3/1){+.+.}-{4:4}, at: ksmbd_vfs_kern_path_locked+0x17d/0x660 CPU: 5 PID: 7596 Comm: kworker/5:21 Not tainted 6.1.162-00456-gc29b353f383b #138 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014 Workqueue: ksmbd-io handle_ksmbd_work Call Trace: dump_stack_lvl+0x44/0x5b process_one_work.cold+0x57/0x5c worker_thread+0x82/0x600 kthread+0x153/0x190 ret_from_fork+0x22/0x30 Found by Linux Verification Center (linuxtesting.org).

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45930
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: mctp: ensure our nlmsg responses are initialised Syed Faraz Abrar (@farazsth98) from Zellic, and Pumpkin (@u1f383) from DEVCORE Research Team working with Trend Micro Zero Day Initiative report that a RTM_GETNEIGH will return uninitalised data in the pad bytes of the ndmsg data. Ensure we're initialising the netlink data to zero, in the link, addr and neigh response messages.

Опубликовано: 2026-05-27Изменено: 2026-06-25
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45943
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: erofs: fix inline data read failure for ztailpacking pclusters Compressed folios for ztailpacking pclusters must be valid before adding these pclusters to I/O chains. Otherwise, z_erofs_decompress_pcluster() may assume they are already valid and then trigger a NULL pointer dereference. It is somewhat hard to reproduce because the inline data is in the same block as the tail of the compressed indexes, which are usually read just before. However, it may still happen if a fatal signal arrives while read_mapping_folio() is running, as shown below: erofs: (device dm-1): z_erofs_pcluster_begin: failed to get inline data -4 Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 ... pc : z_erofs_decompress_queue+0x4c8/0xa14 lr : z_erofs_decompress_queue+0x160/0xa14 sp : ffffffc08b3eb3a0 x29: ffffffc08b3eb570 x28: ffffffc08b3eb418 x27: 0000000000001000 x26: ffffff8086ebdbb8 x25: ffffff8086ebdbb8 x24: 0000000000000001 x23: 0000000000000008 x22: 00000000fffffffb x21: dead000000000700 x20: 00000000000015e7 x19: ffffff808babb400 x18: ffffffc089edc098 x17: 00000000c006287d x16: 00000000c006287d x15: 0000000000000004 x14: ffffff80ba8f8000 x13: 0000000000000004 x12: 00000006589a77c9 x11: 0000000000000015 x10: 0000000000000000 x9 : 0000000000000000 x8 : 0000000000000000 x7 : 0000000000000000 x6 : 000000000000003f x5 : 0000000000000040 x4 : ffffffffffffffe0 x3 : 0000000000000020 x2 : 0000000000000008 x1 : 0000000000000000 x0 : 0000000000000000 Call trace: z_erofs_decompress_queue+0x4c8/0xa14 z_erofs_runqueue+0x908/0x97c z_erofs_read_folio+0x128/0x228 filemap_read_folio+0x68/0x128 filemap_get_pages+0x44c/0x8b4 filemap_read+0x12c/0x5b8 generic_file_read_iter+0x4c/0x15c do_iter_readv_writev+0x188/0x1e0 vfs_iter_read+0xac/0x1a4 backing_file_read_iter+0x170/0x34c ovl_read_iter+0xf0/0x140 vfs_read+0x28c/0x344 ksys_read+0x80/0xf0 __arm64_sys_read+0x24/0x34 invoke_syscall+0x60/0x114 el0_svc_common+0x88/0xe4 do_el0_svc+0x24/0x30 el0_svc+0x40/0xa8 el0t_64_sync_handler+0x70/0xbc el0t_64_sync+0x1bc/0x1c0 Fix this by reading the inline data before allocating and adding the pclusters to the I/O chains.

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-45986
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: crypto: ccree - fix a memory leak in cc_mac_digest() Add cc_unmap_result() if cc_map_hash_request_final() fails to prevent potential memory leak.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45987
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: KVM: nSVM: Sync interrupt shadow to cached vmcb12 after VMRUN of L2 After VMRUN in guest mode, nested_sync_control_from_vmcb02() syncs fields written by the CPU from vmcb02 to the cached vmcb12. This is because the cached vmcb12 is used as the authoritative copy of some of the controls, and is the payload when saving/restoring nested state. int_state is also written by the CPU, specifically bit 0 (i.e. SVM_INTERRUPT_SHADOW_MASK) for nested VMs, but it is not sync'd to cached vmcb12. This does not cause a problem if KVM_SET_NESTED_STATE preceeds KVM_SET_VCPU_EVENTS in the restore path, as an interrupt shadow would be correctly restored to vmcb02 (KVM_SET_VCPU_EVENTS overwrites what KVM_SET_NESTED_STATE restored in int_state). However, if KVM_SET_VCPU_EVENTS preceeds KVM_SET_NESTED_STATE, an interrupt shadow would be restored into vmcb01 instead of vmcb02. This would mostly be benign for L1 (delays an interrupt), but not for L2. For L2, the vCPU could hang (e.g. if a wakeup interrupt is delivered before a HLT that should have been in an interrupt shadow). Sync int_state to the cached vmcb12 in nested_sync_control_from_vmcb02() to avoid this problem. With that, KVM_SET_NESTED_STATE restores the correct interrupt shadow state, and if KVM_SET_VCPU_EVENTS follows it would overwrite it with the same value.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45988
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix re-decryption of RESPONSE packets If a RESPONSE packet gets a temporary failure during processing, it may end up in a partially decrypted state - and then get requeued for a retry. Fix this by just discarding the packet; we will send another CHALLENGE packet and thereby elicit a further response. Similarly, discard an incoming CHALLENGE packet if we get an error whilst generating a RESPONSE; the server will send another CHALLENGE.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-45989
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: of: unittest: fix use-after-free in testdrv_probe() The function testdrv_probe() retrieves the device_node from the PCI device, applies an overlay, and then immediately calls of_node_put(dn). This releases the reference held by the PCI core, potentially freeing the node if the reference count drops to zero. Later, the same freed pointer 'dn' is passed to of_platform_default_populate(), leading to a use-after-free. The reference to pdev->dev.of_node is owned by the device model and should not be released by the driver. Remove the erroneous of_node_put() to prevent premature freeing.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-45991
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: udf: fix partition descriptor append bookkeeping Mounting a crafted UDF image with repeated partition descriptors can trigger a heap out-of-bounds write in part_descs_loc[]. handle_partition_descriptor() deduplicates entries by partition number, but appended slots never record partnum. As a result duplicate Partition Descriptors are appended repeatedly and num_part_descs keeps growing. Once the table is full, the growth path still sizes the allocation from partnum even though inserts are indexed by num_part_descs. If partnum is already aligned to PART_DESC_ALLOC_STEP, ALIGN(partnum, step) can keep the old capacity and the next append writes past the end of the table. Store partnum in the appended slot and size growth from the next append count so deduplication and capacity tracking follow the same model.

Опубликовано: 2026-05-27Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-45993
MEDIUM5.5

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

Опубликовано: 2026-05-27Изменено: 2026-06-19
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45994
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: ibmasm: fix OOB reads in command_file_write due to missing size checks The command_file_write() handler allocates a kernel buffer of exactly count bytes and copies user data into it, but does not validate the buffer against the dot command protocol before passing it to get_dot_command_size() and get_dot_command_timeout(). Since both the allocation size (count) and the header fields (command_size, data_size) are independently user-controlled, an attacker can cause get_dot_command_size() to return a value exceeding the allocation, triggering OOB reads in get_dot_command_timeout() and an out-of-bounds memcpy_toio() that leaks kernel heap memory to the service processor. Fix with two guards: reject writes smaller than sizeof(struct dot_command_header) before allocation, then after copying user data reject commands where the buffer is smaller than the total size declared by the header (sizeof(header) + command_size + data_size). This ensures all subsequent header and payload field accesses stay within the buffer.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-45996
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: spi: imx: fix use-after-free on unbind The SPI subsystem frees the controller and any subsystem allocated driver data as part of deregistration (unless the allocation is device managed). Take another reference before deregistering the controller so that the driver data is not freed until the driver is done with it.

Опубликовано: 2026-05-27Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-45997
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: scsi: sd: fix missing put_disk() when device_add(&disk_dev) fails If device_add(&sdkp->disk_dev) fails, put_device() runs scsi_disk_release(), which frees the scsi_disk but leaves the gendisk referenced. The device_add_disk() error path in sd_probe() calls put_disk(gd); call put_disk(gd) here to mirror that cleanup.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-45998
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix potential UAF after skb_unshare() failure If skb_unshare() fails to unshare a packet due to allocation failure in rxrpc_input_packet(), the skb pointer in the parent (rxrpc_io_thread()) will be NULL'd out. This will likely cause the call to trace_rxrpc_rx_done() to oops. Fix this by moving the unsharing down to where rxrpc_input_call_event() calls rxrpc_input_call_packet(). There are a number of places prior to that where we ignore DATA packets for a variety of reasons (such as the call already being complete) for which an unshare is then avoided. And with that, rxrpc_input_packet() doesn't need to take a pointer to the pointer to the packet, so change that to just a pointer.

Опубликовано: 2026-05-27Изменено: 2026-07-03
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-45999
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: erofs: fix unsigned underflow in z_erofs_lz4_handle_overlap() Some crafted images can have illegal (!partial_decoding && m_llen < m_plen) extents, and the LZ4 inplace decompression path can be wrongly hit, but it cannot handle (outpages < inpages) properly: "outpages - inpages" wraps to a large value and the subsequent rq->out[] access reads past the decompressed_pages array. However, such crafted cases can correctly result in a corruption report in the normal LZ4 non-inplace path. Let's add an additional check to fix this for backporting. Reproducible image (base64-encoded gzipped blob): H4sIAJGR12kCA+3SPUoDQRgG4MkmkkZk8QRbRFIIi9hbpEjrHQI5ghfwCN5BLCzTGtLbBI+g dilSJo1CnIm7GEXFxhT6PDDwfrs73/ywIQD/1ePD4r7Ou6ETsrq4mu7XcWfj++Pb58nJU/9i PNtbjhan04/9GtX4qVYc814WDqt6FaX5s+ZwXXeq52lndT6IuVvlblytLMvh4Gzwaf90nsvz 2DF/21+20T/ldgp5s1jXRaN4t/8izsy/OUB6e/Qa79r+JwAAAAAAAL52vQVuGQAAAP6+my1w ywAAAAAAAADwu14ATsEYtgBQAAA= $ mount -t erofs -o cache_strategy=disabled foo.erofs /mnt $ dd if=/mnt/data of=/dev/null bs=4096 count=1

Опубликовано: 2026-05-27Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46000
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix conn-level packet handling to unshare RESPONSE packets The security operations that verify the RESPONSE packets decrypt bits of it in place - however, the sk_buff may be shared with a packet sniffer, which would lead to the sniffer seeing an apparently corrupt packet (actually decrypted). Fix this by handing a copy of the packet off to the specific security handler if the packet was cloned.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46001
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: hwmon: (pt5161l) Fix bugs in pt5161l_read_block_data() Fix two bugs in pt5161l_read_block_data(): 1. Buffer overrun: The local buffer rbuf is declared as u8 rbuf[24], but i2c_smbus_read_block_data() can return up to I2C_SMBUS_BLOCK_MAX (32) bytes. The i2c-core copies the data into the caller's buffer before the return value can be checked, so the post-read length validation does not prevent a stack overrun if a device returns more than 24 bytes. Resize the buffer to I2C_SMBUS_BLOCK_MAX. 2. Unexpected positive return on length mismatch: When all three retries are exhausted because the device returns data with an unexpected length, i2c_smbus_read_block_data() returns a positive byte count. The function returns this directly, and callers treat any non-negative return as success, processing stale or incomplete buffer contents. Return -EIO when retries are exhausted with a positive return value, preserving the negative error code on I2C failure.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46002
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ext2: reject inodes with zero i_nlink and valid mode in ext2_iget() ext2_iget() already rejects inodes with i_nlink == 0 when i_mode is zero or i_dtime is set, treating them as deleted. However, the case of i_nlink == 0 with a non-zero mode and zero dtime slips through. Since ext2 has no orphan list, such a combination can only result from filesystem corruption - a legitimate inode deletion always sets either i_dtime or clears i_mode before freeing the inode. A crafted image can exploit this gap to present such an inode to the VFS, which then triggers WARN_ON inside drop_nlink() (fs/inode.c) via ext2_unlink(), ext2_rename() and ext2_rmdir(): WARNING: CPU: 3 PID: 609 at fs/inode.c:336 drop_nlink+0xad/0xd0 fs/inode.c:336 CPU: 3 UID: 0 PID: 609 Comm: syz-executor Not tainted 6.12.77+ #1 Call Trace: inode_dec_link_count include/linux/fs.h:2518 [inline] ext2_unlink+0x26c/0x300 fs/ext2/namei.c:295 vfs_unlink+0x2fc/0x9b0 fs/namei.c:4477 do_unlinkat+0x53e/0x730 fs/namei.c:4541 __x64_sys_unlink+0xc6/0x110 fs/namei.c:4587 do_syscall_64+0xf5/0x220 arch/x86/entry/common.c:78 entry_SYSCALL_64_after_hwframe+0x77/0x7f WARNING: CPU: 0 PID: 646 at fs/inode.c:336 drop_nlink+0xad/0xd0 fs/inode.c:336 CPU: 0 UID: 0 PID: 646 Comm: syz.0.17 Not tainted 6.12.77+ #1 Call Trace: inode_dec_link_count include/linux/fs.h:2518 [inline] ext2_rename+0x35e/0x850 fs/ext2/namei.c:374 vfs_rename+0xf2f/0x2060 fs/namei.c:5021 do_renameat2+0xbe2/0xd50 fs/namei.c:5178 __x64_sys_rename+0x7e/0xa0 fs/namei.c:5223 do_syscall_64+0xf5/0x220 arch/x86/entry/common.c:78 entry_SYSCALL_64_after_hwframe+0x77/0x7f WARNING: CPU: 0 PID: 634 at fs/inode.c:336 drop_nlink+0xad/0xd0 fs/inode.c:336 CPU: 0 UID: 0 PID: 634 Comm: syz-executor Not tainted 6.12.77+ #1 Call Trace: inode_dec_link_count include/linux/fs.h:2518 [inline] ext2_rmdir+0xca/0x110 fs/ext2/namei.c:311 vfs_rmdir+0x204/0x690 fs/namei.c:4348 do_rmdir+0x372/0x3e0 fs/namei.c:4407 __x64_sys_unlinkat+0xf0/0x130 fs/namei.c:4577 do_syscall_64+0xf5/0x220 arch/x86/entry/common.c:78 entry_SYSCALL_64_after_hwframe+0x77/0x7f Extend the existing i_nlink == 0 check to also catch this case, reporting the corruption via ext2_error() and returning -EFSCORRUPTED. This rejects the inode at load time and prevents it from reaching any of the namei.c paths. Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46003
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: qrtr: ns: Limit the total number of nodes Currently, the nameserver doesn't limit the number of nodes it handles. This can be an attack vector if a malicious client starts registering random nodes, leading to memory exhaustion. Hence, limit the maximum number of nodes to 64. Note that, limit of 64 is chosen based on the current platform requirements. If requirement changes in the future, this limit can be increased.

Опубликовано: 2026-05-27Изменено: 2026-06-19
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46004
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ALSA: caiaq: Handle probe errors properly The probe procedure of setup_card() in caiaq driver doesn't treat the error cases gracefully, e.g. the error from snd_card_register() calls snd_card_free() but continues. This would lead to a UAF for the further calls like snd_usb_caiaq_control_init(), as Berk suggested in another patch in the link below. However, the problem is not only that; in general, this function drops the all error handlings (as it's a void function) although its caller can propagate an error to snd_probe(), which eventually calls snd_card_free() as a proper error path. That said, we should treat each error case in setup_card(), and just return the error code promptly, which is then handled later as a fatal error in snd_probe(). This patch achieves it by changing the setup_card() to return an error code. Also, the superfluous snd_card_free() call is removed, too. Note that card->private_free can be set still safely at returning an error. All called functions in card_free() have checks of the unassigned resources or NULL checks.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46005
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xfs: fix a resource leak in xfs_alloc_buftarg() In the error path, call fs_put_dax() to drop the DAX device reference.

Опубликовано: 2026-05-27Изменено: 2026-06-19
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46006
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: drm/nouveau: fix u32 overflow in pushbuf reloc bounds check nouveau_gem_pushbuf_reloc_apply() validates each relocation with if (r->reloc_bo_offset + 4 > nvbo->bo.base.size) but reloc_bo_offset is __u32 (uapi/drm/nouveau_drm.h) and the integer literal 4 promotes to unsigned int, so the addition is performed in 32 bits and wraps before the comparison against the size_t bo size. Cast to u64 so the addition happens in 64-bit arithmetic. [ Add Fixes: tag. - Danilo ]

Опубликовано: 2026-05-27Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46007
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: hwmon: (powerz) Avoid cacheline sharing for DMA buffer Depending on the architecture the transfer buffer may share a cacheline with the following mutex. As the buffer may be used for DMA, that is problematic. Use the high-level DMA helpers to make sure that cacheline sharing can not happen. Also drop the comment, as the helpers are documentation enough. https://sashiko.dev/#/message/20260408175814.934BFC19421%40smtp.kernel.org

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46009
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-ntb: Remove duplicate resource teardown epf_ntb_epc_destroy() duplicates the teardown that the caller is supposed to do later. This leads to an oops when .allow_link fails or when .drop_link is performed. Remove the helper. Also drop pci_epc_put(). EPC device refcounting is tied to configfs EPC group lifetime, and pci_epc_put() in the .drop_link path is sufficient.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46011
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: media: mtk-jpeg: fix use-after-free in release path due to uncancelled work The mtk_jpeg_release() function frees the context structure (ctx) without first cancelling any pending or running work in ctx->jpeg_work. This creates a race window where the workqueue callback may still be accessing the context memory after it has been freed. Race condition: CPU 0 (release) CPU 1 (workqueue) ---------------- ------------------ close() mtk_jpeg_release() mtk_jpegenc_worker() ctx = work->data // accessing ctx kfree(ctx) // freed! access ctx // UAF! The work is queued via queue_work() during JPEG encode/decode operations (via mtk_jpeg_device_run). If the device is closed while work is pending or running, the work handler will access freed memory. Fix this by calling cancel_work_sync() BEFORE acquiring the mutex. This ordering is critical: if cancel_work_sync() is called after mutex_lock(), and the work handler also tries to acquire the same mutex, it would cause a deadlock. 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 ioctl operations.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46012
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix memory leaks in rxkad_verify_response() Fix rxkad_verify_response() to free the ticket and the server key under all circumstances by initialising the ticket pointer to NULL and then making all paths through the function after the first allocation has been done go through a single common epilogue that just releases everything - where all the releases skip on a NULL pointer.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46015
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: tcp: call sk_data_ready() after listener migration When inet_csk_listen_stop() migrates an established child socket from a closing listener to another socket in the same SO_REUSEPORT group, the target listener gets a new accept-queue entry via inet_csk_reqsk_queue_add(), but that path never notifies the target listener's waiters. A nonblocking accept() still works because it checks the queue directly, but poll()/epoll_wait() waiters and blocking accept() callers can also remain asleep indefinitely. Call READ_ONCE(nsk->sk_data_ready)(nsk) after a successful migration in inet_csk_listen_stop(). However, after inet_csk_reqsk_queue_add() succeeds, the ref acquired in reuseport_migrate_sock() is effectively transferred to nreq->rsk_listener. Another CPU can then dequeue nreq via accept() or listener shutdown, hit reqsk_put(), and drop that listener ref. Since listeners are SOCK_RCU_FREE, wrap the post-queue_add() dereferences of nsk in rcu_read_lock()/rcu_read_unlock(), which also covers the existing sock_net(nsk) access in that path. The reqsk_timer_handler() path does not need the same changes for two reasons: half-open requests become readable only after the final ACK, where tcp_child_process() already wakes the listener; and once nreq is visible via inet_ehash_insert(), the success path no longer touches nsk directly.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46016
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: remoteproc: xlnx: Only access buffer information if IPI is buffered In the receive callback check if message is NULL to prevent possibility of crash by NULL pointer dereferencing.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46018
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ALSA: usb-audio: stop parsing UAC2 rates at MAX_NR_RATES parse_uac2_sample_rate_range() caps the number of enumerated rates at MAX_NR_RATES, but it only breaks out of the current rate loop. A malformed UAC2 RANGE response with additional triplets continues parsing the remaining triplets and repeatedly prints "invalid uac2 rates" while probe still holds register_mutex. Stop the whole parse once the cap is reached and return the number of rates collected so far.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46019
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: crypto: atmel-aes - Fix 3-page memory leak in atmel_aes_buff_cleanup atmel_aes_buff_init() allocates 4 pages using __get_free_pages() with ATMEL_AES_BUFFER_ORDER, but atmel_aes_buff_cleanup() frees only the first page using free_page(), leaking the remaining 3 pages. Use free_pages() with ATMEL_AES_BUFFER_ORDER to fix the memory leak.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46021
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: thermal: core: Fix thermal zone governor cleanup issues If thermal_zone_device_register_with_trips() fails after adding a thermal governor to the thermal zone being registered, the governor is not removed from it as appropriate which may lead to a memory leak. In turn, thermal_zone_device_unregister() calls thermal_set_governor() without acquiring the thermal zone lock beforehand which may race with a governor update via sysfs and may lead to a use-after-free in that case. Address these issues by adding two thermal_set_governor() calls, one to thermal_release() to remove the governor from the given thermal zone, and one to the thermal zone registration error path to cover failures preceding the thermal zone device registration.

Опубликовано: 2026-05-27Изменено: 2026-06-19
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46022
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: misc: ibmasm: fix OOB MMIO read in ibmasm_handle_mouse_interrupt() ibmasm_handle_mouse_interrupt() performs an out-of-bounds MMIO read when the queue reader or writer index from hardware exceeds REMOTE_QUEUE_SIZE (60). A compromised service processor can trigger this by writing an out-of-range value to the reader or writer MMIO register before asserting an interrupt. Since writer is re-read from hardware on every loop iteration, it can also be set to an out-of-range value after the loop has already started. The root cause is that get_queue_reader() and get_queue_writer() return raw readl() values that are passed directly into get_queue_entry(), which computes: queue_begin + reader * sizeof(struct remote_input) with no bounds check. This unchecked MMIO address is then passed to memcpy_fromio(), reading 8 bytes from unintended device registers. For sufficiently large values the address falls outside the PCI BAR mapping entirely, triggering a machine check exception. Fix by checking both indices against REMOTE_QUEUE_SIZE at the top of the loop body, before any call to get_queue_entry(). On an out-of-range value, reset the reader register to 0 via set_queue_reader() before breaking, so that normal queue operation can resume if the corrupted hardware state is transient.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46023
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: dm mirror: fix integer overflow in create_dirty_log() The argument count calculation in create_dirty_log() performs `*args_used = 2 + param_count` before validating against argc. When a user provides a param_count close to UINT_MAX via the device mapper table string, this unsigned addition wraps around to a small value, causing the subsequent `argc < *args_used` check to be bypassed. The overflowed param_count is then passed as argc to dm_dirty_log_create(), where it can cause out-of-bounds reads on the argv array. Fix by comparing param_count against argc - 2 before performing the addition, following the same pattern used by parse_features() in the same file. Since argc >= 2 is already guaranteed, the subtraction is safe.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46024
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: libceph: Prevent potential null-ptr-deref in ceph_handle_auth_reply() If a message of type CEPH_MSG_AUTH_REPLY contains a zero value for both protocol and result, this is currently not treated as an error. In case of ac->negotiating == true and ac->protocol > 0, this leads to setting ac->protocol = 0 and ac->ops = NULL. Thereafter, the check for ac->protocol != protocol returns false, and init_protocol() is not called. Subsequently, ac->ops->handle_reply() is called, which leads to a null pointer dereference, because ac->ops is still NULL. This patch changes the check for ac->protocol != protocol to !ac->protocol, as this also includes the case when the protocol was set to zero in the message. This causes the message to be treated as containing a bad auth protocol.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46026
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: qrtr: ns: Limit the maximum number of lookups Current code does no bound checking on the number of lookups a client can perform. Though the code restricts the lookups to local clients, there is still a possibility of a malicious local client sending a flood of NEW_LOOKUP messages over the same socket. Fix this issue by limiting the maximum number of lookups to 64 globally. Since the nameserver allows only atmost one local observer, this global lookup count will ensure that the lookups stay within the limit. Note that, limit of 64 is chosen based on the current platform requirements. If requirement changes in the future, this limit can be increased.

Опубликовано: 2026-05-27Изменено: 2026-06-19
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46027
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: net/smc: avoid early lgr access in smc_clc_wait_msg A CLC decline can be received while the handshake is still in an early stage, before the connection has been associated with a link group. The decline handling in smc_clc_wait_msg() updates link-group level sync state for first-contact declines, but that state only exists after link group setup has completed. Guard the link-group update accordingly and keep the per-socket peer diagnosis handling unchanged. This preserves the existing sync_err handling for established link-group contexts and avoids touching link-group state before it is available.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46028
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: crypto: algif_aead - snapshot IV for async AEAD requests AF_ALG AEAD AIO requests currently use the socket-wide IV buffer during request processing. For async requests, later socket activity can update that shared state before the original request has fully completed, which can lead to inconsistent IV handling. Snapshot the IV into per-request storage when preparing the AEAD request, so in-flight operations no longer depend on mutable socket state.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46031
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: net: ks8851: Reinstate disabling of BHs around IRQ handler If the driver executes ks8851_irq() AND a TX packet has been sent, then the driver enables TX queue via netif_wake_queue() which schedules TX softirq to queue packets for this device. If CONFIG_PREEMPT_RT=y is set AND a packet has also been received by the MAC, then ks8851_rx_pkts() calls netdev_alloc_skb_ip_align() to allocate SKBs for the received packets. If netdev_alloc_skb_ip_align() is called with BH enabled, then local_bh_enable() at the end of netdev_alloc_skb_ip_align() will trigger the pending softirq processing, which may ultimately call the .xmit callback ks8851_start_xmit_par(). The ks8851_start_xmit_par() will try to lock struct ks8851_net_par .lock spinlock, which is already locked by ks8851_irq() from which ks8851_start_xmit_par() was called. This leads to a deadlock, which is reported by the kernel, including a trace listed below. If CONFIG_PREEMPT_RT is not set, then since commit 0913ec336a6c0 ("net: ks8851: Fix deadlock with the SPI chip variant") the deadlock can also be triggered without received packet in the RX FIFO. The pending softirqs will be processed on return from spin_unlock_bh(&ks->statelock) in ks8851_irq(), which triggers the deadlock as well. Fix the problem by disabling BH around critical sections, including the IRQ handler, thus preventing the net_tx_action() softirq from triggering during these critical sections. The net_tx_action() softirq is triggered once BH are re-enabled and at the end of the IRQ handler, once all the other IRQ handler actions have been completed. __schedule from schedule_rtlock+0x1c/0x34 schedule_rtlock from rtlock_slowlock_locked+0x548/0x904 rtlock_slowlock_locked from rt_spin_lock+0x60/0x9c rt_spin_lock from ks8851_start_xmit_par+0x74/0x1a8 ks8851_start_xmit_par from netdev_start_xmit+0x20/0x44 netdev_start_xmit from dev_hard_start_xmit+0xd0/0x188 dev_hard_start_xmit from sch_direct_xmit+0xb8/0x25c sch_direct_xmit from __qdisc_run+0x1f8/0x4ec __qdisc_run from qdisc_run+0x1c/0x28 qdisc_run from net_tx_action+0x1f0/0x268 net_tx_action from handle_softirqs+0x1a4/0x270 handle_softirqs from __local_bh_enable_ip+0xcc/0xe0 __local_bh_enable_ip from __alloc_skb+0xd8/0x128 __alloc_skb from __netdev_alloc_skb+0x3c/0x19c __netdev_alloc_skb from ks8851_irq+0x388/0x4d4 ks8851_irq from irq_thread_fn+0x24/0x64 irq_thread_fn from irq_thread+0x178/0x28c irq_thread from kthread+0x12c/0x138 kthread from ret_from_fork+0x14/0x28

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46033
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: crypto: authencesn - reject short ahash digests during instance creation authencesn requires either a zero authsize or an authsize of at least 4 bytes because the ESN encrypt/decrypt paths always move 4 bytes of high-order sequence number data at the end of the authenticated data. While crypto_authenc_esn_setauthsize() already rejects explicit non-zero authsizes in the range 1..3, crypto_authenc_esn_create() still copied auth->digestsize into inst->alg.maxauthsize without validating it. The AEAD core then initialized the tfm's default authsize from that value. As a result, selecting an ahash with digest size 1..3, such as cbcmac(cipher_null), exposed authencesn instances whose default authsize was invalid even though setauthsize() would have rejected the same value. AF_ALG could then trigger the ESN tail handling with a too-short tag and hit an out-of-bounds access. Reject authencesn instances whose ahash digest size is in the invalid non-zero range 1..3 so that no tfm can inherit an unsupported default authsize.

Опубликовано: 2026-05-27Изменено: 2026-06-30
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46034
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: vfio/cdx: Fix NULL pointer dereference in interrupt trigger path Add validation to ensure MSI is configured before accessing cdx_irqs array in vfio_cdx_set_msi_trigger(). Without this check, userspace can trigger a NULL pointer dereference by calling VFIO_DEVICE_SET_IRQS with VFIO_IRQ_SET_DATA_BOOL or VFIO_IRQ_SET_DATA_NONE flags before ever setting up interrupts via VFIO_IRQ_SET_DATA_EVENTFD. The vfio_cdx_msi_enable() function allocates the cdx_irqs array and sets config_msi to 1 only when called through the EVENTFD path. The trigger loop (for DATA_BOOL/DATA_NONE) assumed this had already been done, but there was no enforcement of this call ordering. This matches the protection used in the PCI VFIO driver where vfio_pci_set_msi_trigger() checks irq_is() before the trigger loop.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46036
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: vfio/cdx: Serialize VFIO_DEVICE_SET_IRQS with a per-device mutex vfio_cdx_set_msi_trigger() reads vdev->config_msi and operates on the vdev->cdx_irqs array based on its value, but provides no serialization against concurrent VFIO_DEVICE_SET_IRQS ioctls. Two callers can race such that one observes config_msi as set while another clears it and frees cdx_irqs via vfio_cdx_msi_disable(), resulting in a use-after-free of the cdx_irqs array. Add a cdx_irqs_lock mutex to struct vfio_cdx_device and acquire it in vfio_cdx_set_msi_trigger(), which is the single chokepoint through which all updates to config_msi, cdx_irqs, and msi_count flow, covering both the ioctl path and the close-device cleanup path. This keeps the test of config_msi atomic with the subsequent enable, disable, or trigger operations. Drop the pre-call !cdx_irqs test from vfio_cdx_irqs_cleanup() as part of this change: the optimization it provided is redundant with the !config_msi early-return inside vfio_cdx_msi_disable(), and leaving the test in place would be an unsynchronized read of state the new lock is meant to protect.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46037
HIGH8.2

In the Linux kernel, the following vulnerability has been resolved: ipv4: icmp: validate reply type before using icmp_pointers Extended echo replies use ICMP_EXT_ECHOREPLY as the outbound reply type. That value is outside the range covered by icmp_pointers[], which only describes the traditional ICMP types up to NR_ICMP_TYPES. Avoid consulting icmp_pointers[] for reply types outside that range, and use array_index_nospec() for the remaining in-range lookup. Normal ICMP replies keep their existing behavior unchanged.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.2
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H
Ссылки
CVE-2026-46038
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: qrtr: ns: Free the node during ctrl_cmd_bye() A node sends the BYE packet when it is about to go down. So the nameserver should advertise the removal of the node to all remote and local observers and free the node finally. But currently, the nameserver doesn't free the node memory even after processing the BYE packet. This causes the node memory to leak. Hence, remove the node from Xarray list and free the node memory during both success and failure case of ctrl_cmd_bye().

Опубликовано: 2026-05-27Изменено: 2026-06-19
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46040
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: inotify: fix watch count leak when fsnotify_add_inode_mark_locked() fails When fsnotify_add_inode_mark_locked() fails in inotify_new_watch(), the error path calls inotify_remove_from_idr() but does not call dec_inotify_watches() to undo the preceding inc_inotify_watches(). This leaks a watch count, and repeated failures can exhaust the max_user_watches limit with -ENOSPC even when no watches are active. Prior to commit 1cce1eea0aff ("inotify: Convert to using per-namespace limits"), the watch count was incremented after fsnotify_add_mark_locked() succeeded, so this path was not affected. The conversion moved inc_inotify_watches() before the mark insertion without adding the corresponding rollback. Add the missing dec_inotify_watches() call in the error path.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46041
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: greybus: gb-beagleplay: fix sleep in atomic context in hdlc_tx_frames() hdlc_append() calls usleep_range() to wait for circular buffer space, but it is called with tx_producer_lock (a spinlock) held via hdlc_tx_frames() -> hdlc_append_tx_frame()/hdlc_append_tx_u8()/etc. Sleeping while holding a spinlock is illegal and can trigger "BUG: scheduling while atomic". Fix this by moving the buffer-space wait out of hdlc_append() and into hdlc_tx_frames(), before the spinlock is acquired. The new flow: 1. Pre-calculate the worst-case encoded frame length. 2. Wait (with sleep) outside the lock until enough space is available, kicking the TX consumer work to drain the buffer. 3. Acquire the spinlock, re-verify space, and write the entire frame atomically. This ensures that sleeping only happens without any lock held, and that frames are either fully enqueued or not written at all. This bug is found by CodeQL static analysis tool (interprocedural sleep-in-atomic query) and my code review.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46043
CRITICAL9.1

In the Linux kernel, the following vulnerability has been resolved: RDMA/rxe: Validate pad and ICRC before payload_size() in rxe_rcv rxe_rcv() currently checks only that the incoming packet is at least header_size(pkt) bytes long before payload_size() is used. However, payload_size() subtracts both the attacker-controlled BTH pad field and RXE_ICRC_SIZE from pkt->paylen: payload_size = pkt->paylen - offset[RXE_PAYLOAD] - bth_pad(pkt) - RXE_ICRC_SIZE This means a short packet can still make payload_size() underflow even if it includes enough bytes for the fixed headers. Simply requiring header_size(pkt) + RXE_ICRC_SIZE is not sufficient either, because a packet with a forged non-zero BTH pad can still leave payload_size() negative and pass an underflowed value to later receive-path users. Fix this by validating pkt->paylen against the full minimum length required by payload_size(): header_size(pkt) + bth_pad(pkt) + RXE_ICRC_SIZE.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46046
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ext4: fix missing brelse() in ext4_xattr_inode_dec_ref_all() The commit c8e008b60492 ("ext4: ignore xattrs past end") introduced a refcount leak in when block_csum is false. ext4_xattr_inode_dec_ref_all() calls ext4_get_inode_loc() to get iloc.bh, but never releases it with brelse().

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46047
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: qrtr: ns: Fix use-after-free in driver remove() In the remove callback, if a packet arrives after destroy_workqueue() is called, but before sock_release(), the qrtr_ns_data_ready() callback will try to queue the work, causing use-after-free issue. Fix this issue by saving the default 'sk_data_ready' callback during qrtr_ns_init() and use it to replace the qrtr_ns_data_ready() callback at the start of remove(). This ensures that even if a packet arrives after destroy_workqueue(), the work struct will not be dereferenced. Note that it is also required to ensure that the RX threads are completed before destroying the workqueue, because the threads could be using the qrtr_ns_data_ready() callback.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46049
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ALSA: ctxfi: Add fallback to default RSR for S/PDIF spdif_passthru_playback_get_resources() uses atc->pll_rate as the RSR for the MSR calculation loop. However, pll_rate is only updated in atc_pll_init() and not in hw_pll_init(), so it remains 0 after the card init. When spdif_passthru_playback_setup() skips atc_pll_init() for 32000 Hz, (rsr * desc.msr) always becomes 0, causing the loop to spin indefinitely. Add fallback to use atc->rsr when atc->pll_rate is 0. This reflects the hardware state, since hw_card_init() already configures the PLL to the default RSR.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46050
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: md/raid10: fix deadlock with check operation and nowait requests When an array check is running it will raise the barrier at which point normal requests will become blocked and increment the nr_pending value to signal there is work pending inside of wait_barrier(). NOWAIT requests do not block and so will return immediately with an error, and additionally do not increment nr_pending in wait_barrier(). Upstream change commit 43806c3d5b9b ("raid10: cleanup memleak at raid10_make_request") added a call to raid_end_bio_io() to fix a memory leak when NOWAIT requests hit this condition. raid_end_bio_io() eventually calls allow_barrier() and it will unconditionally do an atomic_dec_and_test(&conf->nr_pending) even though the corresponding increment on nr_pending didn't happen in the NOWAIT case. This can be easily seen by starting a check operation while an application is doing nowait IO on the same array. This results in a deadlocked state due to nr_pending value underflowing and so the md resync thread gets stuck waiting for nr_pending to == 0. Output of r10conf state of the array when we hit this condition: crash> struct r10conf barrier = 1, nr_pending = { counter = -41 }, nr_waiting = 15, nr_queued = 0, Example of md_sync thread stuck waiting on raise_barrier() and other requests stuck in wait_barrier(): md1_resync [<0>] raise_barrier+0xce/0x1c0 [<0>] raid10_sync_request+0x1ca/0x1ed0 [<0>] md_do_sync+0x779/0x1110 [<0>] md_thread+0x90/0x160 [<0>] kthread+0xbe/0xf0 [<0>] ret_from_fork+0x34/0x50 [<0>] ret_from_fork_asm+0x1a/0x30 kworker/u1040:2+flush-253:4 [<0>] wait_barrier+0x1de/0x220 [<0>] regular_request_wait+0x30/0x180 [<0>] raid10_make_request+0x261/0x1000 [<0>] md_handle_request+0x13b/0x230 [<0>] __submit_bio+0x107/0x1f0 [<0>] submit_bio_noacct_nocheck+0x16f/0x390 [<0>] ext4_io_submit+0x24/0x40 [<0>] ext4_do_writepages+0x254/0xc80 [<0>] ext4_writepages+0x84/0x120 [<0>] do_writepages+0x7a/0x260 [<0>] __writeback_single_inode+0x3d/0x300 [<0>] writeback_sb_inodes+0x1dd/0x470 [<0>] __writeback_inodes_wb+0x4c/0xe0 [<0>] wb_writeback+0x18b/0x2d0 [<0>] wb_workfn+0x2a1/0x400 [<0>] process_one_work+0x149/0x330 [<0>] worker_thread+0x2d2/0x410 [<0>] kthread+0xbe/0xf0 [<0>] ret_from_fork+0x34/0x50 [<0>] ret_from_fork_asm+0x1a/0x30

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46051
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: md/raid5: fix soft lockup in retry_aligned_read() When retry_aligned_read() encounters an overlapped stripe, it releases the stripe via raid5_release_stripe() which puts it on the lockless released_stripes llist. In the next raid5d loop iteration, release_stripe_list() drains the stripe onto handle_list (since STRIPE_HANDLE is set by the original IO), but retry_aligned_read() runs before handle_active_stripes() and removes the stripe from handle_list via find_get_stripe() -> list_del_init(). This prevents handle_stripe() from ever processing the stripe to resolve the overlap, causing an infinite loop and soft lockup. Fix this by using __release_stripe() with temp_inactive_list instead of raid5_release_stripe() in the failure path, so the stripe does not go through the released_stripes llist. This allows raid5d to break out of its loop, and the overlap will be resolved when the stripe is eventually processed by handle_stripe().

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46052
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: ceph: only d_add() negative dentries when they are unhashed Ceph can call d_add(dentry, NULL) on a negative dentry that is already present in the primary dcache hash. In the current VFS that is not safe. d_add() goes through __d_add() to __d_rehash(), which unconditionally reinserts dentry->d_hash into the hlist_bl bucket. If the dentry is already hashed, reinserting the same node can corrupt the bucket, including creating a self-loop. Once that happens, __d_lookup() can spin forever in the hlist_bl walk, typically looping only on the d_name.hash mismatch check and eventually triggering RCU stall reports like this one: rcu: INFO: rcu_sched self-detected stall on CPU rcu: 87-....: (2100 ticks this GP) idle=3a4c/1/0x4000000000000000 softirq=25003319/25003319 fqs=829 rcu: (t=2101 jiffies g=79058445 q=698988 ncpus=192) CPU: 87 UID: 2952868916 PID: 3933303 Comm: php-cgi8.3 Not tainted 6.18.17-i1-amd #950 NONE Hardware name: Dell Inc. PowerEdge R7615/0G9DHV, BIOS 1.6.6 09/22/2023 RIP: 0010:__d_lookup+0x46/0xb0 Code: c1 e8 07 48 8d 04 c2 48 8b 00 49 89 fc 49 89 f5 48 89 c3 48 83 e3 fe 48 83 f8 01 77 0f eb 2d 0f 1f 44 00 00 48 8b 1b 48 85 db <74> 20 39 6b 18 75 f3 48 8d 7b 78 e8 ba 85 d0 00 4c 39 63 10 74 1f RSP: 0018:ff745a70c8253898 EFLAGS: 00000282 RAX: ff26e470054cb208 RBX: ff26e470054cb208 RCX: 000000006e958966 RDX: ff26e48267340000 RSI: ff745a70c82539b0 RDI: ff26e458f74655c0 RBP: 000000006e958966 R08: 0000000000000180 R09: 9cd08d909b919a89 R10: ff26e458f74655c0 R11: 0000000000000000 R12: ff26e458f74655c0 R13: ff745a70c82539b0 R14: d0d0d0d0d0d0d0d0 R15: 2f2f2f2f2f2f2f2f FS: 00007f5770896980(0000) GS:ff26e482c5d88000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f5764de50c0 CR3: 000000a72abb5001 CR4: 0000000000771ef0 PKRU: 55555554 Call Trace: lookup_fast+0x9f/0x100 walk_component+0x1f/0x150 link_path_walk+0x20e/0x3d0 path_lookupat+0x68/0x180 filename_lookup+0xdc/0x1e0 vfs_statx+0x6c/0x140 vfs_fstatat+0x67/0xa0 __do_sys_newfstatat+0x24/0x60 do_syscall_64+0x6a/0x230 entry_SYSCALL_64_after_hwframe+0x76/0x7e This is reachable with reused cached negative dentries. A Ceph lookup or atomic_open can be handed a negative dentry that is already hashed, and fs/ceph/dir.c then hits one of two paths that incorrectly assume "negative" also means "unhashed": - ceph_finish_lookup(): MDS reply is -ENOENT with no trace -> d_add(dentry, NULL) - ceph_lookup(): local ENOENT fast path for a complete directory with shared caps -> d_add(dentry, NULL) Both paths can therefore re-add an already-hashed negative dentry. Ceph already uses the correct pattern elsewhere: ceph_fill_trace() only calls d_add(dn, NULL) for a negative null-dentry reply when d_unhashed(dn) is true. Fix both fs/ceph/dir.c sites the same way: only call d_add() for a negative dentry when it is actually unhashed. If the negative dentry is already hashed, leave it in place and reuse it as-is. This preserves the existing behavior for unhashed dentries while avoiding d_hash list corruption for reused hashed negatives.

Опубликовано: 2026-05-27Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46053
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: rds: fix MR cleanup on copy error __rds_rdma_map() hands sg/pages ownership to the transport after get_mr() succeeds. If copying the generated cookie back to user space fails after that point, the error path must not free those resources again before dropping the MR reference. Remove the duplicate unpin/free from the put_user() failure branch so that MR teardown is handled only through the existing final cleanup path.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46056
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_event: fix potential UAF in SSP passkey handlers hci_conn lookup and field access must be covered by hdev lock in hci_user_passkey_notify_evt() and hci_keypress_notify_evt(), otherwise the connection can be freed concurrently. Extend the hci_dev_lock critical section to cover all conn usage in both handlers. Keep the existing keypress notification behavior unchanged by routing the early exits through a common unlock path.

Опубликовано: 2026-05-27Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46058
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: media: amphion: Fix race between m2m job_abort and device_run Fix kernel panic caused by race condition where v4l2_m2m_ctx_release() frees m2m_ctx while v4l2_m2m_try_run() is about to call device_run with the same context. Race sequence: v4l2_m2m_try_run(): v4l2_m2m_ctx_release(): lock/unlock v4l2_m2m_cancel_job() job_abort() v4l2_m2m_job_finish() kfree(m2m_ctx) <- frees ctx device_run() <- use-after-free crash at 0x538 Crash trace: Unable to handle kernel read from unreadable memory at virtual address 0000000000000538 v4l2_m2m_try_run+0x78/0x138 v4l2_m2m_device_run_work+0x14/0x20 The amphion vpu driver does not rely on the m2m framework's device_run callback to perform encode/decode operations. Fix the race by preventing m2m framework job scheduling entirely: - Add job_ready callback returning 0 (no jobs ready for m2m framework) - Remove job_abort callback to avoid the race condition

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46061
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: jbd2: fix deadlock in jbd2_journal_cancel_revoke() Commit f76d4c28a46a ("fs/jbd2: use sleeping version of __find_get_block()") changed jbd2_journal_cancel_revoke() to use __find_get_block_nonatomic() which holds the folio lock instead of i_private_lock. This breaks the lock ordering (folio -> buffer) and causes an ABBA deadlock when the filesystem blocksize < pagesize: T1 T2 ext4_mkdir() ext4_init_new_dir() ext4_append() ext4_getblk() lock_buffer() <- A sync_blockdev() blkdev_writepages() writeback_iter() writeback_get_folio() folio_lock() <- B ext4_journal_get_create_access() jbd2_journal_cancel_revoke() __find_get_block_nonatomic() folio_lock() <- B block_write_full_folio() lock_buffer() <- A This can occasionally cause generic/013 to hang. Fix by only calling __find_get_block_nonatomic() when the passed buffer_head doesn't belong to the bdev, which is the only case that we need to look up its bdev alias. Otherwise, the lookup is redundant since the found buffer_head is equal to the one we passed in.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46062
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ntfs3: fix integer overflow in run_unpack() volume boundary check The volume boundary check `lcn + len > sbi->used.bitmap.nbits` uses raw addition which can wrap around for large lcn and len values, bypassing the validation. Use check_add_overflow() as is already done for the adjacent prev_lcn + dlcn and vcn64 + len checks added by commit 3ac37e100385 ("ntfs3: Fix integer overflow in run_unpack()"). Found by fuzzing with a source-patched harness (LibAFL + QEMU).

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46063
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: x86/shstk: Prevent deadlock during shstk sigreturn During sigreturn the shadow stack signal frame is popped. The kernel does this by reading the shadow stack using normal read accesses. When it can't assume the memory is shadow stack, it takes extra steps to makes sure it is reading actual shadow stack memory and not other normal readable memory. It does this by holding the mmap read lock while doing the access and checking the flags of the VMA. Unfortunately that is not safe. If the read of the shadow stack sigframe hits a page fault, the fault handler will try to recursively grab another mmap read lock. This normally works ok, but if a writer on another CPU is also waiting, the second read lock could fail and cause a deadlock. Fix this by not holding mmap lock during the read access to userspace. Instead use mmap_lock_speculate_...() to watch for changes between dropping mmap lock and the userspace access. Retry if anything grabbed an mmap write lock in between and could have changed the VMA. These mmap_lock_speculate_...() helpers use mm::mm_lock_seq, which is only available when PER_VMA_LOCK is configured. So make X86_USER_SHADOW_STACK depend on it. On x86, PER_VMA_LOCK is a default configuration for SMP kernels. So drop support for the other configs under the assumption that the !SMP shadow stack user base does not exist. Currently there is a check that skips the lookup work when the SSP can be assumed to be on a shadow stack. While reorganizing the function, remove the optimization to make the tricky code flows more common, such that issues like this cannot escape detection for so long.

Опубликовано: 2026-05-27Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46064
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: ibmasm: fix heap over-read in ibmasm_send_i2o_message() The ibmasm_send_i2o_message() function uses get_dot_command_size() to compute the byte count for memcpy_toio(), but this value is derived from user-controlled fields in the dot_command_header (command_size: u8, data_size: u16) and is never validated against the actual allocation size. A root user can write a small buffer with inflated header fields, causing memcpy_toio() to read up to ~65 KB past the end of the allocation into adjacent kernel heap, which is then forwarded to the service processor over MMIO. Silently clamping the copy size is not sufficient: if the header fields claim a larger size than the buffer, the SP receives a dot command whose own header is inconsistent with the I2O message length, which can cause the SP to desynchronize. Reject such commands outright by returning failure. Validate command_size before calling get_mfa_inbound() to avoid leaking an I2O message frame: reading INBOUND_QUEUE_PORT dequeues a hardware frame from the controller's free pool, and returning without a corresponding set_mfa_inbound() call would permanently exhaust it. Additionally, clamp command_size to I2O_COMMAND_SIZE before the memcpy_toio() so the MMIO write stays within the I2O message frame, consistent with the clamping already performed by outgoing_message_size() for the header field.

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46065
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: fbdev: defio: Disconnect deferred I/O from the lifetime of struct fb_info Hold state of deferred I/O in struct fb_deferred_io_state. Allocate an instance as part of initializing deferred I/O and remove it only after the final mapping has been closed. If the fb_info and the contained deferred I/O meanwhile goes away, clear struct fb_deferred_io_state.info to invalidate the mapping. Any access will then result in a SIGBUS signal. Fixes a long-standing problem, where a device hot-unplug happens while user space still has an active mapping of the graphics memory. The hot- unplug frees the instance of struct fb_info. Accessing the memory will operate on undefined state.

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46068
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: crypto: nx - fix bounce buffer leaks in nx842_crypto_{alloc,free}_ctx The bounce buffers are allocated with __get_free_pages() using BOUNCE_BUFFER_ORDER (order 2 = 4 pages), but both the allocation error path and nx842_crypto_free_ctx() release the buffers with free_page(). Use free_pages() with the matching order instead.

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46069
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: wifi: mwifiex: fix use-after-free in mwifiex_adapter_cleanup() The mwifiex_adapter_cleanup() function uses timer_delete() (non-synchronous) for the wakeup_timer before the adapter structure is freed. This is incorrect because timer_delete() does not wait for any running timer callback to complete. If the wakeup_timer callback (wakeup_timer_fn) is executing when mwifiex_adapter_cleanup() is called, the callback will continue to access adapter fields (adapter->hw_status, adapter->if_ops.card_reset, etc.) which may be freed by mwifiex_free_adapter() called later in the mwifiex_remove_card() path. Use timer_delete_sync() instead to ensure any running timer callback has completed before returning.

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46070
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: md/raid5: validate payload size before accessing journal metadata r5c_recovery_analyze_meta_block() and r5l_recovery_verify_data_checksum_for_mb() iterate over payloads in a journal metadata block using on-disk payload size fields without validating them against the remaining space in the metadata block. A corrupted journal contains payload sizes extending beyond the PAGE_SIZE boundary can cause out-of-bounds reads when accessing payload fields or computing offsets. Add bounds validation for each payload type to ensure the full payload fits within meta_size before processing.

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46072
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ntfs3: add buffer boundary checks to run_unpack() run_unpack() checks `run_buf < run_last` at the top of the while loop but then reads size_size and offset_size bytes via run_unpack_s64() without verifying they fit within the remaining buffer. A crafted NTFS image with truncated run data in an MFT attribute triggers an OOB heap read of up to 15 bytes when the filesystem is mounted. Add boundary checks before each run_unpack_s64() call to ensure the declared field size does not exceed the remaining buffer. Found by fuzzing with a source-patched harness (LibAFL + QEMU).

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46073
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: hwmon: (powerz) Fix missing usb_kill_urb() on signal interrupt wait_for_completion_interruptible_timeout() returns -ERESTARTSYS when interrupted. This needs to abort the URB and return an error. No data has been received from the device so any reads from the transfer buffer are invalid. The original code tests !ret, which only catches the timeout case (0). On signal delivery (-ERESTARTSYS), !ret is false so the function skips usb_kill_urb() and falls through to read from the unfilled transfer buffer. Fix by capturing the return value into a long (matching the function return type) and handling signal (negative) and timeout (zero) cases with separate checks that both call usb_kill_urb() before returning.

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46074
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: spi: ch341: fix memory leaks on probe failures Make sure to deregister the controller, disable pins, and kill and free the RX URB on probe failures to mirror disconnect and avoid memory leaks and use-after-free. Also add an explicit URB kill on disconnect for symmetry (even if that is not strictly required as USB core would have stopped it in the current setup).

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46075
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: crypto: atmel-sha204a - Fix potential UAF and memory leak in remove path Unregister the hwrng to prevent new ->read() calls and flush the Atmel I2C workqueue before teardown to prevent a potential UAF if a queued callback runs while the device is being removed. Drop the early return to ensure sysfs entries are removed and ->hwrng.priv is freed, preventing a memory leak.

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46076
HIGH7.9

In the Linux kernel, the following vulnerability has been resolved: KVM: nSVM: Raise #UD if unhandled VMMCALL isn't intercepted by L1 Explicitly synthesize a #UD for VMMCALL if L2 is active, L1 does NOT want to intercept VMMCALL, nested_svm_l2_tlb_flush_enabled() is true, and the hypercall is something other than one of the supported Hyper-V hypercalls. When all of the above conditions are met, KVM will intercept VMMCALL but never forward it to L1, i.e. will let L2 make hypercalls as if it were L1. The TLFS says a whole lot of nothing about this scenario, so go with the architectural behavior, which says that VMMCALL #UDs if it's not intercepted. Opportunistically do a 2-for-1 stub trade by stub-ifying the new API instead of the helpers it uses. The last remaining "single" stub will soon be dropped as well. [sean: rewrite changelog and comment, tag for stable, remove defunct stubs]

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.9
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:L/I:L/A:H
Ссылки
CVE-2026-46077
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: crypto: atmel-tdes - fix DMA sync direction Before DMA output is consumed by the CPU, ->dma_addr_out must be synced with dma_sync_single_for_cpu() instead of dma_sync_single_for_device(). Using the wrong direction can return stale cache data on non-coherent platforms.

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46078
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: erofs: fix the out-of-bounds nameoff handling for trailing dirents Currently we already have boundary-checks for nameoffs, but the trailing dirents are special since the namelens are calculated with strnlen() with unchecked nameoffs. If a crafted EROFS has a trailing dirent with nameoff >= maxsize, maxsize - nameoff can underflow, causing strnlen() to read past the directory block. nameoff0 should also be verified to be a multiple of `sizeof(struct erofs_dirent)` as well [1]. [1] https://sashiko.dev/#/patchset/20260416063511.3173774-1-hsiangkao%40linux.alibaba.com

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46079
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: rbd: fix null-ptr-deref when device_add_disk() fails do_rbd_add() publishes the device with device_add() before calling device_add_disk(). If device_add_disk() fails after device_add() succeeds, the error path calls rbd_free_disk() directly and then later falls through to rbd_dev_device_release(), which calls rbd_free_disk() again. This double teardown can leave blk-mq cleanup operating on invalid state and trigger a null-ptr-deref in __blk_mq_free_map_and_rqs(), reached from blk_mq_free_tag_set(). Fix this by following the normal remove ordering: call device_del() before rbd_dev_device_release() when device_add_disk() fails after device_add(). That keeps the teardown sequence consistent and avoids re-entering disk cleanup through the wrong path. The bug was first flagged by an experimental analysis tool we are developing for kernel memory-management bugs while analyzing v6.13-rc1. The tool is still under development and is not yet publicly available. We reproduced the bug on v7.0 with a real Ceph backend and a QEMU x86_64 guest booted with KASAN and CONFIG_FAILSLAB enabled. The reproducer confines failslab injections to the __add_disk() range and injects fail-nth while mapping an RBD image through /sys/bus/rbd/add_single_major. On the unpatched kernel, fail-nth=4 reliably triggered the fault: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 0 UID: 0 PID: 273 Comm: bash Not tainted 7.0.0-01247-gd60bc1401583 #6 PREEMPT(lazy) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014 RIP: 0010:__blk_mq_free_map_and_rqs+0x8c/0x240 Code: 00 00 48 8b 6b 60 41 89 f4 49 c1 e4 03 4c 01 e5 45 85 ed 0f 85 0a 01 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 e9 48 c1 e9 03 <80> 3c 01 00 0f 85 31 01 00 00 4c 8b 6d 00 4d 85 ed 0f 84 e2 00 00 RSP: 0018:ff1100000ab0fac8 EFLAGS: 00000246 RAX: dffffc0000000000 RBX: ff1100000c4806a0 RCX: 0000000000000000 RDX: 0000000000000002 RSI: 0000000000000000 RDI: ff1100000c4806f4 RBP: 0000000000000000 R08: 0000000000000001 R09: ffe21c000189001b R10: ff1100000c4800df R11: ff1100006cf37be0 R12: 0000000000000000 R13: 0000000000000000 R14: ff1100000c480700 R15: ff1100000c480004 FS: 00007f0fbe8fe740(0000) GS:ff110000e5851000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe53473b2e0 CR3: 0000000012eef000 CR4: 00000000007516f0 PKRU: 55555554 Call Trace: blk_mq_free_tag_set+0x77/0x460 do_rbd_add+0x1446/0x2b80 ? __pfx_do_rbd_add+0x10/0x10 ? lock_acquire+0x18c/0x300 ? find_held_lock+0x2b/0x80 ? sysfs_file_kobj+0xb6/0x1b0 ? __pfx_sysfs_kf_write+0x10/0x10 kernfs_fop_write_iter+0x2f4/0x4a0 vfs_write+0x98e/0x1000 ? expand_files+0x51f/0x850 ? __pfx_vfs_write+0x10/0x10 ksys_write+0xf2/0x1d0 ? __pfx_ksys_write+0x10/0x10 do_syscall_64+0x115/0x690 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f0fbea15907 Code: 10 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24 RSP: 002b:00007ffe22346ea8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000058 RCX: 00007f0fbea15907 RDX: 0000000000000058 RSI: 0000563ace6c0ef0 RDI: 0000000000000001 RBP: 0000563ace6c0ef0 R08: 0000563ace6c0ef0 R09: 6b6435726d694141 R10: 5250337279762f78 R11: 0000000000000246 R12: 0000000000000058 R13: 00007f0fbeb1c780 R14: ff1100000c480700 R15: ff1100000c480004 With this fix applied, rerunning the reproducer over fail-nth=1..256 yields no KASAN reports. [ idryomov: rename err_out_device_del -> err_out_device ]

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46080
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ocfs2: split transactions in dio completion to avoid credit exhaustion During ocfs2 dio operations, JBD2 may report warnings via following call trace: ocfs2_dio_end_io_write ocfs2_mark_extent_written ocfs2_change_extent_flag ocfs2_split_extent ocfs2_try_to_merge_extent ocfs2_extend_rotate_transaction ocfs2_extend_trans jbd2__journal_restart start_this_handle output: JBD2: kworker/6:2 wants too many credits credits:5450 rsv_credits:0 max:5449 To prevent exceeding the credits limit, modify ocfs2_dio_end_io_write() to handle extents in a batch of transaction. Additionally, relocate ocfs2_del_inode_from_orphan(). The orphan inode should only be removed from the orphan list after the extent tree update is complete. This ensures that if a crash occurs in the middle of extent tree updates, we won't leave stale blocks beyond EOF. This patch also changes the logic for updating the inode size and removing orphan, making it similar to ext4_dio_write_end_io(). Both operations are performed only when everything looks good. Finally, thanks to Jans and Joseph for providing the bug fix prototype and suggestions.

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46082
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: KVM: SVM: Inject #UD for INVLPGA if EFER.SVME=0 INVLPGA should cause a #UD when EFER.SVME is not set. Add a check to properly inject #UD when EFER.SVME=0. [sean: tag for stable@]

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46083
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: spi: fix resource leaks on device setup failure Make sure to call controller cleanup() if spi_setup() fails while registering a device to avoid leaking any resources allocated by setup().

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46084
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: RDMA/mana_ib: Disable RX steering on RSS QP destroy When an RSS QP is destroyed (e.g. DPDK exit), mana_ib_destroy_qp_rss() destroys the RX WQ objects but does not disable vPort RX steering in firmware. This leaves stale steering configuration that still points to the destroyed RX objects. If traffic continues to arrive (e.g. peer VM is still transmitting) and the VF interface is subsequently brought up (mana_open), the firmware may deliver completions using stale CQ IDs from the old RX objects. These CQ IDs can be reused by the ethernet driver for new TX CQs, causing RX completions to land on TX CQs: WARNING: mana_poll_tx_cq+0x1b8/0x220 [mana] (is_sq == false) WARNING: mana_gd_process_eq_events+0x209/0x290 (cq_table lookup fails) Fix this by disabling vPort RX steering before destroying RX WQ objects. Note that mana_fence_rqs() cannot be used here because the fence completion is delivered on the CQ, which is polled by user-mode (e.g. DPDK) and not visible to the kernel driver. Refactor the disable logic into a shared mana_disable_vport_rx() in mana_en, exported for use by mana_ib, replacing the duplicate code. The ethernet driver's mana_dealloc_queues() is also updated to call this common function.

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46086
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: bridge: use a stable FDB dst snapshot in RCU readers Local FDB entries can be rewritten in place by `fdb_delete_local()`, which updates `f->dst` to another port or to `NULL` while keeping the entry alive. Several bridge RCU readers inspect `f->dst`, including `br_fdb_fillbuf()` through the `brforward_read()` sysfs path. These readers currently load `f->dst` multiple times and can therefore observe inconsistent values across the check and later dereference. In `br_fdb_fillbuf()`, this means a concurrent local-FDB update can change `f->dst` after the NULL check and before the `port_no` dereference, leading to a NULL-ptr-deref. Fix this by taking a single `READ_ONCE()` snapshot of `f->dst` in each affected RCU reader and using that snapshot for the rest of the access sequence. Also publish the in-place `f->dst` updates in `fdb_delete_local()` with `WRITE_ONCE()` so the readers and writer use matching access patterns.

Опубликовано: 2026-05-27Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46088
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ALSA: control: Validate buf_len before strnlen() in snd_ctl_elem_init_enum_names() snd_ctl_elem_init_enum_names() advances pointer p through the names buffer while decrementing buf_len. If buf_len reaches zero but items remain, the next iteration calls strnlen(p, 0). While strnlen(p, 0) returns 0 and would hit the existing name_len == 0 error path, CONFIG_FORTIFY_SOURCE's fortified strnlen() first checks maxlen against __builtin_dynamic_object_size(). When Clang loses track of p's object size inside the loop, this triggers a BRK exception panic before the return value is examined. Add a buf_len == 0 guard at the loop entry to prevent calling fortified strnlen() on an exhausted buffer. Found by kernel fuzz testing through Xiaomi Smartphone.

Опубликовано: 2026-05-27Изменено: 2026-06-25
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46089
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: zram: do not forget to endio for partial discard requests As reported by Qu Wenruo and Avinesh Kumar, the following getconf PAGESIZE 65536 blkdiscard -p 4k /dev/zram0 takes literally forever to complete. zram doesn't support partial discards and just returns immediately w/o doing any discard work in such cases. The problem is that we forget to endio on our way out, so blkdiscard sleeps forever in submit_bio_wait(). Fix this by jumping to end_bio label, which does bio_endio().

Опубликовано: 2026-05-27Изменено: 2026-06-25
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46090
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ALSA: aloop: Fix peer runtime UAF during format-change stop loopback_check_format() may stop the capture side when playback starts with parameters that no longer match a running capture stream. Commit 826af7fa62e3 ("ALSA: aloop: Fix racy access at PCM trigger") moved the peer lookup under cable->lock, but the actual snd_pcm_stop() still runs after dropping that lock. A concurrent close can clear the capture entry from cable->streams[] and detach or free its runtime while the playback trigger path still holds a stale peer substream pointer. Keep a per-cable count of in-flight peer stops before dropping cable->lock, and make free_cable() wait for those stops before detaching the runtime. This preserves the existing behavior while making the peer runtime lifetime explicit.

Опубликовано: 2026-05-27Изменено: 2026-07-07
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46091
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: media: rc: igorplugusb: heed coherency rules In a control request, the USB request structure can be subject to DMA on some HCs. Hence it must obey the rules for DMA coherency. Allocate it separately.

Опубликовано: 2026-05-27Изменено: 2026-06-25
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46094
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: ext4: fix bounds check in check_xattrs() to prevent out-of-bounds access The bounds check for the next xattr entry in check_xattrs() uses (void *)next >= end, which allows next to point within sizeof(u32) bytes of end. On the next loop iteration, IS_LAST_ENTRY() reads 4 bytes via *(__u32 *)(entry), which can overrun the valid xattr region. For example, if next lands at end - 1, the check passes since next < end, but IS_LAST_ENTRY() reads 4 bytes starting at end - 1, accessing 3 bytes beyond the valid region. Fix this by changing the check to (void *)next + sizeof(u32) > end, ensuring there is always enough space for the IS_LAST_ENTRY() read on the subsequent iteration.

Опубликовано: 2026-05-27Изменено: 2026-06-25
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46098
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: caif: clear client service pointer on teardown `caif_connect()` can tear down an existing client after remote shutdown by calling `caif_disconnect_client()` followed by `caif_free_client()`. `caif_free_client()` releases the service layer referenced by `adap_layer->dn`, but leaves that pointer stale. When the socket is later destroyed, `caif_sock_destructor()` calls `caif_free_client()` again and dereferences the freed service pointer. Clear the client/service links before releasing the service object so repeated teardown becomes harmless.

Опубликовано: 2026-05-27Изменено: 2026-06-25
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46099
HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: net: ipv6: fix NOREF dst use in seg6 and rpl lwtunnels seg6_input_core() and rpl_input() call ip6_route_input() which sets a NOREF dst on the skb, then pass it to dst_cache_set_ip6() invoking dst_hold() unconditionally. On PREEMPT_RT, ksoftirqd is preemptible and a higher-priority task can release the underlying pcpu_rt between the lookup and the caching through a concurrent FIB lookup on a shared nexthop. Simplified race sequence: ksoftirqd/X higher-prio task (same CPU X) ----------- -------------------------------- seg6_input_core(,skb)/rpl_input(skb) dst_cache_get() -> miss ip6_route_input(skb) -> ip6_pol_route(,skb,flags) [RT6_LOOKUP_F_DST_NOREF in flags] -> FIB lookup resolves fib6_nh [nhid=N route] -> rt6_make_pcpu_route() [creates pcpu_rt, refcount=1] pcpu_rt->sernum = fib6_sernum [fib6_sernum=W] -> cmpxchg(fib6_nh.rt6i_pcpu, NULL, pcpu_rt) [slot was empty, store succeeds] -> skb_dst_set_noref(skb, dst) [dst is pcpu_rt, refcount still 1] rt_genid_bump_ipv6() -> bumps fib6_sernum [fib6_sernum from W to Z] ip6_route_output() -> ip6_pol_route() -> FIB lookup resolves fib6_nh [nhid=N] -> rt6_get_pcpu_route() pcpu_rt->sernum != fib6_sernum [W <> Z, stale] -> prev = xchg(rt6i_pcpu, NULL) -> dst_release(prev) [prev is pcpu_rt, refcount 1->0, dead] dst = skb_dst(skb) [dst is the dead pcpu_rt] dst_cache_set_ip6(dst) -> dst_hold() on dead dst -> WARN / use-after-free For the race to occur, ksoftirqd must be preemptible (PREEMPT_RT without PREEMPT_RT_NEEDS_BH_LOCK) and a concurrent task must be able to release the pcpu_rt. Shared nexthop objects provide such a path, as two routes pointing to the same nhid share the same fib6_nh and its rt6i_pcpu entry. Fix seg6_input_core() and rpl_input() by calling skb_dst_force() after ip6_route_input() to force the NOREF dst into a refcounted one before caching. The output path is not affected as ip6_route_output() already returns a refcounted dst.

Опубликовано: 2026-05-27Изменено: 2026-06-30
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46101
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: reject zero shift in nft_bitwise Reject zero shift operands for nft_bitwise left and right shift expressions during initialization. The carry propagation logic computes the carry from the adjacent 32-bit word using BITS_PER_TYPE(u32) - shift. A zero shift operand turns this into a 32-bit shift, which is undefined behaviour. Reject zero shift operands in the control plane, alongside the existing check for values greater than or equal to 32, so malformed rules never reach the packet path.

Опубликовано: 2026-05-27Изменено: 2026-06-25
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46102
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: net: strparser: fix skb_head leak in strp_abort_strp() When the stream parser is aborted, for example after a message assembly timeout, it can still hold a reference to a partially assembled message in strp->skb_head. That skb is not released in strp_abort_strp(), which leaks the partially assembled message and can be triggered repeatedly to exhaust memory. Fix this by freeing strp->skb_head and resetting the parser state in the abort path. Leave strp_stop() unchanged so final cleanup still happens in strp_done() after the work and timer have been synchronized.

Опубликовано: 2026-05-27Изменено: 2026-06-25
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46103
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: can: ucan: 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 control message buffer lifetime so that it is released on driver unbind.

Опубликовано: 2026-05-27Изменено: 2026-06-25
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46106
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: eventfs: Hold eventfs_mutex and SRCU when remount walks events Commit 340f0c7067a9 ("eventfs: Update all the eventfs_inodes from the events descriptor") had eventfs_set_attrs() recurse through ei->children on remount. The walk only holds the rcu_read_lock() taken by tracefs_apply_options() over tracefs_inodes, which is wrong: - list_for_each_entry over ei->children races with the list_del_rcu() in eventfs_remove_rec() -- LIST_POISON1 deref, same shape as d2603279c7d6. - eventfs_inodes are freed via call_srcu(&eventfs_srcu, ...). rcu_read_lock() does not extend an SRCU grace period, so ti->private can be reclaimed under the walk. - The writes to ei->attr race with eventfs_set_attr(), which holds eventfs_mutex. Reproducer: while :; do mount -o remount,uid=$((RANDOM%1000)) /sys/kernel/tracing; done & while :; do echo "p:kp submit_bio" > /sys/kernel/tracing/kprobe_events echo > /sys/kernel/tracing/kprobe_events done Wrap the events portion of tracefs_apply_options() in eventfs_remount_lock()/_unlock() that take eventfs_mutex and srcu_read_lock(&eventfs_srcu). eventfs_set_attrs() doesn't sleep so the nested rcu_read_lock() is fine; lockdep_assert_held() pins the contract. Comment in tracefs_drop_inode() said "RCU cycle" -- it is SRCU.

Опубликовано: 2026-05-28Изменено: 2026-06-25
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46107
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: dm-thin: fix metadata refcount underflow There's a bug in dm-thin in the function rebalance_children. If the internal btree node has one entry, the code tries to copy all btree entries from the node's child to the node itself and then decrement the child's reference count. If the child node is shared (it has reference count > 1), we won't free it, so there would be two pointers to each of the grandchildren nodes. But the reference counts of the grandchildren is not increased, thus the reference count doesn't match the number of pointers that point to the grandchildren. This results in "device mapper: space map common: unable to decrement block" errors. Fix this bug by incrementing reference counts on the grandchildren if the btree node is shared.

Опубликовано: 2026-05-28Изменено: 2026-06-25
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46108
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ipmi:si: Return state to normal if message allocation fails There were places where nothing would get started if a message allocation failed, so the driver needs to return to normal state.

Опубликовано: 2026-05-28Изменено: 2026-06-25
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46110
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: net: stmmac: Prevent NULL deref when RX memory exhausted The CPU receives frames from the MAC through conventional DMA: the CPU allocates buffers for the MAC, then the MAC fills them and returns ownership to the CPU. For each hardware RX queue, the CPU and MAC coordinate through a shared ring array of DMA descriptors: one descriptor per DMA buffer. Each descriptor includes the buffer's physical address and a status flag ("OWN") indicating which side owns the buffer: OWN=0 for CPU, OWN=1 for MAC. The CPU is only allowed to set the flag and the MAC is only allowed to clear it, and both must move through the ring in sequence: thus the ring is used for both "submissions" and "completions." In the stmmac driver, stmmac_rx() bookmarks its position in the ring with the `cur_rx` index. The main receive loop in that function checks for rx_descs[cur_rx].own=0, gives the corresponding buffer to the network stack (NULLing the pointer), and increments `cur_rx` modulo the ring size. After the loop exits, stmmac_rx_refill(), which bookmarks its position with `dirty_rx`, allocates fresh buffers and rearms the descriptors (setting OWN=1). If it fails any allocation, it simply stops early (leaving OWN=0) and will retry where it left off when next called. This means descriptors have a three-stage lifecycle (terms my own): - `empty` (OWN=1, buffer valid) - `full` (OWN=0, buffer valid and populated) - `dirty` (OWN=0, buffer NULL) But because stmmac_rx() only checks OWN, it confuses `full`/`dirty`. In the past (see 'Fixes:'), there was a bug where the loop could cycle `cur_rx` all the way back to the first descriptor it dirtied, resulting in a NULL dereference when mistaken for `full`. The aforementioned commit resolved that *specific* failure by capping the loop's iteration limit at `dma_rx_size - 1`, but this is only a partial fix: if the previous stmmac_rx_refill() didn't complete, then there are leftover `dirty` descriptors that the loop might encounter without needing to cycle fully around. The current code therefore panics (see 'Closes:') when stmmac_rx_refill() is memory-starved long enough for `cur_rx` to catch up to `dirty_rx`. Fix this by explicitly checking, before advancing `cur_rx`, if the next entry is dirty; exit the loop if so. This prevents processing of the final, used descriptor until stmmac_rx_refill() succeeds, but fully prevents the `cur_rx == dirty_rx` ambiguity as the previous bugfix intended: so remove the clamp as well. Since stmmac_rx_zc() is a copy-paste-and-tweak of stmmac_rx() and the code structure is identical, any fix to stmmac_rx() will also need a corresponding fix for stmmac_rx_zc(). Therefore, apply the same check there. In stmmac_rx() (not stmmac_rx_zc()), a related bug remains: after the MAC sets OWN=0 on the final descriptor, it will be unable to send any further DMA-complete IRQs until it's given more `empty` descriptors. Currently, the driver simply *hopes* that the next stmmac_rx_refill() succeeds, risking an indefinite stall of the receive process if not. But this is not a regression, so it can be addressed in a future change.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46111
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_conn: fix potential UAF in create_big_sync Add hci_conn_valid() check in create_big_sync() to detect stale connections before proceeding with BIG creation. Handle the resulting -ECANCELED in create_big_complete() and re-validate the connection under hci_dev_lock() before dereferencing, matching the pattern used by create_le_conn_complete() and create_pa_complete(). Keep the hci_conn object alive across the async boundary by taking a reference via hci_conn_get() when queueing create_big_sync(), and dropping it in the completion callback. The refcount and the lock are complementary: the refcount keeps the object allocated, while hci_dev_lock() serializes hci_conn_hash_del()'s list_del_rcu() on hdev->conn_hash, as required by hci_conn_del(). hci_conn_put() is called outside hci_dev_unlock() so the final put (which resolves to kfree() via bt_link_release) does not run under hdev->lock, though the release path would be safe either way. Without this, create_big_complete() would unconditionally dereference the conn pointer on error, causing a use-after-free via hci_connect_cfm() and hci_conn_del().

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46112
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: RDMA/hns: Fix unlocked call to hns_roce_qp_remove() Sashiko points out that hns_roce_qp_remove() requires the caller to hold locks. The error flow in hns_roce_create_qp_common() doesn't hold those locks for the error unwind so it risks corrupting memory. Grab the same locks the other two callers use.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46113
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: KVM: x86: Fix shadow paging use-after-free due to unexpected GFN The shadow MMU computes GFNs for direct shadow pages using sp->gfn plus the SPTE index. This assumption breaks for shadow paging if the guest page tables are modified between VM entries (similar to commit aad885e77496, "KVM: x86/mmu: Drop/zap existing present SPTE even when creating an MMIO SPTE", 2026-03-27). The flow is as follows: - a PDE is installed for a 2MB mapping, and a page in that area is accessed. KVM creates a kvm_mmu_page consisting of 512 4KB pages; the kvm_mmu_page is marked by FNAME(fetch) as direct-mapped because the guest's mapping is a huge page (and thus contiguous). - the PDE mapping is changed from outside the guest. - the guest accesses another page in the same 2MB area. KVM installs a new leaf SPTE and rmap entry; the SPTE uses the "correct" GFN (i.e. based on the new mapping, as changed in the previous step) but that GFN is outside of the [sp->gfn, sp->gfn + 511] range; therefore the rmap entry cannot be found and removed when the kvm_mmu_page is zapped. - the memslot that covers the first 2MB mapping is deleted, and the kvm_mmu_page for the now-invalid GPA is zapped. However, rmap_remove() only looks at the [sp->gfn, sp->gfn + 511] range established in step 1, and fails to find the rmap entry that was recorded by step 3. - any operation that causes an rmap walk for the same page accessed by step 3 then walks a stale rmap and dereferences a freed kvm_mmu_page. This includes dirty logging or MMU notifier invalidations (e.g., from MADV_DONTNEED). The underlying issue is that KVM's walking of shadow PTEs assumes that if a SPTE is present when KVM wants to install a non-leaf SPTE, then the existing kvm_mmu_page must be for the correct gfn. Because the only way for the gfn to be wrong is if KVM messed up and failed to zap a SPTE... which shouldn't happen, but *actually* only happens in response to a guest write. That bug dates back literally forever, as even the first version of KVM assumes that the GFN matches and walks into the "wrong" shadow page. However, that was only an imprecision until 2032a93d66fa ("KVM: MMU: Don't allocate gfns page for direct mmu pages") came along. Fix it by checking for a target gfn mismatch and zapping the existing SPTE. That way the old SP and rmap entries are gone, KVM installs the rmap in the right location, and everyone is happy.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Ссылки
CVE-2026-46114
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: RDMA/rxe: Reject non-8-byte ATOMIC_WRITE payloads atomic_write_reply() at drivers/infiniband/sw/rxe/rxe_resp.c unconditionally dereferences 8 bytes at payload_addr(pkt): value = *(u64 *)payload_addr(pkt); check_rkey() previously accepted an ATOMIC_WRITE request with pktlen == resid == 0 because the length validation only compared pktlen against resid. A remote initiator that sets the RETH length to 0 therefore reaches atomic_write_reply() with a zero-byte logical payload, and the responder reads sizeof(u64) bytes from past the logical end of the packet into skb->head tailroom, then writes those 8 bytes into the attacker's MR via rxe_mr_do_atomic_write(). That is a remote disclosure of 4 bytes of kernel tailroom per probe (the other 4 bytes are the packet's own trailing ICRC). IBA oA19-28 defines ATOMIC_WRITE as exactly 8 bytes. Anything else is protocol-invalid. Hoist a strict length check into check_rkey() so the responder never reaches the unchecked dereference, and keep the existing WRITE-family length logic for the normal RDMA WRITE path. Reproduced on mainline with an unmodified rxe driver: a sustained zero-length ATOMIC_WRITE probe repeatedly leaks adjacent skb head-buffer bytes into the attacker's MR, including recognisable kernel strings and partial kernel-direct-map pointer words. With this patch applied the responder rejects the PDU and the MR stays all-zero.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Ссылки
CVE-2026-46115
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: block: add pgmap check to biovec_phys_mergeable biovec_phys_mergeable() is used by the request merge, DMA mapping, and integrity merge paths to decide if two physically contiguous bvec segments can be coalesced into one. It currently has no check for whether the segments belong to different dev_pagemaps. When zone device memory is registered in multiple chunks, each chunk gets its own dev_pagemap. A single bio can legitimately contain bvecs from different pgmaps -- iov_iter_extract_bvecs() breaks at pgmap boundaries but the outer loop in bio_iov_iter_get_pages() continues filling the same bio. If such bvecs are physically contiguous, biovec_phys_mergeable() will coalesce them, making it impossible to recover the correct pgmap for the merged segment via page_pgmap(). Add a zone_device_pages_have_same_pgmap() check to prevent merging bvec segments that span different pgmaps.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46116
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: xfrm: defensively unhash xfrm_state lists in __xfrm_state_delete KASAN reproduces a slab-use-after-free in __xfrm_state_delete()'s hlist_del_rcu calls under syzkaller load on linux-6.12.y stable (reproduced on 6.12.47, also reachable via the same code path on torvalds/master and on the ipsec tree). Nine unique signatures cluster in the xfrm_state lifecycle, the load-bearing one being: BUG: KASAN: slab-use-after-free in __hlist_del include/linux/list.h:990 [inline] BUG: KASAN: slab-use-after-free in hlist_del_rcu include/linux/rculist.h:516 [inline] BUG: KASAN: slab-use-after-free in __xfrm_state_delete net/xfrm/xfrm_state.c Write of size 8 at addr ffff8881198bcb70 by task kworker/u8:9/435 Workqueue: netns cleanup_net Call Trace: __hlist_del / hlist_del_rcu __xfrm_state_delete xfrm_state_delete xfrm_state_flush xfrm_state_fini ops_exit_list cleanup_net The other observed signatures hit the same slab object from __xfrm_state_lookup, xfrm_alloc_spi, __xfrm_state_insert and an OOB write variant of __xfrm_state_delete, all on the byseq/byspi hash chains. __xfrm_state_delete() guards its byseq and byspi unhashes with value-based predicates: if (x->km.seq) hlist_del_rcu(&x->byseq); if (x->id.spi) hlist_del_rcu(&x->byspi); while everywhere else in the file (e.g. state_cache, state_cache_input) the safer hlist_unhashed() check is used. xfrm_alloc_spi() sets x->id.spi = newspi inside xfrm_state_lock and then immediately inserts into byspi, but a path that observes x->id.spi != 0 outside of xfrm_state_lock can still skip-or-hit the byspi unhash inconsistently with whether x is actually on the list. The same holds for x->km.seq versus byseq, and the bydst/bysrc unhashes have no predicate at all, so a second __xfrm_state_delete() on the same object writes through LIST_POISON pprev. The defensive change here: - Use hlist_del_init_rcu() instead of hlist_del_rcu() on bydst, bysrc, byseq and byspi so a second deletion is a no-op rather than a write through LIST_POISON pprev. The byseq/byspi nodes are already initialised in xfrm_state_alloc(). - Test hlist_unhashed() rather than the value predicate for byseq/byspi, so the unhash decision tracks list state rather than mutable scalar fields. Empirical verification: applied this patch on top of v6.12.47, rebuilt, and re-ran the same syzkaller harness for 1h16m on a previously-crashy configuration that produced ~100 hits each of slab-use-after-free Read in xfrm_alloc_spi / Read in __xfrm_state_lookup / Write in __xfrm_state_delete. After the patch, 7.1M execs across 32 VMs at ~1550 exec/sec produced zero xfrm_state UAF/OOB hits. /proc/slabinfo confirms the xfrm_state slab is actively allocated and freed during the run (~143 KiB resident), so the fuzzer is still exercising those code paths -- they just no longer crash. Reproduction: - Linux 6.12.47 x86_64 + KASAN_GENERIC + KASAN_INLINE + KCOV - syzkaller @ 746545b8b1e4c3a128db8652b340d3df90ce61db - 32 QEMU/KVM VMs x 2 vCPU on AWS c5.metal bare metal - 9 unique signatures collected in ~9h, all within xfrm_state lifecycle

Опубликовано: 2026-05-28Изменено: 2026-07-07
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46117
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: RDMA/mana: Remove user triggerable WARN_ON() in mana_ib_create_qp_rss() Sashiko points out that the user can specify WQs sharing the same CQ as a part of the uAPI and this will trigger the WARN_ON() then go on to corrupt the kernel. Just reject it outright and fail the QP creation.

Опубликовано: 2026-05-28Изменено: 2026-06-30
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46119
CRITICAL9.1

In the Linux kernel, the following vulnerability has been resolved: libceph: Fix slab-out-of-bounds access in auth message processing If a (potentially corrupted) message of type CEPH_MSG_AUTH_REPLY contains a positive value in its result field, it is treated as an error code by ceph_handle_auth_reply() and returned to handle_auth_reply(). Thereafter, an attempt is made to send the preallocated message of type CEPH_MSG_AUTH, where the returned value is interpreted as the size of the front segment to send. If the result value in the message is greater than the size of the memory buffer allocated for the front segment, an out-of-bounds access occurs, and the content of the memory region beyond this buffer is sent out. This patch fixes the issue by treating only negative values in the result field as errors. Positive values are therefore treated as success in the same way as a zero value. Additionally, a BUG_ON is added to __send_prepared_auth_request() comparing the len parameter to front_alloc_len to prevent sending the message if it exceeds the bounds of the allocation and to make it easier to catch any logic flaws leading to this.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xКРИТИЧЕСКАЯ 9.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46120
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ip6_gre: Use cached t->net in ip6erspan_changelink(). After commit 5e72ce3e3980 ("net: ipv6: Use link netns in newlink() of rtnl_link_ops"), ip6erspan_newlink() correctly resolves the per-netns ip6gre hash via link_net. ip6erspan_changelink() was not converted in that series and still uses dev_net(dev), which diverges from the device's creation netns after IFLA_NET_NS_FD migration. This re-inserts the tunnel into the wrong per-netns hash. The original netns keeps a stale entry. When that netns is later destroyed, ip6gre_exit_rtnl_net() walks the stale entry, producing a slab-use-after-free reported by KASAN, followed by a kernel BUG at net/core/dev.c (LIST_POISON1) in unregister_netdevice_many_notify(). Reachable from an unprivileged user namespace (unshare --user --map-root-user --net). ip6gre_changelink() earlier in the same file already uses the cached t->net; only ip6erspan_changelink() has the wrong shape.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46121
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: mm/damon/sysfs-schemes: protect memcg_path kfree() with damon_sysfs_lock Patch series "mm/damon/sysfs-schemes: fix use-after-free for [memcg_]path". Reads of 'memcg_path' and 'path' files in DAMON sysfs interface could race with their writes, results in use-after-free. Fix those. This patch (of 2): damon_sysfs_scheme_filter->mmecg_path can be read and written by users, via DAMON sysfs memcg_path file. It can also be indirectly read, for the parameters {on,off}line committing to DAMON. The reads for parameters committing are protected by damon_sysfs_lock to avoid the sysfs files being destroyed while any of the parameters are being read. But the user-driven direct reads and writes are not protected by any lock, while the write is deallocating the memcg_path-pointing buffer. As a result, the readers could read the already freed buffer (user-after-free). Note that the user-reads don't race when the same open file is used by the writer, due to kernfs's open file locking. Nonetheless, doing the reads and writes with separate open files would be common. Fix it by protecting both the user-direct reads and writes with damon_sysfs_lock.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46122
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: wifi: b43: enforce bounds check on firmware key index in b43_rx() The firmware-controlled key index in b43_rx() can exceed the dev->key[] array size (58 entries). The existing B43_WARN_ON is non-enforcing in production builds, allowing an out-of-bounds read. Make the B43_WARN_ON check enforcing by dropping the frame when the firmware returns an invalid key index.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46123
HIGH7.7

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: virtio_bt: clamp rx length before skb_put virtbt_rx_work() calls skb_put(skb, len) where len comes directly from virtqueue_get_buf() with no validation against the buffer we posted to the device. The RX skb is allocated in virtbt_add_inbuf() and exposed to virtio as exactly 1000 bytes via sg_init_one(). Checking len against skb_tailroom(skb) is not sufficient because alloc_skb() can leave more tailroom than the 1000 bytes actually handed to the device. A malicious or buggy backend can therefore report used.len between 1001 and skb_tailroom(skb), causing skb_put() to include uninitialized kernel heap bytes that were never written by the device. The same path also accepts len == 0, in which case skb_put(skb, 0) leaves the skb empty but virtbt_rx_handle() still reads the pkt_type byte from skb->data, consuming uninitialized memory. Define VIRTBT_RX_BUF_SIZE once and reuse it in alloc_skb() and sg_init_one(), and gate virtbt_rx_work() on that same constant so the bound checked matches the buffer actually exposed to the device. Reject used.len == 0 in the same gate so an empty completion can no longer reach virtbt_rx_handle(). Use bt_dev_err_ratelimited() because the length value comes from an untrusted backend that can otherwise flood the kernel log. Same class of bug as commit c04db81cd028 ("net/9p: Fix buffer overflow in USB transport layer"), which hardened the USB 9p transport against unchecked device-reported length.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.7
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46124
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: isofs: validate block number from NFS file handle in isofs_export_iget isofs_fh_to_dentry() and isofs_fh_to_parent() pass an attacker- controlled block number (ifid->block or ifid->parent_block) from the NFS file handle to isofs_export_iget(), which only rejects block == 0 before calling isofs_iget() and ultimately sb_bread(). A crafted file handle with fh_len sufficient to pass the check added by commit 0405d4b63d08 ("isofs: Prevent the use of too small fid") can still drive the server to read any in-range block on the backing device as if it were an iso_directory_record. That earlier fix was assigned CVE-2025-37780. sb_bread() on an out-of-range block returns NULL cleanly via the EIO path, so there is no memory-safety violation. For in-range reads of adjacent-partition data on the same block device, the unrelated bytes end up in iso_inode_info fields that reach the NFS client as dentry metadata. The deployment surface (isofs exported over NFS from loop-mounted images) is narrow and requires an authenticated NFS peer, but the malformed-file-handle class is reportable as hardening next to the existing CVE-2025-37780 fix. Reject block >= ISOFS_SB(sb)->s_nzones in isofs_export_iget() so the check covers both isofs_fh_to_dentry() and isofs_fh_to_parent() call sites with a single line.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Ссылки
CVE-2026-46125
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: remove station if connection prep fails If connection preparation fails for MLO connections, then the interface is completely reset to non-MLD. In this case, we must not keep the station since it's related to the link of the vif being removed. Delete an existing station. Any "new_sta" is already being removed, so that doesn't need changes. This fixes a use-after-free/double-free in debugfs if that's enabled, because a vif going from MLD (and to MLD, but that's not relevant here) recreates its entire debugfs.

Опубликовано: 2026-05-28Изменено: 2026-06-30
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46126
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: RDMA/mana: Fix mana_destroy_wq_obj() cleanup in mana_ib_create_qp_rss() Sashiko points out there are two bugs here in the error unwind flow, both related to how the WQ table is unwound. First there is a double i-- on the first failure path due to the while loop having a i--, remove it. Second if mana_ib_install_cq_cb() fails then mana_create_wq_obj() is not undone due to the above i--.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46127
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: RDMA/ocrdma: Don't NULL deref uctx on errors in ocrdma_copy_pd_uresp() Sashiko points out that pd->uctx isn't initialized until late in the function so all these error flow references are NULL and will crash. Use the uctx that isn't NULL.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46128
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ipmi: Check event message buffer response for bad data The event message buffer response data size got checked later when processing, but check it right after the response comes back. It appears some BMCs may return an empty message instead of an error when fetching events. There are apparently some new BMCs that make this error, so we need to compensate.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46129
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: btrfs: fix double free in create_space_info() error path When kobject_init_and_add() fails, the call chain is: create_space_info() -> btrfs_sysfs_add_space_info_type() -> kobject_init_and_add() -> failure -> kobject_put(&space_info->kobj) -> space_info_release() -> kfree(space_info) Then control returns to create_space_info(): btrfs_sysfs_add_space_info_type() returns error -> goto out_free -> kfree(space_info) This causes a double free. Keep the direct kfree(space_info) for the earlier failure path, but after btrfs_sysfs_add_space_info_type() has called kobject_put(), let the kobject release callback handle the cleanup.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46131
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: KVM: x86: check for nEPT/nNPT in slow flush hypercalls Checking is_guest_mode(vcpu) is incorrect, because translate_nested_gpa() is only valid if an L2 guest is running *with nested EPT/NPT enabled*. Instead use the same condition as translate_nested_gpa() itself.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46132
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: rtnetlink: zero ifla_vf_broadcast to avoid stack infoleak in rtnl_fill_vfinfo rtnl_fill_vfinfo() declares struct ifla_vf_broadcast on the stack without initialisation: struct ifla_vf_broadcast vf_broadcast; The struct contains a single fixed 32-byte field: /* include/uapi/linux/if_link.h */ struct ifla_vf_broadcast { __u8 broadcast[32]; }; The function then copies dev->broadcast into it using dev->addr_len as the length: memcpy(vf_broadcast.broadcast, dev->broadcast, dev->addr_len); On Ethernet devices (the overwhelming majority of SR-IOV NICs) dev->addr_len is 6, so only the first 6 bytes of broadcast[] are written. The remaining 26 bytes retain whatever was previously on the kernel stack. The full struct is then handed to userspace via: nla_put(skb, IFLA_VF_BROADCAST, sizeof(vf_broadcast), &vf_broadcast) leaking up to 26 bytes of uninitialised kernel stack per VF per RTM_GETLINK request, repeatable. The other vf_* structs in the same function are explicitly zeroed for exactly this reason - see the memset() calls for ivi, vf_vlan_info, node_guid and port_guid a few lines above. vf_broadcast was simply missed when it was added. Reachability: any unprivileged local process can open AF_NETLINK / NETLINK_ROUTE without capabilities and send RTM_GETLINK with an IFLA_EXT_MASK attribute carrying RTEXT_FILTER_VF. The kernel walks each VF and emits IFLA_VF_BROADCAST, leaking 26 bytes of stack per VF per request. Stack residue at this call site can include return addresses and transient sensitive data; KASAN with stack instrumentation, or KMSAN, will flag the nla_put() when reproduced. Zero the on-stack struct before the partial memcpy, matching the existing pattern used for the other vf_* structs in the same function.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46133
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: RDMA/rxe: Reject unknown opcodes before ICRC processing Even after applying commit 7244491dab34 ("RDMA/rxe: Validate pad and ICRC before payload_size() in rxe_rcv"), a single unauthenticated UDP packet can still trigger panic. That patch handled payload_size() underflow only for valid opcodes with short packets, not for packets carrying an unknown opcode. The unknown-opcode OOB read described below predates that commit and reaches back to the initial Soft RoCE driver. The check added there reads pkt->paylen < header_size(pkt) + bth_pad(pkt) + RXE_ICRC_SIZE where header_size(pkt) expands to rxe_opcode[pkt->opcode].length. The rxe_opcode[] array has 256 entries but is only populated for defined IB opcodes; any other entry (for example opcode 0xff) is zero-initialized, so length == 0 and the check degenerates to pkt->paylen < 0 + bth_pad(pkt) + RXE_ICRC_SIZE which does not constrain pkt->paylen enough. rxe_icrc_hdr() then computes rxe_opcode[pkt->opcode].length - RXE_BTH_BYTES which underflows when length == 0 and passes a huge value to rxe_crc32(), causing an out-of-bounds read of the skb payload. Reproduced on v7.0-rc7 with that fix applied, QEMU/KVM with CONFIG_RDMA_RXE=y and CONFIG_KASAN=y, after rdma link add rxe0 type rxe netdev eth0 A single 48-byte UDP packet to port 4791 with BTH opcode=0xff and QPN=IB_MULTICAST_QPN triggers: BUG: KASAN: slab-out-of-bounds in crc32_le+0x115/0x170 Read of size 1 at addr ... The buggy address is located 0 bytes to the right of allocated 704-byte region Call Trace: crc32_le+0x115/0x170 rxe_icrc_hdr.isra.0+0x226/0x300 rxe_icrc_check+0x13f/0x3a0 rxe_rcv+0x6e1/0x16e0 rxe_udp_encap_recv+0x20a/0x320 udp_queue_rcv_one_skb+0x7ed/0x12c0 Subsequent packets with the same shape fault on unmapped memory and panic the kernel. The trigger requires only module load and "rdma link add"; no QP, no connection, and no authentication. Fix this by rejecting packets whose opcode has no rxe_opcode[] entry, detected via the zero mask or zero length, before any length arithmetic runs.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46135
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: nvmet-tcp: fix race between ICReq handling and queue teardown nvmet_tcp_handle_icreq() updates queue->state after sending an Initialization Connection Response (ICResp), but it does so without serializing against target-side queue teardown. If an NVMe/TCP host sends an Initialization Connection Request (ICReq) and immediately closes the connection, target-side teardown may start in softirq context before io_work drains the already buffered ICReq. In that case, nvmet_tcp_schedule_release_queue() sets queue->state to NVMET_TCP_Q_DISCONNECTING and drops the queue reference under state_lock. If io_work later processes that ICReq, nvmet_tcp_handle_icreq() can still overwrite the state back to NVMET_TCP_Q_LIVE. That defeats the DISCONNECTING-state guard in nvmet_tcp_schedule_release_queue() and allows a later socket state change to re-enter teardown and issue a second kref_put() on an already released queue. The ICResp send failure path has the same problem. If teardown has already moved the queue to DISCONNECTING, a send error can still overwrite the state with NVMET_TCP_Q_FAILED, again reopening the window for a second teardown path to drop the queue reference. Fix this by serializing both post-send state transitions with state_lock and bailing out if teardown has already started. Use -ESHUTDOWN as an internal sentinel for that bail-out path rather than propagating it as a transport error like -ECONNRESET. Keep nvmet_tcp_socket_error() setting rcv_state to NVMET_TCP_RECV_ERR before honoring that sentinel so receive-side parsing stays quiesced until the existing release path completes.

Опубликовано: 2026-05-28Изменено: 2026-07-04
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46136
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: mt7921: fix a potential clc buffer length underflow The buf_len is used to limit the iterations for retrieving the country power setting and may underflow under certain conditions due to changes in the power table in CLC. This underflow leads to an almost infinite loop or an invalid power setting resulting in driver initialization failure.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46137
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: mptcp: pm: ADD_ADDR rtx: fix potential data-race This mptcp_pm_add_timer() helper is executed as a timer callback in softirq context. To avoid any data races, the socket lock needs to be held with bh_lock_sock(). If the socket is in use, retry again soon after, similar to what is done with the keepalive timer.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46138
HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_event: Fix OOB read and infinite loop in hci_le_create_big_complete_evt hci_le_create_big_complete_evt() iterates over BT_BOUND connections for a BIG handle using a while loop, accessing ev->bis_handle[i++] on each iteration. However, there is no check that i stays within ev->num_bis before the array access. When a controller sends a LE_Create_BIG_Complete event with fewer bis_handle entries than there are BT_BOUND connections for that BIG, or with num_bis=0, the loop reads beyond the valid bis_handle[] flex array into adjacent heap memory. Since the out-of-bounds values typically exceed HCI_CONN_HANDLE_MAX (0x0EFF), hci_conn_set_handle() rejects them and the connection remains in BT_BOUND state. The same connection is then found again by hci_conn_hash_lookup_big_state(), creating an infinite loop with hci_dev_lock held. Fix this by terminating the BIG if in case not all BIS could be setup properly.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46139
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: smb: client: use kzalloc to zero-initialize security descriptor buffer Commit 62e7dd0a39c2d ("smb: common: change the data type of num_aces to le16") split struct smb_acl's __le32 num_aces field into __le16 num_aces and __le16 reserved. The reserved field corresponds to Sbz2 in the MS-DTYP ACL wire format, which must be zero [1]. When building an ACL descriptor in build_sec_desc(), we are using a kmalloc()'ed descriptor buffer and writing the fields explicitly using le16() writes now. This never writes to the 2 byte reserved field, leaving it as uninitialized heap data. When the reserved field happens to contain non-zero slab garbage, Samba rejects the security descriptor with "ndr_pull_security_descriptor failed: Range Error", causing chmod to fail with EINVAL. Change kmalloc() to kzalloc() to ensure the entire buffer is zero-initialized. [1] https://learn.microsoft.com/en-us/openspecs/windows_protocols/ms-dtyp/20233ed8-a6c6-4097-aafa-dd545ed24428

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46140
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: btmtk: validate WMT event SKB length before struct access btmtk_usb_hci_wmt_sync() casts the WMT event response SKB data to struct btmtk_hci_wmt_evt (7 bytes) and struct btmtk_hci_wmt_evt_funcc (9 bytes) without first checking that the SKB contains enough data. A short firmware response causes out-of-bounds reads from SKB tailroom. Use skb_pull_data() to validate and advance past the base WMT event header. For the FUNC_CTRL case, pull the additional status field bytes before accessing them.

Опубликовано: 2026-05-28Изменено: 2026-07-04
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46142
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: libwx: fix VF illegal register access Register WX_CFG_PORT_ST is a PF restricted register. When a VF is initialized, attempting to read this register triggers an illegal register access, which lead to a system hang. When the device is VF, the bus function ID can be obtained directly from the PCI_FUNC(pdev->devfn).

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46143
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ASoC: qcom: q6apm-lpass-dai: Fix multiple graph opens As prepare can be called mulitple times, this can result in multiple graph opens for playback path. This will result in a memory leaks, fix this by adding a check before opening.

Опубликовано: 2026-05-28Изменено: 2026-06-24
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46144
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: RDMA/mana: Fix error unwind in mana_ib_create_qp_rss() Sashiko points out that mana_ib_cfg_vport_steering() is leaked, the normal destroy path cleans it up.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46145
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: RDMA/mana: Validate rx_hash_key_len Sashiko points out that rx_hash_key_len comes from a uAPI structure and is blindly passed to memcpy, allowing the userspace to trash kernel memory. Bounds check it so the memcpy cannot overflow.

Опубликовано: 2026-05-28Изменено: 2026-06-30
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46146
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ALSA: usb-audio: Avoid potential endless loop in convert_chmap_v3() The convert_chmap_v3() has a loop with its increment size of cs_desc->wLength, but we forgot to validate cs_desc->wLength itself, which may lead to potential endless loop by a malformed descriptor. Add a proper size check to abort the loop for plugging the hole.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46149
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: scsi: target: configfs: Bound snprintf() return in tg_pt_gp_members_show() target_tg_pt_gp_members_show() formats LUN paths with snprintf() into a 256-byte stack buffer, then will memcpy() cur_len bytes from that buffer. snprintf() returns the length the output would have had, which can exceed the buffer size when the fabric WWN is long because iSCSI IQN names can be up to 223 bytes. The check at the memcpy() site only guards the destination page write, not the source read, so memcpy() will read past the stack buffer and copy adjacent stack contents to the sysfs reader, which when CONFIG_FORTIFY_SOURCE is enabled, fortify_panic() will be triggered. Commit 27e06650a5ea ("scsi: target: target_core_configfs: Add length check to avoid buffer overflow") added the same bound to the target_lu_gp_members_show() but the tg_pt_gp variant was missed so resolve that here.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46150
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: fanotify: fix false positive on permission events fsnotify_get_mark_safe() may return false for a mark on an unrelated group, which results in bypassing the permission check. Fix by skipping over detached marks that are not in the current group.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
Ссылки
CVE-2026-46151
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: usblp: fix heap leak in IEEE 1284 device ID via short response usblp_ctrl_msg() collapses the usb_control_msg() return value to 0/-errno, discarding the actual number of bytes transferred. A broken printer can complete the GET_DEVICE_ID control transfer short and the driver has no way to know. usblp_cache_device_id_string() reads the 2-byte big-endian length prefix from the response and trusts it (clamped only to the buffer bounds). The buffer is kmalloc(1024) at probe time. A device that sends exactly two bytes (e.g. 0x03 0xFF, claiming a 1023-byte ID) leaves device_id_string[2..1022] holding stale kmalloc heap. That stale data is then exposed: - via the ieee1284_id sysfs attribute (sprintf("%s", buf+2), truncated at the first NUL in the stale heap), and - via the IOCNR_GET_DEVICE_ID ioctl, which copy_to_user()s the full claimed length regardless of NULs, up to 1021 bytes of uninitialized heap, with the leak size chosen by the device. Fix this up by just zapping the buffer with zeros before each request sent to the device.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46152
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: drop stray 'static' from fast-RX rx_result ieee80211_invoke_fast_rx() is documented as safe for parallel RX, but its per-invocation rx_result is declared static. Concurrent callers then share one instance and can overwrite each other's result between ieee80211_rx_mesh_data() and the switch on res. That can make a packet that was queued or consumed by ieee80211_rx_mesh_data() fall through into ieee80211_rx_8023(), or make a packet that should continue return as queued. Make res an automatic variable so each invocation keeps its own result.

Опубликовано: 2026-05-28Изменено: 2026-06-30
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46155
CRITICAL9.1

In the Linux kernel, the following vulnerability has been resolved: smb/client: fix out-of-bounds read in smb2_compound_op() If a server sends a truncated response but a large OutputBufferLength, and terminates the EA list early, check_wsl_eas() returns success without validating that the entire OutputBufferLength fits within iov_len. Then smb2_compound_op() does: memcpy(idata->wsl.eas, data[0], size[0]); Where size[0] is OutputBufferLength. If iov_len is smaller than size[0], memcpy can read beyond the end of the rsp_iov allocation and leak adjacent kernel heap memory.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46157
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ALSA: pcm: oss: Fix data race at accessing runtime.oss.trigger Currently the runtime.oss.trigger field may be accessed concurrently without protection, which may lead to the data race. And, in this case, it may lead to more severe problem because it's a bit field; as writing the data, it may overwrite other bit fields as well, which confuses the operation completely, as spotted by fuzzing. Fix it by covering runtime.oss.trigger bit fled also with the existing params_lock mutex in both snd_pcm_oss_get_trigger() and snd_pcm_oss_poll().

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46158
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mptcp: pm: ADD_ADDR rtx: always decrease sk refcount When an ADD_ADDR is retransmitted, the sk is held in sk_reset_timer(). It should then be released in all cases at the end. Some (unlikely) checks were returning directly instead of calling sock_put() to decrease the refcount. Jump to a new 'exit' label to call __sock_put() (which will become sock_put() in the next commit) to fix this potential leak. While at it, drop the '!msk' check which cannot happen because it is never reset, and explicitly mark the remaining one as "unlikely".

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46159
MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: btrfs: fix btrfs_ioctl_space_info() slot_count TOCTOU which can lead to info-leak btrfs_ioctl_space_info() has a TOCTOU race between two passes over the block group RAID type lists. The first pass counts entries to determine the allocation size, then the second pass fills the buffer. The groups_sem rwlock is released between passes, allowing concurrent block group removal to reduce the entry count. When the second pass fills fewer entries than the first pass counted, copy_to_user() copies the full alloc_size bytes including trailing uninitialized kmalloc bytes to userspace. Fix by copying only total_spaces entries (the actually-filled count from the second pass) instead of alloc_size bytes, and switch to kzalloc so any future copy size mismatch cannot leak heap data.

Опубликовано: 2026-05-28Изменено: 2026-06-19
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46160
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: btrfs: fix missing last_unlink_trans update when removing a directory When removing a directory we are not updating its last_unlink_trans field, which can result in incorrect fsync behaviour in case some one fsyncs the directory after it was removed because it's holding a file descriptor on it. Example scenario: mkdir /mnt/dir1 mkdir /mnt/dir1/dir2 mkdir /mnt/dir3 sync -f /mnt # Do some change to the directory and fsync it. chmod 700 /mnt/dir1 xfs_io -c fsync /mnt/dir1 # Move dir2 out of dir1 so that dir1 becomes empty. mv /mnt/dir1/dir2 /mnt/dir3/ open fd on /mnt/dir1 call rmdir(2) on path "/mnt/dir1" fsync fd When attempting to mount the filesystem, the log replay will fail with an -EIO error and dmesg/syslog has the following: [445771.626482] BTRFS info (device dm-0): first mount of filesystem 0368bbea-6c5e-44b5-b409-09abe496e650 [445771.626486] BTRFS info (device dm-0): using crc32c checksum algorithm [445771.627912] BTRFS info (device dm-0): start tree-log replay [445771.628335] page: refcount:2 mapcount:0 mapping:0000000061443ddc index:0x1d00 pfn:0x7072a5 [445771.629453] memcg:ffff89f400351b00 [445771.629892] aops:btree_aops [btrfs] ino:1 [445771.630737] flags: 0x17fffc00000402a(uptodate|lru|private|writeback|node=0|zone=2|lastcpupid=0x1ffff) [445771.632359] raw: 017fffc00000402a fffff47284d950c8 fffff472907b7c08 ffff89f458e412b8 [445771.633713] raw: 0000000000001d00 ffff89f6c51d1a90 00000002ffffffff ffff89f400351b00 [445771.635029] page dumped because: eb page dump [445771.635825] BTRFS critical (device dm-0): corrupt leaf: root=5 block=30408704 slot=10 ino=258, invalid nlink: has 2 expect no more than 1 for dir [445771.638088] BTRFS info (device dm-0): leaf 30408704 gen 10 total ptrs 17 free space 14878 owner 5 [445771.638091] BTRFS info (device dm-0): refs 4 lock_owner 0 current 3581087 [445771.638094] item 0 key (256 INODE_ITEM 0) itemoff 16123 itemsize 160 [445771.638097] inode generation 3 transid 9 size 16 nbytes 16384 [445771.638098] block group 0 mode 40755 links 1 uid 0 gid 0 [445771.638100] rdev 0 sequence 2 flags 0x0 [445771.638102] atime 1775744884.0 [445771.660056] ctime 1775744885.645502983 [445771.660058] mtime 1775744885.645502983 [445771.660060] otime 1775744884.0 [445771.660062] item 1 key (256 INODE_REF 256) itemoff 16111 itemsize 12 [445771.660064] index 0 name_len 2 [445771.660066] item 2 key (256 DIR_ITEM 1843588421) itemoff 16077 itemsize 34 [445771.660068] location key (259 1 0) type 2 [445771.660070] transid 9 data_len 0 name_len 4 [445771.660075] item 3 key (256 DIR_ITEM 2363071922) itemoff 16043 itemsize 34 [445771.660076] location key (257 1 0) type 2 [445771.660077] transid 9 data_len 0 name_len 4 [445771.660078] item 4 key (256 DIR_INDEX 2) itemoff 16009 itemsize 34 [445771.660079] location key (257 1 0) type 2 [445771.660080] transid 9 data_len 0 name_len 4 [445771.660081] item 5 key (256 DIR_INDEX 3) itemoff 15975 itemsize 34 [445771.660082] location key (259 1 0) type 2 [445771.660083] transid 9 data_len 0 name_len 4 [445771.660084] item 6 key (257 INODE_ITEM 0) itemoff 15815 itemsize 160 [445771.660086] inode generation 9 transid 9 size 8 nbytes 0 [445771.660087] block group 0 mode 40777 links 1 uid 0 gid 0 [445771.660088] rdev 0 sequence 2 flags 0x0 [445771.660089] atime 1775744885.641174097 [445771.660090] ctime 1775744885.645502983 [445771.660091] mtime 1775744885.645502983 [445771.660105] otime 1775744885.641174097 [445771.660106] item 7 key (257 INODE_REF 256) itemoff 15801 itemsize 14 [445771.660107] index 2 name_len 4 [445771.660108] item 8 key (257 DIR_ITEM 2676584006) itemoff 15767 itemsize 34 [445771.660109] location key (2 ---truncated---

Опубликовано: 2026-05-28Изменено: 2026-06-19
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46161
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: md/raid10: fix divide-by-zero in setup_geo() with zero far_copies setup_geo() extracts near_copies (nc) and far_copies (fc) from the user-provided layout parameter without checking for zero. When fc=0 with the "improved" far set layout selected, 'geo->far_set_size = disks / fc' triggers a divide-by-zero. Validate nc and fc immediately after extraction, returning -1 if either is zero.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46162
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ice: fix double free in ice_sf_eth_activate() error path When auxiliary_device_add() fails, ice_sf_eth_activate() jumps to aux_dev_uninit and calls auxiliary_device_uninit(&sf_dev->adev). The device release callback ice_sf_dev_release() frees sf_dev, but the current error path falls through to sf_dev_free and calls kfree(sf_dev) again, causing a double free. Keep kfree(sf_dev) for the auxiliary_device_init() failure path, but avoid falling through to sf_dev_free after auxiliary_device_uninit().

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46163
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: wifi: b43legacy: enforce bounds check on firmware key index in RX path Same fix as b43: the firmware-controlled key index in b43legacy_rx() can exceed dev->max_nr_keys. The existing B43legacy_WARN_ON is non-enforcing in production builds, allowing an out-of-bounds read of dev->key[]. Make the check enforcing by dropping the frame for invalid indices.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46164
HIGH7.0

In the Linux kernel, the following vulnerability has been resolved: btrfs: fix double free in create_space_info_sub_group() error path When kobject_init_and_add() fails, the call chain is: create_space_info_sub_group() -> btrfs_sysfs_add_space_info_type() -> kobject_init_and_add() -> failure -> kobject_put(&sub_group->kobj) -> space_info_release() -> kfree(sub_group) Then control returns to create_space_info_sub_group(), where: btrfs_sysfs_add_space_info_type() returns error -> kfree(sub_group) Thus, sub_group is freed twice. Keep parent->sub_group[index] = NULL for the failure path, but after btrfs_sysfs_add_space_info_type() has called kobject_put(), let the kobject release callback handle the cleanup.

Опубликовано: 2026-05-28Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.0
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46166
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: use safe list iteration in radar detect work The call to ieee80211_dfs_cac_cancel can cause the iterated chanctx to be freed and removed from the list. Guard against this to avoid a slab-use-after-free error.

Опубликовано: 2026-05-28Изменено: 2026-06-30
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46167
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: usblp: fix uninitialized heap leak via LPGETSTATUS ioctl Just like in a previous problem in this driver, usblp_ctrl_msg() will collapse the usb_control_msg() return value to 0/-errno, discarding the actual number of bytes transferred. Ideally that short command should be detected and error out, but many printers are known to send "incorrect" responses back so we can't just do that. statusbuf is kmalloc(8) at probe time and never filled before the first LPGETSTATUS ioctl. usblp_read_status() requests 1 byte. If a malicious printer responds with zero bytes, *statusbuf is one byte of stale kmalloc heap, sign-extended into the local int status, which the LPGETSTATUS path then copy_to_user()s directly to the ioctl caller. Fix this all by just zapping out the memory buffer when allocated at probe time. If a later call does a short read, the data will be identical to what the device sent it the last time, so there is no "leak" of information happening.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46168
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mptcp: fix scheduling with atomic in timestamp sockopt Using lock_sock_fast() (atomic context) around sock_set_timestamp() and sock_set_timestamping() is unsafe, as both helpers can sleep. Replace lock_sock_fast() with sleepable lock_sock()/release_sock() to avoid scheduling while atomic panic.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46169
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: hfsplus: fix uninit-value by validating catalog record size Syzbot reported a KMSAN uninit-value issue in hfsplus_strcasecmp(). The root cause is that hfs_brec_read() doesn't validate that the on-disk record size matches the expected size for the record type being read. When mounting a corrupted filesystem, hfs_brec_read() may read less data than expected. For example, when reading a catalog thread record, the debug output showed: HFSPLUS_BREC_READ: rec_len=520, fd->entrylength=26 HFSPLUS_BREC_READ: WARNING - entrylength (26) < rec_len (520) - PARTIAL READ! hfs_brec_read() only validates that entrylength is not greater than the buffer size, but doesn't check if it's less than expected. It successfully reads 26 bytes into a 520-byte structure and returns success, leaving 494 bytes uninitialized. This uninitialized data in tmp.thread.nodeName then gets copied by hfsplus_cat_build_key_uni() and used by hfsplus_strcasecmp(), triggering the KMSAN warning when the uninitialized bytes are used as array indices in case_fold(). Fix by introducing hfsplus_brec_read_cat() wrapper that: 1. Calls hfs_brec_read() to read the data 2. Validates the record size based on the type field: - Fixed size for folder and file records - Variable size for thread records (depends on string length) 3. Returns -EIO if size doesn't match expected For thread records, check against HFSPLUS_MIN_THREAD_SZ before reading nodeName.length to avoid reading uninitialized data at call sites that don't zero-initialize the entry structure. Also initialize the tmp variable in hfsplus_find_cat() as defensive programming to ensure no uninitialized data even if validation is bypassed.

Опубликовано: 2026-05-28Изменено: 2026-06-19
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46170
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mptcp: pm: ADD_ADDR rtx: free sk if last When an ADD_ADDR is retransmitted, the sk is held in sk_reset_timer(), and released at the end. If at that moment, it was the last reference being held, the sk would not be freed. sock_put() should then be called instead of __sock_put(). But that's not enough: if it is the last reference, sock_put() will call sk_free(), which will end up calling sk_stop_timer_sync() on the same timer, and waiting indefinitely to finish. So it is needed to mark that the timer is done at the end of the timer handler when it has not been rescheduled, not to call sk_stop_timer_sync() on "itself".

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46172
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ipv6: xfrm6: release dst on error in xfrm6_rcv_encap() xfrm6_rcv_encap() performs an IPv6 route lookup when the skb does not already have a dst attached. ip6_route_input_lookup() returns a referenced dst entry even when the lookup resolves to an error route. If dst->error is set, xfrm6_rcv_encap() drops the skb without attaching the dst to the skb and without releasing the reference returned by the lookup. Repeated packets hitting this path therefore leak dst entries. Release the dst before jumping to the drop path.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46173
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: exit: prevent preemption of oopsing TASK_DEAD task When an already-exiting task oopses, make_task_dead() currently calls do_task_dead() with preemption enabled. That is forbidden: do_task_dead() calls __schedule(), which has a comment saying "WARNING: must be called with preemption disabled!". If an oopsing task is preempted in do_task_dead(), between becoming TASK_DEAD and entering the scheduler explicitly, bad things happen: finish_task_switch() assumes that once the scheduler has switched away from a TASK_DEAD task, the task can never run again and its stack is no longer needed; but that assumption apparently doesn't hold if the dead task was preempted (the SM_PREEMPT case). This means that the scheduler ends up repeatedly dropping references on the dead task's stack, which can lead to use-after-free or double-free of the entire task stack; in other words, two tasks can end up running on the same stack, resulting in various kinds of memory corruption. (This does not just affect "recursively oopsing" tasks; it is enough to oops once during task exit, for example in a file_operations::release handler)

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46174
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: x86/CPU/AMD: Prevent improper isolation of shared resources in Zen2's op cache Make sure resources are not improperly shared in the op cache and cause instruction corruption this way.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Ссылки
CVE-2026-46176
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: RDMA/mlx5: Fix error path fall-through in mlx5_ib_dev_res_srq_init() mlx5_ib_dev_res_srq_init() allocates two SRQs, s0 and s1. When ib_create_srq() fails for s1, the error branch destroys s0 but falls through and unconditionally assigns the freed s0 and the ERR_PTR s1 to devr->s0 and devr->s1. This leads to several problems: the lock-free fast path checks "if (devr->s1) return 0;" and treats the ERR_PTR as already initialised; users in mlx5_ib_create_qp() dereference the freed SRQ or ERR_PTR via to_msrq(devr->s0)->msrq.srqn; and mlx5_ib_dev_res_cleanup() dereferences the ERR_PTR and double-frees s0 on teardown. Fix by adding the same `goto unlock` in the s1 failure path.

Опубликовано: 2026-05-28Изменено: 2026-07-02
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46177
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: ipmi: Add limits to event and receive message requests The driver would just fetch events and receive messages until the BMC said it was done. To avoid issues with BMCs that never say they are done, add a limit of 10 fetches at a time. In addition, an si interface has an attn state it can return from the hardware which is supposed to cause a flag fetch to see if the driver needs to fetch events or message or a few other things. If the attn bit gets stuck, it's a similar problem. So allow messages in between flag fetches so the driver itself doesn't get stuck. This is a more general fix than the previous fix for the specific bad BMC, but should fix the more general issue of a BMC that won't stop saying it has data. This has been there from the beginning of the driver. It's not a bug per-se, but it is accounting for bugs in BMCs.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46178
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: RDMA/mlx4: Fix resource leak on error in mlx4_ib_create_srq() Sashiko points out that mlx4_srq_alloc() was not undone during error unwind, add the missing call to mlx4_srq_free().

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46179
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ASoC: SOF: Don't allow pointer operations on unconfigured streams When reporting the pointer for a compressed stream we report the current I/O frame position by dividing the position by the number of channels multiplied by the number of container bytes. These values default to 0 and are only configured as part of setting the stream parameters so this allows a divide by zero to be configured. Validate that they are non zero, returning an error if not

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46180
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: wifi: brcmfmac: Fix potential use-after-free issue when stopping watchdog task Watchdog task might end between send_sig() and kthread_stop() calls, what results in the use-after-free issue. Fix this by increasing watchdog task reference count before calling send_sig() and dropping it by switching to kthread_stop_put().

Опубликовано: 2026-05-28Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46184
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: sound: ua101: fix division by zero at probe Add a missing sanity check for bNrChannels in detect_usb_format() to prevent a division by zero in playback_urb_complete() and capture_urb_complete(). USB core does not validate class-specific descriptor fields such as bNrChannels, so drivers must verify them before use. If a device provides bNrChannels = 0, frame_bytes becomes zero and is later used as a divisor in the URB completion handlers, leading to a kernel crash.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46185
CRITICAL9.1

In the Linux kernel, the following vulnerability has been resolved: smb/client: fix out-of-bounds read in symlink_data() Since smb2_check_message() returns success without length validation for the symlink error response, in symlink_data() it is possible for iov->iov_len to be smaller than sizeof(struct smb2_err_rsp). If the buffer only contains the base SMB2 header (64 bytes), accessing err->ErrorContextCount (at offset 66) or err->ByteCount later in symlink_data() will cause an out-of-bounds read.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xКРИТИЧЕСКАЯ 9.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46186
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: virtio_bt: validate rx pkt_type header length virtbt_rx_handle() reads the leading pkt_type byte from the RX skb and forwards the remainder to hci_recv_frame() for every event/ACL/SCO/ISO type, without checking that the remaining payload is at least the fixed HCI header for that type. After the preceding patch bounds the backend-supplied used.len to [1, VIRTBT_RX_BUF_SIZE], a one-byte completion still reaches hci_recv_frame() with skb->len already pulled to 0. If the byte happened to be HCI_ACLDATA_PKT, the ACL-vs-ISO classification fast-path in hci_dev_classify_pkt_type() dereferences hci_acl_hdr(skb)->handle whenever the HCI device has an active CIS_LINK, BIS_LINK, or PA_LINK connection, reading two bytes of uninitialized RX-buffer data. The same hazard exists for every packet type the driver accepts because none of the switch cases in virtbt_rx_handle() check skb->len against the per-type minimum HCI header size before handing the frame to the core. After stripping pkt_type, require skb->len to cover the fixed header size for the selected type (event 2, ACL 4, SCO 3, ISO 4) before calling hci_recv_frame(); drop ratelimited otherwise. Unknown pkt_type values still take the original kfree_skb() default path. Use bt_dev_err_ratelimited() because both the length and pkt_type values come from an untrusted backend that can otherwise flood the kernel log.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46187
MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: wifi: rsi: fix kthread lifetime race between self-exit and external-stop RSI driver use both self-exit(kthread_complete_and_exit) and external-stop (kthread_stop) when killing a kthread. Generally, kthread_stop() is called first, and in this case, no particular issues occur. However, in rare instances where kthread_complete_and_exit() is called first and then kthread_stop() is called, a UAF occurs because the kthread object, which has already exited and been freed, is accessed again. Therefore, to prevent this with minimal modification, you must remove kthread_stop() and change the code to wait until the self-exit operation is completed.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46188
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: octeon_ep_vf: add NULL check for napi_build_skb() napi_build_skb() can return NULL on allocation failure. In __octep_vf_oq_process_rx(), the result is used directly without a NULL check in both the single-buffer and multi-fragment paths, leading to a NULL pointer dereference. Add NULL checks after both napi_build_skb() calls, properly advancing descriptors and consuming remaining fragments on failure.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46189
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: RDMA/vmw_pvrdma: Fix double free on pvrdma_alloc_ucontext() error path Sashiko points out that pvrdma_uar_free() is already called within pvrdma_dealloc_ucontext(), so calling it before triggers a double free.

Опубликовано: 2026-05-28Изменено: 2026-07-07
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46190
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: mtd: spi-nor: debugfs: fix out-of-bounds read in spi_nor_params_show() Sashiko noticed an out-of-bounds read [1]. In spi_nor_params_show(), the snor_f_names array is passed to spi_nor_print_flags() using sizeof(snor_f_names). Since snor_f_names is an array of pointers, sizeof() returns the total number of bytes occupied by the pointers (element_count * sizeof(void *)) rather than the element count itself. On 64-bit systems, this makes the passed length 8x larger than intended. Inside spi_nor_print_flags(), the 'names_len' argument is used to bounds-check the 'names' array access. An out-of-bounds read occurs if a flag bit is set that exceeds the array's actual element count but is within the inflated byte-size count. Correct this by using ARRAY_SIZE() to pass the actual number of string pointers in the array.

Опубликовано: 2026-05-28Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46191
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: fbcon: Avoid OOB font access if console rotation fails Clear the font buffer if the reallocation during console rotation fails in fbcon_rotate_font(). The putcs implementations for the rotated buffer will return early in this case. See [1] for an example. Currently, fbcon_rotate_font() keeps the old buffer, which is too small for the rotated font. Printing to the rotated console with a high-enough character code will overflow the font buffer. v2: - fix typos in commit message

Опубликовано: 2026-05-28Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46193
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xfrm: ah: account for ESN high bits in async callbacks AH allocates its temporary auth/ICV layout differently when ESN is enabled: the async ahash setup appends a 4-byte seqhi slot before the ICV or auth_data area, but the async completion callbacks still reconstruct the temporary layout as if seqhi were absent. With an async AH implementation selected, that makes AH copy or compare the wrong bytes on both the IPv4 and IPv6 paths. In UML repro on IPv4 AH with ESN and forced async hmac(sha1), ping fails with 100% packet loss, and the callback logs show the pre-fix drift: ah4 output_done: esn=1 err=0 icv_off=20 expected_off=24 ah4 input_done: esn=1 auth_off=20 expected_auth_off=24 icv_off=32 expected_icv_off=36 Reconstruct the callback-side layout the same way the setup path built it by skipping the ESN seqhi slot before locating the saved auth_data or ICV. Per RFC 4302, the ESN high-order 32 bits participate in the AH ICV computation, so the async callbacks must account for the seqhi slot. Post-fix, the same IPv4 AH+ESN+forced-async-hmac(sha1) UML repro shows the corrected offset (ah4 output_done: esn=1 err=0 icv_off=24 expected_off=24) and ping succeeds; net/ipv4/ah4.o and net/ipv6/ah6.o build clean at W=1. IPv6 AH+ESN was not exercised at runtime, and the change has not been tested against a real async hardware AH engine.

Опубликовано: 2026-05-28Изменено: 2026-06-19
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46194
MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: f2fs: fix node_cnt race between extent node destroy and writeback f2fs_destroy_extent_node() does not set FI_NO_EXTENT before clearing extent nodes. When called from f2fs_drop_inode() with I_SYNC set, concurrent kworker writeback can insert new extent nodes into the same extent tree, racing with the destroy and triggering f2fs_bug_on() in __destroy_extent_node(). The scenario is as follows: drop inode writeback - iput - f2fs_drop_inode // I_SYNC set - f2fs_destroy_extent_node - __destroy_extent_node - while (node_cnt) { write_lock(&et->lock) __free_extent_tree write_unlock(&et->lock) - __writeback_single_inode - f2fs_outplace_write_data - f2fs_update_read_extent_cache - __update_extent_tree_range // FI_NO_EXTENT not set, // insert new extent node } // node_cnt == 0, exit while - f2fs_bug_on(node_cnt) // node_cnt > 0 Additionally, __update_extent_tree_range() only checks FI_NO_EXTENT for EX_READ type, leaving EX_BLOCK_AGE updates completely unprotected. This patch set FI_NO_EXTENT under et->lock in __destroy_extent_node(), consistent with other callers (__update_extent_tree_range and __drop_extent_tree) and check FI_NO_EXTENT for both EX_READ and EX_BLOCK_AGE tree.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 4.7
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46195
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: smb: client: validate dacloffset before building DACL pointers parse_sec_desc(), build_sec_desc(), and the chown path in id_mode_to_cifs_acl() all add the server-supplied dacloffset to pntsd before proving a DACL header fits inside the returned security descriptor. On 32-bit builds a malicious server can return dacloffset near U32_MAX, wrap the derived DACL pointer below end_of_acl, and then slip past the later pointer-based bounds checks. build_sec_desc() and id_mode_to_cifs_acl() can then dereference DACL fields from the wrapped pointer in the chmod/chown rewrite paths. Validate dacloffset numerically before building any DACL pointer and reuse the same helper at the three DACL entry points.

Опубликовано: 2026-05-28Изменено: 2026-06-30
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46196
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: tracepoint: balance regfunc() on func_add() failure in tracepoint_add_func() When a tracepoint goes through the 0 -> 1 transition, tracepoint_add_func() invokes the subsystem's ext->regfunc() before attempting to install the new probe via func_add(). If func_add() then fails (for example, when allocate_probes() cannot allocate a new probe array under memory pressure and returns -ENOMEM), the function returns the error without calling the matching ext->unregfunc(), leaving the side effects of regfunc() behind with no installed probe to justify them. For syscall tracepoints this is particularly unpleasant: syscall_regfunc() bumps sys_tracepoint_refcount and sets SYSCALL_TRACEPOINT on every task. After a leaked failure, the refcount is stuck at a non-zero value with no consumer, and every task continues paying the syscall trace entry/exit overhead until reboot. Other subsystems providing regfunc()/unregfunc() pairs exhibit similarly scoped persistent state. Mirror the existing 1 -> 0 cleanup and call ext->unregfunc() in the func_add() error path, gated on the same condition used there so the unwind is symmetric with the registration.

Опубликовано: 2026-05-28Изменено: 2026-06-19
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46197
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: validate SVM ioctl nattr against buffer size Validate nattr field against the buffer size, preventing out-of-bounds buffer access via user-controlled attribute count. (cherry picked from commit 5eca8bfdfa456c3304ca77523718fe24254c172f)

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46198
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: batman-adv: fix integer overflow on buff_pos Fixing an integer overflow present in batadv_iv_ogm_send_to_if. The size check is done using the int type in batadv_iv_ogm_aggr_packet whereas the buff_pos variable uses the s16 type. This could lead to an out-of-bound read.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46199
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu/vcn4: Prevent OOB reads when parsing dec msg Check bounds against the end of the BO whenever we access the msg.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46200
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: spi: mpc52xx: fix controller deregistration Make sure to deregister the controller before disabling and releasing underlying resources like interrupts and gpios during driver unbind.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46201
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: drm/xe: Fix dma-buf attachment leak in xe_gem_prime_import() When xe_dma_buf_init_obj() fails, the attachment from dma_buf_dynamic_attach() is not detached. Add dma_buf_detach() before returning the error. Note: we cannot use goto out_err here because xe_dma_buf_init_obj() already frees bo on failure, and out_err would double-free it. (cherry picked from commit a828eb185aac41800df8eae4b60501ccc0dbbe51)

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46204
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu/vcn4: Prevent OOB reads when parsing IB Rewrite the IB parsing to use amdgpu_ib_get_value() which handles the bounds checks.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46205
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: staging: media: atomisp: Disallow all private IOCTLs Disallow all private IOCTLs. These aren't quite as safe as one could assume of IOCTL handlers; disable them for now. Instead of removing the code, return in the beginning of the function if cmd is non-zero in order to keep static checkers happy.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46206
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: batman-adv: reject new tp_meter sessions during teardown Prevent tp_meter from starting new sender or receiver sessions after mesh_state has left BATADV_MESH_ACTIVE.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46207
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: vsock/virtio: fix empty payload in tap skb for non-linear buffers For non-linear skbs, virtio_transport_build_skb() goes through virtio_transport_copy_nonlinear_skb() to copy the original payload in the new skb to be delivered to the vsockmon tap device. This manually initializes an iov_iter but does not set iov_iter.count. Since the iov_iter is zero-initialized, the copy length is zero and no payload is actually copied to the monitor interface, leaving data un-initialized. Fix this by removing the linear vs non-linear split and using skb_copy_datagram_iter() with iov_iter_kvec() for all cases, as vhost-vsock already does. This handles both linear and non-linear skbs, properly initializes the iov_iter, and removes the now unused virtio_transport_copy_nonlinear_skb(). While touching this code, let's also check the return value of skb_copy_datagram_iter(), even though it's unlikely to fail.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46208
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: batman-adv: stop tp_meter sessions during mesh teardown TP meter sessions remain linked on bat_priv->tp_list after the netlink request has already finished. When the mesh interface is removed, batadv_mesh_free() currently tears down the mesh without first draining these sessions. A running sender thread or a late incoming tp_meter packet can then keep processing against a mesh instance which is already shutting down. Synchronize tp_meter with the mesh lifetime by stopping all active sessions from batadv_mesh_free() and waiting for sender threads to exit before teardown continues.

Опубликовано: 2026-05-28Изменено: 2026-06-19
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46209
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: drm/gem: Fix inconsistent plane dimension calculation in drm_gem_fb_init_with_funcs() drm_gem_fb_init_with_funcs() computes sub-sampled plane dimensions using plain integer division: unsigned int width = mode_cmd->width / (i ? info->hsub : 1); unsigned int height = mode_cmd->height / (i ? info->vsub : 1); However, the ioctl-level framebuffer_check() in drm_framebuffer.c uses drm_format_info_plane_width/height() which round up dimensions via DIV_ROUND_UP(). This inconsistency corrupts the subsequent GEM object size check for certain pixel format and dimension combinations. For example, with NV12 (vsub=2) and a 1-pixel-tall framebuffer the GEM size validation path sees height=0 instead of height=1. The expression (height - 1) then wraps to UINT_MAX as an unsigned int, causing min_size to overflow and wrap back to a small value. A tiny GEM object therefore passes the size guard, yet when the GPU accesses the chroma plane it will read or write memory beyond the object's bounds. Fix by replacing the open-coded divisions with drm_format_info_plane_width() and drm_format_info_plane_height(), which use DIV_ROUND_UP() and match the calculation already used in framebuffer_check().

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46211
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/msm/gem: fix error handling in msm_ioctl_gem_info_get_metadata() msm_ioctl_gem_info_get_metadata() always returns 0 regardless of errors. When copy_to_user() fails or the user buffer is too small, the error code stored in ret is ignored because the function unconditionally returns 0. This causes userspace to believe the ioctl succeeded when it did not. Additionally, kmemdup() can return NULL on allocation failure, but the return value is not checked. This leads to a NULL pointer dereference in the subsequent copy_to_user() call. Add the missing NULL check for kmemdup() and return ret instead of 0. Note that the SET counterpart (msm_ioctl_gem_info_set_metadata) correctly returns ret. Patchwork: https://patchwork.freedesktop.org/patch/714478/

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46212
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: batman-adv: bla: prevent use-after-free when deleting claims When batadv_bla_del_backbone_claims() removes all claims for a backbone, it does this by dropping the link entry in the hash list. This list entry itself was one of the references which need to be dropped at the same time via batadv_claim_put(). But the batadv_claim_put() must not be done before the last access to the claim object in this function. Otherwise the claim might be freed already by the batadv_claim_release() function before the list entry was dropped.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46214
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: vsock/virtio: fix accept queue count leak on transport mismatch virtio_transport_recv_listen() calls sk_acceptq_added() before vsock_assign_transport(). If vsock_assign_transport() fails or selects a different transport, the error path returns without calling sk_acceptq_removed(), permanently incrementing sk_ack_backlog. After approximately backlog+1 such failures, sk_acceptq_is_full() returns true, causing the listener to reject all new connections. Fix by moving sk_acceptq_added() to after the transport validation, matching the pattern used by vmci_transport and hyperv_transport.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46216
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/xe/hdcp: Add NULL check for media_gt in intel_hdcp_gsc_check_status() When media GT is disabled via configfs, there is no allocation for media_gt, which is kept as NULL. In such scenario, intel_hdcp_gsc_check_status() results in a kernel pagefault error due to >->uc.gsc being evaluated as an invalid memory address. Fix that by introducing a NULL check on media_gt and bailing out early if so. While at it, also drop the NULL check for gsc, since it can't be NULL if media_gt is not NULL. v2: - Get address for gsc only after checking that gt is not NULL. (Shuicheng) - Drop the NULL check for gsc. (Shuicheng) v3: - Add "Fixes" and "Cc: " tags. (Matt) (cherry picked from commit bfaf87e84ca3ca3f6e275f9ae56da47a8b55ffd1)

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46218
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Add bounds checking to ib_{get,set}_value The uvd/vce/vcn code accesses the IB at predefined offsets without checking that the IB is large enough. Check the bounds here. The caller is responsible for making sure it can handle arbitrary return values. Also make the idx a uint32_t to prevent overflows causing the condition to fail.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46219
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: spi: mpc52xx: fix use-after-free on unbind The state machine work is scheduled by the interrupt handler and therefore needs to be cancelled after disabling interrupts to avoid a potential use-after-free.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46220
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu/sdma4: replace BUG_ON with WARN_ON in fence emission sdma_v4_0_ring_emit_fence() contains two BUG_ON(addr & 0x3) assertions that verify fence writeback addresses are dword-aligned. These assertions can be reached from unprivileged userspace via crafted DRM_IOCTL_AMDGPU_CS submissions, causing a fatal kernel panic in a scheduler worker thread. Replace both BUG_ON() calls with WARN_ON() to log the condition without crashing the kernel. A misaligned fence address at this point indicates a driver bug, but crashing the kernel is never the correct response when the assertion is reachable from userspace. The CS IOCTL path is the correct place to filter invalid submissions; the ring emission callback is too late to do anything about it. (cherry picked from commit b90250bd933afd1ba94d86d6b13821997b22b18e)

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46225
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: spi: rspi: fix controller deregistration Make sure to deregister the controller before releasing underlying resources like DMA during driver unbind.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46226
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: spi: fsl: fix controller deregistration Make sure to deregister the controller before releasing underlying resources like DMA during driver unbind.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46227
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: sctp: revalidate list cursor after sctp_sendmsg_to_asoc() in SCTP_SENDALL The SCTP_SENDALL path in sctp_sendmsg() iterates ep->asocs with list_for_each_entry_safe(), which caches the next entry in @tmp before the loop body runs. The body calls sctp_sendmsg_to_asoc(), which may drop the socket lock inside sctp_wait_for_sndbuf(). While the lock is dropped, another thread can SCTP_SOCKOPT_PEELOFF the association cached in @tmp, migrating it to a new endpoint via sctp_sock_migrate() (list_del_init() + list_add_tail() to newep->asocs), and optionally close the new socket which frees the association via kfree_rcu(). The cached @tmp can also be freed by a network ABORT for that association, processed in softirq while the lock is dropped. sctp_wait_for_sndbuf() revalidates @asoc (the current entry) on re-lock via the "sk != asoc->base.sk" and "asoc->base.dead" checks, but nothing revalidates @tmp. After a successful return, the iterator advances to the stale @tmp, yielding either a use-after-free (if the peeled socket was closed) or a list-walk onto the new endpoint's list head (type confusion of &newep->asocs as a struct sctp_association *). Both are reachable from CapEff=0; the type-confusion path gives controlled indirect call via the outqueue.sched->init_sid pointer. Fix by re-deriving @tmp from @asoc after sctp_sendmsg_to_asoc() returns. @asoc is known to still be on ep->asocs at that point: the only callers that list_del an association from ep->asocs are sctp_association_free() (which sets asoc->base.dead) and sctp_assoc_migrate() (which changes asoc->base.sk), and sctp_wait_for_sndbuf() checks both under the lock before any successful return; a tripped check propagates as err < 0 and the loop bails before the re-derive. The SCTP_ABORT path in sctp_sendmsg_check_sflags() returns 0 and the loop hits 'continue' before sctp_sendmsg_to_asoc() is ever called, so the @tmp cached by list_for_each_entry_safe() still covers the lock-held free that ba59fb027307 ("sctp: walk the list of asoc safely") was added for.

Опубликовано: 2026-05-28Изменено: 2026-07-08
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46229
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: Clear VRAM on allocation to prevent stale data exposure KFD VRAM allocations set AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE but not AMDGPU_GEM_CREATE_VRAM_CLEARED, leaving freshly allocated VRAM with stale data from prior use observable by compute kernels. The GEM ioctl path already sets VRAM_CLEARED for all userspace allocations via amdgpu_gem_create_ioctl() and amdgpu_mode_dumb_create(). The KFD path was missing this flag, allowing stale page table remnants to leak into user buffers. This causes crashes in RCCL P2P transport where non-zero data in ptrExchange/head/tail fields corrupts the protocol handshake.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46230
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu/vcn3: Prevent OOB reads when parsing dec msg Check bounds against the end of the BO whenever we access the msg.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46231
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: batman-adv: bla: put backbone reference on failed claim hash insert When batadv_bla_add_claim() fails to insert a new claim into the hash, it leaked a reference to the backbone_gw for which the claim was intended. Call batadv_backbone_gw_put() on the error path to release the reference and avoid leaking the backbone_gw object.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46232
HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: HID: playstation: Clamp num_touch_reports A device would never lie about the number of touch reports would it? If it does the loop in dualshock4_parse_report will read off the end of the touch_reports array, up to about 2 KiB for the maximum number of 256 loop iteraions. The data that is read is emitted via evdev if the DS4_TOUCH_POINT_INACTIVE bit happens to be set. Protect against this by clamping the num_touch_reports value provided by the device to the maximum size of the touch_reports array.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-46233
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: batman-adv: bla: only purge non-released claims When batadv_bla_purge_claims() goes through the list of claims, it is only traversing the hash list with an rcu_read_lock(). Due to a potential parallel batadv_claim_put(), it can happen that it encounters a claim which was actually in the process of being released+freed by batadv_claim_release(). In this case, backbone_gw is set to NULL before the delayed RCU kfree is started. Calling batadv_bla_claim_get_backbone_gw() is then no longer allowed because it would cause a NULL-ptr derefence. To avoid this, only claims with a valid reference counter must be purged. All others are already taken care of.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46234
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: vsock: fix buffer size clamping order In vsock_update_buffer_size(), the buffer size was being clamped to the maximum first, and then to the minimum. If a user sets a minimum buffer size larger than the maximum, the minimum check overrides the maximum check, inverting the constraint. This breaks the intended socket memory boundaries by allowing the vsk->buffer_size to grow beyond the configured vsk->buffer_max_size. Fix this by checking the minimum first, and then the maximum. This ensures the buffer size never exceeds the buffer_max_size.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46235
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: media: saa7164: add ioremap return checks and cleanups Add checks for ioremap return values in saa7164_dev_setup(). If ioremap for BAR0 or BAR2 fails, release the already allocated PCI memory regions, remove the device from the global list, decrement the device count, and return -ENODEV. This prevents potential null pointer dereferences and ensures proper cleanup on memory mapping failures.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46236
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: media: rc: xbox_remote: heed DMA restrictions The buffer for IO must not be part of the device structure because that violates the DMA coherency rules.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-46238
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: batman-adv: stop caching unowned originator pointers in BAT IV BAT IV keeps the last-hop neighbor address in each neigh_node, but some paths also cache an originator pointer derived from a temporary lookup. That pointer is not owned by the neigh_node and may no longer refer to a live originator entry after purge handling runs. Stop storing the auxiliary originator pointer in the BAT IV neighbor state. When BAT IV needs the neighbor originator data, resolve it from the stored neighbor address and drop the reference again after use. [sven: avoid bonding logic for outgoing OGM]

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/CVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46241
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: spi: mpc52xx: fix use-after-free on registration failure Make sure to disable and free the interrupts in case controller registration fails to avoid a potential use-after-free and resource leak. This issue was flagged by Sashiko when reviewing a controller deregistration fix.

Опубликовано: 2026-05-28Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46243
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: smb: client: reject userspace cifs.spnego descriptions cifs.spnego key descriptions contain authority-bearing fields such as pid, uid, creduid, and upcall_target that cifs.upcall treats as kernel-originating inputs. However, userspace can also create keys of this type through request_key(2) or add_key(2), allowing those fields to be supplied without CIFS origin. Only accept cifs.spnego descriptions while CIFS is using its private spnego_cred to request the key.

Опубликовано: 2026-06-01Изменено: 2026-07-08
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
Ссылки
CVE-2026-46244
CRITICAL9.1

In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_inner: Fix IPv6 inner_thoff desync In nft_inner_parse_l2l3(), when processing inner IPv6 packets, ipv6_find_hdr() correctly computes the transport header offset traversing all extension headers, but the result is immediately overwritten with nhoff + sizeof(_ip6h) (40 bytes), which only accounts for the IPv6 base header. This creates a desync between inner_thoff (wrong — points to extension header start) and l4proto (correct — e.g., IPPROTO_TCP), enabling transport header forgery and potential firewall bypass. This issue affects stable versions from Linux 6.2. For comparison, the normal (non-inner) IPv6 path correctly preserves ipv6_find_hdr()'s result. Removing the incorrect overwrite ensures that ipv6_find_hdr()'s calculated transport header offset is preserved, thereby fixing the desynchronization.

Опубликовано: 2026-06-03Изменено: 2026-07-07
CVSS 3.xКРИТИЧЕСКАЯ 9.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
Ссылки
CVE-2026-46273
HIGH8.6

In the Linux kernel, the following vulnerability has been resolved: ibmveth: Disable GSO for packets with small MSS Some physical adapters on Power systems do not support segmentation offload when the MSS is less than 224 bytes. Attempting to send such packets causes the adapter to freeze, stopping all traffic until manually reset. Implement ndo_features_check to disable GSO for packets with small MSS values. The network stack will perform software segmentation instead. The 224-byte minimum matches ibmvnic commit ("ibmvnic: Enforce stronger sanity checks on GSO packets") which uses the same physical adapters in SEA configurations. The issue occurs specifically when the hardware attempts to perform segmentation (gso_segs > 1) with a small MSS. Single-segment GSO packets (gso_segs == 1) do not trigger the problematic LSO code path and are transmitted normally without segmentation. Add an ndo_features_check callback to disable GSO when MSS < 224 bytes. Also call vlan_features_check() to ensure proper handling of VLAN packets, particularly QinQ (802.1ad) configurations where the hardware parser may not support certain offload features. Validated using iptables to force small MSS values. Without the fix, the adapter freezes. With the fix, packets are segmented in software and transmission succeeds. Comprehensive regression testing completedd (MSS tests, performance, stability).

Опубликовано: 2026-06-03Изменено: 2026-06-17
CVSS 3.xВЫСОКАЯ 8.6
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:N/I:N/A:H
Ссылки
CVE-2026-46300
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: skbuff: preserve shared-frag marker during coalescing skb_try_coalesce() can attach paged frags from @from to @to. If @from has SKBFL_SHARED_FRAG set, the resulting @to skb can contain the same externally-owned or page-cache-backed frags, but the shared-frag marker is currently lost. That breaks the invariant relied on by later in-place writers. In particular, ESP input checks skb_has_shared_frag() before deciding whether an uncloned nonlinear skb can skip skb_cow_data(). If TCP receive coalescing has moved shared frags into an unmarked skb, ESP can see skb_has_shared_frag() as false and decrypt in place over page-cache backed frags. Propagate SKBFL_SHARED_FRAG when skb_try_coalesce() transfers paged frags. The tailroom copy path does not need the marker because it copies bytes into @to's linear data rather than transferring frag descriptors.

Опубликовано: 2026-05-23Изменено: 2026-07-02
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-46333
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: ptrace: slightly saner 'get_dumpable()' logic The 'dumpability' of a task is fundamentally about the memory image of the task - the concept comes from whether it can core dump or not - and makes no sense when you don't have an associated mm. And almost all users do in fact use it only for the case where the task has a mm pointer. But we have one odd special case: ptrace_may_access() uses 'dumpable' to check various other things entirely independently of the MM (typically explicitly using flags like PTRACE_MODE_READ_FSCREDS). Including for threads that no longer have a VM (and maybe never did, like most kernel threads). It's not what this flag was designed for, but it is what it is. The ptrace code does check that the uid/gid matches, so you do have to be uid-0 to see kernel thread details, but this means that the traditional "drop capabilities" model doesn't make any difference for this all. Make it all make a *bit* more sense by saying that if you don't have a MM pointer, we'll use a cached "last dumpability" flag if the thread ever had a MM (it will be zero for kernel threads since it is never set), and require a proper CAP_SYS_PTRACE capability to override.

Опубликовано: 2026-05-15Изменено: 2026-07-01
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
Ссылки
CVE-2026-53202
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: accel/ivpu: Fix signed integer truncation in IPC receive Fix potential buffer overflow where firmware-supplied data_size is cast to signed int before being used in min_t(). Large unsigned values (>= 0x80000000) become negative, causing unsigned wraparound and oversized memcpy operations that can overflow the stack buffer. Change min_t(int, ...) to min() as both values are unsigned and can be handled by min() without explicit cast.

Опубликовано: 2026-06-25Изменено: 2026-07-03
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-53203
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: accel/ivpu: Add buffer overflow check in MS get_info_ioctl Add validation that the info size returned from the metric stream info query is not exceeded when checked against the allocated buffer size. If the firmware returns a size larger than the buffer, reject the operation with -EOVERFLOW instead of proceeding with an incorrect buffer copy.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-53205
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: accel/ivpu: Add bounds checks for firmware log indices Add validation that read and write indices in the firmware log buffer are within valid bounds (< data_size) before using them. If out-of-bounds indices are encountered (from firmware), clamp them to safe values instead of proceeding with invalid offsets. This prevents potential out-of-bounds buffer access when firmware supplies invalid log indices.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-53207
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: mm/memory-failure: fix hugetlb_lock AA deadlock in get_huge_page_for_hwpoison Two concurrent madvise(MADV_HWPOISON) calls on the same hugetlb page can trigger a recursive spinlock self-deadlock (AA deadlock) on hugetlb_lock when racing with a concurrent unmap: thread#0 thread#1 -------- -------- madvise(folio, MADV_HWPOISON) -> poisons the folio successfully madvise(folio, MADV_HWPOISON) unmap(folio) try_memory_failure_hugetlb get_huge_page_for_hwpoison spin_lock_irq(&hugetlb_lock) <- held __get_huge_page_for_hwpoison hugetlb_update_hwpoison() -> MF_HUGETLB_FOLIO_PRE_POISONED goto out: folio_put() refcount: 1 -> 0 free_huge_folio() spin_lock_irqsave(&hugetlb_lock) -> AA DEADLOCK! The out: path in __get_huge_page_for_hwpoison() calls folio_put() to drop the GUP reference while the hugetlb_lock is still held by the hugetlb.c wrapper get_huge_page_for_hwpoison(). If concurrent unmap has released the page table mapping reference, folio_put() drops the folio refcount to zero, triggering free_huge_folio() which attempts to re-acquire the non-recursive hugetlb_lock. Fix this by moving hugetlb_lock acquisition from the hugetlb.c wrapper into get_huge_page_for_hwpoison(). Place spin_unlock_irq() before the folio_put() at the out: label so the folio is always released outside the lock. [akpm@linux-foundation.org: fix race, rename label per Miaohe]

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-53208
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: reject BR/EDR signaling packets over MTUsig net/bluetooth/l2cap_core.c:l2cap_sig_channel() accepts BR/EDR signaling packets up to the channel MTU and dispatches each command without enforcing the signaling MTU (MTUsig). A Bluetooth BR/EDR peer within radio range can send a fixed-channel CID 0x0001 packet that is larger than MTUsig and contains many L2CAP_ECHO_REQ commands before pairing. In a real-radio stock-kernel run, one 681-byte signaling packet containing 168 zero-length ECHO_REQ commands made the target transmit 168 ECHO_RSP frames over about 220 ms. Impact: a Bluetooth BR/EDR peer within radio range, before pairing, can force 168 ECHO_RSP frames from one 681-byte fixed-channel signaling packet containing packed ECHO_REQ commands. Define Linux's BR/EDR signaling MTU as the spec minimum of 48 bytes and reject any larger signaling packet with one L2CAP_COMMAND_REJECT_RSP carrying L2CAP_REJ_MTU_EXCEEDED before any command is dispatched. The Bluetooth Core spec wording for MTUExceeded says the reject identifier shall match the first request command in the packet, and that packets containing only responses shall be silently discarded. Linux intentionally deviates from that prescription: silently discarding desynchronizes the peer because the remote stack never learns its responses were dropped, and locating the first request command requires walking command headers past MTUsig, i.e. processing bytes from a packet we have already decided is too large to process. We therefore always emit one reject and use the identifier from the first command header, a single fixed-offset byte read. The unrestricted BR/EDR signaling parser and ECHO_REQ response path both trace to the initial git import; no later introducing commit is available for a Fixes tag.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-53209
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_sync: reject oversized Broadcast Announcement prepend Existing advertising instances can already hold the maximum extended advertising payload. When hci_adv_bcast_annoucement() prepends the Broadcast Announcement service data to that payload, the combined data may no longer fit in the temporary buffer used to rebuild the advertising data. Reject that case before copying the existing payload and report the failure through the device log. This keeps the existing advertising data intact and avoids overrunning the temporary buffer.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-53210
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: tee: shm: fix shm leak in register_shm_helper() register_shm_helper() allocates shm before calling iov_iter_npages(). If iov_iter_npages() returns 0, the function jumps to err_ctx_put and leaks shm. This can be triggered by TEE_IOC_SHM_REGISTER with struct tee_ioctl_shm_register_data where length is 0. Jump to err_free_shm instead.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-53212
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_tunnel: fix use-after-free on object destroy nft_tunnel_obj_destroy() calls metadata_dst_free() which directly kfree()s the metadata_dst, ignoring the dst_entry refcount. Packets that took a reference via dst_hold() in nft_tunnel_obj_eval() and are still queued (e.g. in a netem qdisc) are left with a dangling pointer. When these packets are eventually dequeued, dst_release() operates on freed memory. Replace metadata_dst_free() with dst_release() so the metadata_dst is freed only after all references are dropped. The dst subsystem already handles metadata_dst cleanup in dst_destroy() when DST_METADATA is set.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-53213
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/vc4: fix krealloc() memory leak Don't just overwrite the original pointer passed to krealloc() with its return value without checking latter: MEM = krealloc(MEM, SZ, GFP); If krealloc() returns NULL, that erases the pointer to the still allocated memory, hence leaks this memory. Instead, use a temporary variable, check it's not NULL and only then assign it to the original pointer: TMP = krealloc(MEM, SZ, GFP); if (!TMP) return; MEM = TMP; While on it, use krealloc_array().

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-53214
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ipv6: Fix a potential NPD in cleanup_prefix_route() addrconf_get_prefix_route() can return the fib6_null_entry sentinel entry which has a NULL fib6_table pointer. Therefore, before setting the route's expiration time, check that we are not working with this entry, as otherwise a NPD will be triggered [1]. Note that the other callers of addrconf_get_prefix_route() are not susceptible to this bug: 1. addrconf_prefix_rcv(): Requests a route with the 'RTF_ADDRCONF | RTF_PREFIX_RT' flags which are not set on fib6_null_entry. 2. modify_prefix_route(): Fixed by commit a747e02430df ("ipv6: avoid possible NULL deref in modify_prefix_route()"). 3. __ipv6_ifa_notify(): Calls ip6_del_rt() which specifically checks for fib6_null_entry and returns an error. [1] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000006: 0000 [#1] SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037] [...] Call Trace: __kasan_check_byte (mm/kasan/common.c:573) lock_acquire.part.0 (kernel/locking/lockdep.c:5842 (discriminator 1)) _raw_spin_lock_bh (kernel/locking/spinlock.c:182 (discriminator 1)) cleanup_prefix_route (net/ipv6/addrconf.c:1280) ipv6_del_addr (net/ipv6/addrconf.c:1342) inet6_addr_del.isra.0 (net/ipv6/addrconf.c:3119) inet6_rtm_deladdr (net/ipv6/addrconf.c:4812) rtnetlink_rcv_msg (net/core/rtnetlink.c:6997) netlink_rcv_skb (net/netlink/af_netlink.c:2555) netlink_unicast (net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1899) __sock_sendmsg (net/socket.c:802 (discriminator 4)) ____sys_sendmsg (net/socket.c:2698) ___sys_sendmsg (net/socket.c:2752) __sys_sendmsg (net/socket.c:2784) 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:121)

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-53215
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: net: mvpp2: refill RX buffers before XDP or skb use The RX error path returns the current descriptor buffer to the hardware BM pool. That is only valid while the driver still owns the buffer. mvpp2_rx_refill() can fail after the current buffer has been handed to XDP or attached to an skb. In those cases mvpp2_run_xdp() may have recycled, redirected, or queued the page for XDP_TX, and an skb free also retires the data buffer. Returning such a buffer to BM lets hardware DMA into memory that is no longer owned by the RX ring. Refill the BM pool before handing the current buffer to XDP or to the skb. If the allocation fails there, drop the packet and return the still-owned current buffer to BM, preserving the pool depth. Once the refill succeeds, later local drops retire/free the current buffer instead of returning it to BM.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-53216
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: net: mvpp2: limit XDP frame size to the RX buffer mvpp2 has short and long BM pools, and short pool buffers can be smaller than PAGE_SIZE. The XDP path nevertheless initializes every xdp_buff with PAGE_SIZE as frame size. XDP helpers use frame_sz to validate tail growth and to derive the hard end of the data area. Advertising PAGE_SIZE for short buffers can let bpf_xdp_adjust_tail() grow a packet past the real allocation, corrupting memory or later tripping skb tailroom checks. Initialize the XDP buffer with bm_pool->frag_size so XDP tailroom matches the actual buffer backing the packet.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-53217
HIGH8.6

In the Linux kernel, the following vulnerability has been resolved: net: mvpp2: sync RX data at the hardware packet offset mvpp2 programs the RX queue packet offset, so hardware writes received data at dma_addr + MVPP2_SKB_HEADROOM. The current CPU sync starts at dma_addr and only covers rx_bytes + MVPP2_MH_SIZE bytes, which syncs the unused headroom and misses the same number of bytes at the packet tail. On non-coherent DMA systems this can leave the CPU reading stale cache contents for the end of the received frame. Use dma_sync_single_range_for_cpu() with MVPP2_SKB_HEADROOM as the range offset so the sync covers the Marvell header and packet data actually written by hardware.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xВЫСОКАЯ 8.6
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:L
Ссылки
CVE-2026-53218
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_exthdr: fix register tracking for F_PRESENT flag nft_exthdr_init() passes user-controlled priv->len to nft_parse_register_store(), which marks that many bytes in the register bitmap as initialized. However, when NFT_EXTHDR_F_PRESENT is set, the eval paths write only 1 byte (nft_reg_store8) or 4 bytes (*dest = 0 on TCP/DCCP error path). When len > 4, registers beyond the first are never written, retaining uninitialized stack data from nft_regs. Bail out if userspace requests too much data when F_PRESENT is set.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-53219
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: x_tables: avoid leaking percpu counter pointers The native and compat get-entries paths copy the fixed rule entry header from the kernelized rule blob to userspace before overwriting the entry's counter fields with a sanitized counter snapshot. On SMP kernels, entry->counters.pcnt contains the percpu allocation address used by x_tables rule counters. A caller can provide a userspace buffer that faults during the initial fixed-header copy after pcnt has been copied but before the later sanitized counter copy runs. The syscall then returns -EFAULT while leaving the raw percpu pointer in userspace. Copy only the fixed entry prefix before counters from the kernelized rule blob, then copy the sanitized counter snapshot into the counter field. Apply this ordering to the IPv4, IPv6, and ARP native and compat get-entries implementations so a fault cannot expose the internal percpu counter pointer.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-53220
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: revalidate bridge ports ebt_redirect_tg() dereferences br_port_get_rcu() return without a NULL check, causing a kernel panic when the bridge port has been removed between the original hook invocation and an NFQUEUE reinject. A mere NULL check isn't sufficient, however. As sashiko review points out userspace can not only remove the port from the bridge, it could also place the device in a different virtual device, e.g. macvlan. If this happens, we must drop the packet, there is no way for us to reinject it into the bridge path. Switch to _upper API, we don't need the bridge port structure. Also, this fix keeps another bug intact: Both nfnetlink_log and nfnetlink_queue use CONFIG_BRIDGE_NETFILTER too aggressive, which prevents certain logging features when queueing in bridge family: NETFILTER_FAMILY_BRIDGE can be enabled while the old CONFIG_BRIDGE_NETFILTER cruft is off. Fixes tag is a common ancestor, this was always broken.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-53221
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ip6_vti: fix incorrect tunnel matching in vti6_tnl_lookup() In vti6_tnl_lookup(), when an exact match for a tunnel fails, the code falls back to searching for wildcard tunnels: - Tunnels matching the packet's local address, with any remote address wildcard remote). - Tunnels matching the packet's remote address, with any local address (wildcard local). However, vti6 stores all these different types of tunnels in the same hash table (ip6n->tnls_r_l) prone to hash collisions. The bug is that the fallback search loops in vti6_tnl_lookup() were missing checks to ensure that the candidate tunnel actually has a wildcard address.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-53223
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: net: guard timestamp cmsgs to real error queue skbs skb_is_err_queue() treats PACKET_OUTGOING as the sole marker for an skb from sk_error_queue. That assumption is not true for AF_PACKET sockets: outgoing packet taps are also delivered to packet sockets with skb->pkt_type == PACKET_OUTGOING, but their skb->cb is owned by AF_PACKET instead of struct sock_exterr_skb. If such an skb is received with timestamping enabled, the generic timestamp cmsg path can read AF_PACKET control-buffer state as sock_exterr_skb::opt_stats. With SO_RXQ_OVFL enabled, the packet drop counter overlaps opt_stats. An odd drop count makes the path emit SCM_TIMESTAMPING_OPT_STATS with skb->len and skb->data. For non-linear skbs this copies past the linear head and can trigger hardened usercopy or disclose adjacent heap contents. Keep skb_is_err_queue() local to net/socket.c, but make it verify that the PACKET_OUTGOING marker is paired with the sock_rmem_free destructor installed by sock_queue_err_skb(). AF_PACKET receive skbs use normal receive ownership and no longer pass as error-queue skbs, while legitimate sk_error_queue entries keep the PACKET_OUTGOING marker and sock_rmem_free ownership.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-53225
CRITICAL9.1

In the Linux kernel, the following vulnerability has been resolved: sctp: fix uninit-value in __sctp_rcv_asconf_lookup() __sctp_rcv_asconf_lookup() in net/sctp/input.c only checks that the ASCONF chunk can hold the ADDIP header and a parameter header, then calls af->from_addr_param(), which reads the full address (16 bytes for IPv6) trusting the parameter's declared length. An unauthenticated peer can send a truncated trailing ASCONF chunk that declares an IPv6 address parameter but stops after the 4-byte parameter header; reached from the no-association lookup path, from_addr_param() then reads uninitialized bytes past the parameter. Impact: an unauthenticated SCTP peer makes the receive path read up to 16 bytes of uninitialized memory past a truncated ASCONF address parameter. The sibling __sctp_rcv_init_lookup() bounds parameters with sctp_walk_params(); this path open-codes the fetch and omits the bound. Verify the whole address parameter lies within the chunk before from_addr_param() reads it, the same class of fix as commit 51e5ad549c43 ("net: sctp: fix KMSAN uninit-value in sctp_inq_pop").

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xКРИТИЧЕСКАЯ 9.1
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Ссылки
CVE-2026-53227
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: openvswitch: fix possible kfree_skb of ERR_PTR After the patch in the "Fixes" tag, the allocation of the "reply" skb can happen either before or after locking the ovs_mutex. However, error cleanups still follow the classical reversed order, assuming "reply" is allocated before locking: it is freed after unlocking. If "reply" allocation happens after locking the mutex and it fails, "reply" is left with an ERR_PTR, and execution jumps to the correspondent cleanup stage which will try to free an invalid pointer. Fix this by setting the pointer to NULL after having saved its error value.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-53228
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ipv6: sit: reload inner IPv6 header after GSO offloads ipip6_tunnel_xmit() caches the inner IPv6 header pointer at function entry and continues using it after iptunnel_handle_offloads(). For GSO skbs, iptunnel_handle_offloads() calls skb_header_unclone(). When the skb header is cloned, skb_header_unclone() can call pskb_expand_head(), which may move the skb head. The pskb_expand_head() contract requires pointers into the skb header to be reloaded after the call. If the later skb_realloc_headroom() branch is not taken, SIT uses the stale iph6 pointer to read the inner hop limit and DS field. That can read from a freed skb head after the old head's remaining clone is released. Reload iph6 after the offload helper succeeds and before subsequent reads from the inner IPv6 header. Keep the existing reload after skb_realloc_headroom(), since that branch can also replace the skb.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xКРИТИЧЕСКАЯ 9.8
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Ссылки
CVE-2026-53229
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: xsk: Fix DMA and xdp_frame leak on XDP_TX xmit failure In the XSK branch of mlx5e_xmit_xdp_buff(), when sq->xmit_xdp_frame() returns false (e.g. XDPSQ is full), the function returns without unmapping the DMA address or freeing the xdp_frame allocated by xdp_convert_zc_to_xdp_frame(). The xdpi_fifo push only happens on success, so the completion path cannot recover these entries. With CONFIG_DMA_API_DEBUG=y, the leak surfaces on driver unbind: DMA-API: pci 0000:08:00.0: device driver has pending DMA allocations while released from device [count=1116] One of leaked entries details: [device address=0x000000010ffd7028] [size=1534 bytes] [mapped with DMA_TO_DEVICE] [mapped as phy] WARNING: kernel/dma/debug.c:881 at dma_debug_device_change+0x127/0x180 ... DMA-API: Mapped at: debug_dma_map_phys+0x4b/0xd0 dma_map_phys+0xfd/0x2d0 mlx5e_xdp_handle+0x5ae/0xac0 [mlx5_core] mlx5e_xsk_skb_from_cqe_mpwrq_linear+0xc4/0x170 [mlx5_core] mlx5e_handle_rx_cqe_mpwrq+0xc1/0x290 [mlx5_core] Add the missing unmap + xdp_return_frame, matching the cleanup already done in mlx5e_xdp_xmit(). has_frags is rejected earlier in this branch, so no per-frag unmap is needed.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-53230
HIGH8.7

In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Fix slab-out-of-bounds in mlx5_query_nic_vport_mac_list mlx5_query_nic_vport_mac_list() sizes its firmware command buffer using the PF's log_max_current_uc/mc_list capabilities. When querying a VF vport with a larger configured max (via devlink), the firmware response can overflow this buffer: BUG: KASAN: slab-out-of-bounds in mlx5_query_nic_vport_mac_list+0x453/0x4c0 [mlx5_core] Read of size 4 at addr ff1100013ffc8a12 by task kworker/u96:2/385 CPU: 12 UID: 0 PID: 385 Comm: kworker/u96:2 Not tainted 7.0.0-rc6+ #1 PREEMPT Hardware name: QEMU Standard PC (Q35 + ICH9, 2009) Workqueue: mlx5_esw_wq esw_vport_change_handler [mlx5_core] Call Trace: dump_stack_lvl+0x69/0xa0 print_report+0x176/0x4e4 kasan_report+0xc8/0x100 mlx5_query_nic_vport_mac_list+0x453/0x4c0 [mlx5_core] esw_update_vport_addr_list+0x2e3/0xda0 [mlx5_core] esw_vport_change_handle_locked+0xa1f/0x1060 [mlx5_core] esw_vport_change_handler+0x6a/0x90 [mlx5_core] process_one_work+0x87f/0x15e0 worker_thread+0x62b/0x1020 kthread+0x375/0x490 ret_from_fork+0x4dc/0x810 ret_from_fork_asm+0x11/0x20 Fix by querying the vport's own HCA caps to size the buffer correctly. Refactor the function to allocate and return the MAC list internally, removing the caller's dependency on knowing the correct max.

Опубликовано: 2026-06-25Изменено: 2026-07-02
CVSS 3.xВЫСОКАЯ 8.7
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:H
Ссылки
GHSA-m38g-vww2-mvgx
HIGH7.5

Talos Linux has a local privilege escalation from untrusted workloads

Опубликовано: 2026-05-07Изменено: 2026-06-08
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:C/C:H/I:H/A:N
Ссылки