Все бюллетени/p11/ALT-PU-2026-7006-43
ALT-PU-2026-7006-43

Обновление пакета kernel-image-6.12 в ветке p11

Версия6.12.85-alt1
Задание#416828
Опубликовано2026-09-05
Макс. серьёзностьCRITICAL
Серьёзность:

Закрытые проблемы (1546)

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: 2026-08-06
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
BDU:2026-03485
MEDIUM5.5

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

Опубликовано: 2026-03-23Изменено: 2026-08-31
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
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
BDU:2026-03487
MEDIUM5.5

Уязвимость функции xfarray_destroy() и xfblob_destroy() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-03-23Изменено: 2026-08-31
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
BDU:2026-03582
MEDIUM5.5

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

Опубликовано: 2026-03-24Изменено: 2026-08-31
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
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
BDU:2026-04167
MEDIUM6.2

Уязвимость функции dvb_ringbuffer_init() модуля drivers/media/dvb-core/dmxdev.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-03-29Изменено: 2026-05-26
CVSS 3.xСРЕДНЯЯ 6.2
CVSS:3.x/AV:L/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:H
CVSS 2.0СРЕДНЯЯ 5.2
CVSS:2.0/AV:L/AC:H/Au:N/C:P/I:P/A:C
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
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: 2026-08-03
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
BDU:2026-04644
MEDIUM5.5

Уязвимость компонента ntfs3 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-04-05Изменено: 2026-08-31
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
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
BDU:2026-04852
HIGH7.5

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

Опубликовано: 2026-04-07Изменено: 2026-08-30
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
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
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
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
BDU:2026-05019
MEDIUM5.5

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

Опубликовано: 2026-04-12Изменено: 2026-08-31
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
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: 2026-08-03
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
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
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
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
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
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
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: 2026-08-04
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
BDU:2026-06430
HIGH7.8

Уязвимость функции espintcp_close() ядра операционной системы Linux, позволяющая нарушителю выполнить произвольный код

Опубликовано: 2026-05-07Изменено: 2026-08-30
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
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
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
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
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
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
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
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
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
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
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
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
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: 2026-08-30
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
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
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: 2026-08-30
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
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
BDU:2026-07605
HIGH7.8

Уязвимость модуля безопасности ядра AppArmor операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-05-31Изменено: 2026-08-31
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
BDU:2026-07606
HIGH7.8

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

Опубликовано: 2026-05-31Изменено: 2026-08-31
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
BDU:2026-07607
MEDIUM6.3

Уязвимость модуля безопасности ядра AppArmor операционной системы Linux, позволяющая нарушителю оказать воздействие на целостность и доступность защищаемой информации

Опубликовано: 2026-05-31Изменено: 2026-08-31
CVSS 3.xСРЕДНЯЯ 6.3
CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:L/AC:H/Au:S/C:N/I:C/A:C
BDU:2026-07608
HIGH7.8

Уязвимость модуля безопасности ядра AppArmor операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-05-31Изменено: 2026-08-31
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
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
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
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
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
BDU:2026-07837
HIGH7.8

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

Опубликовано: 2026-06-04Изменено: 2026-08-30
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
BDU:2026-07881
MEDIUM6.6

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

Опубликовано: 2026-06-07Изменено: 2026-08-31
CVSS 3.xСРЕДНЯЯ 6.6
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:H
CVSS 2.0СРЕДНЯЯ 5.7
CVSS:2.0/AV:L/AC:L/Au:S/C:P/I:P/A:C
BDU:2026-07882
MEDIUM5.5

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

Опубликовано: 2026-06-07Изменено: 2026-08-31
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
BDU:2026-07883
HIGH7.8

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

Опубликовано: 2026-06-07Изменено: 2026-08-31
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
BDU:2026-07884
MEDIUM5.5

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

Опубликовано: 2026-06-07Изменено: 2026-08-31
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
BDU:2026-07885
HIGH7.8

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

Опубликовано: 2026-06-07Изменено: 2026-08-31
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
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
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: 2026-08-31
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
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
BDU:2026-08416
HIGH7.5

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

Опубликовано: 2026-06-16Изменено: 2026-08-31
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
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
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: 2026-08-30
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
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
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: 2026-08-03
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
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
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
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
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
BDU:2026-08749
HIGH7.1

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

Опубликовано: 2026-06-24Изменено: 2026-08-03
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
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
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
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
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
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
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: 2026-08-03
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
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: 2026-08-03
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
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: 2026-08-03
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
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
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
BDU:2026-08760
CRITICAL9.4

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

Опубликовано: 2026-06-25Изменено: 2026-08-03
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
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
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
BDU:2026-08902
CRITICAL9.1

Уязвимость модулей net/ipv4/icmp.c и net/ipv6/icmp.c ядра операционной системы Linux, позволяющая нарушителю 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:N/I:H/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.4
CVSS:2.0/AV:N/AC:L/Au:N/C:N/I:C/A:C
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: 2026-07-01Изменено: 2026-07-15
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
BDU:2026-09434
MEDIUM6.6

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

Опубликовано: 2026-07-07Изменено: 2026-07-15
CVSS 3.xСРЕДНЯЯ 6.6
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:H
CVSS 2.0СРЕДНЯЯ 5.7
CVSS:2.0/AV:L/AC:L/Au:S/C:P/I:P/A:C
BDU:2026-09446
MEDIUM5.5

Уязвимость компонента fs/xattr ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-07-07Изменено: 2026-07-15
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 4.9
CVSS:2.0/AV:L/AC:L/Au:N/C:N/I:N/A:C
BDU:2026-09448
HIGH7.8

Уязвимость функции ep_free() компонента eventpoll.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-07-07Изменено: 2026-08-09
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
BDU:2026-09450
MEDIUM5.5

Уязвимость компонента net/netfilter/ipset ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-07-07Изменено: 2026-08-04
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
BDU:2026-09454
HIGH7.8

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

Опубликовано: 2026-07-07Изменено: 2026-08-03
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
BDU:2026-09455
HIGH7.8

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

Опубликовано: 2026-07-07Изменено: 2026-08-03
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
BDU:2026-09456
MEDIUM5.5

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

Опубликовано: 2026-07-07Изменено: 2026-08-31
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
BDU:2026-09457
HIGH7.8

Уязвимость компонента perf ядра операционной системы Linux, связанная с истечением срока действия ресурса, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-07-07Изменено: 2026-08-04
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
BDU:2026-09460
HIGH7.8

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

Опубликовано: 2026-07-07Изменено: 2026-08-04
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
BDU:2026-09717
CRITICAL9.8

Уязвимость функции tls_do_encryption компонента net/tls/tls_sw.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-07-14Изменено: 2026-08-30
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
BDU:2026-10167
HIGH7.1

Уязвимость функции nvme_dbbuf_set() модуля drivers/nvme/host/pci.c драйвера NVME ядра Linux, позволяющая нарушителю повысить свои привилегии или выполнить произвольный код

Опубликовано: 2026-07-20Изменено: 2026-08-03
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
BDU:2026-10711
MEDIUM5.5

Уязвимость функции alps_raw_event() модуля drivers/hid/hid-alps.c драйвера подсистемы устройств пользовательского интерфейса ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10712
MEDIUM5.5

Уязвимость функции s32ton() модуля drivers/hid/hid-core.c драйвера подсистемы устройств пользовательского интерфейса ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10714
MEDIUM5.5

Уязвимость функции build_report() модуля net/xfrm/xfrm_user.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10715
MEDIUM5.5

Уязвимость функции build_polexpire() модуля net/xfrm/xfrm_user.c реализации сетевых функций ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10716
MEDIUM5.5

Уязвимость функции rxrpc_server_keyring() модуля net/rxrpc/server_key.c поддержки сокетов сеанса RxRPC ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10718
MEDIUM5.5

Уязвимость функции init_amd_zen1() модуля arch/x86/kernel/cpu/amd.c поддержки платформы x86 ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10720
CRITICAL9.8

Уязвимость функции smc_tcp_syn_recv_sock() модуля net/smc/af_smc.c реализации семейства протоколов сокетов SMC ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10721
HIGH8.8

Уязвимость функции smb_lazy_parent_lease_break_close() модуля fs/smb/server/oplock.c подсистемы Smb ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-29Изменено: 2026-08-18
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.0
CVSS:2.0/AV:N/AC:L/Au:S/C:C/I:C/A:C
BDU:2026-10722
MEDIUM4.8

Уязвимость функции check_removing_space_info() модуля fs/btrfs/block-group.c файловой системы Btrfs ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-07-29Изменено: 2026-08-30
CVSS 3.xСРЕДНЯЯ 4.8
CVSS:3.x/AV:A/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.3
CVSS:2.0/AV:A/AC:H/Au:S/C:N/I:N/A:C
BDU:2026-10723
HIGH7.1

Уязвимость функции tcf_csum_act() модуля net/sched/act_csum.c подсистемы управления трафиком net/sched ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10725
MEDIUM5.5

Уязвимость функции nvme_poll() модуля drivers/nvme/host/pci.c драйвера NVME ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10726
MEDIUM5.5

Уязвимость функций session_free(), hidp_session_remove(), hidp_session_thread() модуля net/bluetooth/hidp/core.c подсистемы Bluetooth ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10727
MEDIUM5.5

Уязвимость функций l2cap_register_user(), l2cap_unregister_user() модуля net/bluetooth/l2cap_core.c подсистемы Bluetooth ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-07-29
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
BDU:2026-10728
CRITICAL9.8

Уязвимость функции x25_queue_rx_frame() модуля net/x25/x25_in.c реализации сетевых функций ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10729
CRITICAL9.8

Уязвимость функций __ksmbd_close_fd() и ksmbd_reopen_durable_fd() модуля fs/smb/server/vfs_cache.c файловой системы Smb ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10730
CRITICAL9.8

Уязвимость функции smb2_get_ea() модуля fs/smb/server/smb2pdu.c файловой системы Smb ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10731
CRITICAL9.8

Уязвимость функции mptcp_subflow_init() модуля net/mptcp/protocol.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10732
CRITICAL9.8

Уязвимость функции seg6_build_state() модуля net/ipv6/seg6_iptunnel.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10733
CRITICAL9.8

Уязвимость функций batadv_bla_claim_dump_entry() и batadv_bla_backbone_dump() модуля net/batman-adv/bridge_loop_avoidance.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10736
HIGH8.0

Уязвимость функции me2600_xilinx_download() модуля drivers/comedi/drivers/me_daq.c поддержки устройств сбора данных ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10737
HIGH8.0

Уязвимость функции me4000_xilinx_download() модуля drivers/comedi/drivers/me4000.c поддержки устройств сбора данных ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-29Изменено: 2026-08-18
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
BDU:2026-10887
HIGH7.8

Уязвимость функции ti_adc_read_measurement() модуля drivers/iio/adc/ti-adc161s626.c драйвера различных типов встроенных датчиков ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30Изменено: 2026-08-18
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
BDU:2026-10888
HIGH7.8

Уязвимость функции usbtmc_release() модуля drivers/usb/class/usbtmc.c драйвера устройств шины USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30Изменено: 2026-08-18
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
BDU:2026-10889
HIGH7.8

Уязвимость функции f_audio_out_ep_complete() модуля drivers/usb/gadget/function/f_uac1_legacy.c драйвера гаджетов USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30Изменено: 2026-08-18
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
BDU:2026-10890
HIGH7.8

Уязвимость функции zynqmp_efuse_access() модуля drivers/nvmem/zynqmp_nvmem.c драйвера устройств NVMEM (энергонезависимой памяти) ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30Изменено: 2026-08-18
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
BDU:2026-10891
HIGH7.8

Уязвимость функции tpacket_snd() модуля net/packet/af_packet.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30Изменено: 2026-08-18
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
BDU:2026-10895
HIGH7.8

Уязвимость модуля net/netfilter/nf_conntrack_netlink.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30Изменено: 2026-08-18
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
BDU:2026-10898
HIGH7.1

Уязвимость функции fastrpc_init_create_static_process() модуля drivers/misc/fastrpc.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30Изменено: 2026-08-18
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/AV:A/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.5
CVSS:2.0/AV:A/AC:H/Au:S/C:C/I:C/A:C
BDU:2026-10901
HIGH7.8

Уязвимость функции buildid_show() модуля drivers/xen/privcmd.c драйвера устройств кадрового буфера ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30Изменено: 2026-08-18
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
BDU:2026-10903
HIGH7.0

Уязвимость функции vxlan_na_create() модуля drivers/net/vxlan/vxlan_core.c драйвера сетевых устройств ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30Изменено: 2026-08-18
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
BDU:2026-10904
HIGH7.0

Уязвимость функции ucsi_notify_common() модуля drivers/usb/typec/ucsi/ucsi.c драйвера интерфейса разъема USB Type C (UCSI) ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30Изменено: 2026-08-18
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
BDU:2026-10908
HIGH7.0

Уязвимость функции dwc2_hsotg_udc_stop() модуля drivers/usb/dwc2/gadget.c драйвера устройств шины USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30
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
BDU:2026-10909
HIGH7.0

Уязвимость функции __cdns3_gadget_init() модуля drivers/usb/cdns3/cdns3-gadget.c драйвера устройств шины USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30Изменено: 2026-08-18
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
BDU:2026-10910
HIGH7.0

Уязвимость функции br_nd_send() модуля net/bridge/br_arp_nd_proxy.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30Изменено: 2026-08-18
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
BDU:2026-10912
MEDIUM5.5

Уязвимость функции rxrpc_destroy_call() модуля net/rxrpc/call_object.c поддержки сокетов сеанса RxRPC ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-07-30Изменено: 2026-08-18
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
BDU:2026-10914
MEDIUM5.7

Уязвимость функции atmio16d_attach() модуля drivers/comedi/drivers/ni_atmio16d.c поддержки устройств сбора данных ядра операционной системы Linux, позволяющая нарушителю, действующему удалённо, вызвать отказ в обслуживании

Опубликовано: 2026-07-30Изменено: 2026-08-18
CVSS 3.xСРЕДНЯЯ 5.7
CVSS:3.x/AV:A/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:A/AC:L/Au:S/C:N/I:N/A:C
BDU:2026-10916
HIGH7.0

Уязвимость функции drm_compat_ioctl() модуля drivers/gpu/drm/drm_ioc32.c драйвера инфраструктуры прямого рендеринга (DRI) ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30Изменено: 2026-08-18
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
BDU:2026-10917
HIGH7.0

Уязвимость функции ulpi_register_interface() модуля drivers/usb/common/ulpi.c драйвера устройств шины USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-07-30Изменено: 2026-08-18
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
BDU:2026-11067
MEDIUM5.5

Уязвимость функции bcm_vk_read() модуля drivers/misc/bcm-vk/bcm_vk_msg.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11087
HIGH7.9

Уязвимость функции vmload_vmsave_interception() модуля arch/x86/kvm/svm/svm.c подсистемы виртуализации на платформе x86 ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-05Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 7.9
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:C/C:L/I:L/A:H
CVSS 2.0СРЕДНЯЯ 5.7
CVSS:2.0/AV:L/AC:L/Au:S/C:P/I:P/A:C
BDU:2026-11088
HIGH8.6

Уязвимость функции xfrm6_get_saddr() модуля net/ipv6/xfrm6_policy.c реализации протокола IPv6 ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-05Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 8.6
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.0
CVSS:2.0/AV:N/AC:L/Au:N/C:P/I:P/A:C
BDU:2026-11089
HIGH7.1

Уязвимость функции switchtec_ntb_init_mw() модуля drivers/ntb/hw/mscc/ntb_hw_switchtec.c драйвера непрозрачных мостов ядра операционной системы Linux, позволяющая нарушителю получить доступ к защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11090
HIGH7.8

Уязвимость функции arm_cmn_discover() модуля drivers/perf/arm-cmn.c драйвера мониторинга производительности ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11091
CRITICAL9.4

Уязвимость функции __ioam6_fill_trace_data() и ioam6_validate_trace_hdr() ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-05Изменено: 2026-08-31
CVSS 3.xКРИТИЧЕСКАЯ 9.4
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.7
CVSS:2.0/AV:N/AC:L/Au:N/C:P/I:C/A:C
BDU:2026-11092
HIGH8.2

Уязвимость функции tcpmss_mt() модуля net/netfilter/xt_tcpmss.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-05Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 8.2
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H
CVSS 2.0ВЫСОКАЯ 8.5
CVSS:2.0/AV:N/AC:L/Au:N/C:P/I:N/A:C
BDU:2026-11093
HIGH7.8

Уязвимость функции pruss_clk_mux_setup() модуля drivers/soc/ti/pruss.c драйвера SOC (система на кристалле) ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11094
HIGH7.5

Уязвимость функции fore200e_shutdown() модуля drivers/atm/fore200e.c драйвера сетевого адаптера ATM ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-05Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:N/AC:H/Au:M/C:C/I:C/A:C
BDU:2026-11095
HIGH7.8

Уязвимость функции kfd_event_page_set() модуля drivers/gpu/drm/amd/amdkfd/kfd_events.c драйвера инфраструктуры прямого рендеринга (DRI) видеокарт AMD ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11096
HIGH7.8

Уязвимость функции mtk_mdp_probe() модуля drivers/media/platform/mediatek/mdp/mtk_mdp_core.c драйвера мультимедийных устройств ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11097
HIGH7.8

Уязвимость функции pci_slot_trylock() модуля drivers/pci/pci.c драйвера устройств PCI ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11098
HIGH7.8

Уязвимость функции __get_sregs2() модуля arch/x86/kvm/x86.c подсистемы виртуализации на платформе x86 ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11099
HIGH7.5

Уязвимость функции rds_conn_shutdown() модуля net/rds/connection.c реализации сетевых функций ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11100
HIGH8.8

Уязвимость функции fst_remove_one() модуля drivers/net/wan/farsync.c драйвера сетевых устройств ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-05Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
CVSS 2.0ВЫСОКАЯ 8.3
CVSS:2.0/AV:N/AC:L/Au:M/C:C/I:C/A:C
BDU:2026-11101
HIGH8.2

Уязвимость функции decode_choice() модуля net/netfilter/nf_conntrack_h323_asn1.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю получить доступ к защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-08-05Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 8.2
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H
CVSS 2.0ВЫСОКАЯ 8.5
CVSS:2.0/AV:N/AC:L/Au:N/C:P/I:N/A:C
BDU:2026-11102
HIGH7.8

Уязвимость функции atmel_hlcdc_plane_atomic_duplicate_state() модуля drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c драйвера инфраструктуры прямого рендеринга (DRI) ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11103
HIGH7.1

Уязвимость функции switchtec_ntb_init_shared() модуля drivers/ntb/hw/mscc/ntb_hw_switchtec.c драйвера непрозрачных мостов ядра операционной системы Linux, позволяющая нарушителю получить доступ к защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11104
MEDIUM5.5

Уязвимость функции spectre_bhb_loop_affected() модуля arch/arm64/kernel/proton-pack.c поддержки платформы ARM 64бит ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11105
MEDIUM5.5

Уязвимость функции drm_property_create_blob() модуля drivers/gpu/drm/drm_property.c драйвера инфраструктуры прямого рендеринга (DRI) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11106
HIGH8.8

Уязвимость функций set_secret(), ceph_crypto_key_decode() модуля net/ceph/crypto.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-05Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.0
CVSS:2.0/AV:N/AC:L/Au:S/C:C/I:C/A:C
BDU:2026-11107
MEDIUM5.5

Уязвимость функции ov5647_probe() модуля drivers/media/i2c/ov5647.c драйвера мультимедийных устройств ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11108
MEDIUM5.5

Уязвимость функции acpi_processor_errata_piix4() модуля drivers/acpi/acpi_processor.c драйвера ACPI (расширенный интерфейс конфигурации и питания) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-05Изменено: 2026-08-31
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
BDU:2026-11240
CRITICAL9.8

Уязвимость функции tls_sw_cancel_work_tx() модуля net/tls/tls_sw.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-09Изменено: 2026-08-30
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 9.0
CVSS:2.0/AV:N/AC:L/Au:S/C:C/I:C/A:C
BDU:2026-11258
HIGH7.8

Уязвимость компонента net/packet/af_packet.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-09Изменено: 2026-08-30
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
BDU:2026-11320
CRITICAL9.8

Уязвимость функций __ioam6_fill_trace_data(), ioam6_fill_trace_data() модуля net/ipv6/ioam6.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-09Изменено: 2026-08-18
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
BDU:2026-11321
CRITICAL9.8

Уязвимость функции smb2_calc_max_out_buf_len() модуля fs/smb/server/smb2pdu.c файловой системы Smb ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-09Изменено: 2026-08-18
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
BDU:2026-11322
HIGH8.8

Уязвимость функции maybe_fork_scalars() модуля fs/smb/server/smb2pdu.c подсистемы Smb ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-09Изменено: 2026-08-18
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.0
CVSS:2.0/AV:N/AC:L/Au:S/C:C/I:C/A:C
BDU:2026-11323
HIGH8.8

Уязвимость модуля drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c драйвера адаптеров беспроводной связи Broadcom ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-09Изменено: 2026-08-18
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
BDU:2026-11324
HIGH8.8

Уязвимость функции digital_in_recv_sdd_res() модуля net/nfc/digital_technology.c подсистемы NFC ядра операционной системы Linux, позволяющая нарушителю оказать влияние на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-09Изменено: 2026-08-18
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
BDU:2026-11325
MEDIUM5.5

Уязвимость функций set_posix_acl_entries_dacl() и set_ntacl_dacl() модуля fs/smb/server/smbacl.c поддержки сервера SMB ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-09Изменено: 2026-08-18
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
BDU:2026-11330
HIGH8.8

Уязвимость функции smp_cmd_pairing_req() модуля net/bluetooth/smp.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-09Изменено: 2026-08-18
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
BDU:2026-11524
MEDIUM5.5

Уязвимость компонента ntfs3/attrib.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-12Изменено: 2026-08-31
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
BDU:2026-11525
MEDIUM5.5

Уязвимость компонента ntfs3/attrlist.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-12Изменено: 2026-08-31
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
BDU:2026-11538
MEDIUM4.7

Уязвимость компонента rpmsg/rpmsg_core.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-13Изменено: 2026-08-31
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
BDU:2026-11539
MEDIUM5.5

Уязвимость компонента jfs/namei.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-13Изменено: 2026-08-31
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
BDU:2026-11540
MEDIUM5.5

Уязвимость компонента fs/buffer ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-13Изменено: 2026-08-31
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
BDU:2026-11541
MEDIUM5.5

Уязвимость компонента wireless/realtek/rtw88/rtw8822b.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-13Изменено: 2026-08-31
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
BDU:2026-11542
MEDIUM5.5

Уязвимость компонента smack/smackfs.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-13Изменено: 2026-08-31
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
BDU:2026-11543
MEDIUM5.5

Уязвимость компонента drm/display/dp_mst ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-13Изменено: 2026-08-31
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
BDU:2026-11664
HIGH7.5

Уязвимость компонента drivers/infiniband/sw/siw/siw_qp_rx.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11665
HIGH7.8

Уязвимость компонента drivers/infiniband/core/user_mad.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11667
HIGH7.8

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

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11668
HIGH7.1

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

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11670
HIGH7.8

Уязвимость компонента drivers/net/macvlan.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11672
MEDIUM5.5

Уязвимость компонента drivers/video/fbdev/core/fbcon.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11673
MEDIUM5.5

Уязвимость компонента fs/pstore/ram_core.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11674
HIGH7.8

Уязвимость компонента drivers/infiniband/core/umem_dmabuf.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11675
MEDIUM5.5

Уязвимость компонента drivers/iommu/intel/pasid.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11676
MEDIUM5.5

Уязвимость компонента drivers/md/dm-verity-fec.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11677
HIGH8.1

Уязвимость компонента net/bluetooth/l2cap_core.c ядра операционной системы Linux, позволяющая нарушителю получить доступ к конфиденциальным данным и нарушить их целостность

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
CVSS 2.0ВЫСОКАЯ 7.8
CVSS:2.0/AV:A/AC:L/Au:N/C:C/I:C/A:N
BDU:2026-11678
MEDIUM5.5

Уязвимость компонента drivers/media/pci/cx23885/cx23885-alsa.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11679
MEDIUM5.5

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

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11680
MEDIUM5.5

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

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11681
MEDIUM5.5

Уязвимость компонента drivers/mfd/mfd-core.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11682
MEDIUM5.5

Уязвимость компонента drivers/remoteproc/imx_rproc.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11683
MEDIUM5.5

Уязвимость компонента drivers/pci/iov.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11684
MEDIUM5.5

Уязвимость компонента arch/powerpc/kernel/smp.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11685
MEDIUM5.5

Уязвимость компонента drivers/net/wan/fsl_ucc_hdlc.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11686
MEDIUM5.5

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

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11687
MEDIUM5.5

Уязвимость компонента drivers/net/usb/pegasus.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11688
MEDIUM5.5

Уязвимость компонента drivers/net/ethernet/marvell/octeontx2/af/cgx.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11689
HIGH8.8

Уязвимость компонента fs/xfs/libxfs/xfs_attr_leaf.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.0
CVSS:2.0/AV:N/AC:L/Au:S/C:C/I:C/A:C
BDU:2026-11690
MEDIUM5.5

Уязвимость компонента drivers/staging/rtl8723bs/core/rtw_mlme.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11691
MEDIUM4.7

Уязвимость компонента drivers/md/md-bitmap.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11692
MEDIUM5.5

Уязвимость компонента fs/ocfs2/xattr.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11693
MEDIUM5.5

Уязвимость компонента drivers/firmware/efi/cper.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11694
MEDIUM5.5

Уязвимость компонента drivers/net/ethernet/xscale/ixp4xx_eth.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11695
HIGH7.8

Уязвимость компонента drivers/net/usb/kaweth.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11696
MEDIUM5.5

Уязвимость компонента drivers/media/i2c/ccs/ccs-core.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11697
MEDIUM5.5

Уязвимость компонента drivers/media/pci/cx25821/cx25821-core.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11698
HIGH7.5

Уязвимость компонента drivers/block/rnbd/rnbd-srv.c ядра операционной системы Linux, позволяющая нарушителю получить доступ к конфиденциальным данным

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 7.5
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
CVSS 2.0ВЫСОКАЯ 7.8
CVSS:2.0/AV:N/AC:L/Au:N/C:C/I:N/A:N
BDU:2026-11699
HIGH8.8

Уязвимость компонента fs/xfs/libxfs/xfs_attr_leaf.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.0
CVSS:2.0/AV:N/AC:L/Au:S/C:C/I:C/A:C
BDU:2026-11700
MEDIUM5.5

Уязвимость компонента drivers/pci/endpoint/pci-ep-cfs.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11701
MEDIUM5.5

Уязвимость компонента drivers/video/fbdev/vt8500lcdfb.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11702
HIGH7.8

Уязвимость компонента drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11703
MEDIUM5.5

Уязвимость компонента fs/minix/inode.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11704
HIGH7.8

Уязвимость компонента arch/loongarch/include/asm/topology.h ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11705
MEDIUM5.5

Уязвимость компонента drivers/media/i2c/tw9903.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11706
MEDIUM5.5

Уязвимость компонента drivers/char/ipmi/ipmi_ipmb.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11707
MEDIUM5.5

Уязвимость компонента drivers/media/usb/pvrusb2/pvrusb2-hdw.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11708
MEDIUM5.5

Уязвимость компонента drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11709
HIGH7.5

Уязвимость компонентов rds ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11710
MEDIUM5.5

Уязвимость компонента drivers/clocksource/sh_tmu.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11711
MEDIUM5.5

Уязвимость компонента drivers/media/radio/radio-keene.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11712
MEDIUM5.5

Уязвимость компонента act_skbedit.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11713
MEDIUM5.5

Уязвимость компонентов x86/kexec ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11716
MEDIUM5.5

Уязвимость компонента k3-socinfo ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11721
MEDIUM5.5

Уязвимость функции tw9906_probe() компонента i2c/tw9906.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11722
MEDIUM5.5

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

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11723
MEDIUM5.5

Уязвимость функции usb_tx_block() компонента libertas ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11724
MEDIUM5.5

Уязвимость функции snd_cx88_hw_params() компонента cx88 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11725
MEDIUM5.5

Уязвимость компонента gfs2 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11726
MEDIUM5.5

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

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11727
MEDIUM5.5

Уязвимость компонентов EFI/CPER ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11728
MEDIUM5.5

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

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11729
MEDIUM5.5

Уязвимость компонентов drm/atmel-hlcdc ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11730
MEDIUM5.5

Уязвимость компонента mtk-mdp ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11731
MEDIUM5.5

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

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11732
MEDIUM4.7

Уязвимость компонента core/ufshcd.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11733
MEDIUM5.5

Уязвимость компонентов APEI/GHES ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11734
HIGH7.8

Уязвимость компонента dm-rq.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11735
HIGH7.8

Уязвимость модуля usb-audio ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11736
HIGH8.8

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

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11737
MEDIUM5.5

Уязвимость модуля kexec ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11738
HIGH8.3

Уязвимость модуля nci ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 8.3
CVSS:3.x/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:H
CVSS 2.0ВЫСОКАЯ 8.0
CVSS:2.0/AV:A/AC:L/Au:N/C:C/I:P/A:C
BDU:2026-11739
MEDIUM5.5

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

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11740
HIGH7.5

Уязвимость модуля octeontx2-af ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11741
MEDIUM5.5

Уязвимость компонентов drm/v3d ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11742
MEDIUM5.5

Уязвимость компонента dm-rq.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11743
MEDIUM5.5

Уязвимость компонента svm/nested.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11744
MEDIUM5.5

Уязвимость компонента solo6x10 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11745
MEDIUM5.5

Уязвимость модуля net ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11746
MEDIUM5.5

Уязвимость модуля apparmor ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11747
MEDIUM5.5

Уязвимость ядра операционной системы Linux, связанная с отсутствием проверки блокировки, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11748
HIGH7.8

Уязвимость модуля rxe ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11749
HIGH7.1

Уязвимость компонента uverbs_cmd.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11750
MEDIUM5.5

Уязвимость компонента csio_scsi.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11751
HIGH7.5

Уязвимость модуля nf_conncount ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11752
HIGH7.8

Уязвимость компонента drivers/iommu/intel/pasid.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:C/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
BDU:2026-11753
MEDIUM5.5

Уязвимость компонентов fs/ntfs3 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11754
MEDIUM4.0

Уязвимость компонента mctp-i2c.c ядра операционной системы Linux, позволяющая нарушителю получить доступ к конфиденциальным данным

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xСРЕДНЯЯ 4.0
CVSS:3.x/AV:L/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
CVSS 2.0НИЗКАЯ 2.1
CVSS:2.0/AV:L/AC:L/Au:N/C:P/I:N/A:N
BDU:2026-11755
HIGH7.0

Уязвимость компонента caif_serial.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11756
MEDIUM5.0

Уязвимость компонента act8945a_charger.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xСРЕДНЯЯ 5.0
CVSS:3.x/AV:L/AC:L/PR:L/UI:R/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
BDU:2026-11757
MEDIUM5.5

Уязвимость компонента pinctrl-single.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11758
MEDIUM4.7

Уязвимость компонента wm97xx_battery.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11759
MEDIUM5.5

Уязвимость модуля auth_gss ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11760
MEDIUM5.5

Уязвимость компонента st33zp24 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11761
MEDIUM5.5

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

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11762
MEDIUM5.5

Уязвимость компонента nft_set_rbtree.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11763
MEDIUM4.4

Уязвимость компонента arizona-core.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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 4.3
CVSS:2.0/AV:L/AC:L/Au:M/C:N/I:N/A:C
BDU:2026-11764
MEDIUM4.7

Уязвимость компонента bq25980_charger.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11765
MEDIUM4.4

Уязвимость компонента mtk-svs.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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 4.3
CVSS:2.0/AV:L/AC:L/Au:M/C:N/I:N/A:C
BDU:2026-11766
MEDIUM4.0

Уязвимость функции sca3000_probe() компонента sca3000.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xСРЕДНЯЯ 4.0
CVSS:3.x/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
CVSS 2.0НИЗКАЯ 2.1
CVSS:2.0/AV:L/AC:L/Au:N/C:N/I:N/A:P
BDU:2026-11767
MEDIUM6.3

Уязвимость компонента cpcap-battery.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xСРЕДНЯЯ 6.3
CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:N/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:L/AC:H/Au:S/C:C/I:N/A:C
BDU:2026-11768
HIGH7.0

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

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11769
MEDIUM6.5

Уязвимость компонента xen-netback ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xСРЕДНЯЯ 6.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:C/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
BDU:2026-11770
MEDIUM5.5

Уязвимость компонента hns3 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11771
MEDIUM6.3

Уязвимость компонента bq256xx_charger.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xСРЕДНЯЯ 6.3
CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:L/AC:H/Au:S/C:N/I:C/A:C
BDU:2026-11772
MEDIUM5.5

Уязвимость компонента powerpc/eeh ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11773
MEDIUM5.5

Уязвимость компонента net/ipv4/icmp.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11774
HIGH7.0

Уязвимость компонента fs/ext4/extents.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11775
MEDIUM5.5

Уязвимость компонента drivers/hwmon/ibmpex.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11776
MEDIUM5.5

Уязвимость модуля fat ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11777
MEDIUM5.5

Уязвимость компонента sbs-battery.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11778
MEDIUM5.5

Уязвимость функции rto_next_cpu() компонента sched/rt.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11779
MEDIUM5.5

Уязвимость компонента drivers/net/usb/catc.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11780
HIGH7.8

Уязвимость компонента fs/ntfs3/fslog.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:N/UI:R/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
BDU:2026-11781
MEDIUM5.5

Уязвимость компонента goldfish_battery.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11782
MEDIUM5.5

Уязвимость компонента tpm_i2c_infineon.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11783
HIGH7.8

Уязвимость компонента ab8500_charger.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11784
MEDIUM5.5

Уязвимость компонента fs/ext4/extents.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11785
MEDIUM5.5

Уязвимость компонента au1200fb.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11786
MEDIUM5.5

Уязвимость компонента s/hfsplus/bnode.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11787
MEDIUM5.5

Уязвимость компонента drivers/block/ublk_drv.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11788
MEDIUM5.5

Уязвимость компонента auth_gss.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11789
MEDIUM5.5

Уязвимость модуля apparmor ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11790
MEDIUM5.5

Уязвимость компонента drivers/cpuidle/cpuidle.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11791
MEDIUM5.5

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

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11792
HIGH7.8

Уязвимость компонента bond_main.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11793
CRITICAL9.8

Уязвимость компонента fs/smb/client/smb2file.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11794
MEDIUM5.5

Уязвимость компонента fs/btrfs/qgroup.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11795
MEDIUM5.5

Уязвимость компонента greybus/light.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11796
MEDIUM5.5

Уязвимость компонента drivers/s390/cio/css.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11797
MEDIUM5.5

Уязвимость компонента acpica/evregion.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11798
MEDIUM5.5

Уязвимость модуля nfsd ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11799
HIGH7.8

Уязвимость компонента fs/gfs2/bmap.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11800
MEDIUM5.5

Уязвимость компонента clk-rcg2.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11801
MEDIUM5.5

Уязвимость модуля octeontx2-af ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11802
HIGH7.3

Уязвимость компонента arch/mips/kernel/relocate.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 7.3
CVSS:3.x/AV:L/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H
CVSS 2.0СРЕДНЯЯ 6.1
CVSS:2.0/AV:L/AC:L/Au:N/C:P/I:P/A:C
BDU:2026-11803
HIGH8.4

Уязвимость компонента fs/btrfs/transaction.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11804
HIGH7.8

Уязвимость компонента fs/pstore/ram_core.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11805
HIGH7.8

Уязвимость компонента fs/proc/array.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11806
MEDIUM5.5

Уязвимость компонента fsl_xcvr.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11807
HIGH7.5

Уязвимость компонента hns_roce_hw_v2.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11808
HIGH7.8

Уязвимость компонента hci/llc_shdlc.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11809
HIGH8.4

Уязвимость компонента rt9455_charger.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11811
HIGH7.3

Уязвимость компонента apparmor/resource.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xВЫСОКАЯ 7.3
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:C/C:N/I:L/A:H
CVSS 2.0СРЕДНЯЯ 5.2
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:P/A:C
BDU:2026-11813
HIGH8.0

Уязвимость функции rga_buf_init() модуля drivers/media/platform/rockchip/rga/rga-buf.c драйвера мультимедийных устройств ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11814
HIGH7.8

Уязвимость функции adxl380_irq_handler() модуля drivers/iio/accel/adxl380.c драйвера различных типов встроенных датчиков ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11815
HIGH7.8

Уязвимость функции rockchip_vpu981_av1_dec_init() модуля drivers/media/platform/verisilicon/rockchip_vpu981_hw_av1_dec.c драйвера мультимедийных устройств ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11816
HIGH7.0

Уязвимость функции bpf_crypto_ctx_release() модуля kernel/bpf/crypto.c поддержки интерпретатора BPF ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11817
MEDIUM5.5

Уязвимость функции amdgpu_device_ip_init() модуля drivers/gpu/drm/amd/amdgpu/amdgpu_device.c драйвера инфраструктуры прямого рендеринга (DRI) AMD GPU ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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
BDU:2026-11818
MEDIUM5.7

Уязвимость функции jdi_panel_dsi_remove() модуля drivers/gpu/drm/panel/panel-jdi-lpm102a188a.c драйвера инфраструктуры прямого рендеринга (DRI) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
CVSS 3.xСРЕДНЯЯ 5.7
CVSS:3.x/AV:A/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:A/AC:L/Au:S/C:N/I:N/A:C
BDU:2026-11819
MEDIUM5.5

Уязвимость функции eqbr_irq_ack() модуля drivers/pinctrl/pinctrl-equilibrium.c драйвера контроллеров выводов PINCTRL ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-18
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
BDU:2026-11820
HIGH7.1

Уязвимость функции mt7996_mac_write_txwi_80211() модуля drivers/net/wireless/mediatek/mt76/mt7996/mac.c драйвера адаптеров беспроводной связи mediatek ядра операционной системы Linux, позволяющая нарушителю получить несанкционированный доступ к защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-18
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
BDU:2026-11823
MEDIUM5.5

Уязвимость функции audit_classes_init() модуля lib/audit.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-31
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 4.9
CVSS:2.0/AV:L/AC:L/Au:N/C:N/I:N/A:C
BDU:2026-11838
HIGH7.1

Уязвимость функции nvme_pr_read_keys() модуля drivers/nvme/host/pr.c ядра операционной системы Linux, позволяющая нарушителю раскрыть защищаемую информацию или вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-18
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
BDU:2026-11839
MEDIUM5.9

Уязвимость функции ieee80211_ml_reconfiguration() модуля net/mac80211/mlme.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на целостность защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-18
CVSS 3.xСРЕДНЯЯ 5.9
CVSS:3.x/AV:A/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:H
CVSS 2.0СРЕДНЯЯ 5.3
CVSS:2.0/AV:A/AC:H/Au:N/C:N/I:P/A:C
BDU:2026-11840
MEDIUM5.7

Уязвимость функции __req_mod() модуля drivers/block/drbd/drbd_req.c драйвера блочных устройств ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-18
CVSS 3.xСРЕДНЯЯ 5.7
CVSS:3.x/AV:A/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:A/AC:L/Au:S/C:N/I:N/A:C
BDU:2026-11841
MEDIUM5.5

Уязвимость функции nfsd_nl_threads_set_doit() модуля fs/nfsd/nfsctl.c файловой системы Nfsd ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-18
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
BDU:2026-11843
MEDIUM5.5

Уязвимость функции f81604_read_int_callback() модуля drivers/crypto/ccp/sev-dev-tsm.c драйвера криптографического ускорителя ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-18
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
BDU:2026-11844
MEDIUM5.5

Уязвимость функции f81604_read_int_callback() модуля drivers/crypto/ccp/sev-dev-tsm.c драйвера криптографического ускорителя ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-18
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
BDU:2026-11845
MEDIUM5.5

Уязвимость функции f81604_read_int_callback() модуля drivers/crypto/ccp/sev-dev-tsm.c драйвера криптографического ускорителя ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-16Изменено: 2026-08-18
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
BDU:2026-11847
MEDIUM5.5

Уязвимость функции nvme_alloc_admin_tag_set() модуля drivers/nvme/host/core.c драйвера NVME ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-16Изменено: 2026-08-18
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
BDU:2026-11848
HIGH7.1

Уязвимость функции mt7925_mac_write_txwi_80211() модуля drivers/net/wireless/mediatek/mt76/mt7925/mac.c драйвера адаптеров беспроводной связи mediatek ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность и доступность защищаемой информации

Опубликовано: 2026-08-16Изменено: 2026-08-18
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
BDU:2026-11849
MEDIUM5.5

Уязвимость функции rsi_mac80211_config() модуля drivers/net/wireless/rsi/rsi_91x_mac80211.c драйвера адаптеров беспроводной связи Redpine Signals ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-16Изменено: 2026-08-18
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
BDU:2026-11850
HIGH7.8

Уязвимость функции cs42l43_pin_probe() модуля drivers/pinctrl/cirrus/pinctrl-cs42l43.c драйвера контроллеров выводов PINCTRL ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-16Изменено: 2026-08-18
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
BDU:2026-12036
MEDIUM5.5

Уязвимость компонента soc/sof/ipc4-topology.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12037
MEDIUM5.5

Уязвимость компонента arm64/boot/dts/xilinx/zynqmp.dtsi ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12038
MEDIUM5.5

Уязвимость компонента fs/ntfs3 ядра операционной системы Linux, позволяющая нарушителю получить доступ к конфиденциальным данным

Опубликовано: 2026-08-23Изменено: 2026-08-31
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
CVSS 2.0СРЕДНЯЯ 4.6
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:N/A:N
BDU:2026-12039
MEDIUM5.5

Уязвимость компонента drm/panthor ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12084
CRITICAL9.1

Уязвимость функции ceph_handle_auth_reply() модуля net/ceph/auth.c ядра операционной системы Linux, позволяющая нарушителю получить доступ к защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-08-23
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
BDU:2026-12086
CRITICAL9.1

Уязвимость функции btrfs_sync_file() модуля include/trace/events/btrfs.h ядра операционной системы Linux, позволяющая нарушителю получить доступ к защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-08-23
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
BDU:2026-12088
CRITICAL9.1

Уязвимость функции process_message_header() модуля net/ceph/messenger_v2.c ядра операционной системы Linux, позволяющая нарушителю получить доступ к защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-08-23
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
BDU:2026-12091
CRITICAL9.4

Уязвимость функций tcp_inbound_md5_hash(), tcp_v4_send_reset() и tcp_v6_send_reset() ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-23
CVSS 3.xКРИТИЧЕСКАЯ 9.4
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.7
CVSS:2.0/AV:N/AC:L/Au:N/C:P/I:C/A:C
BDU:2026-12095
CRITICAL9.8

Уязвимость функции dlm_search_rsb_tree() модуля fs/dlm/lock.c подсистемы Dlm ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-23
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
BDU:2026-12112
MEDIUM5.5

Уязвимость функции mpu3050_common_remove() модуля drivers/iio/gyro/mpu3050-core.c драйвера различных типов встроенных датчиков ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-23
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
BDU:2026-12165
MEDIUM5.5

Уязвимость компонента drivers/net/can/usb/f81604.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23
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
BDU:2026-12166
HIGH7.8

Уязвимость компонента arch/x86/entry/entry_fred.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23
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
BDU:2026-12167
MEDIUM5.5

Уязвимость компонента i2c/busses/i2c-i801.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23
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
BDU:2026-12168
MEDIUM5.5

Уязвимость компонентов tracing ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23
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
BDU:2026-12169
HIGH7.8

Уязвимость компонентов client ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12171
HIGH7.8

Уязвимость компонента drivers/reset/reset-gpio.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12172
MEDIUM5.5

Уязвимость компонента drivers/gpu/drm/drm_buddy.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12173
MEDIUM5.5

Уязвимость компонента drivers/clk/clk-renesas-pcie.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12174
MEDIUM5.5

Уязвимость компонента drivers/media/pci/intel/ipu6/ipu6.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12175
HIGH7.8

Уязвимость компонента fs/proc/task_mmu.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12176
MEDIUM5.5

Уязвимость компонента drivers/media/v4l2-core/v4l2-async.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12177
HIGH7.5

Уязвимость компонента drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12178
MEDIUM5.5

Уязвимость ядра операционной системы Linux, связанная с выходом операции за границы буфера в памяти, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12179
MEDIUM5.5

Уязвимость компонента kernel/trace/ring_buffer.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12180
MEDIUM5.5

Уязвимость компонента drivers/media/platform/chips-media/wave5/wave5-vpu.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12181
MEDIUM5.5

Уязвимость компонентов drm/amd/display ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12182
HIGH7.8

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

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12183
MEDIUM5.5

Уязвимость компонента vmalloc.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12184
MEDIUM5.5

Уязвимость модуля wave5 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12185
MEDIUM5.5

Уязвимость компонентаspi/spidev.c ядра операционной системы Linux, связанная с недостаточной блокировкой, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12186
MEDIUM5.5

Уязвимость компонента dce110_hwseq.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12187
MEDIUM5.5

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

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12188
MEDIUM5.5

Уязвимость компонента amdgpu_gmc.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12189
HIGH7.8

Уязвимость компонента gfs2 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12190
MEDIUM5.5

Уязвимость функции dw_i3c_master_i2c_xfers() компонента dw-i3c-master.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12191
MEDIUM5.5

Уязвимость компонента imx8qm-hsio ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12192
HIGH7.8

Уязвимость компонентов drm/amdkfd ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12193
MEDIUM5.5

Уязвимость компонента p2pdma.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12194
MEDIUM4.7

Уязвимость компонента pm8916_bms_vm.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12195
MEDIUM5.5

Уязвимость модуля apparmor ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12196
MEDIUM5.5

Уязвимость компонента md/raid1.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12197
MEDIUM5.5

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

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12198
CRITICAL9.8

Уязвимость компонентов RDMA/iwcm ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12199
MEDIUM5.5

Уязвимость функции dpaa2_caam_probe()компонента caamalg_qi2.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12200
HIGH7.8

Уязвимость компонентов RDMA/rxe ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12201
MEDIUM5.5

Уязвимость модуля mcast ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12202
LOW3.3

Уязвимость компонента tplink_safeloader.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
CVSS 3.xНИЗКАЯ 3.3
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
CVSS 2.0НИЗКАЯ 1.7
CVSS:2.0/AV:L/AC:L/Au:S/C:N/I:N/A:P
BDU:2026-12203
MEDIUM5.5

Уязвимость компонента mlx5/std_types.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12204
MEDIUM5.5

Уязвимость компонента thermal_of.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12205
MEDIUM5.7

Уязвимость компонентов wave5 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
CVSS 3.xСРЕДНЯЯ 5.7
CVSS:3.x/AV:A/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:A/AC:L/Au:S/C:N/I:N/A:C
BDU:2026-12206
HIGH7.8

Уязвимость компонента verifier.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12207
HIGH8.0

Уязвимость компонента pm8916_lbc.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12208
MEDIUM5.5

Уязвимость компонента amdgpu_acpi.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12209
MEDIUM5.5

Уязвимость компонента jh7110-aes.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12210
MEDIUM5.5

Уязвимость компонента RDMA/mlx5 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12211
MEDIUM5.5

Уязвимость компонента amdgpu_ras.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12212
HIGH7.8

Уязвимость компонента pm8916_lbc.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12213
MEDIUM5.5

Уязвимость компонента drivers/dma/fsl-edma-main.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12214
HIGH7.8

Уязвимость компонента net/ipv6/ip6_fib.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12215
MEDIUM5.5

Уязвимость компонента drivers/spi/spi-wpcm-fiu.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12216
HIGH7.8

Уязвимость компонентов drm/amd/display ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12217
HIGH8.4

Уязвимость компонента mprls0025pa_spi.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12218
HIGH7.8

Уязвимость компонента drivers/md/dm-zone.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12219
MEDIUM5.5

Уязвимость компонента fs/erofs/fileio.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-23Изменено: 2026-08-31
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
BDU:2026-12225
MEDIUM5.5

Уязвимость функции ice_set_ringparam() модуля drivers/net/ethernet/intel/ice/ice_ethtool.c драйвера сетевых адаптеров ethernet intel ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12226
HIGH7.8

Уязвимость функции xt_ct_tg_destroy() модуля net/netfilter/xt_CT.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12228
MEDIUM5.5

Уязвимость функции set_new_password() модуля drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c драйвера устройств X86 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12229
HIGH7.1

Уязвимость функции nfnl_osf_add_callback() модуля net/netfilter/nfnetlink_osf.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12230
MEDIUM5.5

Уязвимость функции f81604_read_int_callback() модуля drivers/crypto/ccp/sev-dev-tsm.c драйвера криптографического ускорителя ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24Изменено: 2026-08-27
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
BDU:2026-12231
MEDIUM5.5

Уязвимость функции irdma_create_user_ah() модуля drivers/infiniband/hw/irdma/verbs.c драйвера InfiniBand ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12235
HIGH7.8

Уязвимость функции cdc_ncm_rx_verify_ndp32() модуля drivers/net/usb/cdc_ncm.c драйвера сетевых адаптеров USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12236
HIGH7.0

Уязвимость функции pm_runtime_reinit() модуля drivers/base/power/runtime.c драйвера шинных устройства ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12237
HIGH7.0

Уязвимость функции mana_hwc_destroy_channel() модуля drivers/net/ethernet/microsoft/mana/hw_channel.c драйвера сетевых адаптеров ethernet microsoft ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12238
CRITICAL9.1

Уязвимость функции DecodeQ931() модуля net/netfilter/nf_conntrack_h323_asn1.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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 2.0ВЫСОКАЯ 8.5
CVSS:2.0/AV:N/AC:L/Au:S/C:C/I:N/A:C
BDU:2026-12240
HIGH8.1

Уязвимость функции ibmvfc_discover_targets_done() модуля drivers/scsi/ibmvscsi/ibmvfc.c драйвера устройств SCSI ядра операционной системы Linux, позволяющая нарушителю получить доступ к защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-08-24Изменено: 2026-08-27
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
BDU:2026-12241
CRITICAL9.4

Уязвимость функции ext4_ext_map_blocks() модуля fs/ext4/extents.c файловой системы Ext4 ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
CVSS 3.xКРИТИЧЕСКАЯ 9.4
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.7
CVSS:2.0/AV:N/AC:L/Au:N/C:P/I:C/A:C
BDU:2026-12244
HIGH8.8

Уязвимость функции cgw_csum_crc8_rel() модуля net/can/gw.c подсистемы шины CAN ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12247
CRITICAL9.8

Уязвимость функции rxkad_decrypt_ticket() модуля net/rxrpc/rxkad.c поддержки сокетов сеанса RxRPC ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12248
CRITICAL9.8

Уязвимость функции jumbo_frm() модуля drivers/net/ethernet/stmicro/stmmac/chain_mode.c драйвера сетевых адаптеров ethernet stmicro ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12249
HIGH8.1

Уязвимость функции match_session() модуля fs/smb/client/connect.c файловой системы Smb ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/AV:L/AC:L/PR:H/UI:N/S:C/C:H/I:H/A:L
CVSS 2.0СРЕДНЯЯ 6.4
CVSS:2.0/AV:L/AC:L/Au:S/C:C/I:C/A:P
BDU:2026-12250
CRITICAL9.8

Уязвимость функции llist_abort_desc() модуля drivers/dma/idxd/submit.c драйвера движка DMA Intel Data Accelerator ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12251
CRITICAL9.8

Уязвимость функции usbip_pack_ret_submit() модуля drivers/usb/usbip/usbip_common.c драйвера устройств шины USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12252
HIGH8.2

Уязвимость функции decode_int() модуля net/netfilter/nf_conntrack_h323_asn1.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность и доступность защищаемой информации

Опубликовано: 2026-08-24
CVSS 3.xВЫСОКАЯ 8.2
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H
CVSS 2.0ВЫСОКАЯ 7.5
CVSS:2.0/AV:N/AC:L/Au:S/C:P/I:N/A:C
BDU:2026-12253
MEDIUM5.5

Уязвимость функции fw_change() модуля net/sched/cls_fw.c подсистемы управления трафиком net/sched ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12254
MEDIUM5.5

Уязвимость функции rtsc_min() модуля net/sched/sch_hfsc.c подсистемы управления трафиком net/sched ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12255
MEDIUM5.5

Уязвимость функций xt_check_match() и xt_check_target() модуля net/netfilter/x_tables.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12256
MEDIUM5.5

Уязвимость функции __build_packet_message() модуля net/netfilter/nfnetlink_log.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12257
MEDIUM5.5

Уязвимость функции flow_change() модуля net/sched/cls_flow.c подсистемы управления трафиком net/sched ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12268
CRITICAL9.8

Уязвимость функций ctnetlink_exp_dump_expect() модуля net/netfilter/nf_conntrack_netlink.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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 9.0
CVSS:2.0/AV:N/AC:L/Au:S/C:C/I:C/A:C
BDU:2026-12269
HIGH7.0

Уязвимость функции acpi_ec_setup() модуля drivers/acpi/ec.c драйвера расширенного интерфейса конфигурации и питания ACPI ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12270
MEDIUM5.8

Уязвимость функции process_sdp() модуля net/netfilter/nf_conntrack_sip.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
CVSS 3.xСРЕДНЯЯ 5.8
CVSS:3.x/AV:L/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:H
CVSS 2.0СРЕДНЯЯ 5.0
CVSS:2.0/AV:L/AC:H/Au:S/C:P/I:P/A:C
BDU:2026-12271
MEDIUM5.5

Уязвимость функции ip6_datagram_send_ctl() модуля net/ipv6/datagram.c реализации протокола IPv6 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12272
MEDIUM5.5

Уязвимость функции nfulnl_log_packet() модуля net/netfilter/nfnetlink_log.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12286
HIGH7.8

Уязвимость функции xfrm_nat_keepalive_net_init() модуля net/xfrm/xfrm_nat_keepalive.c реализации сетевых функций ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12288
HIGH7.8

Уязвимость функций tcf_ct_init() модуля net/sched/act_ct.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12289
MEDIUM5.5

Уязвимость функций ip6tunnel_xmit() (include/net/ip6_tunnel.h) и iptunnel_xmit() (net/ipv4/ip_tunnel_core.c) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12290
MEDIUM5.5

Уязвимость функции teql_master_xmit() модуля net/sched/sch_teql.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12293
HIGH8.2

Уязвимость функции privcmd_init() модуля drivers/xen/privcmd.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
CVSS 3.xВЫСОКАЯ 8.2
CVSS:3.x/AV:L/AC:L/PR:H/UI:N/S:C/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.5
CVSS:2.0/AV:L/AC:L/Au:M/C:C/I:C/A:C
BDU:2026-12296
HIGH7.1

Уязвимость функции x509_process_extension() модуля crypto/asymmetric_keys/x509_cert_parser.c криптографической подсистемы ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12298
HIGH7.0

Уязвимость функции file_thp_enabled() модуля mm/huge_memory.c подсистемы управления памятью ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12299
HIGH7.0

Уязвимость функции bpf_int_jit_compile() модуля arch/arm64/net/bpf_jit_comp.c поддержки сети на платформе ARM 64бит ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12300
MEDIUM6.6

Уязвимость функции squashfs_read_metadata() модуля fs/squashfs/cache.c файловой системы Squashfs ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
CVSS 3.xСРЕДНЯЯ 6.6
CVSS:3.x/AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:H
CVSS 2.0СРЕДНЯЯ 5.7
CVSS:2.0/AV:L/AC:L/Au:S/C:P/I:P/A:C
BDU:2026-12301
HIGH7.8

Уязвимость функции f81604_read_int_callback() модуля drivers/crypto/ccp/sev-dev-tsm.c драйвера криптографического ускорителя ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24Изменено: 2026-08-27
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
BDU:2026-12302
HIGH8.8

Уязвимость функции l2cap_ecred_conn_req() модуля net/bluetooth/l2cap_core.c подсистемы Bluetooth ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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 7.7
CVSS:2.0/AV:A/AC:L/Au:S/C:C/I:C/A:C
BDU:2026-12303
HIGH7.8

Уязвимость функции f81604_read_int_callback() модуля drivers/crypto/ccp/sev-dev-tsm.c драйвера криптографического ускорителя ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24Изменено: 2026-08-27
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
BDU:2026-12306
MEDIUM5.5

Уязвимость функции lec_arp_clear_vccs() модуля net/atm/lec.c реализации сетевых функций ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12307
MEDIUM5.5

Уязвимость функции plic_irq_disable() модуля drivers/irqchip/irq-sifive-plic.c драйвера IRQ-чипов ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12308
MEDIUM5.5

Уязвимость функции target_core_item_dbroot_store() модуля drivers/target/target_core_configfs.c драйвера TCM ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12309
MEDIUM5.5

Уязвимость функции route_shortcircuit() модуля drivers/net/vxlan/vxlan_core.c драйвера сетевых устройств ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12310
MEDIUM5.5

Уязвимость функции scsi_alloc_sdev() модуля drivers/scsi/scsi_scan.c драйвера устройств SCSI ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12311
MEDIUM5.5

Уязвимость функции ucan_read_bulk_callback() модуля drivers/net/can/usb/ucan.c драйвера сетевых устройств CAN ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12312
MEDIUM5.5

Уязвимость функции fib6_nh_init() модуля net/ipv6/route.c реализации протокола IPv6 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12314
MEDIUM5.5

Уязвимость функции cifs_set_cifscreds() модуля fs/smb/client/connect.c файловой системы Smb ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12318
MEDIUM5.5

Уязвимость функции ip6_rt_get_dev_rcu() модуля net/ipv6/route.c реализации протокола IPv6 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12319
MEDIUM5.5

Уязвимость функции ems_usb_read_bulk_callback() модуля drivers/net/can/usb/ems_usb.c драйвера сетевых устройств CAN ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12321
MEDIUM5.5

Уязвимость функции kaweth_probe() модуля drivers/net/usb/kaweth.c драйвера сетевых адаптеров USB ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12322
MEDIUM5.5

Уязвимость функции mt76_connac2_mac_write_txwi_80211() модуля drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c драйвера адаптеров беспроводной связи mediatek ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12326
HIGH7.8

Уязвимость функции f81604_read_int_callback() модуля drivers/crypto/ccp/sev-dev-tsm.c драйвера криптографического ускорителя ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12327
HIGH7.8

Уязвимость функции f81604_read_int_callback() модуля drivers/crypto/ccp/sev-dev-tsm.c драйвера криптографического ускорителя ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12329
HIGH7.8

Уязвимость функции f81604_read_int_callback() модуля drivers/crypto/ccp/sev-dev-tsm.c драйвера криптографического ускорителя ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24Изменено: 2026-08-27
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
BDU:2026-12330
MEDIUM5.5

Уязвимость функции mcp251x_open() модуля drivers/net/can/spi/mcp251x.c драйвера сетевых устройств CAN ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12332
HIGH7.8

Уязвимость функции dw_pcie_ep_raise_msix_irq() модуля drivers/pci/controller/dwc/pcie-designware-ep.c драйвера устройств PCI ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12333
MEDIUM5.5

Уязвимость функции kalmia_bind() модуля drivers/net/usb/kalmia.c драйвера сетевых адаптеров USB ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12336
MEDIUM5.5

Уязвимость функции ieee80211_radiotap_iterator_next() модуля net/wireless/radiotap.c поддержки беспроводной связи ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12337
MEDIUM5.5

Уязвимость функции __blk_add_trace() модуля kernel/trace/blktrace.c поддержки трассировки ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12339
MEDIUM5.5

Уязвимость функции ets_offload_change() модуля net/sched/sch_ets.c подсистемы управления трафиком net/sched ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12341
HIGH7.8

Уязвимость функции spi_register_controller() модуля drivers/spi/spi.c драйвера устройств SPI ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24Изменено: 2026-08-27
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
BDU:2026-12342
HIGH7.0

Уязвимость функции ieee80211_chan_bw_change() модуля net/mac80211/chan.c реализации стека mac80211 ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12344
HIGH8.1

Уязвимость функции l2cap_information_rsp() модуля net/bluetooth/l2cap_core.c подсистемы Bluetooth ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность и доступность защищаемой информации

Опубликовано: 2026-08-24
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 7.1
CVSS:2.0/AV:A/AC:L/Au:S/C:C/I:N/A:C
BDU:2026-12346
MEDIUM5.5

Уязвимость функции udp_sock_create6() модуля include/net/udp_tunnel.h ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12347
HIGH7.8

Уязвимость функции cdc_ncm_rx_verify_ndp16() модуля drivers/net/usb/cdc_ncm.c драйвера сетевых адаптеров USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12348
MEDIUM5.5

Уязвимость функции log_conflicting_inodes() модуля fs/btrfs/tree-log.c файловой системы Btrfs ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12349
HIGH8.6

Уязвимость функции sip_help_tcp() модуля net/netfilter/nf_conntrack_sip.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
CVSS 3.xВЫСОКАЯ 8.6
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H
CVSS 2.0ВЫСОКАЯ 8.0
CVSS:2.0/AV:N/AC:L/Au:S/C:P/I:P/A:C
BDU:2026-12350
HIGH7.8

Уязвимость функции bpf_nf_link_update() модуля net/netfilter/nf_bpf_link.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12351
MEDIUM5.5

Уязвимость функции bpf_jit_blind_insn() модуля kernel/bpf/core.c поддержки интерпретатора BPF ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12353
MEDIUM5.5

Уязвимость функции sev_es_sync_vmsa() модуля arch/x86/kvm/svm/sev.c подсистемы виртуализации на платформе x86 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12354
MEDIUM5.5

Уязвимость функции ncm_unwrap_ntb() модуля drivers/usb/gadget/function/f_ncm.c драйвера гаджетов USB ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12355
MEDIUM5.5

Уязвимость функции setup_lass() модуля arch/x86/kernel/cpu/common.c поддержки платформы x86 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12358
MEDIUM5.5

Уязвимость функции sev_pin_memory() модуля arch/x86/kvm/svm/sev.c подсистемы виртуализации на платформе x86 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12359
HIGH7.8

Уязвимость функции start_xmit() модуля drivers/net/virtio_net.c драйвера сетевых устройств ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12360
MEDIUM5.5

Уязвимость функции intel_engines_reset_default_submission() модуля drivers/gpu/drm/i915/gt/intel_engine_cs.c драйвера инфраструктуры прямого рендеринга (DRI) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12361
MEDIUM5.5

Уязвимость функции uv_system_init_hub() модуля arch/x86/kernel/apic/x2apic_uv_x.c поддержки платформы x86 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12363
MEDIUM5.5

Уязвимость функции bond_debug_rlb_hash_show() модуля drivers/net/bonding/bond_debugfs.c драйвера сетевых устройств ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12364
MEDIUM5.5

Уязвимость функции bcm2835_asb_control() модуля drivers/pmdomain/bcm/bcm2835-power.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12365
MEDIUM5.5

Уязвимость функции btusb_work() модуля drivers/bluetooth/btusb.c драйвера устройств Bluetooth ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12450
HIGH7.8

Уязвимость модуля drivers/gpu/drm/exynos/exynos_drm_vidi.c драйвера инфраструктуры прямого рендеринга (DRI) ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12452
HIGH7.5

Уязвимость функции mesh_rx_csa_frame() модуля net/mac80211/mesh.c реализации стека mac80211 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12454
HIGH8.0

Уязвимость функции lbs_free_adapter() модуля drivers/net/wireless/marvell/libertas/main.c драйвера адаптеров беспроводной связи marvell ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12456
MEDIUM5.5

Уязвимость функции mtk_xdp_setup() модуля drivers/net/ethernet/mediatek/mtk_eth_soc.c драйвера сетевых адаптеров ethernet mediatek ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24Изменено: 2026-08-27
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
BDU:2026-12457
MEDIUM5.7

Уязвимость функции pn533_usb_disconnect() модуля drivers/nfc/pn533/usb.c драйвера NFC ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
CVSS 3.xСРЕДНЯЯ 5.7
CVSS:3.x/AV:A/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:A/AC:L/Au:S/C:N/I:N/A:C
BDU:2026-12459
HIGH7.8

Уязвимость функции pm8001_queue_command() модуля drivers/scsi/pm8001/pm8001_sas.c драйвера устройств SCSI ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24Изменено: 2026-08-27
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
BDU:2026-12464
MEDIUM5.5

Уязвимость функции f81604_read_int_callback() модуля drivers/crypto/ccp/sev-dev-tsm.c драйвера криптографического ускорителя ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12468
MEDIUM5.5

Уязвимость функции f81604_read_int_callback() модуля drivers/crypto/ccp/sev-dev-tsm.c драйвера криптографического ускорителя ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12473
MEDIUM5.5

Уязвимость функции f81604_read_int_callback() модуля drivers/crypto/ccp/sev-dev-tsm.c драйвера криптографического ускорителя ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12477
MEDIUM5.5

Уязвимость функции bcm_rx_setup() модуля net/can/bcm.c подсистемы шины CAN ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12478
HIGH8.0

Уязвимость функции rawsock_release() модуля net/nfc/rawsock.c подсистемы NFC ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12480
MEDIUM5.5

Уязвимость функции mesh_matches_local() модуля net/mac80211/mesh.c реализации стека mac80211 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12481
MEDIUM5.5

Уязвимость функции rds_tcp_tune() модуля net/rds/tcp.c реализации сетевых функций ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12482
MEDIUM5.5

Уязвимость функции wl1271_op_resume() модуля drivers/net/wireless/ti/wlcore/main.c драйвера адаптеров беспроводной связи Texas Instrument ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12484
HIGH7.8

Уязвимость функции dpaa2_switch_irq0_handler_thread() модуля drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c драйвера сетевых адаптеров ethernet freescale ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24Изменено: 2026-08-27
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
BDU:2026-12487
MEDIUM5.5

Уязвимость функции logicvc_drm_config_parse() модуля drivers/gpu/drm/logicvc/logicvc_drm.c драйвера инфраструктуры прямого рендеринга (DRI) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24Изменено: 2026-08-27
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
BDU:2026-12488
CRITICAL9.8

Уязвимость функции parse_durable_handle_context() модуля fs/smb/server/smb2pdu.c файловой системы Smb ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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 9.0
CVSS:2.0/AV:N/AC:L/Au:S/C:C/I:C/A:C
BDU:2026-12489
CRITICAL9.8

Уязвимость функции smb2_get_ksmbd_tcon() модуля fs/smb/server/smb2pdu.c файловой системы Smb ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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 9.0
CVSS:2.0/AV:N/AC:L/Au:S/C:C/I:C/A:C
BDU:2026-12494
MEDIUM5.5

Уязвимость функции mvpp2_bm_switch_buffers() модуля drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c драйвера сетевых адаптеров ethernet marvell ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12495
HIGH8.0

Уязвимость функции aqc111_suspend() модуля drivers/net/usb/aqc111.c драйвера сетевых адаптеров USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12498
MEDIUM5.7

Уязвимость функции rose_connect() модуля net/rose/af_rose.c реализации сетевых функций ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
CVSS 3.xСРЕДНЯЯ 5.7
CVSS:3.x/AV:A/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:A/AC:L/Au:S/C:N/I:N/A:C
BDU:2026-12499
MEDIUM5.7

Уязвимость функции mpfs_sys_controller_probe() модуля drivers/soc/microchip/mpfs-sys-controller.c драйвера SOC (система на кристалле) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
CVSS 3.xСРЕДНЯЯ 5.7
CVSS:3.x/AV:A/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:A/AC:L/Au:S/C:N/I:N/A:C
BDU:2026-12500
MEDIUM5.5

Уязвимость функции pvr_power_reset() модуля drivers/gpu/drm/imagination/pvr_power.c драйвера инфраструктуры прямого рендеринга (DRI) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12502
MEDIUM5.7

Уязвимость функции parse_redboot_partitions() модуля drivers/mtd/parsers/redboot.c драйвера памяти MTD ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
CVSS 3.xСРЕДНЯЯ 5.7
CVSS:3.x/AV:A/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:A/AC:L/Au:S/C:N/I:N/A:C
BDU:2026-12504
MEDIUM5.7

Уязвимость функции atmel_sha204a_rng_read_nonblocking() модуля drivers/crypto/atmel-sha204a.c драйвера криптографического ускорителя ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
CVSS 3.xСРЕДНЯЯ 5.7
CVSS:3.x/AV:A/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:A/AC:L/Au:S/C:N/I:N/A:C
BDU:2026-12505
HIGH8.0

Уязвимость функции gem_ptp_remove() модуля drivers/net/ethernet/cadence/macb_ptp.c драйвера сетевых адаптеров ethernet cadence ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12506
CRITICAL9.8

Уязвимость функции handle_one_ule_extension() модуля drivers/media/dvb-core/dvb_net.c драйвера мультимедийных устройств ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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 9.0
CVSS:2.0/AV:N/AC:L/Au:S/C:C/I:C/A:C
BDU:2026-12507
HIGH8.0

Уязвимость функции check_command_size_in_blocks() модуля drivers/usb/gadget/function/f_mass_storage.c драйвера гаджетов USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12508
HIGH8.0

Уязвимость функций x25_queue_rx_frame() и x25_clear_queues() модуля net/x25/x25_in.c реализации сетевых функций ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12510
MEDIUM5.5

Уязвимость функции rds_ib_get_mr() модуля net/rds/ib_rdma.c реализации сетевых функций ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12511
HIGH8.8

Уязвимость функции get_file_all_info() модуля fs/smb/server/smb2pdu.c файловой системы Smb ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.0
CVSS:2.0/AV:N/AC:L/Au:S/C:C/I:C/A:C
BDU:2026-12512
MEDIUM5.5

Уязвимость функции xdma_probe() модуля drivers/dma/xilinx/xdma.c драйвера движка DMA ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12513
MEDIUM5.5

Уязвимость функции idxd_device_evl_free() модуля drivers/dma/idxd/device.c драйвера движка DMA Intel Data Accelerator ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12515
HIGH7.8

Уязвимость функций ext4_register_sysfs(), ext4_unregister_sysfs() модуля fs/ext4/sysfs.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.5
CVSS:2.0/AV:L/AC:L/Au:M/C:C/I:C/A:C
BDU:2026-12516
HIGH7.8

Уязвимость функции ext4_feature_set_ok() модуля fs/ext4/super.c файловой системы Ext4 ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.5
CVSS:2.0/AV:L/AC:L/Au:M/C:C/I:C/A:C
BDU:2026-12518
HIGH7.8

Уязвимость функции ext4_ext_correct_indexes() модуля fs/ext4/extents.c файловой системы Ext4 ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
CVSS 3.xВЫСОКАЯ 7.8
CVSS:3.x/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
CVSS 2.0СРЕДНЯЯ 6.5
CVSS:2.0/AV:L/AC:L/Au:M/C:C/I:C/A:C
BDU:2026-12519
HIGH7.8

Уязвимость функции xfsaild_push() модуля fs/xfs/xfs_trans_ail.c файловой системы Xfs ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12527
HIGH8.2

Уязвимость функции smb2_sess_setup() модуля fs/smb/server/smb2pdu.c файловой системы Smb ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на целостность защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12529
MEDIUM5.5

Уязвимость функций system_call() и mcck_int_handler() модуля arch/s390/kernel/entry.S ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12530
MEDIUM5.5

Уязвимость функции __do_syscall() модуля arch/s390/kernel/syscall.c поддержки платформы S390 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12531
HIGH7.8

Уязвимость функции meson_spicc_remove() модуля drivers/spi/spi-meson-spicc.c драйвера устройств SPI ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12534
HIGH7.8

Уязвимость функции gem_get_ethtool_stats() модуля drivers/net/ethernet/cadence/macb_main.c драйвера сетевых адаптеров ethernet cadence ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12535
MEDIUM5.5

Уязвимость функции exp_seq_show() модуля net/netfilter/nf_conntrack_expect.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12536
HIGH7.8

Уязвимость функции btintel_hw_error() модуля drivers/bluetooth/btintel.c драйвера устройств Bluetooth ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12538
HIGH7.8

Уязвимость функции team_setup_by_port() модуля drivers/net/team/team_core.c драйвера сетевых устройств ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12539
HIGH7.8

Уязвимость функций iavf_get_sset_count() и iavf_get_ethtool_stats() модуля drivers/net/ethernet/intel/iavf/iavf_ethtool.c драйвера сетевых адаптеров ethernet intel ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12540
HIGH7.8

Уязвимость функций bcmasp_remove(), bcmasp_probe() модуля drivers/net/ethernet/broadcom/asp2/bcmasp.c драйвера сетевых адаптеров ethernet broadcom ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12541
HIGH7.8

Уязвимость функции smc_rx_pipe_buf_release() модуля net/smc/smc_rx.c реализации семейства протоколов сокетов SMC ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12542
MEDIUM5.5

Уязвимость функции nci_close_device() модуля net/nfc/nci/core.c поддержки реализации NFC NCI ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12543
HIGH7.8

Уязвимость функции mgmt_add_adv_patterns_monitor_complete() модуля net/bluetooth/mgmt.c подсистемы Bluetooth ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12545
HIGH7.8

Уязвимость функции xfrm_policy_fini() модуля net/xfrm/xfrm_policy.c реализации сетевых функций ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12547
MEDIUM5.5

Уязвимость функции esp_output_done() модуля net/ipv4/esp4.c реализации протокола IPv4 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12548
MEDIUM5.5

Уязвимость функции apple_report_fixup() модуля drivers/hid/hid-apple.c драйвера подсистемы устройств пользовательского интерфейса ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12549
MEDIUM5.5

Уязвимость функции simplify_symbols() модуля kernel/module/main.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12550
MEDIUM5.5

Уязвимость функции magicmouse_report_fixup() модуля drivers/hid/hid-magicmouse.c драйвера подсистемы устройств пользовательского интерфейса ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12551
MEDIUM5.5

Уязвимость функции asus_report_fixup() модуля drivers/hid/hid-asus.c драйвера подсистемы устройств пользовательского интерфейса ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12555
MEDIUM5.5

Уязвимость функции nxp_nci_i2c_set_mode() модуля drivers/nfc/nxp-nci/i2c.c драйвера NFC ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12557
HIGH7.8

Уязвимость функции cfg80211_pmsr_wdev_down() модуля net/wireless/pmsr.c поддержки беспроводной связи ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12558
MEDIUM5.5

Уязвимость функции cp2615_i2c_probe() модуля drivers/i2c/busses/i2c-cp2615.c драйвера аппаратной шины I2C ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12560
HIGH7.8

Уязвимость функции SYSCALL_DEFINE4() модуля kernel/futex/syscalls.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12561
HIGH8.8

Уязвимость функции kvm_get_vcpu_by_cpuid() модуля arch/loongarch/kvm/vcpu.c поддержки архитектуры LoongArch ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12562
MEDIUM5.5

Уязвимость функции init_cpu_fullname() модуля arch/loongarch/kernel/env.c поддержки архитектуры LoongArch ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12566
HIGH7.8

Уязвимость функции amdgpu_amdkfd_submit_ib() модуля drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c драйвера инфраструктуры прямого рендеринга (DRI) AMD GPU ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24Изменено: 2026-08-27
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
BDU:2026-12569
HIGH7.8

Уязвимость функции hackrf_probe() модуля drivers/media/usb/hackrf/hackrf.c драйвера мультимедийных устройств USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12570
HIGH7.8

Уязвимость функции as102_usb_probe() модуля drivers/media/usb/as102/as102_usb_drv.c драйвера мультимедийных устройств USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12571
HIGH7.8

Уязвимость функции cached_dev_free() модуля drivers/md/bcache/super.c драйвера программного RAID/LVM ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12572
HIGH7.8

Уязвимость функций usb6fire_chip_abort() и usb6fire_chip_disconnect() модуля sound/usb/6fire/chip.c звуковой подсистемы ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12573
HIGH7.8

Уязвимость функции em28xx_v4l2_open() модуля drivers/media/usb/em28xx/em28xx-video.c драйвера мультимедийных устройств USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12574
HIGH7.8

Уязвимость функции fops_vcodec_release() модуля drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c драйвера мультимедийных устройств ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12575
MEDIUM5.5

Уязвимость функции vidtv_start_feed() модуля drivers/media/test-drivers/vidtv/vidtv_bridge.c драйвера мультимедийных устройств ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12576
HIGH7.8

Уязвимость функции cgwb_release_workfn() модуля mm/backing-dev.c подсистемы управления памятью ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12577
MEDIUM5.5

Уязвимость функции epf_ntb_epc_init() модуля drivers/pci/endpoint/functions/pci-epf-vntb.c драйвера устройств PCI ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12578
HIGH7.8

Уязвимость функции ocfs2_fault() модуля fs/ocfs2/mmap.c файловой системы Ocfs2 ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12579
MEDIUM5.5

Уязвимость функции vidtv_channel_pmt_match_sections() модуля drivers/media/test-drivers/vidtv/vidtv_channel.c драйвера мультимедийных устройств ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12581
HIGH7.8

Уязвимость функции ct_vm_map() модуля sound/pci/ctxfi/ctvmem.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12582
MEDIUM5.5

Уязвимость функции lynxfb_ops_check_var() модуля drivers/staging/sm750fb/sm750.c поддержки дополнительных устройств ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12583
MEDIUM5.5

Уязвимость функции dlfb_ops_check_var() модуля drivers/video/fbdev/udlfb.c драйвера устройств кадрового буфера ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12585
HIGH8.6

Уязвимость функции parse_dacl() модуля fs/smb/server/smbacl.c файловой системы Smb ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
CVSS 3.xВЫСОКАЯ 8.6
CVSS:3.x/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.0
CVSS:2.0/AV:N/AC:L/Au:N/C:P/I:P/A:C
BDU:2026-12587
MEDIUM5.5

Уязвимость функции pn_rx_complete() модуля drivers/usb/gadget/function/f_phonet.c драйвера гаджетов USB ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12588
MEDIUM5.5

Уязвимость функции tdfxfb_check_var() модуля drivers/video/fbdev/tdfxfb.c драйвера устройств кадрового буфера ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12589
HIGH7.1

Уязвимость функции rtw_BIP_verify() модуля drivers/staging/rtl8723bs/core/rtw_security.c поддержки дополнительных устройств ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
CVSS 3.xВЫСОКАЯ 7.1
CVSS:3.x/AV:A/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:H
CVSS 2.0СРЕДНЯЯ 6.8
CVSS:2.0/AV:A/AC:L/Au:N/C:N/I:P/A:C
BDU:2026-12590
HIGH7.8

Уязвимость функции i2c_s3c_irq_nextbyte() модуля drivers/i2c/busses/i2c-s3c2410.c драйвера аппаратной шины I2C ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12591
HIGH7.5

Уязвимость функции rxrpc_input_packet_on_conn() модуля net/rxrpc/io_thread.c поддержки сокетов сеанса RxRPC ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12594
HIGH7.8

Уязвимость функции lan966x_fdma_reload() модуля drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c драйвера сетевых адаптеров ethernet microchip ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12595
HIGH7.8

Уязвимость функции filemap_map_pages() модуля mm/filemap.c подсистемы управления памятью ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12598
CRITICAL9.8

Уязвимость функции batadv_tt_prepare_tvlv_global_data() модуля net/batman-adv/translation-table.c реализации сетевых функций ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12599
HIGH7.5

Уязвимость функции tipc_group_proto_rcv() модуля net/tipc/group.c реализации протокола TIPC ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12600
HIGH7.8

Уязвимость функции nft_ct_timeout_obj_destroy() модуля net/netfilter/nft_ct.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12601
HIGH7.8

Уязвимость функции lookup_extent_data_ref() модуля fs/btrfs/extent-tree.c файловой системы Btrfs ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12602
HIGH7.8

Уязвимость функции sk_diag_dump_name() модуля net/unix/diag.c реализации сетевых функций ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12603
HIGH7.1

Уязвимость функции rt_mt6_check() модуля net/ipv6/netfilter/ip6t_rt.c реализации протокола IPv6 ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12604
HIGH7.8

Уязвимость функции netem_enqueue() модуля net/sched/sch_netem.c подсистемы управления трафиком net/sched ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12605
HIGH7.5

Уязвимость функции rxrpc_process_event() модуля net/rxrpc/conn_event.c поддержки сокетов сеанса RxRPC ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-24
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
BDU:2026-12606
HIGH7.8

Уязвимость функции ovs_netdev_tunnel_destroy() модуля net/openvswitch/vport-netdev.c поддержки маршрутизаторов Open vSwitch ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12607
HIGH7.1

Уязвимость функции validate_set() модуля net/openvswitch/flow_netlink.c поддержки маршрутизаторов Open vSwitch ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность и доступность защищаемой информации

Опубликовано: 2026-08-24
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
BDU:2026-12638
MEDIUM5.5

Уязвимость функции vub300_disconnect() модуля drivers/mmc/host/vub300.c драйвера карт MMC/SD/SDIO ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-25
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
BDU:2026-12639
MEDIUM5.5

Уязвимость функции __cdns3_gadget_ep_queue() модуля drivers/usb/cdns3/cdns3-gadget.c драйвера устройств шины USB ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-25
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
BDU:2026-12642
MEDIUM5.5

Уязвимость функции gether_disconnect() модуля drivers/usb/gadget/function/u_ether.c драйвера гаджетов USB ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-25
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
BDU:2026-12644
MEDIUM5.5

Уязвимость функции edac_mc_alloc() модуля drivers/edac/edac_mc.c драйвера EDAC (обнаружение и исправление ошибок) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-25Изменено: 2026-08-27
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
BDU:2026-12645
MEDIUM5.5

Уязвимость функции ipv6_srh_rcv() и seg6_hmac_validate_skb() ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-25
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
BDU:2026-12651
MEDIUM5.5

Уязвимость функции pn532_receive_buf() модуля drivers/nfc/pn533/uart.c драйвера NFC ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-25
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
BDU:2026-12664
MEDIUM5.5

Уязвимость функции mpu3050_trigger_probe() модуля drivers/iio/gyro/mpu3050-core.c драйвера различных типов встроенных датчиков ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-25
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
BDU:2026-12671
MEDIUM4.6

Уязвимость функции rz_mtu3_count_enable_write() модуля drivers/counter/rz-mtu3-cnt.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-25
CVSS 3.xСРЕДНЯЯ 4.6
CVSS:3.x/AV:A/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:L
CVSS 2.0СРЕДНЯЯ 4.0
CVSS:2.0/AV:A/AC:H/Au:S/C:P/I:P/A:P
BDU:2026-12673
MEDIUM4.8

Уязвимость функции dt2815_attach() модуля drivers/comedi/drivers/dt2815.c поддержки устройств сбора данных ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-25
CVSS 3.xСРЕДНЯЯ 4.8
CVSS:3.x/AV:A/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 4.3
CVSS:2.0/AV:A/AC:H/Au:S/C:N/I:N/A:C
BDU:2026-12677
CRITICAL9.8

Уязвимость функции tcp_ao_verify_hash() модуля net/ipv4/tcp_ao.c реализации протокола IPv4 ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-25
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
BDU:2026-12723
HIGH7.8

Уязвимость функции thermal_zone_device_register_with_trips() модуля drivers/thermal/thermal_core.c драйвера управления температурой ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-26
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
BDU:2026-12724
HIGH7.8

Уязвимость функции ahash_setkey() модуля drivers/crypto/caam/caamalg_qi2.c драйвера криптографического ускорителя ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-26
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
BDU:2026-12726
HIGH7.8

Уязвимость функции __acquires() модуля drivers/usb/chipidea/udc.c драйвера устройств шины USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-26
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
BDU:2026-12727
HIGH8.0

Уязвимость функции usbhs_remove() модуля drivers/usb/renesas_usbhs/common.c драйвера устройств шины USB ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-26
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
BDU:2026-12728
HIGH8.0

Уязвимость функции amdgpu_dma_buf_move_notify() модуля drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c драйвера инфраструктуры прямого рендеринга (DRI) AMD GPU ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-26
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
BDU:2026-12730
HIGH8.0

Уязвимость функции s3fwrn82_uart_read() модуля drivers/nfc/s3fwrn5/uart.c драйвера NFC ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-26
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
BDU:2026-12731
HIGH8.0

Уязвимость функции q54sj108a2_debugfs_read() модуля drivers/hwmon/pmbus/q54sj108a2.c драйвера мониторинга оборудования ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-26
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
BDU:2026-12733
HIGH8.8

Уязвимость функции opinfo_add() модуля fs/smb/server/oplock.c подсистемы Smb ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-26
CVSS 3.xВЫСОКАЯ 8.8
CVSS:3.x/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS 2.0КРИТИЧЕСКАЯ 9.0
CVSS:2.0/AV:N/AC:L/Au:S/C:C/I:C/A:C
BDU:2026-12735
HIGH7.8

Уязвимость функции addrconf_permanent_addr() модуля net/ipv6/addrconf.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-26
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
BDU:2026-12736
HIGH7.8

Уязвимость функции roccat_report_event() модуля drivers/hid/hid-roccat.c драйвера подсистемы устройств пользовательского интерфейса ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-26
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
BDU:2026-12737
HIGH7.8

Уязвимость функции vfe_isr() модуля drivers/media/platform/qcom/camss/camss-vfe-480.c драйвера мультимедийных устройств ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-26Изменено: 2026-08-27
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
BDU:2026-12738
HIGH7.8

Уязвимость функции scx_cgroup_init() модуля kernel/sched/ext.c поддержки системы учета ресурсов ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-26
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
BDU:2026-12758
MEDIUM5.5

Уязвимость функции mctp_flow_prepare_output() модуля net/mctp/route.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-27
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
BDU:2026-12759
MEDIUM5.5

Уязвимость функции mctp_i2c_recv() модуля drivers/net/mctp/mctp-i2c.c драйвера последовательного транспорта MCTP ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12760
MEDIUM5.5

Уязвимость функции vcpu_block() модуля arch/x86/kvm/x86.c подсистемы виртуализации на платформе x86 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12763
HIGH7.5

Уязвимость функции bond_rcv_validate() модуля drivers/net/bonding/bond_main.c драйвера сетевых устройств ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12793
HIGH7.8

Уязвимость функции init_kfd_vm() модуля drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c драйвера инфраструктуры прямого рендеринга (DRI) AMD GPU ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-27
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
BDU:2026-12795
HIGH7.8

Уязвимость функции xfrm_policy_fini() модуля net/xfrm/xfrm_policy.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-27
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
BDU:2026-12797
HIGH7.8

Уязвимость функции shmem_sg_alloc_table() модуля drivers/gpu/drm/i915/gem/i915_gem_shmem.c драйвера инфраструктуры прямого рендеринга (DRI) ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-27
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
BDU:2026-12798
HIGH7.5

Уязвимость модуля drivers/net/ipa/reg/gsi_reg-v5.0.c драйвера сетевых устройств ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12799
HIGH7.8

Уязвимость функции xdp_umem_reg() модуля net/xdp/xdp_umem.c реализации сетевых функций ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-27
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
BDU:2026-12800
HIGH7.8

Уязвимость функции af_alg_pull_tsgl() модуля crypto/af_alg.c криптографической подсистемы ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-27
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
BDU:2026-12801
HIGH7.5

Уязвимость функции rpcrdma_post_recvs() модуля net/sunrpc/xprtrdma/verbs.c реализации протокола RPC ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12802
HIGH7.5

Уязвимость функции icmp_build_probe() модуля net/ipv4/icmp.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12803
HIGH8.1

Уязвимость модуля net/netfilter/nft_set_pipapo_avx2.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-27
CVSS 3.xВЫСОКАЯ 8.1
CVSS:3.x/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
CVSS 2.0ВЫСОКАЯ 8.5
CVSS:2.0/AV:N/AC:L/Au:S/C:C/I:C/A:N
BDU:2026-12806
HIGH7.5

Уязвимость функции ceph_monmap_decode() модуля net/ceph/mon_client.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12827
MEDIUM5.5

Уязвимость компонента mtk-smi ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12830
HIGH7.5

Уязвимость компонента net/tls/tls_sw.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12831
MEDIUM5.5

Уязвимость компонента drivers/spi/spi.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12835
HIGH7.5

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

Опубликовано: 2026-08-27
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
BDU:2026-12836
HIGH8.1

Уязвимость компонента mvm модуля wifi ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12853
MEDIUM5.5

Уязвимость компонентов net/mlx5 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12854
MEDIUM5.5

Уязвимость компонента net/mptcp/pm_kernel.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12855
MEDIUM5.5

Уязвимость компонента btrfs/inode.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12856
HIGH7.8

Уязвимость компонента io_uring/kbuf.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12857
MEDIUM5.5

Уязвимость компонента qcom/qdsp6 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-12858
MEDIUM5.5

Уязвимость компонента net/mlx5 ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-27
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
BDU:2026-13225
MEDIUM5.7

Уязвимость функции hx9023s_set_samp_freq() модуля drivers/iio/proximity/hx9023s.c драйвера различных типов встроенных датчиков ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-30
CVSS 3.xСРЕДНЯЯ 5.7
CVSS:3.x/AV:A/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:A/AC:L/Au:S/C:N/I:N/A:C
BDU:2026-13226
MEDIUM5.5

Уязвимость функции check_mem_access() модуля kernel/bpf/verifier.c поддержки интерпретатора BPF ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-30
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
BDU:2026-13228
HIGH7.0

Уязвимость функции build_mapping() модуля net/xfrm/xfrm_user.c реализации сетевых функций ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-30
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
BDU:2026-13229
HIGH7.0

Уязвимость функции uncore_discovery_pci() модуля arch/x86/events/intel/uncore_discovery.c поддержки платформы x86 ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-30
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
BDU:2026-13230
HIGH7.1

Уязвимость функции _aead_recvmsg() модуля crypto/algif_aead.c криптографической подсистемы ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-30
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
BDU:2026-13231
HIGH7.1

Уязвимость функций dcache_init_early(), dcache_init() модуля fs/dcache.c файловой системы ядра операционной системы Linux, позволяющая нарушителю получить доступ к защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-08-30
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
BDU:2026-13232
HIGH7.1

Уязвимость функции fw_mbox_index_xlate() модуля drivers/mailbox/mailbox.c драйвера оборудования почтовых ящиков ядра операционной системы Linux, позволяющая нарушителю получить доступ к защищаемой информации или вызвать отказ в обслуживании

Опубликовано: 2026-08-30
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
BDU:2026-13233
MEDIUM5.5

Уязвимость функции comedi_device_attach() модуля drivers/comedi/drivers.c ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-30
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
BDU:2026-13236
MEDIUM5.5

Уязвимость функции most_register_interface() модуля drivers/most/core.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-30
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
BDU:2026-13239
MEDIUM5.7

Уязвимость функции geth_alloc_inst() модуля drivers/usb/gadget/function/f_subset.c драйвера гаджетов USB ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-30
CVSS 3.xСРЕДНЯЯ 5.7
CVSS:3.x/AV:A/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:A/AC:L/Au:S/C:N/I:N/A:C
BDU:2026-13240
MEDIUM5.7

Уязвимость функции most_register_interface() модуля drivers/most/core.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-30
CVSS 3.xСРЕДНЯЯ 5.7
CVSS:3.x/AV:A/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 2.0СРЕДНЯЯ 5.5
CVSS:2.0/AV:A/AC:L/Au:S/C:N/I:N/A:C
BDU:2026-13243
MEDIUM5.5

Уязвимость функции pqm_update_queue_properties() модуля drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c драйвера инфраструктуры прямого рендеринга (DRI) видеокарт AMD ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на доступность защищаемой информации

Опубликовано: 2026-08-30
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
BDU:2026-13244
MEDIUM5.5

Уязвимость функции mtk_smi_larb_remove() модуля drivers/memory/mtk-smi.c драйвера контроллера памяти ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-30
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
BDU:2026-13245
MEDIUM5.5

Уязвимость функции __ufshcd_wl_suspend() модуля drivers/ufs/core/ufshcd.c поддержки хост-контроллеров UFS (Universal Flash Storage). ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-30
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
BDU:2026-13246
MEDIUM5.5

Уязвимость функции idxd_conf_device_release() модуля drivers/dma/idxd/sysfs.c драйвера движка DMA Intel Data Accelerator ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-30
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
BDU:2026-13247
MEDIUM5.5

Уязвимость функции tipc_sk_filter_connect() модуля net/tipc/socket.c реализации протокола TIPC ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-30
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
BDU:2026-13248
MEDIUM5.5

Уязвимость функции wdm_in_callback() модуля drivers/usb/class/cdc-wdm.c драйвера устройств шины USB ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-30
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
BDU:2026-13252
MEDIUM5.5

Уязвимость функции ksz_ptp_msg_irq_setup() модуля drivers/net/dsa/microchip/ksz_ptp.c драйвера DSA ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-08-30
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
BDU:2026-13257
MEDIUM5.5

Уязвимость функции ufshcd_add_command_trace() модуля drivers/ufs/core/ufshcd.c поддержки хост-контроллеров UFS (Universal Flash Storage) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-30
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
BDU:2026-13258
MEDIUM5.5

Уязвимость функции xfrm_migrate_policy_find() модуля net/xfrm/xfrm_policy.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-30
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
BDU:2026-13259
MEDIUM5.5

Уязвимость функции e1000_tx_map() модуля drivers/net/ethernet/intel/e1000/e1000_main.c драйвера сетевых адаптеров Ethernet Intel ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-08-30
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
BDU:2026-13685
MEDIUM5.5

Уязвимость функции vc4_free_hang_state() модуля drivers/gpu/drm/vc4/vc4_gem.c драйвера инфраструктуры прямого рендеринга (DRI) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-09-01
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
BDU:2026-13689
MEDIUM5.5

Уязвимость функции l2tp_xmit_core() модуля net/l2tp/l2tp_core.c реализации протокола туннелирования второго уровня (L2TP) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-09-01
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
BDU:2026-13702
MEDIUM5.5

Уязвимость функции lapbeth_free_device() модуля drivers/net/wan/lapbether.c драйвера сетевых устройств ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-09-01
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
BDU:2026-13703
MEDIUM5.5

Уязвимость функции serial8250_tx_dma_flush() модуля drivers/tty/serial/8250/8250_dma.c драйвера консоли TTY на последовательном порте ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-09-01
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
BDU:2026-13710
MEDIUM5.5

Уязвимость функции download_firmware() модуля drivers/bluetooth/hci_ll.c драйвера устройств Bluetooth ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-09-01
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
BDU:2026-13810
MEDIUM5.5

Уязвимость функции ishtp_bus_remove_all_clients() модуля drivers/hid/intel-ish-hid/ishtp/bus.c драйвера подсистемы устройств пользовательского интерфейса ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-09-02
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
BDU:2026-13812
HIGH7.1

Уязвимость функции unpack_table() модуля security/apparmor/match.c компонента обеспечения безопасности AppArmor ядра операционной системы Linux, позволяющая нарушителю раскрыть защищаемую информацию или вызвать отказ в обслуживании

Опубликовано: 2026-09-02
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
BDU:2026-13814
MEDIUM5.5

Уязвимость функции cdns_resume() модуля drivers/usb/cdns3/core.c драйвера устройств шины USB ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-09-02
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
BDU:2026-14139
MEDIUM5.5

Уязвимость функции xhci_irq() модуля drivers/usb/host/xhci-ring.c драйвера устройств шины USB ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-09-03
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
BDU:2026-14140
HIGH7.8

Уязвимость функции sps30_i2c_read_meas() модуля drivers/iio/chemical/sps30_i2c.c драйвера различных типов встроенных датчиков ядра операционной системы Linux, позволяющая нарушителю оказать воздействие на конфиденциальность, целостность и доступность защищаемой информации

Опубликовано: 2026-09-03
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
BDU:2026-14142
MEDIUM5.5

Уязвимость функции cgroup_migrate_add_task() модуля kernel/cgroup/cgroup.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-09-03
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
BDU:2026-14143
MEDIUM5.5

Уязвимость функции xhci_disable_slot() модуля drivers/usb/host/xhci.c драйвера устройств шины USB ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-09-03
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
BDU:2026-14144
MEDIUM5.5

Уязвимость функции xe_sync_entry_parse() модуля drivers/gpu/drm/xe/xe_sync.c драйвера инфраструктуры прямого рендеринга (DRI) ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-09-03
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
BDU:2026-14148
MEDIUM5.5

Уязвимость драйвера Qualcomm IPA модуля drivers/net/ipa/reg/gsi_reg-v5.0.c ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-09-03
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
BDU:2026-14149
HIGH7.1

Уязвимость функции pipapo_drop() модуля net/netfilter/nft_set_pipapo.c компонента netfilter ядра операционной системы Linux, позволяющая нарушителю вызвать отказ в обслуживании

Опубликовано: 2026-09-03
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
CVE-2024-14027
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: fs/xattr: missing fdput() in fremovexattr error path In the Linux kernel, the fremovexattr() syscall calls fdget() to acquire a file reference but returns early without calling fdput() when strncpy_from_user() fails on the name argument. In multi-threaded processes where fdget() takes the slow path, this permanently leaks one file reference per call, pinning the struct file and associated kernel objects in memory. An unprivileged local user can exploit this to cause kernel memory exhaustion. The issue was inadvertently fixed by commit a71874379ec8 ("xattr: switch to CLASS(fd)").

Опубликовано: 2026-03-09Изменено: 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
CVE-2025-71239
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: audit: add fchmodat2() to change attributes class fchmodat2(), introduced in version 6.6 is currently not in the change attribute class of audit. Calling fchmodat2() to change a file attribute in the same fashion than chmod() or fchmodat() will bypass audit rules such as: -w /tmp/test -p rwa -k test_rwa The current patch adds fchmodat2() to the change attributes class.

Опубликовано: 2026-03-17Изменено: 2026-06-17
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2025-71265
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: fs: ntfs3: fix infinite loop in attr_load_runs_range on inconsistent metadata We found an infinite loop bug in the ntfs3 file system that can lead to a Denial-of-Service (DoS) condition. A malformed NTFS image can cause an infinite loop when an attribute header indicates an empty run list, while directory entries reference it as containing actual data. In NTFS, setting evcn=-1 with svcn=0 is a valid way to represent an empty run list, and run_unpack() correctly handles this by checking if evcn + 1 equals svcn and returning early without parsing any run data. However, this creates a problem when there is metadata inconsistency, where the attribute header claims to be empty (evcn=-1) but the caller expects to read actual data. When run_unpack() immediately returns success upon seeing this condition, it leaves the runs_tree uninitialized with run->runs as a NULL. The calling function attr_load_runs_range() assumes that a successful return means that the runs were loaded and sets clen to 0, expecting the next run_lookup_entry() call to succeed. Because runs_tree remains uninitialized, run_lookup_entry() continues to fail, and the loop increments vcn by zero (vcn += 0), leading to an infinite loop. This patch adds a retry counter to detect when run_lookup_entry() fails consecutively after attr_load_runs_vcn(). If the run is still not found on the second attempt, it indicates corrupted metadata and returns -EINVAL, preventing the Denial-of-Service (DoS) vulnerability.

Опубликовано: 2026-03-18Изменено: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2025-71266
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: fs: ntfs3: check return value of indx_find to avoid infinite loop We found an infinite loop bug in the ntfs3 file system that can lead to a Denial-of-Service (DoS) condition. A malformed dentry in the ntfs3 filesystem can cause the kernel to hang during the lookup operations. By setting the HAS_SUB_NODE flag in an INDEX_ENTRY within a directory's INDEX_ALLOCATION block and manipulating the VCN pointer, an attacker can cause the indx_find() function to repeatedly read the same block, allocating 4 KB of memory each time. The kernel lacks VCN loop detection and depth limits, causing memory exhaustion and an OOM crash. This patch adds a return value check for fnd_push() to prevent a memory exhaustion vulnerability caused by infinite loops. When the index exceeds the size of the fnd->nodes array, fnd_push() returns -EINVAL. The indx_find() function checks this return value and stops processing, preventing further memory allocation.

Опубликовано: 2026-03-18Изменено: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2025-71267
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: fs: ntfs3: fix infinite loop triggered by zero-sized ATTR_LIST We found an infinite loop bug in the ntfs3 file system that can lead to a Denial-of-Service (DoS) condition. A malformed NTFS image can cause an infinite loop when an ATTR_LIST attribute indicates a zero data size while the driver allocates memory for it. When ntfs_load_attr_list() processes a resident ATTR_LIST with data_size set to zero, it still allocates memory because of al_aligned(0). This creates an inconsistent state where ni->attr_list.size is zero, but ni->attr_list.le is non-null. This causes ni_enum_attr_ex to incorrectly assume that no attribute list exists and enumerates only the primary MFT record. When it finds ATTR_LIST, the code reloads it and restarts the enumeration, repeating indefinitely. The mount operation never completes, hanging the kernel thread. This patch adds validation to ensure that data_size is non-zero before memory allocation. When a zero-sized ATTR_LIST is detected, the function returns -EINVAL, preventing a DoS vulnerability.

Опубликовано: 2026-03-18Изменено: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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: 2026-07-30
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
CVE-2025-71272
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: most: core: fix resource leak in most_register_interface error paths The function most_register_interface() did not correctly release resources if it failed early (before registering the device). In these cases, it returned an error code immediately, leaking the memory allocated for the interface. Fix this by initializing the device early via device_initialize() and calling put_device() on all error paths. The most_register_interface() is expected to call put_device() on error which frees the resources allocated in the caller. The put_device() either calls release_mdev() or dim2_release(), depending on the caller. Switch to using device_add() instead of device_register() to handle the split initialization.

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
CVE-2025-71273
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: Use devm_kmemdup() in rtw_set_supported_band() Simplify the code by using device managed memory allocations. This also fixes a memory leak in rtw_register_hw(). The supported bands were not freed in the error path. Copied from commit 145df52a8671 ("wifi: rtw89: Convert rtw89_core_set_supported_band to use devm_*").

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
CVE-2025-71274
MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: rpmsg: core: fix race in driver_override_show() and use core helper The driver_override_show function reads the driver_override string without holding the device_lock. However, the store function modifies and frees the string while holding the device_lock. This creates a race condition where the string can be freed by the store function while being read by the show function, leading to a use-after-free. To fix this, replace the rpmsg_string_attr macro with explicit show and store functions. The new driver_override_store uses the standard driver_set_override helper. Since the introduction of driver_set_override, the comments in include/linux/rpmsg.h have stated that this helper must be used to set or clear driver_override, but the implementation was not updated until now. Because driver_set_override modifies and frees the string while holding the device_lock, the new driver_override_show now correctly holds the device_lock during the read operation to prevent the race. Additionally, since rpmsg_string_attr has only ever been used for driver_override, removing the macro simplifies the code.

Опубликовано: 2026-05-06Изменено: 2026-07-30
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
CVE-2025-71286
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ASoC: SOF: ipc4-topology: Correct the allocation size for bytes controls The size of the data behind of scontrol->ipc_control_data for bytes controls is: [1] sizeof(struct sof_ipc4_control_data) + // kernel only struct [2] sizeof(struct sof_abi_hdr)) + payload The max_size specifies the size of [2] and it is coming from topology. Change the function to take this into account and allocate adequate amount of memory behind scontrol->ipc_control_data. With the change we will allocate [1] amount more memory to be able to hold the full size of data.

Опубликовано: 2026-05-06Изменено: 2026-07-30
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
CVE-2025-71287
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: memory: mtk-smi: fix device leak on larb probe Make sure to drop the reference taken when looking up the SMI device during larb probe on late probe failure (e.g. probe deferral) and on driver unbind.

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
CVE-2025-71288
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: memory: mtk-smi: fix device leaks on common probe Make sure to drop the reference taken when looking up the SMI device during common probe on late probe failure (e.g. probe deferral) and on driver unbind.

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
CVE-2025-71291
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: misc: bcm_vk: Fix possible null-pointer dereferences in bcm_vk_read() In the function bcm_vk_read(), the pointer entry is checked, indicating that it can be NULL. If entry is NULL and rc is set to -EMSGSIZE, the following code may cause null-pointer dereferences: struct vk_msg_blk tmp_msg = entry->to_h_msg[0]; set_msg_id(&tmp_msg, entry->usr_msg_id); tmp_msg.size = entry->to_h_blks - 1; To prevent these possible null-pointer dereferences, copy to_h_msg, usr_msg_id, and to_h_blks from iter into temporary variables, and return these temporary variables to the application instead of accessing them through a potentially NULL 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
CVE-2025-71292
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: jfs: nlink overflow in jfs_rename If nlink is maximal for a directory (-1) and inside that directory you perform a rename for some child directory (not moving from the parent), then the nlink of the first directory is first incremented and later decremented. Normally this is fine, but when nlink = -1 this causes a wrap around to 0, and then drop_nlink issues a warning. After applying the patch syzbot no longer issues any warnings. I also ran some basic fs tests to look for any regressions.

Опубликовано: 2026-05-06Изменено: 2026-07-30
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
CVE-2025-71294
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: fix NULL pointer issue buffer funcs If SDMA block not enabled, buffer_funcs will not initialize, fix the null pointer issue if buffer_funcs not initialized.

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
CVE-2025-71295
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: fs/buffer: add alert in try_to_free_buffers() for folios without buffers try_to_free_buffers() can be called on folios with no buffers attached when filemap_release_folio() is invoked on a folio belonging to a mapping with AS_RELEASE_ALWAYS set but no release_folio operation defined. In such cases, folio_needs_release() returns true because of the AS_RELEASE_ALWAYS flag, but the folio has no private buffer data. This causes try_to_free_buffers() to call drop_buffers() on a folio with no buffers, leading to a null pointer dereference. Adding a check in try_to_free_buffers() to return early if the folio has no buffers attached, with WARN_ON_ONCE() to alert about the misconfiguration. This provides defensive hardening.

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
CVE-2025-71297
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: 8822b: Avoid WARNING in rtw8822b_config_trx_mode() rtw8822b_set_antenna() can be called from userspace when the chip is powered off. In that case a WARNING is triggered in rtw8822b_config_trx_mode() because trying to read the RF registers when the chip is powered off returns an unexpected value. Call rtw8822b_config_trx_mode() in rtw8822b_set_antenna() only when the chip is powered on. ------------[ cut here ]------------ write RF mode table fail WARNING: CPU: 0 PID: 7183 at rtw8822b.c:824 rtw8822b_config_trx_mode.constprop.0+0x835/0x840 [rtw88_8822b] CPU: 0 UID: 0 PID: 7183 Comm: iw Tainted: G W OE 6.17.5-arch1-1 #1 PREEMPT(full) 01c39fc421df2af799dd5e9180b572af860b40c1 Tainted: [W]=WARN, [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Hardware name: LENOVO 82KR/LNVNB161216, BIOS HBCN18WW 08/27/2021 RIP: 0010:rtw8822b_config_trx_mode.constprop.0+0x835/0x840 [rtw88_8822b] Call Trace: rtw8822b_set_antenna+0x57/0x70 [rtw88_8822b 370206f42e5890d8d5f48eb358b759efa37c422b] rtw_ops_set_antenna+0x50/0x80 [rtw88_core 711c8fb4f686162be4625b1d0b8e8c6a5ac850fb] ieee80211_set_antenna+0x60/0x100 [mac80211 f1845d85d2ecacf3b71867635a050ece90486cf3] nl80211_set_wiphy+0x384/0xe00 [cfg80211 296485ee85696d2150309a6d21a7fbca83d3dbda] ? netdev_run_todo+0x63/0x550 genl_family_rcv_msg_doit+0xfc/0x160 genl_rcv_msg+0x1aa/0x2b0 ? __pfx_nl80211_pre_doit+0x10/0x10 [cfg80211 296485ee85696d2150309a6d21a7fbca83d3dbda] ? __pfx_nl80211_set_wiphy+0x10/0x10 [cfg80211 296485ee85696d2150309a6d21a7fbca83d3dbda] ? __pfx_nl80211_post_doit+0x10/0x10 [cfg80211 296485ee85696d2150309a6d21a7fbca83d3dbda] ? __pfx_genl_rcv_msg+0x10/0x10 netlink_rcv_skb+0x59/0x110 genl_rcv+0x28/0x40 netlink_unicast+0x285/0x3c0 ? __alloc_skb+0xdb/0x1a0 netlink_sendmsg+0x20d/0x430 ____sys_sendmsg+0x39f/0x3d0 ? import_iovec+0x2f/0x40 ___sys_sendmsg+0x99/0xe0 ? refill_obj_stock+0x12e/0x240 __sys_sendmsg+0x8a/0xf0 do_syscall_64+0x81/0x970 ? do_syscall_64+0x81/0x970 ? ksys_read+0x73/0xf0 ? do_syscall_64+0x81/0x970 ? count_memcg_events+0xc2/0x190 ? handle_mm_fault+0x1d7/0x2d0 ? do_user_addr_fault+0x21a/0x690 ? exc_page_fault+0x7e/0x1a0 entry_SYSCALL_64_after_hwframe+0x76/0x7e ---[ end trace 0000000000000000 ]---

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
CVE-2025-71300
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Revert "arm64: zynqmp: Add an OP-TEE node to the device tree" This reverts commit 06d22ed6b6635b17551f386b50bb5aaff9b75fbe. OP-TEE logic in U-Boot automatically injects a reserved-memory node along with optee firmware node to kernel device tree. The injection logic is dependent on that there is no manually defined optee node. Having the node in zynqmp.dtsi effectively breaks OP-TEE's insertion of the reserved-memory node, causing memory access violations during runtime.

Опубликовано: 2026-05-08Изменено: 2026-07-30
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
CVE-2025-71304
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: smack: /smack/doi: accept previously used values Writing to /smack/doi a value that has ever been written there in the past disables networking for non-ambient labels. E.g. # cat /smack/doi 3 # netlabelctl -p cipso list Configured CIPSO mappings (1) DOI value : 3 mapping type : PASS_THROUGH # netlabelctl -p map list Configured NetLabel domain mappings (3) domain: "_" (IPv4) protocol: UNLABELED domain: DEFAULT (IPv4) protocol: CIPSO, DOI = 3 domain: DEFAULT (IPv6) protocol: UNLABELED # cat /smack/ambient _ # cat /proc/$$/attr/smack/current _ # ping -c1 10.1.95.12 64 bytes from 10.1.95.12: icmp_seq=1 ttl=64 time=0.964 ms # echo foo >/proc/$$/attr/smack/current # ping -c1 10.1.95.12 64 bytes from 10.1.95.12: icmp_seq=1 ttl=64 time=0.956 ms unknown option 86 # echo 4 >/smack/doi # echo 3 >/smack/doi !> [ 214.050395] smk_cipso_doi:691 cipso add rc = -17 # echo 3 >/smack/doi !> [ 249.402261] smk_cipso_doi:678 remove rc = -2 !> [ 249.402261] smk_cipso_doi:691 cipso add rc = -17 # ping -c1 10.1.95.12 !!> ping: 10.1.95.12: Address family for hostname not supported # echo _ >/proc/$$/attr/smack/current # ping -c1 10.1.95.12 64 bytes from 10.1.95.12: icmp_seq=1 ttl=64 time=0.617 ms This happens because Smack keeps decommissioned DOIs, fails to re-add them, and consequently refuses to add the “default” domain map: # netlabelctl -p cipso list Configured CIPSO mappings (2) DOI value : 3 mapping type : PASS_THROUGH DOI value : 4 mapping type : PASS_THROUGH # netlabelctl -p map list Configured NetLabel domain mappings (2) domain: "_" (IPv4) protocol: UNLABELED !> (no ipv4 map for default domain here) domain: DEFAULT (IPv6) protocol: UNLABELED Fix by clearing decommissioned DOI definitions and serializing concurrent DOI updates with a new lock. Also: - allow /smack/doi to live unconfigured, since adding a map (netlbl_cfg_cipsov4_map_add) may fail. CIPSO_V4_DOI_UNKNOWN(0) indicates the unconfigured DOI - add new DOI before removing the old default map, so the old map remains if the add fails (2008-02-04, Casey Schaufler)

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
CVE-2025-71305
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/display/dp_mst: Add protection against 0 vcpi When releasing a timeslot there is a slight chance we may end up with the wrong payload mask due to overflow if the delayed_destroy_work ends up coming into play after a DP 2.1 monitor gets disconnected which causes vcpi to become 0 then we try to make the payload = ~BIT(vcpi - 1) which is a negative shift. VCPI id should never really be 0 hence skip changing the payload mask if VCPI is 0. Otherwise it leads to <7> [515.287237] xe 0000:03:00.0: [drm:drm_dp_mst_get_port_malloc [drm_display_helper]] port ffff888126ce9000 (3) <4> [515.287267] -----------[ cut here ]----------- <3> [515.287268] UBSAN: shift-out-of-bounds in ../drivers/gpu/drm/display/drm_dp_mst_topology.c:4575:36 <3> [515.287271] shift exponent -1 is negative <4> [515.287275] CPU: 7 UID: 0 PID: 3108 Comm: kworker/u64:33 Tainted: G S U 6.17.0-rc6-lgci-xe-xe-3795-3e79699fa1b216e92+ #1 PREEMPT(voluntary) <4> [515.287279] Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER <4> [515.287279] Hardware name: ASUS System Product Name/PRIME Z790-P WIFI, BIOS 1645 03/15/2024 <4> [515.287281] Workqueue: drm_dp_mst_wq drm_dp_delayed_destroy_work [drm_display_helper] <4> [515.287303] Call Trace: <4> [515.287304] <4> [515.287306] dump_stack_lvl+0xc1/0xf0 <4> [515.287313] dump_stack+0x10/0x20 <4> [515.287316] __ubsan_handle_shift_out_of_bounds+0x133/0x2e0 <4> [515.287324] ? drm_atomic_get_private_obj_state+0x186/0x1d0 <4> [515.287333] drm_dp_atomic_release_time_slots.cold+0x17/0x3d [drm_display_helper] <4> [515.287355] mst_connector_atomic_check+0x159/0x180 [xe] <4> [515.287546] drm_atomic_helper_check_modeset+0x4d9/0xfa0 <4> [515.287550] ? __ww_mutex_lock.constprop.0+0x6f/0x1a60 <4> [515.287562] intel_atomic_check+0x119/0x2b80 [xe] <4> [515.287740] ? find_held_lock+0x31/0x90 <4> [515.287747] ? lock_release+0xce/0x2a0 <4> [515.287754] drm_atomic_check_only+0x6a2/0xb40 <4> [515.287758] ? drm_atomic_add_affected_connectors+0x12b/0x140 <4> [515.287765] drm_atomic_commit+0x6e/0xf0 <4> [515.287766] ? _pfx__drm_printfn_info+0x10/0x10 <4> [515.287774] drm_client_modeset_commit_atomic+0x25c/0x2b0 <4> [515.287794] drm_client_modeset_commit_locked+0x60/0x1b0 <4> [515.287795] ? mutex_lock_nested+0x1b/0x30 <4> [515.287801] drm_client_modeset_commit+0x26/0x50 <4> [515.287804] __drm_fb_helper_restore_fbdev_mode_unlocked+0xdc/0x110 <4> [515.287810] drm_fb_helper_hotplug_event+0x120/0x140 <4> [515.287814] drm_fbdev_client_hotplug+0x28/0xd0 <4> [515.287819] drm_client_hotplug+0x6c/0xf0 <4> [515.287824] drm_client_dev_hotplug+0x9e/0xd0 <4> [515.287829] drm_kms_helper_hotplug_event+0x1a/0x30 <4> [515.287834] drm_dp_delayed_destroy_work+0x3df/0x410 [drm_display_helper] <4> [515.287861] process_one_work+0x22b/0x6f0 <4> [515.287874] worker_thread+0x1e8/0x3d0 <4> [515.287879] ? __pfx_worker_thread+0x10/0x10 <4> [515.287882] kthread+0x11c/0x250 <4> [515.287886] ? __pfx_kthread+0x10/0x10 <4> [515.287890] ret_from_fork+0x2d7/0x310 <4> [515.287894] ? __pfx_kthread+0x10/0x10 <4> [515.287897] ret_from_fork_asm+0x1a/0x30

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
CVE-2025-71311
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: fs/ntfs3: Initialize new folios before use KMSAN reports an uninitialized value in longest_match_std(), invoked from ntfs_compress_write(). When new folios are allocated without being marked uptodate and ni_read_frame() is skipped because the caller expects the frame to be completely overwritten, some reserved folios may remain only partially filled, leaving the rest memory uninitialized.

Опубликовано: 2026-05-27Изменено: 2026-07-30
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
CVE-2025-71314
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/panthor: Recover from panthor_gpu_flush_caches() failures We have seen a few cases where the whole memory subsystem is blocked and flush operations never complete. When that happens, we want to: - schedule a reset, so we can recover from this situation - in the reset path, we need to reset the pending_reqs so we can send new commands after the reset - if more panthor_gpu_flush_caches() operations are queued after the timeout, we skip them and return -EIO directly to avoid needless waits (the memory block won't miraculously work again) Note that we drop the WARN_ON()s because these hangs can be triggered with buggy GPU jobs created by the UMD, and there's no way we can prevent it. We do keep the error messages though. v2: - New patch v3: - Collect R-b - Explicitly mention the fact we dropped the WARN_ON()s in the commit message v4: - No changes

Опубликовано: 2026-06-03Изменено: 2026-07-22
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
CVE-2026-23227
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: drm/exynos: vidi: use ctx->lock to protect struct vidi_context member variables related to memory alloc/free Exynos Virtual Display driver performs memory alloc/free operations without lock protection, which easily causes concurrency problem. For example, use-after-free can occur in race scenario like this: ``` CPU0 CPU1 CPU2 ---- ---- ---- vidi_connection_ioctl() if (vidi->connection) // true drm_edid = drm_edid_alloc(); // alloc drm_edid ... ctx->raw_edid = drm_edid; ... drm_mode_getconnector() drm_helper_probe_single_connector_modes() vidi_get_modes() if (ctx->raw_edid) // true drm_edid_dup(ctx->raw_edid); if (!drm_edid) // false ... vidi_connection_ioctl() if (vidi->connection) // false drm_edid_free(ctx->raw_edid); // free drm_edid ... drm_edid_alloc(drm_edid->edid) kmemdup(edid); // UAF!! ... ``` To prevent these vulns, at least in vidi_context, member variables related to memory alloc/free should be protected with ctx->lock.

Опубликовано: 2026-02-18Изменено: 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
CVE-2026-23231
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: fix use-after-free in nf_tables_addchain() nf_tables_addchain() publishes the chain to table->chains via list_add_tail_rcu() (in nft_chain_add()) before registering hooks. If nf_tables_register_hook() then fails, the error path calls nft_chain_del() (list_del_rcu()) followed by nf_tables_chain_destroy() with no RCU grace period in between. This creates two use-after-free conditions: 1) Control-plane: nf_tables_dump_chains() traverses table->chains under rcu_read_lock(). A concurrent dump can still be walking the chain when the error path frees it. 2) Packet path: for NFPROTO_INET, nf_register_net_hook() briefly installs the IPv4 hook before IPv6 registration fails. Packets entering nft_do_chain() via the transient IPv4 hook can still be dereferencing chain->blob_gen_X when the error path frees the chain. Add synchronize_rcu() between nft_chain_del() and the chain destroy so that all RCU readers -- both dump threads and in-flight packet evaluation -- have finished before the chain is freed.

Опубликовано: 2026-03-04Изменено: 2026-07-14
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
CVE-2026-23239
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: espintcp: Fix race condition in espintcp_close() This issue was discovered during a code audit. After cancel_work_sync() is called from espintcp_close(), espintcp_tx_work() can still be scheduled from paths such as the Delayed ACK handler or ksoftirqd. As a result, the espintcp_tx_work() worker may dereference a freed espintcp ctx or sk. The following is a simple race scenario: cpu0 cpu1 espintcp_close() cancel_work_sync(&ctx->work); espintcp_write_space() schedule_work(&ctx->work); To prevent this race condition, cancel_work_sync() is replaced with disable_work_sync().

Опубликовано: 2026-03-10Изменено: 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
CVE-2026-23240
CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: tls: Fix race condition in tls_sw_cancel_work_tx() This issue was discovered during a code audit. After cancel_delayed_work_sync() is called from tls_sk_proto_close(), tx_work_handler() can still be scheduled from paths such as the Delayed ACK handler or ksoftirqd. As a result, the tx_work_handler() worker may dereference a freed TLS object. The following is a simple race scenario: cpu0 cpu1 tls_sk_proto_close() tls_sw_cancel_work_tx() tls_write_space() tls_sw_write_space() if (!test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask)) set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask); cancel_delayed_work_sync(&ctx->tx_work.work); schedule_delayed_work(&tx_ctx->tx_work.work, 0); To prevent this race condition, cancel_delayed_work_sync() is replaced with disable_delayed_work_sync().

Опубликовано: 2026-03-10Изменено: 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
CVE-2026-23242
HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: RDMA/siw: Fix potential NULL pointer dereference in header processing If siw_get_hdr() returns -EINVAL before set_rx_fpdu_context(), qp->rx_fpdu can be NULL. The error path in siw_tcp_rx_data() dereferences qp->rx_fpdu->more_ddp_segs without checking, which may lead to a NULL pointer deref. Only check more_ddp_segs when rx_fpdu is present. KASAN splat: [ 101.384271] KASAN: null-ptr-deref in range [0x00000000000000c0-0x00000000000000c7] [ 101.385869] RIP: 0010:siw_tcp_rx_data+0x13ad/0x1e50

Опубликовано: 2026-03-18Изменено: 2026-07-14
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
CVE-2026-23243
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: RDMA/umad: Reject negative data_len in ib_umad_write ib_umad_write computes data_len from user-controlled count and the MAD header sizes. With a mismatched user MAD header size and RMPP header length, data_len can become negative and reach ib_create_send_mad(). This can make the padding calculation exceed the segment size and trigger an out-of-bounds memset in alloc_send_rmpp_list(). Add an explicit check to reject negative data_len before creating the send buffer. KASAN splat: [ 211.363464] BUG: KASAN: slab-out-of-bounds in ib_create_send_mad+0xa01/0x11b0 [ 211.364077] Write of size 220 at addr ffff88800c3fa1f8 by task spray_thread/102 [ 211.365867] ib_create_send_mad+0xa01/0x11b0 [ 211.365887] ib_umad_write+0x853/0x1c80

Опубликовано: 2026-03-18Изменено: 2026-07-14
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
CVE-2026-23244
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: nvme: fix memory allocation in nvme_pr_read_keys() nvme_pr_read_keys() takes num_keys from userspace and uses it to calculate the allocation size for rse via struct_size(). The upper limit is PR_KEYS_MAX (64K). A malicious or buggy userspace can pass a large num_keys value that results in a 4MB allocation attempt at most, causing a warning in the page allocator when the order exceeds MAX_PAGE_ORDER. To fix this, use kvzalloc() instead of kzalloc(). This bug has the same reasoning and fix with the patch below: https://lore.kernel.org/linux-block/20251212013510.3576091-1-kartikey406@gmail.com/ Warning log: WARNING: mm/page_alloc.c:5216 at __alloc_frozen_pages_noprof+0x5aa/0x2300 mm/page_alloc.c:5216, CPU#1: syz-executor117/272 Modules linked in: CPU: 1 UID: 0 PID: 272 Comm: syz-executor117 Not tainted 6.19.0 #1 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 RIP: 0010:__alloc_frozen_pages_noprof+0x5aa/0x2300 mm/page_alloc.c:5216 Code: ff 83 bd a8 fe ff ff 0a 0f 86 69 fb ff ff 0f b6 1d f9 f9 c4 04 80 fb 01 0f 87 3b 76 30 ff 83 e3 01 75 09 c6 05 e4 f9 c4 04 01 <0f> 0b 48 c7 85 70 fe ff ff 00 00 00 00 e9 8f fd ff ff 31 c0 e9 0d RSP: 0018:ffffc90000fcf450 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 1ffff920001f9ea0 RDX: 0000000000000000 RSI: 000000000000000b RDI: 0000000000040dc0 RBP: ffffc90000fcf648 R08: ffff88800b6c3380 R09: 0000000000000001 R10: ffffc90000fcf840 R11: ffff88807ffad280 R12: 0000000000000000 R13: 0000000000040dc0 R14: 0000000000000001 R15: ffffc90000fcf620 FS: 0000555565db33c0(0000) GS:ffff8880be26c000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000002000000c CR3: 0000000003b72000 CR4: 00000000000006f0 Call Trace: alloc_pages_mpol+0x236/0x4d0 mm/mempolicy.c:2486 alloc_frozen_pages_noprof+0x149/0x180 mm/mempolicy.c:2557 ___kmalloc_large_node+0x10c/0x140 mm/slub.c:5598 __kmalloc_large_node_noprof+0x25/0xc0 mm/slub.c:5629 __do_kmalloc_node mm/slub.c:5645 [inline] __kmalloc_noprof+0x483/0x6f0 mm/slub.c:5669 kmalloc_noprof include/linux/slab.h:961 [inline] kzalloc_noprof include/linux/slab.h:1094 [inline] nvme_pr_read_keys+0x8f/0x4c0 drivers/nvme/host/pr.c:245 blkdev_pr_read_keys block/ioctl.c:456 [inline] blkdev_common_ioctl+0x1b71/0x29b0 block/ioctl.c:730 blkdev_ioctl+0x299/0x700 block/ioctl.c:786 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+0x1bf/0x220 fs/ioctl.c:583 x64_sys_call+0x1280/0x21b0 mnt/fuzznvme_1/fuzznvme/linux-build/v6.19/./arch/x86/include/generated/asm/syscalls_64.h:17 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x71/0x330 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7fb893d3108d Code: 28 c3 e8 46 1e 00 00 66 0f 1f 44 00 00 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 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffff61f2f38 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007ffff61f3138 RCX: 00007fb893d3108d RDX: 0000000020000040 RSI: 00000000c01070ce RDI: 0000000000000003 RBP: 0000000000000001 R08: 0000000000000000 R09: 00007ffff61f3138 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000001 R13: 00007ffff61f3128 R14: 00007fb893dae530 R15: 0000000000000001

Опубликовано: 2026-03-18Изменено: 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
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: 2026-07-14
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
CVE-2026-23246
HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: bounds-check link_id in ieee80211_ml_reconfiguration link_id is taken from the ML Reconfiguration element (control & 0x000f), so it can be 0..15. link_removal_timeout[] has IEEE80211_MLD_MAX_NUM_LINKS (15) elements, so index 15 is out-of-bounds. Skip subelements with link_id >= IEEE80211_MLD_MAX_NUM_LINKS to avoid a stack out-of-bounds write.

Опубликовано: 2026-03-18Изменено: 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
CVE-2026-23249
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xfs: check for deleted cursors when revalidating two btrees The free space and inode btree repair functions will rebuild both btrees at the same time, after which it needs to evaluate both btrees to confirm that the corruptions are gone. However, Jiaming Zhang ran syzbot and produced a crash in the second xchk_allocbt call. His root-cause analysis is as follows (with minor corrections): In xrep_revalidate_allocbt(), xchk_allocbt() is called twice (first for BNOBT, second for CNTBT). The cause of this issue is that the first call nullified the cursor required by the second call. Let's first enter xrep_revalidate_allocbt() via following call chain: xfs_file_ioctl() -> xfs_ioc_scrubv_metadata() -> xfs_scrub_metadata() -> `sc->ops->repair_eval(sc)` -> xrep_revalidate_allocbt() xchk_allocbt() is called twice in this function. In the first call: /* Note that sc->sm->sm_type is XFS_SCRUB_TYPE_BNOPT now */ xchk_allocbt() -> xchk_btree() -> `bs->scrub_rec(bs, recp)` -> xchk_allocbt_rec() -> xchk_allocbt_xref() -> xchk_allocbt_xref_other() since sm_type is XFS_SCRUB_TYPE_BNOBT, pur is set to &sc->sa.cnt_cur. Kernel called xfs_alloc_get_rec() and returned -EFSCORRUPTED. Call chain: xfs_alloc_get_rec() -> xfs_btree_get_rec() -> xfs_btree_check_block() -> (XFS_IS_CORRUPT || XFS_TEST_ERROR), the former is false and the latter is true, return -EFSCORRUPTED. This should be caused by ioctl$XFS_IOC_ERROR_INJECTION I guess. Back to xchk_allocbt_xref_other(), after receiving -EFSCORRUPTED from xfs_alloc_get_rec(), kernel called xchk_should_check_xref(). In this function, *curpp (points to sc->sa.cnt_cur) is nullified. Back to xrep_revalidate_allocbt(), since sc->sa.cnt_cur has been nullified, it then triggered null-ptr-deref via xchk_allocbt() (second call) -> xchk_btree(). So. The bnobt revalidation failed on a cross-reference attempt, so we deleted the cntbt cursor, and then crashed when we tried to revalidate the cntbt. Therefore, check for a null cntbt cursor before that revalidation, and mark the repair incomplete. Also we can ignore the second tree entirely if the first tree was rebuilt but is already corrupt. Apply the same fix to xrep_revalidate_iallocbt because it has the same problem.

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
CVE-2026-23250
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xfs: check return value of xchk_scrub_create_subord Fix this function to return NULL instead of a mangled ENOMEM, then fix the callers to actually check for a null pointer and return ENOMEM. Most of the corrections here are for code merged between 6.2 and 6.10.

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
CVE-2026-23251
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: xfs: only call xf{array,blob}_destroy if we have a valid pointer Only call the xfarray and xfblob destructor if we have a valid pointer, and be sure to null out that pointer afterwards. Note that this patch fixes a large number of commits, most of which were merged between 6.9 and 6.10.

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
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
CVE-2026-23253
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: media: dvb-core: fix wrong reinitialization of ringbuffer on reopen dvb_dvr_open() calls dvb_ringbuffer_init() when a new reader opens the DVR device. dvb_ringbuffer_init() calls init_waitqueue_head(), which reinitializes the waitqueue list head to empty. Since dmxdev->dvr_buffer.queue is a shared waitqueue (all opens of the same DVR device share it), this orphans any existing waitqueue entries from io_uring poll or epoll, leaving them with stale prev/next pointers while the list head is reset to {self, self}. The waitqueue and spinlock in dvr_buffer are already properly initialized once in dvb_dmxdev_init(). The open path only needs to reset the buffer data pointer, size, and read/write positions. Replace the dvb_ringbuffer_init() call in dvb_dvr_open() with direct assignment of data/size and a call to dvb_ringbuffer_reset(), which properly resets pread, pwrite, and error with correct memory ordering without touching the waitqueue or spinlock.

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
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
CVE-2026-23268
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: apparmor: fix unprivileged local user can do privileged policy management An unprivileged local user can load, replace, and remove profiles by opening the apparmorfs interfaces, via a confused deputy attack, by passing the opened fd to a privileged process, and getting the privileged process to write to the interface. This does require a privileged target that can be manipulated to do the write for the unprivileged process, but once such access is achieved full policy management is possible and all the possible implications that implies: removing confinement, DoS of system or target applications by denying all execution, by-passing the unprivileged user namespace restriction, to exploiting kernel bugs for a local privilege escalation. The policy management interface can not have its permissions simply changed from 0666 to 0600 because non-root processes need to be able to load policy to different policy namespaces. Instead ensure the task writing the interface has privileges that are a subset of the task that opened the interface. This is already done via policy for confined processes, but unconfined can delegate access to the opened fd, by-passing the usual policy check.

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
CVE-2026-23269
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: apparmor: validate DFA start states are in bounds in unpack_pdb Start states are read from untrusted data and used as indexes into the DFA state tables. The aa_dfa_next() function call in unpack_pdb() will access dfa->tables[YYTD_ID_BASE][start], and if the start state exceeds the number of states in the DFA, this results in an out-of-bound read. ================================================================== BUG: KASAN: slab-out-of-bounds in aa_dfa_next+0x2a1/0x360 Read of size 4 at addr ffff88811956fb90 by task su/1097 ... Reject policies with out-of-bounds start states during unpacking to prevent the issue.

Опубликовано: 2026-03-18Изменено: 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
CVE-2026-23270
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net/sched: Only allow act_ct to bind to clsact/ingress qdiscs and shared blocks As Paolo said earlier [1]: "Since the blamed commit below, classify can return TC_ACT_CONSUMED while the current skb being held by the defragmentation engine. As reported by GangMin Kim, if such packet is that may cause a UaF when the defrag engine later on tries to tuch again such packet." act_ct was never meant to be used in the egress path, however some users are attaching it to egress today [2]. Attempting to reach a middle ground, we noticed that, while most qdiscs are not handling TC_ACT_CONSUMED, clsact/ingress qdiscs are. With that in mind, we address the issue by only allowing act_ct to bind to clsact/ingress qdiscs and shared blocks. That way it's still possible to attach act_ct to egress (albeit only with clsact). [1] https://lore.kernel.org/netdev/674b8cbfc385c6f37fb29a1de08d8fe5c2b0fbee.1771321118.git.pabeni@redhat.com/ [2] https://lore.kernel.org/netdev/cc6bfb4a-4a2b-42d8-b9ce-7ef6644fb22b@ovn.org/

Опубликовано: 2026-03-18Изменено: 2026-07-14
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
CVE-2026-23271
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: perf: Fix __perf_event_overflow() vs perf_remove_from_context() race Make sure that __perf_event_overflow() runs with IRQs disabled for all possible callchains. Specifically the software events can end up running it with only preemption disabled. This opens up a race vs perf_event_exit_event() and friends that will go and free various things the overflow path expects to be present, like the BPF program.

Опубликовано: 2026-03-20Изменено: 2026-07-14
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
CVE-2026-23273
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: macvlan: observe an RCU grace period in macvlan_common_newlink() error path valis reported that a race condition still happens after my prior patch. macvlan_common_newlink() might have made @dev visible before detecting an error, and its caller will directly call free_netdev(dev). We must respect an RCU period, either in macvlan or the core networking stack. After adding a temporary mdelay(1000) in macvlan_forward_source_one() to open the race window, valis repro was: ip link add p1 type veth peer p2 ip link set address 00:00:00:00:00:20 dev p1 ip link set up dev p1 ip link set up dev p2 ip link add mv0 link p2 type macvlan mode source (ip link add invalid% link p2 type macvlan mode source macaddr add 00:00:00:00:00:20 &) ; sleep 0.5 ; ping -c1 -I p1 1.2.3.4 PING 1.2.3.4 (1.2.3.4): 56 data bytes RTNETLINK answers: Invalid argument BUG: KASAN: slab-use-after-free in macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) Read of size 8 at addr ffff888016bb89c0 by task e/175 CPU: 1 UID: 1000 PID: 175 Comm: e Not tainted 6.19.0-rc8+ #33 NONE Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 Call Trace: dump_stack_lvl (lib/dump_stack.c:123) print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) ? macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) kasan_report (mm/kasan/report.c:597) ? macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) ? tasklet_init (kernel/softirq.c:983) macvlan_handle_frame (drivers/net/macvlan.c:501) Allocated by task 169: kasan_save_stack (mm/kasan/common.c:58) kasan_save_track (./arch/x86/include/asm/current.h:25 mm/kasan/common.c:70 mm/kasan/common.c:79) __kasan_kmalloc (mm/kasan/common.c:419) __kvmalloc_node_noprof (./include/linux/kasan.h:263 mm/slub.c:5657 mm/slub.c:7140) alloc_netdev_mqs (net/core/dev.c:12012) rtnl_create_link (net/core/rtnetlink.c:3648) rtnl_newlink (net/core/rtnetlink.c:3830 net/core/rtnetlink.c:3957 net/core/rtnetlink.c:4072) rtnetlink_rcv_msg (net/core/rtnetlink.c:6958) 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_sendto (net/socket.c:727 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:131) Freed by task 169: kasan_save_stack (mm/kasan/common.c:58) kasan_save_track (./arch/x86/include/asm/current.h:25 mm/kasan/common.c:70 mm/kasan/common.c:79) kasan_save_free_info (mm/kasan/generic.c:587) __kasan_slab_free (mm/kasan/common.c:287) kfree (mm/slub.c:6674 mm/slub.c:6882) rtnl_newlink (net/core/rtnetlink.c:3845 net/core/rtnetlink.c:3957 net/core/rtnetlink.c:4072) rtnetlink_rcv_msg (net/core/rtnetlink.c:6958) 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_sendto (net/socket.c:727 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:131)

Опубликовано: 2026-03-20Изменено: 2026-07-14
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
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: 2026-07-14
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
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
CVE-2026-23279
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: fix NULL pointer dereference in mesh_rx_csa_frame() In mesh_rx_csa_frame(), elems->mesh_chansw_params_ie is dereferenced at lines 1638 and 1642 without a prior NULL check: ifmsh->chsw_ttl = elems->mesh_chansw_params_ie->mesh_ttl; ... pre_value = le16_to_cpu(elems->mesh_chansw_params_ie->mesh_pre_value); The mesh_matches_local() check above only validates the Mesh ID, Mesh Configuration, and Supported Rates IEs. It does not verify the presence of the Mesh Channel Switch Parameters IE (element ID 118). When a received CSA action frame omits that IE, ieee802_11_parse_elems() leaves elems->mesh_chansw_params_ie as NULL, and the unconditional dereference causes a kernel NULL pointer dereference. A remote mesh peer with an established peer link (PLINK_ESTAB) can trigger this by sending a crafted SPECTRUM_MGMT/CHL_SWITCH action frame that includes a matching Mesh ID and Mesh Configuration IE but omits the Mesh Channel Switch Parameters IE. No authentication beyond the default open mesh peering is required. Crash confirmed on kernel 6.17.0-5-generic via mac80211_hwsim: BUG: kernel NULL pointer dereference, address: 0000000000000000 Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:ieee80211_mesh_rx_queued_mgmt+0x143/0x2a0 [mac80211] CR2: 0000000000000000 Fix by adding a NULL check for mesh_chansw_params_ie after mesh_matches_local() returns, consistent with how other optional IEs are guarded throughout the mesh code. The bug has been present since v3.13 (released 2014-01-19).

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
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
CVE-2026-23284
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: ethernet: mtk_eth_soc: Reset prog ptr to old_prog in case of error in mtk_xdp_setup() Reset eBPF program pointer to old_prog and do not decrease its ref-count if mtk_open routine in mtk_xdp_setup() fails.

Опубликовано: 2026-03-25Изменено: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2026-23285
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drbd: fix null-pointer dereference on local read error In drbd_request_endio(), READ_COMPLETED_WITH_ERROR is passed to __req_mod() with a NULL peer_device: __req_mod(req, what, NULL, &m); The READ_COMPLETED_WITH_ERROR handler then unconditionally passes this NULL peer_device to drbd_set_out_of_sync(), which dereferences it, causing a null-pointer dereference. Fix this by obtaining the peer_device via first_peer_device(device), matching how drbd_req_destroy() handles the same situation.

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
CVE-2026-23286
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: atm: lec: fix null-ptr-deref in lec_arp_clear_vccs syzkaller reported a null-ptr-deref in lec_arp_clear_vccs(). This issue can be easily reproduced using the syzkaller reproducer. In the ATM LANE (LAN Emulation) module, the same atm_vcc can be shared by multiple lec_arp_table entries (e.g., via entry->vcc or entry->recv_vcc). When the underlying VCC is closed, lec_vcc_close() iterates over all ARP entries and calls lec_arp_clear_vccs() for each matched entry. For example, when lec_vcc_close() iterates through the hlists in priv->lec_arp_empty_ones or other ARP tables: 1. In the first iteration, for the first matched ARP entry sharing the VCC, lec_arp_clear_vccs() frees the associated vpriv (which is vcc->user_back) and sets vcc->user_back to NULL. 2. In the second iteration, for the next matched ARP entry sharing the same VCC, lec_arp_clear_vccs() is called again. It obtains a NULL vpriv from vcc->user_back (via LEC_VCC_PRIV(vcc)) and then attempts to dereference it via `vcc->pop = vpriv->old_pop`, leading to a null-ptr-deref crash. Fix this by adding a null check for vpriv before dereferencing it. If vpriv is already NULL, it means the VCC has been cleared by a previous call, so we can safely skip the cleanup and just clear the entry's vcc/recv_vcc pointers. The entire cleanup block (including vcc_release_async()) is placed inside the vpriv guard because a NULL vpriv indicates the VCC has already been fully released by a prior iteration — repeating the teardown would redundantly set flags and trigger callbacks on an already-closing socket. The Fixes tag points to the initial commit because the entry->vcc path has been vulnerable since the original code. The entry->recv_vcc path was later added by commit 8d9f73c0ad2f ("atm: fix a memory leak of vcc->user_back") with the same pattern, and both paths are fixed here.

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
CVE-2026-23287
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: irqchip/sifive-plic: Fix frozen interrupt due to affinity setting PLIC ignores interrupt completion message for disabled interrupt, explained by the specification: The PLIC signals it has completed executing an interrupt handler by writing the interrupt ID it received from the claim to the claim/complete register. The PLIC does not check whether the completion ID is the same as the last claim ID for that target. If the completion ID does not match an interrupt source that is currently enabled for the target, the completion is silently ignored. This caused problems in the past, because an interrupt can be disabled while still being handled and plic_irq_eoi() had no effect. That was fixed by checking if the interrupt is disabled, and if so enable it, before sending the completion message. That check is done with irqd_irq_disabled(). However, that is not sufficient because the enable bit for the handling hart can be zero despite irqd_irq_disabled(d) being false. This can happen when affinity setting is changed while a hart is still handling the interrupt. This problem is easily reproducible by dumping a large file to uart (which generates lots of interrupts) and at the same time keep changing the uart interrupt's affinity setting. The uart port becomes frozen almost instantaneously. Fix this by checking PLIC's enable bit instead of irqd_irq_disabled().

Опубликовано: 2026-03-25Изменено: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2026-23290
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: usb: pegasus: validate USB endpoints The pegasus driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.

Опубликовано: 2026-03-25Изменено: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2026-23291
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: nfc: pn533: properly drop the usb interface reference on disconnect When the device is disconnected from the driver, there is a "dangling" reference count on the usb interface that was grabbed in the probe callback. Fix this up by properly dropping the reference after we are done with it.

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
CVE-2026-23292
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: scsi: target: Fix recursive locking in __configfs_open_file() In flush_write_buffer, &p->frag_sem is acquired and then the loaded store function is called, which, here, is target_core_item_dbroot_store(). This function called filp_open(), following which these functions were called (in reverse order), according to the call trace: down_read __configfs_open_file do_dentry_open vfs_open do_open path_openat do_filp_open file_open_name filp_open target_core_item_dbroot_store flush_write_buffer configfs_write_iter target_core_item_dbroot_store() tries to validate the new file path by trying to open the file path provided to it; however, in this case, the bug report shows: db_root: not a directory: /sys/kernel/config/target/dbroot indicating that the same configfs file was tried to be opened, on which it is currently working on. Thus, it is trying to acquire frag_sem semaphore of the same file of which it already holds the semaphore obtained in flush_write_buffer(), leading to acquiring the semaphore in a nested manner and a possibility of recursive locking. Fix this by modifying target_core_item_dbroot_store() to use kern_path() instead of filp_open() to avoid opening the file using filesystem-specific function __configfs_open_file(), and further modifying it to make this fix compatible.

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
CVE-2026-23293
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: vxlan: 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 an IPv6 packet is injected into the interface, route_shortcircuit() is called and a NULL pointer dereference happens on neigh_lookup(). BUG: kernel NULL pointer dereference, address: 0000000000000380 Oops: Oops: 0000 [#1] SMP NOPTI [...] RIP: 0010:neigh_lookup+0x20/0x270 [...] Call Trace: vxlan_xmit+0x638/0x1ef0 [vxlan] dev_hard_start_xmit+0x9e/0x2e0 __dev_queue_xmit+0xbee/0x14e0 packet_sendmsg+0x116f/0x1930 __sys_sendto+0x1f5/0x200 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x12f/0x1590 entry_SYSCALL_64_after_hwframe+0x76/0x7e Fix this by adding an early check on route_shortcircuit() when protocol is ETH_P_IPV6. Note that ipv6_mod_enabled() cannot be used here because VXLAN can be built-in even when IPv6 is built as a module.

Опубликовано: 2026-03-25Изменено: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2026-23296
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: scsi: core: Fix refcount leak for tagset_refcnt This leak will cause a hang when tearing down the SCSI host. For example, iscsid hangs with the following call trace: [130120.652718] scsi_alloc_sdev: Allocation failure during SCSI scanning, some SCSI devices might not be configured PID: 2528 TASK: ffff9d0408974e00 CPU: 3 COMMAND: "iscsid" #0 [ffffb5b9c134b9e0] __schedule at ffffffff860657d4 #1 [ffffb5b9c134ba28] schedule at ffffffff86065c6f #2 [ffffb5b9c134ba40] schedule_timeout at ffffffff86069fb0 #3 [ffffb5b9c134bab0] __wait_for_common at ffffffff8606674f #4 [ffffb5b9c134bb10] scsi_remove_host at ffffffff85bfe84b #5 [ffffb5b9c134bb30] iscsi_sw_tcp_session_destroy at ffffffffc03031c4 [iscsi_tcp] #6 [ffffb5b9c134bb48] iscsi_if_recv_msg at ffffffffc0292692 [scsi_transport_iscsi] #7 [ffffb5b9c134bb98] iscsi_if_rx at ffffffffc02929c2 [scsi_transport_iscsi] #8 [ffffb5b9c134bbf0] netlink_unicast at ffffffff85e551d6 #9 [ffffb5b9c134bc38] netlink_sendmsg at ffffffff85e554ef

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
CVE-2026-23297
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: nfsd: Fix cred ref leak in nfsd_nl_threads_set_doit(). syzbot reported memory leak of struct cred. [0] nfsd_nl_threads_set_doit() passes get_current_cred() to nfsd_svc(), but put_cred() is not called after that. The cred is finally passed down to _svc_xprt_create(), which calls get_cred() with the cred for struct svc_xprt. The ownership of the refcount by get_current_cred() is not transferred to anywhere and is just leaked. nfsd_svc() is also called from write_threads(), but it does not bump file->f_cred there. nfsd_nl_threads_set_doit() is called from sendmsg() and current->cred does not go away. Let's use current_cred() in nfsd_nl_threads_set_doit(). [0]: BUG: memory leak unreferenced object 0xffff888108b89480 (size 184): comm "syz-executor", pid 5994, jiffies 4294943386 hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace (crc 369454a7): kmemleak_alloc_recursive include/linux/kmemleak.h:44 [inline] slab_post_alloc_hook mm/slub.c:4958 [inline] slab_alloc_node mm/slub.c:5263 [inline] kmem_cache_alloc_noprof+0x412/0x580 mm/slub.c:5270 prepare_creds+0x22/0x600 kernel/cred.c:185 copy_creds+0x44/0x290 kernel/cred.c:286 copy_process+0x7a7/0x2870 kernel/fork.c:2086 kernel_clone+0xac/0x6e0 kernel/fork.c:2651 __do_sys_clone+0x7f/0xb0 kernel/fork.c:2792 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xa4/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f

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
CVE-2026-23298
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: can: ucan: Fix infinite loop from zero-length messages If a broken ucan device gets a message with the message length field set to 0, then the driver will loop for forever in ucan_read_bulk_callback(), hanging the system. If the length is 0, just skip the message and go on to the next one. This has been fixed in the kvaser_usb driver in the past in commit 0c73772cd2b8 ("can: kvaser_usb: leaf: Fix potential infinite loop in command parsers"), so there must be some broken devices out there like this somewhere.

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
CVE-2026-23300
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: ipv6: fix panic when IPv4 route references loopback IPv6 nexthop When a standalone IPv6 nexthop object is created with a loopback device (e.g., "ip -6 nexthop add id 100 dev lo"), fib6_nh_init() misclassifies it as a reject route. This is because nexthop objects have no destination prefix (fc_dst=::), causing fib6_is_reject() to match any loopback nexthop. The reject path skips fib_nh_common_init(), leaving nhc_pcpu_rth_output unallocated. If an IPv4 route later references this nexthop, __mkroute_output() dereferences NULL nhc_pcpu_rth_output and panics. Simplify the check in fib6_nh_init() to only match explicit reject routes (RTF_REJECT) instead of using fib6_is_reject(). The loopback promotion heuristic in fib6_is_reject() is handled separately by ip6_route_info_create_nh(). After this change, the three cases behave as follows: 1. Explicit reject route ("ip -6 route add unreachable 2001:db8::/64"): RTF_REJECT is set, enters reject path, skips fib_nh_common_init(). No behavior change. 2. Implicit loopback reject route ("ip -6 route add 2001:db8::/32 dev lo"): RTF_REJECT is not set, takes normal path, fib_nh_common_init() is called. ip6_route_info_create_nh() still promotes it to reject afterward. nhc_pcpu_rth_output is allocated but unused, which is harmless. 3. Standalone nexthop object ("ip -6 nexthop add id 100 dev lo"): RTF_REJECT is not set, takes normal path, fib_nh_common_init() is called. nhc_pcpu_rth_output is properly allocated, fixing the crash when IPv4 routes reference this nexthop.

Опубликовано: 2026-03-25Изменено: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
CVE-2026-23303
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: smb: client: Don't log plaintext credentials in cifs_set_cifscreds When debug logging is enabled, cifs_set_cifscreds() logs the key payload and exposes the plaintext username and password. Remove the debug log to avoid exposing credentials.

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
CVE-2026-23304
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ipv6: fix NULL pointer deref in ip6_rt_get_dev_rcu() l3mdev_master_dev_rcu() can return NULL when the slave device is being un-slaved from a VRF. All other callers deal with this, but we lost the fallback to loopback in ip6_rt_pcpu_alloc() -> ip6_rt_get_dev_rcu() with commit 4832c30d5458 ("net: ipv6: put host and anycast routes on device with address"). KASAN: null-ptr-deref in range [0x0000000000000108-0x000000000000010f] RIP: 0010:ip6_rt_pcpu_alloc (net/ipv6/route.c:1418) Call Trace: ip6_pol_route (net/ipv6/route.c:2318) fib6_rule_lookup (net/ipv6/fib6_rules.c:115) ip6_route_output_flags (net/ipv6/route.c:2607) vrf_process_v6_outbound (drivers/net/vrf.c:437) I was tempted to rework the un-slaving code to clear the flag first and insert synchronize_rcu() before we remove the upper. But looks like the explicit fallback to loopback_dev is an established pattern. And I guess avoiding the synchronize_rcu() is nice, too.

Опубликовано: 2026-03-25Изменено: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2026-23306
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: scsi: pm8001: Fix use-after-free in pm8001_queue_command() Commit e29c47fe8946 ("scsi: pm8001: Simplify pm8001_task_exec()") refactors pm8001_queue_command(), however it introduces a potential cause of a double free scenario when it changes the function to return -ENODEV in case of phy down/device gone state. In this path, pm8001_queue_command() updates task status and calls task_done to indicate to upper layer that the task has been handled. However, this also frees the underlying SAS task. A -ENODEV is then returned to the caller. When libsas sas_ata_qc_issue() receives this error value, it assumes the task wasn't handled/queued by LLDD and proceeds to clean up and free the task again, resulting in a double free. Since pm8001_queue_command() handles the SAS task in this case, it should return 0 to the caller indicating that the task has been handled.

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
CVE-2026-23307
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: can: ems_usb: ems_usb_read_bulk_callback(): check the proper length of a message When looking at the data in a USB urb, the actual_length is the size of the buffer passed to the driver, not the transfer_buffer_length which is set by the driver as the max size of the buffer. When parsing the messages in ems_usb_read_bulk_callback() properly check the size both at the beginning of parsing the message to make sure it is big enough for the expected structure, and at the end of the message to make sure we don't overflow past the end of the buffer for the next message.

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
CVE-2026-23308
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: pinctrl: equilibrium: fix warning trace on load The callback functions 'eqbr_irq_mask()' and 'eqbr_irq_ack()' are also called in the callback function 'eqbr_irq_mask_ack()'. This is done to avoid source code duplication. The problem, is that in the function 'eqbr_irq_mask()' also calles the gpiolib function 'gpiochip_disable_irq()' This generates the following warning trace in the log for every gpio on load. [ 6.088111] ------------[ cut here ]------------ [ 6.092440] WARNING: CPU: 3 PID: 1 at drivers/gpio/gpiolib.c:3810 gpiochip_disable_irq+0x39/0x50 [ 6.097847] Modules linked in: [ 6.097847] CPU: 3 UID: 0 PID: 1 Comm: swapper/0 Tainted: G W 6.12.59+ #0 [ 6.097847] Tainted: [W]=WARN [ 6.097847] RIP: 0010:gpiochip_disable_irq+0x39/0x50 [ 6.097847] Code: 39 c6 48 19 c0 21 c6 48 c1 e6 05 48 03 b2 38 03 00 00 48 81 fe 00 f0 ff ff 77 11 48 8b 46 08 f6 c4 02 74 06 f0 80 66 09 fb c3 <0f> 0b 90 0f 1f 40 00 c3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 [ 6.097847] RSP: 0000:ffffc9000000b830 EFLAGS: 00010046 [ 6.097847] RAX: 0000000000000045 RBX: ffff888001be02a0 RCX: 0000000000000008 [ 6.097847] RDX: ffff888001be9000 RSI: ffff888001b2dd00 RDI: ffff888001be02a0 [ 6.097847] RBP: ffffc9000000b860 R08: 0000000000000000 R09: 0000000000000000 [ 6.097847] R10: 0000000000000001 R11: ffff888001b2a154 R12: ffff888001be0514 [ 6.097847] R13: ffff888001be02a0 R14: 0000000000000008 R15: 0000000000000000 [ 6.097847] FS: 0000000000000000(0000) GS:ffff888041d80000(0000) knlGS:0000000000000000 [ 6.097847] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6.097847] CR2: 0000000000000000 CR3: 0000000003030000 CR4: 00000000001026b0 [ 6.097847] Call Trace: [ 6.097847] [ 6.097847] ? eqbr_irq_mask+0x63/0x70 [ 6.097847] ? no_action+0x10/0x10 [ 6.097847] eqbr_irq_mask_ack+0x11/0x60 In an other driver (drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c) the interrupt is not disabled here. To fix this, do not call the 'eqbr_irq_mask()' and 'eqbr_irq_ack()' function. Implement instead this directly without disabling the interrupts.

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
CVE-2026-23310
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: bpf/bonding: reject vlan+srcmac xmit_hash_policy change when XDP is loaded bond_option_mode_set() already rejects mode changes that would make a loaded XDP program incompatible via bond_xdp_check(). However, bond_option_xmit_hash_policy_set() has no such guard. For 802.3ad and balance-xor modes, bond_xdp_check() returns false when xmit_hash_policy is vlan+srcmac, because the 802.1q payload is usually absent due to hardware offload. This means a user can: 1. Attach a native XDP program to a bond in 802.3ad/balance-xor mode with a compatible xmit_hash_policy (e.g. layer2+3). 2. Change xmit_hash_policy to vlan+srcmac while XDP remains loaded. This leaves bond->xdp_prog set but bond_xdp_check() now returning false for the same device. When the bond is later destroyed, dev_xdp_uninstall() calls bond_xdp_set(dev, NULL, NULL) to remove the program, which hits the bond_xdp_check() guard and returns -EOPNOTSUPP, triggering: WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)) Fix this by rejecting xmit_hash_policy changes to vlan+srcmac when an XDP program is loaded on a bond in 802.3ad or balance-xor mode. commit 39a0876d595b ("net, bonding: Disallow vlan+srcmac with XDP") introduced bond_xdp_check() which returns false for 802.3ad/balance-xor modes when xmit_hash_policy is vlan+srcmac. The check was wired into bond_xdp_set() to reject XDP attachment with an incompatible policy, but the symmetric path -- preventing xmit_hash_policy from being changed to an incompatible value after XDP is already loaded -- was left unguarded in bond_option_xmit_hash_policy_set(). Note: commit 094ee6017ea0 ("bonding: check xdp prog when set bond mode") later added a similar guard to bond_option_mode_set(), but bond_option_xmit_hash_policy_set() remained unprotected.

Опубликовано: 2026-03-25Изменено: 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
CVE-2026-23312
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: usb: kaweth: validate USB endpoints The kaweth driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.

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
CVE-2026-23313
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: i40e: Fix preempt count leak in napi poll tracepoint Using get_cpu() in the tracepoint assignment causes an obvious preempt count leak because nothing invokes put_cpu() to undo it: softirq: huh, entered softirq 3 NET_RX with preempt_count 00000100, exited with 00000101? This clearly has seen a lot of testing in the last 3+ years... Use smp_processor_id() instead.

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
CVE-2026-23315
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: Fix possible oob access in mt76_connac2_mac_write_txwi_80211() Check frame length before accessing the mgmt fields in mt76_connac2_mac_write_txwi_80211 in order to avoid a possible oob access. [fix check to also cover mgmt->u.action.u.addba_req.capab, correct Fixes tag]

Опубликовано: 2026-03-25Изменено: 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
CVE-2026-23316
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: ipv4: fix ARM64 alignment fault in multipath hash seed `struct sysctl_fib_multipath_hash_seed` contains two u32 fields (user_seed and mp_seed), making it an 8-byte structure with a 4-byte alignment requirement. In `fib_multipath_hash_from_keys()`, the code evaluates the entire struct atomically via `READ_ONCE()`: mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed; While this silently works on GCC by falling back to unaligned regular loads which the ARM64 kernel tolerates, it causes a fatal kernel panic when compiled with Clang and LTO enabled. Commit e35123d83ee3 ("arm64: lto: Strengthen READ_ONCE() to acquire when CONFIG_LTO=y") strengthens `READ_ONCE()` to use Load-Acquire instructions (`ldar` / `ldapr`) to prevent compiler reordering bugs under Clang LTO. Since the macro evaluates the full 8-byte struct, Clang emits a 64-bit `ldar` instruction. ARM64 architecture strictly requires `ldar` to be naturally aligned, thus executing it on a 4-byte aligned address triggers a strict Alignment Fault (FSC = 0x21). Fix the read side by moving the `READ_ONCE()` directly to the `u32` member, which emits a safe 32-bit `ldar Wn`. Furthermore, Eric Dumazet pointed out that `WRITE_ONCE()` on the entire struct in `proc_fib_multipath_hash_set_seed()` is also flawed. Analysis shows that Clang splits this 8-byte write into two separate 32-bit `str` instructions. While this avoids an alignment fault, it destroys atomicity and exposes a tear-write vulnerability. Fix this by explicitly splitting the write into two 32-bit `WRITE_ONCE()` operations. Finally, add the missing `READ_ONCE()` when reading `user_seed` in `proc_fib_multipath_hash_seed()` to ensure proper pairing and concurrency safety.

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
CVE-2026-23317
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: drm/vmwgfx: Return the correct value in vmw_translate_ptr functions Before the referenced fixes these functions used a lookup function that returned a pointer. This was changed to another lookup function that returned an error code with the pointer becoming an out parameter. The error path when the lookup failed was not changed to reflect this change and the code continued to return the PTR_ERR of the now uninitialized pointer. This could cause the vmw_translate_ptr functions to return success when they actually failed causing further uninitialized and OOB accesses.

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
CVE-2026-23318
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: ALSA: usb-audio: Use correct version for UAC3 header validation The entry of the validators table for UAC3 AC header descriptor is defined with the wrong protocol version UAC_VERSION_2, while it should have been UAC_VERSION_3. This results in the validator never matching for actual UAC3 devices (protocol == UAC_VERSION_3), causing their header descriptors to bypass validation entirely. A malicious USB device presenting a truncated UAC3 header could exploit this to cause out-of-bounds reads when the driver later accesses unvalidated descriptor fields. The bug was introduced in the same commit as the recently fixed UAC3 feature unit sub-type typo, and appears to be from the same copy-paste error when the UAC3 section was created from the UAC2 section.

Опубликовано: 2026-03-25Изменено: 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
CVE-2026-23319
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix a UAF issue in bpf_trampoline_link_cgroup_shim The root cause of this bug is that when 'bpf_link_put' reduces the refcount of 'shim_link->link.link' to zero, the resource is considered released but may still be referenced via 'tr->progs_hlist' in 'cgroup_shim_find'. The actual cleanup of 'tr->progs_hlist' in 'bpf_shim_tramp_link_release' is deferred. During this window, another process can cause a use-after-free via 'bpf_trampoline_link_cgroup_shim'. Based on Martin KaFai Lau's suggestions, I have created a simple patch. To fix this: Add an atomic non-zero check in 'bpf_trampoline_link_cgroup_shim'. Only increment the refcount if it is not already zero. Testing: I verified the fix by adding a delay in 'bpf_shim_tramp_link_release' to make the bug easier to trigger: static void bpf_shim_tramp_link_release(struct bpf_link *link) { /* ... */ if (!shim_link->trampoline) return; + msleep(100); WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline, NULL)); bpf_trampoline_put(shim_link->trampoline); } Before the patch, running a PoC easily reproduced the crash(almost 100%) with a call trace similar to KaiyanM's report. After the patch, the bug no longer occurs even after millions of iterations.

Опубликовано: 2026-03-25Изменено: 2026-07-14
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2026-23324
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: can: usb: etas_es58x: correctly anchor the urb in the read bulk callback When submitting an urb, that is using the anchor pattern, it needs to be anchored before submitting it otherwise it could be leaked if usb_kill_anchored_urbs() is called. This logic is correctly done elsewhere in the driver, except in the read bulk callback so do that here also.

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
CVE-2026-23325
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: mt7996: Fix possible oob access in mt7996_mac_write_txwi_80211() Check frame length before accessing the mgmt fields in mt7996_mac_write_txwi_80211 in order to avoid a possible oob access.

Опубликовано: 2026-03-25Изменено: 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
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
CVE-2026-23334
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: can: usb: f81604: handle short interrupt urb messages properly If an interrupt urb is received that is not the correct length, properly detect it and don't attempt to treat the data as valid.

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
CVE-2026-23335
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: RDMA/irdma: Fix kernel stack leak in irdma_create_user_ah() struct irdma_create_ah_resp { // 8 bytes, no padding __u32 ah_id; // offset 0 - SET (uresp.ah_id = ah->sc_ah.ah_info.ah_idx) __u8 rsvd[4]; // offset 4 - NEVER SET <- LEAK }; rsvd[4]: 4 bytes of stack memory leaked unconditionally. Only ah_id is assigned before ib_respond_udata(). The reserved members of the structure were not zeroed.

Опубликовано: 2026-03-25Изменено: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2026-23336
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: wifi: cfg80211: cancel rfkill_block work in wiphy_unregister() There is a use-after-free error in cfg80211_shutdown_all_interfaces found by syzkaller: BUG: KASAN: use-after-free in cfg80211_shutdown_all_interfaces+0x213/0x220 Read of size 8 at addr ffff888112a78d98 by task kworker/0:5/5326 CPU: 0 UID: 0 PID: 5326 Comm: kworker/0:5 Not tainted 6.19.0-rc2 #2 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: events cfg80211_rfkill_block_work Call Trace: dump_stack_lvl+0x116/0x1f0 print_report+0xcd/0x630 kasan_report+0xe0/0x110 cfg80211_shutdown_all_interfaces+0x213/0x220 cfg80211_rfkill_block_work+0x1e/0x30 process_one_work+0x9cf/0x1b70 worker_thread+0x6c8/0xf10 kthread+0x3c5/0x780 ret_from_fork+0x56d/0x700 ret_from_fork_asm+0x1a/0x30 The problem arises due to the rfkill_block work is not cancelled when wiphy is being unregistered. In order to fix the issue cancel the corresponding work in wiphy_unregister(). Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

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
CVE-2026-23339
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: nfc: nci: free skb on nci_transceive early error paths nci_transceive() takes ownership of the skb passed by the caller, but the -EPROTO, -EINVAL, and -EBUSY error paths return without freeing it. Due to issues clearing NCI_DATA_EXCHANGE fixed by subsequent changes the nci/nci_dev selftest hits the error path occasionally in NIPA, and kmemleak detects leaks: unreferenced object 0xff11000015ce6a40 (size 640): comm "nci_dev", pid 3954, jiffies 4295441246 hex dump (first 32 bytes): 6b 6b 6b 6b 00 a4 00 0c 02 e1 03 6b 6b 6b 6b 6b kkkk.......kkkkk 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk backtrace (crc 7c40cc2a): kmem_cache_alloc_node_noprof+0x492/0x630 __alloc_skb+0x11e/0x5f0 alloc_skb_with_frags+0xc6/0x8f0 sock_alloc_send_pskb+0x326/0x3f0 nfc_alloc_send_skb+0x94/0x1d0 rawsock_sendmsg+0x162/0x4c0 do_syscall_64+0x117/0xfc0

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
CVE-2026-23340
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: sched: avoid qdisc_reset_all_tx_gt() vs dequeue race for lockless qdiscs When shrinking the number of real tx queues, netif_set_real_num_tx_queues() calls qdisc_reset_all_tx_gt() to flush qdiscs for queues which will no longer be used. qdisc_reset_all_tx_gt() currently serializes qdisc_reset() with qdisc_lock(). However, for lockless qdiscs, the dequeue path is serialized by qdisc_run_begin/end() using qdisc->seqlock instead, so qdisc_reset() can run concurrently with __qdisc_run() and free skbs while they are still being dequeued, leading to UAF. This can easily be reproduced on e.g. virtio-net by imposing heavy traffic while frequently changing the number of queue pairs: iperf3 -ub0 -c $peer -t 0 & while :; do ethtool -L eth0 combined 1 ethtool -L eth0 combined 2 done With KASAN enabled, this leads to reports like: BUG: KASAN: slab-use-after-free in __qdisc_run+0x133f/0x1760 ... Call Trace: ... __qdisc_run+0x133f/0x1760 __dev_queue_xmit+0x248f/0x3550 ip_finish_output2+0xa42/0x2110 ip_output+0x1a7/0x410 ip_send_skb+0x2e6/0x480 udp_send_skb+0xb0a/0x1590 udp_sendmsg+0x13c9/0x1fc0 ... Allocated by task 1270 on cpu 5 at 44.558414s: ... alloc_skb_with_frags+0x84/0x7c0 sock_alloc_send_pskb+0x69a/0x830 __ip_append_data+0x1b86/0x48c0 ip_make_skb+0x1e8/0x2b0 udp_sendmsg+0x13a6/0x1fc0 ... Freed by task 1306 on cpu 3 at 44.558445s: ... kmem_cache_free+0x117/0x5e0 pfifo_fast_reset+0x14d/0x580 qdisc_reset+0x9e/0x5f0 netif_set_real_num_tx_queues+0x303/0x840 virtnet_set_channels+0x1bf/0x260 [virtio_net] ethnl_set_channels+0x684/0xae0 ethnl_default_set_doit+0x31a/0x890 ... Serialize qdisc_reset_all_tx_gt() against the lockless dequeue path by taking qdisc->seqlock for TCQ_F_NOLOCK qdiscs, matching the serialization model already used by dev_reset_queue(). Additionally clear QDISC_STATE_NON_EMPTY after reset so the qdisc state reflects an empty queue, avoiding needless re-scheduling.

Опубликовано: 2026-03-25Изменено: 2026-07-14
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
CVE-2026-23343
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: xdp: produce a warning when calculated tailroom is negative Many ethernet drivers report xdp Rx queue frag size as being the same as DMA write size. However, the only user of this field, namely bpf_xdp_frags_increase_tail(), clearly expects a truesize. Such difference leads to unspecific memory corruption issues under certain circumstances, e.g. in ixgbevf maximum DMA write size is 3 KB, so when running xskxceiver's XDP_ADJUST_TAIL_GROW_MULTI_BUFF, 6K packet fully uses all DMA-writable space in 2 buffers. This would be fine, if only rxq->frag_size was properly set to 4K, but value of 3K results in a negative tailroom, because there is a non-zero page offset. We are supposed to return -EINVAL and be done with it in such case, but due to tailroom being stored as an unsigned int, it is reported to be somewhere near UINT_MAX, resulting in a tail being grown, even if the requested offset is too much (it is around 2K in the abovementioned test). This later leads to all kinds of unspecific calltraces. [ 7340.337579] xskxceiver[1440]: segfault at 1da718 ip 00007f4161aeac9d sp 00007f41615a6a00 error 6 [ 7340.338040] xskxceiver[1441]: segfault at 7f410000000b ip 00000000004042b5 sp 00007f415bffecf0 error 4 [ 7340.338179] in libc.so.6[61c9d,7f4161aaf000+160000] [ 7340.339230] in xskxceiver[42b5,400000+69000] [ 7340.340300] likely on CPU 6 (core 0, socket 6) [ 7340.340302] Code: ff ff 01 e9 f4 fe ff ff 0f 1f 44 00 00 4c 39 f0 74 73 31 c0 ba 01 00 00 00 f0 0f b1 17 0f 85 ba 00 00 00 49 8b 87 88 00 00 00 <4c> 89 70 08 eb cc 0f 1f 44 00 00 48 8d bd f0 fe ff ff 89 85 ec fe [ 7340.340888] likely on CPU 3 (core 0, socket 3) [ 7340.345088] Code: 00 00 00 ba 00 00 00 00 be 00 00 00 00 89 c7 e8 31 ca ff ff 89 45 ec 8b 45 ec 85 c0 78 07 b8 00 00 00 00 eb 46 e8 0b c8 ff ff <8b> 00 83 f8 69 74 24 e8 ff c7 ff ff 8b 00 83 f8 0b 74 18 e8 f3 c7 [ 7340.404334] Oops: general protection fault, probably for non-canonical address 0x6d255010bdffc: 0000 [#1] SMP NOPTI [ 7340.405972] CPU: 7 UID: 0 PID: 1439 Comm: xskxceiver Not tainted 6.19.0-rc1+ #21 PREEMPT(lazy) [ 7340.408006] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-5.fc42 04/01/2014 [ 7340.409716] RIP: 0010:lookup_swap_cgroup_id+0x44/0x80 [ 7340.410455] Code: 83 f8 1c 73 39 48 ba ff ff ff ff ff ff ff 03 48 8b 04 c5 20 55 fa bd 48 21 d1 48 89 ca 83 e1 01 48 d1 ea c1 e1 04 48 8d 04 90 <8b> 00 48 83 c4 10 d3 e8 c3 cc cc cc cc 31 c0 e9 98 b7 dd 00 48 89 [ 7340.412787] RSP: 0018:ffffcc5c04f7f6d0 EFLAGS: 00010202 [ 7340.413494] RAX: 0006d255010bdffc RBX: ffff891f477895a8 RCX: 0000000000000010 [ 7340.414431] RDX: 0001c17e3fffffff RSI: 00fa070000000000 RDI: 000382fc7fffffff [ 7340.415354] RBP: 00fa070000000000 R08: ffffcc5c04f7f8f8 R09: ffffcc5c04f7f7d0 [ 7340.416283] R10: ffff891f4c1a7000 R11: ffffcc5c04f7f9c8 R12: ffffcc5c04f7f7d0 [ 7340.417218] R13: 03ffffffffffffff R14: 00fa06fffffffe00 R15: ffff891f47789500 [ 7340.418229] FS: 0000000000000000(0000) GS:ffff891ffdfaa000(0000) knlGS:0000000000000000 [ 7340.419489] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 7340.420286] CR2: 00007f415bfffd58 CR3: 0000000103f03002 CR4: 0000000000772ef0 [ 7340.421237] PKRU: 55555554 [ 7340.421623] Call Trace: [ 7340.421987] [ 7340.422309] ? softleaf_from_pte+0x77/0xa0 [ 7340.422855] swap_pte_batch+0xa7/0x290 [ 7340.423363] zap_nonpresent_ptes.constprop.0.isra.0+0xd1/0x270 [ 7340.424102] zap_pte_range+0x281/0x580 [ 7340.424607] zap_pmd_range.isra.0+0xc9/0x240 [ 7340.425177] unmap_page_range+0x24d/0x420 [ 7340.425714] unmap_vmas+0xa1/0x180 [ 7340.426185] exit_mmap+0xe1/0x3b0 [ 7340.426644] __mmput+0x41/0x150 [ 7340.427098] exit_mm+0xb1/0x110 [ 7340.427539] do_exit+0x1b2/0x460 [ 7340.427992] do_group_exit+0x2d/0xc0 [ 7340.428477] get_signal+0x79d/0x7e0 [ 7340.428957] arch_do_signal_or_restart+0x34/0x100 [ 7340.429571] exit_to_user_mode_loop+0x8e/0x4c0 [ 7340.430159] do_syscall_64+0x188/ ---truncated---

Опубликовано: 2026-03-25Изменено: 2026-07-14
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
CVE-2026-23347
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: can: usb: f81604: correctly anchor the urb in the read bulk callback When submitting an urb, that is using the anchor pattern, it needs to be anchored before submitting it otherwise it could be leaked if usb_kill_anchored_urbs() is called. This logic is correctly done elsewhere in the driver, except in the read bulk callback so do that here also.

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
CVE-2026-23351
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_set_pipapo: split gc into unlink and reclaim phase Yiming Qian reports Use-after-free in the pipapo set type: Under a large number of expired elements, commit-time GC can run for a very long time in a non-preemptible context, triggering soft lockup warnings and RCU stall reports (local denial of service). We must split GC in an unlink and a reclaim phase. We cannot queue elements for freeing until pointers have been swapped. Expired elements are still exposed to both the packet path and userspace dumpers via the live copy of the data structure. call_rcu() does not protect us: dump operations or element lookups starting after call_rcu has fired can still observe the free'd element, unless the commit phase has made enough progress to swap the clone and live pointers before any new reader has picked up the old version. This a similar approach as done recently for the rbtree backend in commit 35f83a75529a ("netfilter: nft_set_rbtree: don't gc elements on insert").

Опубликовано: 2026-03-25Изменено: 2026-07-14
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
CVE-2026-23352
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: x86/efi: defer freeing of boot services memory efi_free_boot_services() frees memory occupied by EFI_BOOT_SERVICES_CODE and EFI_BOOT_SERVICES_DATA using memblock_free_late(). There are two issue with that: memblock_free_late() should be used for memory allocated with memblock_alloc() while the memory reserved with memblock_reserve() should be freed with free_reserved_area(). More acutely, with CONFIG_DEFERRED_STRUCT_PAGE_INIT=y efi_free_boot_services() is called before deferred initialization of the memory map is complete. Benjamin Herrenschmidt reports that this causes a leak of ~140MB of RAM on EC2 t3a.nano instances which only have 512MB or RAM. If the freed memory resides in the areas that memory map for them is still uninitialized, they won't be actually freed because memblock_free_late() calls memblock_free_pages() and the latter skips uninitialized pages. Using free_reserved_area() at this point is also problematic because __free_page() accesses the buddy of the freed page and that again might end up in uninitialized part of the memory map. Delaying the entire efi_free_boot_services() could be problematic because in addition to freeing boot services memory it updates efi.memmap without any synchronization and that's undesirable late in boot when there is concurrency. More robust approach is to only defer freeing of the EFI boot services memory. Split efi_free_boot_services() in two. First efi_unmap_boot_services() collects ranges that should be freed into an array then efi_free_boot_services() later frees them after deferred init is complete.

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
CVE-2026-23354
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: x86/fred: Correct speculative safety in fred_extint() array_index_nospec() is no use if the result gets spilled to the stack, as it makes the believed safe-under-speculation value subject to memory predictions. For all practical purposes, this means array_index_nospec() must be used in the expression that accesses the array. As the code currently stands, it's the wrong side of irqentry_enter(), and 'index' is put into %ebp across the function call. Remove the index variable and reposition array_index_nospec(), so it's calculated immediately before the array access.

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
CVE-2026-23356
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drbd: fix "LOGIC BUG" in drbd_al_begin_io_nonblock() Even though we check that we "should" be able to do lc_get_cumulative() while holding the device->al_lock spinlock, it may still fail, if some other code path decided to do lc_try_lock() with bad timing. If that happened, we logged "LOGIC BUG for enr=...", but still did not return an error. The rest of the code now assumed that this request has references for the relevant activity log extents. The implcations are that during an active resync, mutual exclusivity of resync versus application IO is not guaranteed. And a potential crash at this point may not realizs that these extents could have been target of in-flight IO and would need to be resynced just in case. Also, once the request completes, it will give up activity log references it does not even hold, which will trigger a BUG_ON(refcnt == 0) in lc_put(). Fix: Do not crash the kernel for a condition that is harmless during normal operation: also catch "e->refcnt == 0", not only "e == NULL" when being noisy about "al_complete_io() called on inactive extent %u\n". And do not try to be smart and "guess" whether something will work, then be surprised when it does not. Deal with the fact that it may or may not work. If it does not, remember a possible "partially in activity log" state (only possible for requests that cross extent boundaries), and return an error code from drbd_al_begin_io_nonblock(). A latter call for the same request will then resume from where we left off.

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
CVE-2026-23357
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: can: mcp251x: fix deadlock in error path of mcp251x_open The mcp251x_open() function call free_irq() in its error path with the mpc_lock mutex held. But if an interrupt already occurred the interrupt handler will be waiting for the mpc_lock and free_irq() will deadlock waiting for the handler to finish. This issue is similar to the one fixed in commit 7dd9c26bd6cf ("can: mcp251x: fix deadlock if an interrupt occurs during mcp251x_open") but for the error path. To solve this issue move the call to free_irq() after the lock is released. Setting `priv->force_quit = 1` beforehand ensure that the IRQ handler will exit right away once it acquired the lock.

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
CVE-2026-23359
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix stack-out-of-bounds write in devmap get_upper_ifindexes() iterates over all upper devices and writes their indices into an array without checking bounds. Also the callers assume that the max number of upper devices is MAX_NEST_DEV and allocate excluded_devices[1+MAX_NEST_DEV] on the stack, but that assumption is not correct and the number of upper devices could be larger than MAX_NEST_DEV (e.g., many macvlans), causing a stack-out-of-bounds write. Add a max parameter to get_upper_ifindexes() to avoid the issue. When there are too many upper devices, return -EOVERFLOW and abort the redirect. To reproduce, create more than MAX_NEST_DEV(8) macvlans on a device with an XDP program attached using BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS. Then send a packet to the device to trigger the XDP redirect path.

Опубликовано: 2026-03-25Изменено: 2026-07-14
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
CVE-2026-23360
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: nvme: fix admin queue leak on controller reset When nvme_alloc_admin_tag_set() is called during a controller reset, a previous admin queue may still exist. Release it properly before allocating a new one to avoid orphaning the old queue. This fixes a regression introduced by commit 03b3bcd319b3 ("nvme: fix admin request_queue lifetime").

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
CVE-2026-23361
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: PCI: dwc: ep: Flush MSI-X write before unmapping its ATU entry Endpoint drivers use dw_pcie_ep_raise_msix_irq() to raise an MSI-X interrupt to the host using a writel(), which generates a PCI posted write transaction. There's no completion for posted writes, so the writel() may return before the PCI write completes. dw_pcie_ep_raise_msix_irq() also unmaps the outbound ATU entry used for the PCI write, so the write races with the unmap. If the PCI write loses the race with the ATU unmap, the write may corrupt host memory or cause IOMMU errors, e.g., these when running fio with a larger queue depth against nvmet-pci-epf: arm-smmu-v3 fc900000.iommu: 0x0000010000000010 arm-smmu-v3 fc900000.iommu: 0x0000020000000000 arm-smmu-v3 fc900000.iommu: 0x000000090000f040 arm-smmu-v3 fc900000.iommu: 0x0000000000000000 arm-smmu-v3 fc900000.iommu: event: F_TRANSLATION client: 0000:01:00.0 sid: 0x100 ssid: 0x0 iova: 0x90000f040 ipa: 0x0 arm-smmu-v3 fc900000.iommu: unpriv data write s1 "Input address caused fault" stag: 0x0 Flush the write by performing a readl() of the same address to ensure that the write has reached the destination before the ATU entry is unmapped. The same problem was solved for dw_pcie_ep_raise_msi_irq() in commit 8719c64e76bf ("PCI: dwc: ep: Cache MSI outbound iATU mapping"), but there it was solved by dedicating an outbound iATU only for MSI. We can't do the same for MSI-X because each vector can have a different msg_addr and the msg_addr may be changed while the vector is masked. [bhelgaas: commit log]

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
CVE-2026-23362
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: can: bcm: fix locking for bcm_op runtime updates Commit c2aba69d0c36 ("can: bcm: add locking for bcm_op runtime updates") added a locking for some variables that can be modified at runtime when updating the sending bcm_op with a new TX_SETUP command in bcm_tx_setup(). Usually the RX_SETUP only handles and filters incoming traffic with one exception: When the RX_RTR_FRAME flag is set a predefined CAN frame is sent when a specific RTR frame is received. Therefore the rx bcm_op uses bcm_can_tx() which uses the bcm_tx_lock that was only initialized in bcm_tx_setup(). Add the missing spin_lock_init() when allocating the bcm_op in bcm_rx_setup() to handle the RTR case properly.

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
CVE-2026-23363
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: mt7925: Fix possible oob access in mt7925_mac_write_txwi_80211() Check frame length before accessing the mgmt fields in mt7925_mac_write_txwi_80211 in order to avoid a possible oob access.

Опубликовано: 2026-03-25Изменено: 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
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
CVE-2026-23365
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: usb: kalmia: validate USB endpoints The kalmia driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.

Опубликовано: 2026-03-25Изменено: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2026-23367
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wifi: radiotap: reject radiotap with unknown bits The radiotap parser is currently only used with the radiotap namespace (not with vendor namespaces), but if the undefined field 18 is used, the alignment/size is unknown as well. In this case, iterator->_next_ns_data isn't initialized (it's only set for skipping vendor namespaces), and syzbot points out that we later compare against this uninitialized value. Fix this by moving the rejection of unknown radiotap fields down to after the in-namespace lookup, so it will really use iterator->_next_ns_data only for vendor namespaces, even in case undefined fields are present.

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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2026-23369
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: i2c: i801: Revert "i2c: i801: replace acpi_lock with I2C bus lock" This reverts commit f707d6b9e7c18f669adfdb443906d46cfbaaa0c1. Under rare circumstances, multiple udev threads can collect i801 device info on boot and walk i801_acpi_io_handler somewhat concurrently. The first will note the area is reserved by acpi to prevent further touches. This ultimately causes the area to be deregistered. The second will enter i801_acpi_io_handler after the area is unregistered but before a check can be made that the area is unregistered. i2c_lock_bus relies on the now unregistered area containing lock_ops to lock the bus. The end result is a kernel panic on boot with the following backtrace; [ 14.971872] ioatdma 0000:09:00.2: enabling device (0100 -> 0102) [ 14.971873] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 14.971880] #PF: supervisor read access in kernel mode [ 14.971884] #PF: error_code(0x0000) - not-present page [ 14.971887] PGD 0 P4D 0 [ 14.971894] Oops: 0000 [#1] PREEMPT SMP PTI [ 14.971900] CPU: 5 PID: 956 Comm: systemd-udevd Not tainted 5.14.0-611.5.1.el9_7.x86_64 #1 [ 14.971905] Hardware name: XXXXXXXXXXXXXXXXXXXXXXX BIOS 1.20.10.SV91 01/30/2023 [ 14.971908] RIP: 0010:i801_acpi_io_handler+0x2d/0xb0 [i2c_i801] [ 14.971929] Code: 00 00 49 8b 40 20 41 57 41 56 4d 8b b8 30 04 00 00 49 89 ce 41 55 41 89 d5 41 54 49 89 f4 be 02 00 00 00 55 4c 89 c5 53 89 fb <48> 8b 00 4c 89 c7 e8 18 61 54 e9 80 bd 80 04 00 00 00 75 09 4c 3b [ 14.971933] RSP: 0018:ffffbaa841483838 EFLAGS: 00010282 [ 14.971938] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff9685e01ba568 [ 14.971941] RDX: 0000000000000008 RSI: 0000000000000002 RDI: 0000000000000000 [ 14.971944] RBP: ffff9685ca22f028 R08: ffff9685ca22f028 R09: ffff9685ca22f028 [ 14.971948] R10: 000000000000000b R11: 0000000000000580 R12: 0000000000000580 [ 14.971951] R13: 0000000000000008 R14: ffff9685e01ba568 R15: ffff9685c222f000 [ 14.971954] FS: 00007f8287c0ab40(0000) GS:ffff96a47f940000(0000) knlGS:0000000000000000 [ 14.971959] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 14.971963] CR2: 0000000000000000 CR3: 0000000168090001 CR4: 00000000003706f0 [ 14.971966] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 14.971968] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 14.971972] Call Trace: [ 14.971977] [ 14.971981] ? show_trace_log_lvl+0x1c4/0x2df [ 14.971994] ? show_trace_log_lvl+0x1c4/0x2df [ 14.972003] ? acpi_ev_address_space_dispatch+0x16e/0x3c0 [ 14.972014] ? __die_body.cold+0x8/0xd [ 14.972021] ? page_fault_oops+0x132/0x170 [ 14.972028] ? exc_page_fault+0x61/0x150 [ 14.972036] ? asm_exc_page_fault+0x22/0x30 [ 14.972045] ? i801_acpi_io_handler+0x2d/0xb0 [i2c_i801] [ 14.972061] acpi_ev_address_space_dispatch+0x16e/0x3c0 [ 14.972069] ? __pfx_i801_acpi_io_handler+0x10/0x10 [i2c_i801] [ 14.972085] acpi_ex_access_region+0x5b/0xd0 [ 14.972093] acpi_ex_field_datum_io+0x73/0x2e0 [ 14.972100] acpi_ex_read_data_from_field+0x8e/0x230 [ 14.972106] acpi_ex_resolve_node_to_value+0x23d/0x310 [ 14.972114] acpi_ds_evaluate_name_path+0xad/0x110 [ 14.972121] acpi_ds_exec_end_op+0x321/0x510 [ 14.972127] acpi_ps_parse_loop+0xf7/0x680 [ 14.972136] acpi_ps_parse_aml+0x17a/0x3d0 [ 14.972143] acpi_ps_execute_method+0x137/0x270 [ 14.972150] acpi_ns_evaluate+0x1f4/0x2e0 [ 14.972158] acpi_evaluate_object+0x134/0x2f0 [ 14.972164] acpi_evaluate_integer+0x50/0xe0 [ 14.972173] ? vsnprintf+0x24b/0x570 [ 14.972181] acpi_ac_get_state.part.0+0x23/0x70 [ 14.972189] get_ac_property+0x4e/0x60 [ 14.972195] power_supply_show_property+0x90/0x1f0 [ 14.972205] add_prop_uevent+0x29/0x90 [ 14.972213] power_supply_uevent+0x109/0x1d0 [ 14.972222] dev_uevent+0x10e/0x2f0 [ 14.972228] uevent_show+0x8e/0x100 [ 14.972236] dev_attr_show+0x19 ---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
CVE-2026-23370
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: platform/x86: dell-wmi-sysman: Don't hex dump plaintext password data set_new_password() hex dumps the entire buffer, which contains plaintext password data, including current and new passwords. Remove the hex dump to avoid leaking credentials.

Опубликовано: 2026-03-25Изменено: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2026-23372
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: nfc: rawsock: cancel tx_work before socket teardown In rawsock_release(), cancel any pending tx_work and purge the write queue before orphaning the socket. rawsock_tx_work runs on the system workqueue and calls nfc_data_exchange which dereferences the NCI device. Without synchronization, tx_work can race with socket and device teardown when a process is killed (e.g. by SIGKILL), leading to use-after-free or leaked references. Set SEND_SHUTDOWN first so that if tx_work is already running it will see the flag and skip transmitting, then use cancel_work_sync to wait for any in-progress execution to finish, and finally purge any remaining queued skbs.

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
CVE-2026-23373
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wifi: rsi: Don't default to -EOPNOTSUPP in rsi_mac80211_config This triggers a WARN_ON in ieee80211_hw_conf_init and isn't the expected behavior from the driver - other drivers default to 0 too.

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
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
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
CVE-2026-23378
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net/sched: act_ife: Fix metalist update behavior Whenever an ife action replace changes the metalist, instead of replacing the old data on the metalist, the current ife code is appending the new metadata. Aside from being innapropriate behavior, this may lead to an unbounded addition of metadata to the metalist which might cause an out of bounds error when running the encode op: [ 138.423369][ C1] ================================================================== [ 138.424317][ C1] BUG: KASAN: slab-out-of-bounds in ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.424906][ C1] Write of size 4 at addr ffff8880077f4ffe by task ife_out_out_bou/255 [ 138.425778][ C1] CPU: 1 UID: 0 PID: 255 Comm: ife_out_out_bou Not tainted 7.0.0-rc1-00169-gfbdfa8da05b6 #624 PREEMPT(full) [ 138.425795][ C1] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 138.425800][ C1] Call Trace: [ 138.425804][ C1] [ 138.425808][ C1] dump_stack_lvl (lib/dump_stack.c:122) [ 138.425828][ C1] print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) [ 138.425839][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425844][ C1] ? __virt_addr_valid (./arch/x86/include/asm/preempt.h:95 (discriminator 1) ./include/linux/rcupdate.h:975 (discriminator 1) ./include/linux/mmzone.h:2207 (discriminator 1) arch/x86/mm/physaddr.c:54 (discriminator 1)) [ 138.425853][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425859][ C1] kasan_report (mm/kasan/report.c:221 mm/kasan/report.c:597) [ 138.425868][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425878][ C1] kasan_check_range (mm/kasan/generic.c:186 (discriminator 1) mm/kasan/generic.c:200 (discriminator 1)) [ 138.425884][ C1] __asan_memset (mm/kasan/shadow.c:84 (discriminator 2)) [ 138.425889][ C1] ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425893][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:171) [ 138.425898][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425903][ C1] ife_encode_meta_u16 (net/sched/act_ife.c:57) [ 138.425910][ C1] ? __pfx_do_raw_spin_lock (kernel/locking/spinlock_debug.c:114) [ 138.425916][ C1] ? __asan_memcpy (mm/kasan/shadow.c:105 (discriminator 3)) [ 138.425921][ C1] ? __pfx_ife_encode_meta_u16 (net/sched/act_ife.c:45) [ 138.425927][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425931][ C1] tcf_ife_act (net/sched/act_ife.c:847 net/sched/act_ife.c:879) To solve this issue, fix the replace behavior by adding the metalist to the ife rcu data structure.

Опубликовано: 2026-03-25Изменено: 2026-07-14
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
CVE-2026-23379
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/sched: ets: fix divide by zero in the offload path Offloading ETS requires computing each class' WRR weight: this is done by averaging over the sums of quanta as 'q_sum' and 'q_psum'. Using unsigned int, the same integer size as the individual DRR quanta, can overflow and even cause division by zero, like it happened in the following splat: Oops: divide error: 0000 [#1] SMP PTI CPU: 13 UID: 0 PID: 487 Comm: tc Tainted: G E 6.19.0-virtme #45 PREEMPT(full) Tainted: [E]=UNSIGNED_MODULE Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets] Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000 FS: 00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0 Call Trace: ets_qdisc_change+0x870/0xf40 [sch_ets] qdisc_create+0x12b/0x540 tc_modify_qdisc+0x6d7/0xbd0 rtnetlink_rcv_msg+0x168/0x6b0 netlink_rcv_skb+0x5c/0x110 netlink_unicast+0x1d6/0x2b0 netlink_sendmsg+0x22e/0x470 ____sys_sendmsg+0x38a/0x3c0 ___sys_sendmsg+0x99/0xe0 __sys_sendmsg+0x8a/0xf0 do_syscall_64+0x111/0xf80 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f440b81c77e Code: 4d 89 d8 e8 d4 bc 00 00 4c 8b 5d f8 41 8b 93 08 03 00 00 59 5e 48 83 f8 fc 74 11 c9 c3 0f 1f 80 00 00 00 00 48 8b 45 10 0f 05 c3 83 e2 39 83 fa 08 75 e7 e8 13 ff ff ff 0f 1f 00 f3 0f 1e fa RSP: 002b:00007fff951e4c10 EFLAGS: 00000202 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000481820 RCX: 00007f440b81c77e RDX: 0000000000000000 RSI: 00007fff951e4cd0 RDI: 0000000000000003 RBP: 00007fff951e4c20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00007fff951f4fa8 R13: 00000000699ddede R14: 00007f440bb01000 R15: 0000000000486980 Modules linked in: sch_ets(E) netdevsim(E) ---[ end trace 0000000000000000 ]--- RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets] Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000 FS: 00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0 Kernel panic - not syncing: Fatal exception Kernel Offset: 0x30000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception ]--- Fix this using 64-bit integers for 'q_sum' and 'q_psum'.

Опубликовано: 2026-03-25Изменено: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2026-23380
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: tracing: Fix WARN_ON in tracing_buffers_mmap_close When a process forks, the child process copies the parent's VMAs but the user_mapped reference count is not incremented. As a result, when both the parent and child processes exit, tracing_buffers_mmap_close() is called twice. On the second call, user_mapped is already 0, causing the function to return -ENODEV and triggering a WARN_ON. Normally, this isn't an issue as the memory is mapped with VM_DONTCOPY set. But this is only a hint, and the application can call madvise(MADVISE_DOFORK) which resets the VM_DONTCOPY flag. When the application does that, it can trigger this issue on fork. Fix it by incrementing the user_mapped reference count without re-mapping the pages in the VMA's open callback.

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
CVE-2026-23381
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: bridge: 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. Then, if neigh_suppress is enabled and an ICMPv6 Neighbor Discovery packet reaches the bridge, br_do_suppress_nd() will dereference ipv6_stub->nd_tbl which is NULL, passing it to neigh_lookup(). This causes a kernel NULL pointer dereference. BUG: kernel NULL pointer dereference, address: 0000000000000268 Oops: 0000 [#1] PREEMPT SMP NOPTI [...] RIP: 0010:neigh_lookup+0x16/0xe0 [...] Call Trace: ? neigh_lookup+0x16/0xe0 br_do_suppress_nd+0x160/0x290 [bridge] br_handle_frame_finish+0x500/0x620 [bridge] br_handle_frame+0x353/0x440 [bridge] __netif_receive_skb_core.constprop.0+0x298/0x1110 __netif_receive_skb_one_core+0x3d/0xa0 process_backlog+0xa0/0x140 __napi_poll+0x2c/0x170 net_rx_action+0x2c4/0x3a0 handle_softirqs+0xd0/0x270 do_softirq+0x3f/0x60 Fix this by replacing IS_ENABLED(IPV6) call with ipv6_mod_enabled() in the callers. This is in essence disabling NS/NA suppression when IPv6 is disabled.

Опубликовано: 2026-03-25Изменено: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2026-23382
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: HID: Add HID_CLAIMED_INPUT guards in raw_event callbacks missing them In commit 2ff5baa9b527 ("HID: appleir: Fix potential NULL dereference at raw event handle"), we handle the fact that raw event callbacks can happen even for a HID device that has not been "claimed" causing a crash if a broken device were attempted to be connected to the system. Fix up the remaining in-tree HID drivers that forgot to add this same check to resolve the same issue.

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
CVE-2026-23383
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bpf, arm64: Force 8-byte alignment for JIT buffer to prevent atomic tearing struct bpf_plt contains a u64 target field. Currently, the BPF JIT allocator requests an alignment of 4 bytes (sizeof(u32)) for the JIT buffer. Because the base address of the JIT buffer can be 4-byte aligned (e.g., ending in 0x4 or 0xc), the relative padding logic in build_plt() fails to ensure that target lands on an 8-byte boundary. This leads to two issues: 1. UBSAN reports misaligned-access warnings when dereferencing the structure. 2. More critically, target is updated concurrently via WRITE_ONCE() in bpf_arch_text_poke() while the JIT'd code executes ldr. On arm64, 64-bit loads/stores are only guaranteed to be single-copy atomic if they are 64-bit aligned. A misaligned target risks a torn read, causing the JIT to jump to a corrupted address. Fix this by increasing the allocation alignment requirement to 8 bytes (sizeof(u64)) in bpf_jit_binary_pack_alloc(). This anchors the base of the JIT buffer to an 8-byte boundary, allowing the relative padding math in build_plt() to correctly align the target field.

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
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
CVE-2026-23387
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: pinctrl: cirrus: cs42l43: Fix double-put in cs42l43_pin_probe() devm_add_action_or_reset() already invokes the action on failure, so the explicit put causes a double-put.

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
CVE-2026-23388
HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: Squashfs: check metadata block offset is within range Syzkaller reports a "general protection fault in squashfs_copy_data" This is ultimately caused by a corrupted index look-up table, which produces a negative metadata block offset. This is subsequently passed to squashfs_copy_data (via squashfs_read_metadata) where the negative offset causes an out of bounds access. The fix is to check that the offset is within range in squashfs_read_metadata. This will trap this and other cases.

Опубликовано: 2026-03-25Изменено: 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
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
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: 2026-07-14
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
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: 2026-07-14
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
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
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
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
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: 2026-07-14
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Ссылки
CVE-2026-23403
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: apparmor: fix memory leak in verify_header The function sets `*ns = NULL` on every call, leaking the namespace string allocated in previous iterations when multiple profiles are unpacked. This also breaks namespace consistency checking since *ns is always NULL when the comparison is made. Remove the incorrect assignment. The caller (aa_unpack) initializes *ns to NULL once before the loop, which is sufficient.

Опубликовано: 2026-04-01Изменено: 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
CVE-2026-23404
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: apparmor: replace recursive profile removal with iterative approach The profile removal code uses recursion when removing nested profiles, which can lead to kernel stack exhaustion and system crashes. Reproducer: $ pf='a'; for ((i=0; i<1024; i++)); do echo -e "profile $pf { \n }" | apparmor_parser -K -a; pf="$pf//x"; done $ echo -n a > /sys/kernel/security/apparmor/.remove Replace the recursive __aa_profile_list_release() approach with an iterative approach in __remove_profile(). The function repeatedly finds and removes leaf profiles until the entire subtree is removed, maintaining the same removal semantic without recursion.

Опубликовано: 2026-04-01Изменено: 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
CVE-2026-23405
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: apparmor: fix: limit the number of levels of policy namespaces Currently the number of policy namespaces is not bounded relying on the user namespace limit. However policy namespaces aren't strictly tied to user namespaces and it is possible to create them and nest them arbitrarily deep which can be used to exhaust system resource. Hard cap policy namespaces to the same depth as user namespaces.

Опубликовано: 2026-04-01Изменено: 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
CVE-2026-23406
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: apparmor: fix side-effect bug in match_char() macro usage The match_char() macro evaluates its character parameter multiple times when traversing differential encoding chains. When invoked with *str++, the string pointer advances on each iteration of the inner do-while loop, causing the DFA to check different characters at each iteration and therefore skip input characters. This results in out-of-bounds reads when the pointer advances past the input buffer boundary. [ 94.984676] ================================================================== [ 94.985301] BUG: KASAN: slab-out-of-bounds in aa_dfa_match+0x5ae/0x760 [ 94.985655] Read of size 1 at addr ffff888100342000 by task file/976 [ 94.986319] CPU: 7 UID: 1000 PID: 976 Comm: file Not tainted 6.19.0-rc7-next-20260127 #1 PREEMPT(lazy) [ 94.986322] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 94.986329] Call Trace: [ 94.986341] [ 94.986347] dump_stack_lvl+0x5e/0x80 [ 94.986374] print_report+0xc8/0x270 [ 94.986384] ? aa_dfa_match+0x5ae/0x760 [ 94.986388] kasan_report+0x118/0x150 [ 94.986401] ? aa_dfa_match+0x5ae/0x760 [ 94.986405] aa_dfa_match+0x5ae/0x760 [ 94.986408] __aa_path_perm+0x131/0x400 [ 94.986418] aa_path_perm+0x219/0x2f0 [ 94.986424] apparmor_file_open+0x345/0x570 [ 94.986431] security_file_open+0x5c/0x140 [ 94.986442] do_dentry_open+0x2f6/0x1120 [ 94.986450] vfs_open+0x38/0x2b0 [ 94.986453] ? may_open+0x1e2/0x2b0 [ 94.986466] path_openat+0x231b/0x2b30 [ 94.986469] ? __x64_sys_openat+0xf8/0x130 [ 94.986477] do_file_open+0x19d/0x360 [ 94.986487] do_sys_openat2+0x98/0x100 [ 94.986491] __x64_sys_openat+0xf8/0x130 [ 94.986499] do_syscall_64+0x8e/0x660 [ 94.986515] ? count_memcg_events+0x15f/0x3c0 [ 94.986526] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986540] ? handle_mm_fault+0x1639/0x1ef0 [ 94.986551] ? vma_start_read+0xf0/0x320 [ 94.986558] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986561] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986563] ? fpregs_assert_state_consistent+0x50/0xe0 [ 94.986572] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986574] ? arch_exit_to_user_mode_prepare+0x9/0xb0 [ 94.986587] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986588] ? irqentry_exit+0x3c/0x590 [ 94.986595] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 94.986597] RIP: 0033:0x7fda4a79c3ea Fix by extracting the character value before invoking match_char, ensuring single evaluation per outer loop.

Опубликовано: 2026-04-01Изменено: 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
CVE-2026-23407
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: apparmor: fix missing bounds check on DEFAULT table in verify_dfa() The verify_dfa() function only checks DEFAULT_TABLE bounds when the state is not differentially encoded. When the verification loop traverses the differential encoding chain, it reads k = DEFAULT_TABLE[j] and uses k as an array index without validation. A malformed DFA with DEFAULT_TABLE[j] >= state_count, therefore, causes both out-of-bounds reads and writes. [ 57.179855] ================================================================== [ 57.180549] BUG: KASAN: slab-out-of-bounds in verify_dfa+0x59a/0x660 [ 57.180904] Read of size 4 at addr ffff888100eadec4 by task su/993 [ 57.181554] CPU: 1 UID: 0 PID: 993 Comm: su Not tainted 6.19.0-rc7-next-20260127 #1 PREEMPT(lazy) [ 57.181558] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 57.181563] Call Trace: [ 57.181572] [ 57.181577] dump_stack_lvl+0x5e/0x80 [ 57.181596] print_report+0xc8/0x270 [ 57.181605] ? verify_dfa+0x59a/0x660 [ 57.181608] kasan_report+0x118/0x150 [ 57.181620] ? verify_dfa+0x59a/0x660 [ 57.181623] verify_dfa+0x59a/0x660 [ 57.181627] aa_dfa_unpack+0x1610/0x1740 [ 57.181629] ? __kmalloc_cache_noprof+0x1d0/0x470 [ 57.181640] unpack_pdb+0x86d/0x46b0 [ 57.181647] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181653] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181656] ? aa_unpack_nameX+0x1a8/0x300 [ 57.181659] aa_unpack+0x20b0/0x4c30 [ 57.181662] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181664] ? stack_depot_save_flags+0x33/0x700 [ 57.181681] ? kasan_save_track+0x4f/0x80 [ 57.181683] ? kasan_save_track+0x3e/0x80 [ 57.181686] ? __kasan_kmalloc+0x93/0xb0 [ 57.181688] ? __kvmalloc_node_noprof+0x44a/0x780 [ 57.181693] ? aa_simple_write_to_buffer+0x54/0x130 [ 57.181697] ? policy_update+0x154/0x330 [ 57.181704] aa_replace_profiles+0x15a/0x1dd0 [ 57.181707] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181710] ? __kvmalloc_node_noprof+0x44a/0x780 [ 57.181712] ? aa_loaddata_alloc+0x77/0x140 [ 57.181715] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181717] ? _copy_from_user+0x2a/0x70 [ 57.181730] policy_update+0x17a/0x330 [ 57.181733] profile_replace+0x153/0x1a0 [ 57.181735] ? rw_verify_area+0x93/0x2d0 [ 57.181740] vfs_write+0x235/0xab0 [ 57.181745] ksys_write+0xb0/0x170 [ 57.181748] do_syscall_64+0x8e/0x660 [ 57.181762] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 57.181765] RIP: 0033:0x7f6192792eb2 Remove the MATCH_FLAG_DIFF_ENCODE condition to validate all DEFAULT_TABLE entries unconditionally.

Опубликовано: 2026-04-01Изменено: 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
CVE-2026-23408
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: apparmor: Fix double free of ns_name in aa_replace_profiles() if ns_name is NULL after 1071 error = aa_unpack(udata, &lh, &ns_name); and if ent->ns_name contains an ns_name in 1089 } else if (ent->ns_name) { then ns_name is assigned the ent->ns_name 1095 ns_name = ent->ns_name; however ent->ns_name is freed at 1262 aa_load_ent_free(ent); and then again when freeing ns_name at 1270 kfree(ns_name); Fix this by NULLing out ent->ns_name after it is transferred to ns_name ")

Опубликовано: 2026-04-01Изменено: 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
CVE-2026-23409
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: apparmor: fix differential encoding verification Differential encoding allows loops to be created if it is abused. To prevent this the unpack should verify that a diff-encode chain terminates. Unfortunately the differential encode verification had two bugs. 1. it conflated states that had gone through check and already been marked, with states that were currently being checked and marked. This means that loops in the current chain being verified are treated as a chain that has already been verified. 2. the order bailout on already checked states compared current chain check iterators j,k instead of using the outer loop iterator i. Meaning a step backwards in states in the current chain verification was being mistaken for moving to an already verified state. Move to a double mark scheme where already verified states get a different mark, than the current chain being kept. This enables us to also drop the backwards verification check that was the cause of the second error as any already verified state is already marked.

Опубликовано: 2026-04-01Изменено: 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
CVE-2026-23410
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: apparmor: fix race on rawdata dereference There is a race condition that leads to a use-after-free situation: because the rawdata inodes are not refcounted, an attacker can start open()ing one of the rawdata files, and at the same time remove the last reference to this rawdata (by removing the corresponding profile, for example), which frees its struct aa_loaddata; as a result, when seq_rawdata_open() is reached, i_private is a dangling pointer and freed memory is accessed. The rawdata inodes weren't refcounted to avoid a circular refcount and were supposed to be held by the profile rawdata reference. However during profile removal there is a window where the vfs and profile destruction race, resulting in the use after free. Fix this by moving to a double refcount scheme. Where the profile refcount on rawdata is used to break the circular dependency. Allowing for freeing of the rawdata once all inode references to the rawdata are put.

Опубликовано: 2026-04-01Изменено: 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
CVE-2026-23411
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: apparmor: fix race between freeing data and fs accessing it AppArmor was putting the reference to i_private data on its end after removing the original entry from the file system. However the inode can aand does live beyond that point and it is possible that some of the fs call back functions will be invoked after the reference has been put, which results in a race between freeing the data and accessing it through the fs. While the rawdata/loaddata is the most likely candidate to fail the race, as it has the fewest references. If properly crafted it might be possible to trigger a race for the other types stored in i_private. Fix this by moving the put of i_private referenced data to the correct place which is during inode eviction.

Опубликовано: 2026-04-01Изменено: 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
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
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
CVE-2026-23419
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/rds: Fix circular locking dependency in rds_tcp_tune syzbot reported a circular locking dependency in rds_tcp_tune() where sk_net_refcnt_upgrade() is called while holding the socket lock: ====================================================== WARNING: possible circular locking dependency detected ====================================================== kworker/u10:8/15040 is trying to acquire lock: ffffffff8e9aaf80 (fs_reclaim){+.+.}-{0:0}, at: __kmalloc_cache_noprof+0x4b/0x6f0 but task is already holding lock: ffff88805a3c1ce0 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at: rds_tcp_tune+0xd7/0x930 The issue occurs because sk_net_refcnt_upgrade() performs memory allocation (via get_net_track() -> ref_tracker_alloc()) while the socket lock is held, creating a circular dependency with fs_reclaim. Fix this by moving sk_net_refcnt_upgrade() outside the socket lock critical section. This is safe because the fields modified by the sk_net_refcnt_upgrade() call (sk_net_refcnt, ns_tracker) are not accessed by any concurrent code path at this point. v2: - Corrected fixes tag - check patch line wrap nits - ai commentary nits

Опубликовано: 2026-04-03Изменено: 2026-07-24
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
CVE-2026-23420
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wifi: wlcore: Fix a locking bug Make sure that wl->mutex is locked before it is unlocked. This has been detected by the Clang thread-safety analyzer.

Опубликовано: 2026-04-03Изменено: 2026-07-24
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
CVE-2026-23422
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: dpaa2-switch: Fix interrupt storm after receiving bad if_id in IRQ handler Commit 31a7a0bbeb00 ("dpaa2-switch: add bounds check for if_id in IRQ handler") introduces a range check for if_id to avoid an out-of-bounds access. If an out-of-bounds if_id is detected, the interrupt status is not cleared. This may result in an interrupt storm. Clear the interrupt status after detecting an out-of-bounds if_id to avoid the problem. Found by an experimental AI code review agent at Google.

Опубликовано: 2026-04-03Изменено: 2026-07-24
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
CVE-2026-23426
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/logicvc: Fix device node reference leak in logicvc_drm_config_parse() The logicvc_drm_config_parse() function calls of_get_child_by_name() to find the "layers" node but fails to release the reference, leading to a device node reference leak. Fix this by using the __free(device_node) cleanup attribute to automatic release the reference when the variable goes out of scope.

Опубликовано: 2026-04-03Изменено: 2026-07-24
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
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
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-14
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-21
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-14
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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-2026-31403
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-07-24
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
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: 2026-08-19
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
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: 2026-07-24
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
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: 2026-07-24
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
CVE-2026-31411
MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: atm: fix crash due to unvalidated vcc pointer in sigd_send() Reproducer available at [1]. The ATM send path (sendmsg -> vcc_sendmsg -> sigd_send) reads the vcc pointer from msg->vcc and uses it directly without any validation. This pointer comes from userspace via sendmsg() and can be arbitrarily forged: int fd = socket(AF_ATMSVC, SOCK_DGRAM, 0); ioctl(fd, ATMSIGD_CTRL); // become ATM signaling daemon struct msghdr msg = { .msg_iov = &iov, ... }; *(unsigned long *)(buf + 4) = 0xdeadbeef; // fake vcc pointer sendmsg(fd, &msg, 0); // kernel dereferences 0xdeadbeef In normal operation, the kernel sends the vcc pointer to the signaling daemon via sigd_enq() when processing operations like connect(), bind(), or listen(). The daemon is expected to return the same pointer when responding. However, a malicious daemon can send arbitrary pointer values. Fix this by introducing find_get_vcc() which validates the pointer by searching through vcc_hash (similar to how sigd_close() iterates over all VCCs), and acquires a reference via sock_hold() if found. Since struct atm_vcc embeds struct sock as its first member, they share the same lifetime. Therefore using sock_hold/sock_put is sufficient to keep the vcc alive while it is being used. Note that there may be a race with sigd_close() which could mark the vcc with various flags (e.g., ATM_VF_RELEASED) after find_get_vcc() returns. However, sock_hold() guarantees the memory remains valid, so this race only affects the logical state, not memory safety. [1]: https://gist.github.com/mrpre/1ba5949c45529c511152e2f4c755b0f3

Опубликовано: 2026-04-08Изменено: 2026-07-25
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
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
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: 2026-07-14
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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
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: 2026-07-28
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
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
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
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
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
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
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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: 2026-07-14
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
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: 2026-07-14
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
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
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: 2026-07-14
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
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
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: 2026-07-14
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
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
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
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
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
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
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
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: 2026-07-14
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
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
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: 2026-07-14
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
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
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
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: 2026-07-14
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
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
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
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
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
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
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
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
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: 2026-07-14
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
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
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: 2026-08-17
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
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
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
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: 2026-07-14
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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
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
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: 2026-07-24
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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: 2026-07-14
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
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
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
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: 2026-07-14
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
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: 2026-07-14
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
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
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
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
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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
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
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
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
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
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
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
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
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: 2026-07-14
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
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
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
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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
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
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
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
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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
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
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
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
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: 2026-07-14
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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: 2026-08-21
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
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: 2026-07-24
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
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
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
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
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
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
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: 2026-08-06
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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: 2026-07-14
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
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
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
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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
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
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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: 2026-07-14
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
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
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
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
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: 2026-07-14
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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
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: 2026-07-14
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
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
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
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
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
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
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: 2026-07-14
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
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
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: 2026-07-14
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
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
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
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
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
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
CVE-2026-31693
HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: cifs: some missing initializations on replay In several places in the code, we have a label to signify the start of the code where a request can be replayed if necessary. However, some of these places were missing the necessary reinitializations of certain local variables before replay. This change makes sure that these variables get initialized after the label.

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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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
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
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
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
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
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
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
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
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: 2026-07-14
CVSS 3.xСРЕДНЯЯ 5.5
CVSS:3.x/CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
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
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
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
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
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