ALT-PU-2026-6793-19 — kernel-image-6.18

BDU:2026-04925

HIGH7.0

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

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

CVSS 3.xHIGH 7.0

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

CVSS 2.0MEDIUM 6.0

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

References

BDU:2026-04968

HIGH7.1

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

Published: 2026-04-09

CVSS 3.xHIGH 7.1

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

CVSS 2.0MEDIUM 6.2

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

References

BDU:2026-05267

HIGH7.0

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

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

CVSS 3.xHIGH 7.0

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

CVSS 2.0MEDIUM 6.0

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

References

BDU:2026-06123

HIGH7.8

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

Published: 2026-04-29Modified: 2026-06-16

CVSS 3.xHIGH 7.8

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

CVSS 2.0MEDIUM 6.8

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

References

BDU:2026-06493

MEDIUM5.5

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

Published: 2026-05-11Modified: 2026-05-26

CVSS 3.xMEDIUM 5.5

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

CVSS 2.0MEDIUM 4.6

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

References

BDU:2026-06494

MEDIUM5.5

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

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

CVSS 3.xMEDIUM 5.5

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

CVSS 2.0MEDIUM 4.6

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

References

BDU:2026-06495

HIGH8.4

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

Published: 2026-05-11Modified: 2026-05-26

CVSS 3.xHIGH 8.4

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

CVSS 2.0HIGH 7.2

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

References

BDU:2026-06496

HIGH7.5

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

Published: 2026-05-11

CVSS 3.xHIGH 7.5

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

CVSS 2.0HIGH 7.8

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

References

BDU:2026-06497

HIGH7.0

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

Published: 2026-05-11Modified: 2026-05-26

CVSS 3.xHIGH 7.0

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

CVSS 2.0MEDIUM 6.0

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

References

BDU:2026-06498

MEDIUM5.5

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

Published: 2026-05-11Modified: 2026-05-26

CVSS 3.xMEDIUM 5.5

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

CVSS 2.0MEDIUM 4.6

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

References

BDU:2026-06499

HIGH7.3

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

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

CVSS 3.xHIGH 7.3

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

CVSS 2.0MEDIUM 6.4

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

References

BDU:2026-06501

HIGH8.4

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

Published: 2026-05-11Modified: 2026-05-26

CVSS 3.xHIGH 8.4

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

CVSS 2.0HIGH 7.2

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

References

BDU:2026-06503

HIGH7.1

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

Published: 2026-05-11Modified: 2026-05-26

CVSS 3.xHIGH 7.1

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

CVSS 2.0MEDIUM 6.2

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

References

BDU:2026-06504

MEDIUM5.5

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

Published: 2026-05-11

CVSS 3.xMEDIUM 5.5

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

CVSS 2.0MEDIUM 4.6

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

References

BDU:2026-06505

HIGH7.8

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

Published: 2026-05-11Modified: 2026-05-26

CVSS 3.xHIGH 7.8

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

CVSS 2.0MEDIUM 6.8

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

References

BDU:2026-06506

HIGH7.8

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

Published: 2026-05-11Modified: 2026-05-26

CVSS 3.xHIGH 7.8

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

CVSS 2.0MEDIUM 6.8

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

References

BDU:2026-06507

HIGH7.8

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

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

CVSS 3.xHIGH 7.8

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

CVSS 2.0MEDIUM 6.8

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

References

BDU:2026-06508

HIGH8.8

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

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

CVSS 3.xHIGH 8.8

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

CVSS 2.0HIGH 8.3

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

References

BDU:2026-06509

HIGH7.8

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

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

CVSS 3.xHIGH 7.8

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

CVSS 2.0MEDIUM 6.8

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

References

BDU:2026-06510

MEDIUM5.5

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

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

CVSS 3.xMEDIUM 5.5

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

CVSS 2.0MEDIUM 4.6

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

References

BDU:2026-06511

HIGH7.8

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

Published: 2026-05-11Modified: 2026-05-26

CVSS 3.xHIGH 7.8

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

CVSS 2.0MEDIUM 6.8

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

References

BDU:2026-07832

CRITICAL9.8

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

Published: 2026-06-04Modified: 2026-06-18

CVSS 3.xCRITICAL 9.8

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

CVSS 2.0CRITICAL 10.0

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

References

BDU:2026-07834

HIGH7.8

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

Published: 2026-06-04Modified: 2026-06-18

CVSS 3.xHIGH 7.8

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

CVSS 2.0MEDIUM 6.8

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

References

BDU:2026-07835

HIGH8.0

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

Published: 2026-06-04Modified: 2026-06-18

CVSS 3.xHIGH 8.0

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

CVSS 2.0HIGH 7.7

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

References

BDU:2026-07836

HIGH7.8

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

Published: 2026-06-04Modified: 2026-06-18

CVSS 3.xHIGH 7.8

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

CVSS 2.0MEDIUM 6.8

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

References

BDU:2026-07837

HIGH7.8

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

Published: 2026-06-04Modified: 2026-06-18

CVSS 3.xHIGH 7.8

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

CVSS 2.0MEDIUM 6.8

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

References

CVE-2026-23389

MEDIUM5.5

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

Published: 2026-03-25Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-23401

MEDIUM5.5

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

Published: 2026-04-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-23402

MEDIUM5.5

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

Published: 2026-04-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-23414

MEDIUM5.5

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

Published: 2026-04-02Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-23415

HIGH7.8

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

Published: 2026-04-02Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-23416

MEDIUM5.5

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

Published: 2026-04-02Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-23417

MEDIUM5.5

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

Published: 2026-04-02Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31406

HIGH7.8

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

Published: 2026-04-06Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31408

HIGH8.8

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

Published: 2026-04-06Modified: 2026-06-17

CVSS 3.xHIGH 8.8

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

References

CVE-2026-31413

HIGH7.8

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

Published: 2026-04-12Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31414

CRITICAL9.8

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

Published: 2026-04-13Modified: 2026-06-17

CVSS 3.xCRITICAL 9.8

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

References

CVE-2026-31415

MEDIUM5.5

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

Published: 2026-04-13Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31416

MEDIUM5.5

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

Published: 2026-04-13Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31417

HIGH7.5

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

Published: 2026-04-13Modified: 2026-06-17

CVSS 3.xHIGH 7.5

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

References

CVE-2026-31418

MEDIUM5.5

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

Published: 2026-04-13Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31419

HIGH7.8

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

Published: 2026-04-13Modified: 2026-06-19

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31421

MEDIUM5.5

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

Published: 2026-04-13Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31422

MEDIUM5.5

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

Published: 2026-04-13Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31423

MEDIUM5.5

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

Published: 2026-04-13Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31424

MEDIUM5.5

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

Published: 2026-04-13Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31425

MEDIUM5.5

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

Published: 2026-04-13Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31426

HIGH7.0

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

Published: 2026-04-13Modified: 2026-06-17

CVSS 3.xHIGH 7.0

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

References

CVE-2026-31427

MEDIUM5.5

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

Published: 2026-04-13Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31428

MEDIUM5.5

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

Published: 2026-04-13Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31431

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31432

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.

Published: 2026-04-22Modified: 2026-06-19

CVSS 3.xHIGH 8.8

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

References

CVE-2026-31433

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.

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 8.8

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

References

CVE-2026-31434

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31435

HIGH8.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 8.8

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

References

CVE-2026-31436

CRITICAL9.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xCRITICAL 9.8

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

References

CVE-2026-31437

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31438

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31439

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31440

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31441

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31442

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31443

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31444

CRITICAL9.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xCRITICAL 9.8

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

References

CVE-2026-31445

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31446

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31447

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31448

CRITICAL9.4

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xCRITICAL 9.4

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

References

CVE-2026-31449

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-19

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31450

HIGH8.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 8.8

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

References

CVE-2026-31451

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31452

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31453

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31454

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31455

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31456

MEDIUM4.7

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 4.7

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

References

CVE-2026-31457

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31458

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31459

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31461

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31462

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31464

HIGH8.1

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 8.1

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

References

CVE-2026-31465

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31466

MEDIUM4.7

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 4.7

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

References

CVE-2026-31467

HIGH7.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.5

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

References

CVE-2026-31469

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31470

HIGH7.1

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.1

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

References

CVE-2026-31471

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31472

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31473

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31474

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31475

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31476

HIGH8.2

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 8.2

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

References

CVE-2026-31477

HIGH7.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.5

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

References

CVE-2026-31478

CRITICAL9.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xCRITICAL 9.8

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

References

CVE-2026-31479

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31480

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31482

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31483

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31485

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31486

HIGH7.1

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

Published: 2026-04-22Modified: 2026-06-19

CVSS 3.xHIGH 7.1

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

References

CVE-2026-31487

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31488

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31489

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-19

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31491

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31492

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31493

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31494

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31495

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31496

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31497

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31498

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31499

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31500

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31502

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31503

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31504

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31505

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31506

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31507

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31508

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31509

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31510

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31511

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31512

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31513

HIGH8.1

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 8.1

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

References

CVE-2026-31514

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31515

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31516

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31517

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31518

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31519

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31520

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31521

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31522

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31523

MEDIUM4.7

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 4.7

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

References

CVE-2026-31524

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31525

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31526

MEDIUM5.5

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31527

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31528

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31530

HIGH7.8

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

Published: 2026-04-22Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31554

HIGH7.8

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31555

MEDIUM5.5

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31556

MEDIUM5.5

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31557

HIGH7.5

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xHIGH 7.5

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

References

CVE-2026-31558

HIGH8.8

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xHIGH 8.8

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

References

CVE-2026-31559

MEDIUM5.5

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31561

MEDIUM5.5

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31562

MEDIUM5.5

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31563

HIGH7.5

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xHIGH 7.5

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

References

CVE-2026-31565

MEDIUM5.5

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31566

HIGH7.8

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31567

MEDIUM5.5

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31568

HIGH7.1

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xHIGH 7.1

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

References

CVE-2026-31569

HIGH7.3

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xHIGH 7.3

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

References

CVE-2026-31570

HIGH8.8

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xHIGH 8.8

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

References

CVE-2026-31571

MEDIUM5.5

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31572

MEDIUM4.7

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

Published: 2026-04-24Modified: 2026-06-17

CVSS 3.xMEDIUM 4.7

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

References

CVE-2026-31674

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: netfilter: ip6t_rt: reject oversized addrnr in rt_mt6_check() Reject rt match rules whose addrnr exceeds IP6T_RT_HOPS. rt_mt6() expects addrnr to stay within the bounds of rtinfo->addrs[]. Validate addrnr during rule installation so malformed rules are rejected before the match logic can use an out-of-range value.

Published: 2026-04-25Modified: 2026-06-17

CVSS 3.xHIGH 7.1

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

References

CVE-2026-31675

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net/sched: sch_netem: fix out-of-bounds access in packet corruption In netem_enqueue(), the packet corruption logic uses get_random_u32_below(skb_headlen(skb)) to select an index for modifying skb->data. When an AF_PACKET TX_RING sends fully non-linear packets over an IPIP tunnel, skb_headlen(skb) evaluates to 0. Passing 0 to get_random_u32_below() takes the variable-ceil slow path which returns an unconstrained 32-bit random integer. Using this unconstrained value as an offset into skb->data results in an out-of-bounds memory access. Fix this by verifying skb_headlen(skb) is non-zero before attempting to corrupt the linear data area. Fully non-linear packets will silently bypass the corruption logic.

Published: 2026-04-25Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31678

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: openvswitch: defer tunnel netdev_put to RCU release ovs_netdev_tunnel_destroy() may run after NETDEV_UNREGISTER already detached the device. Dropping the netdev reference in destroy can race with concurrent readers that still observe vport->dev. Do not release vport->dev in ovs_netdev_tunnel_destroy(). Instead, let vport_netdev_free() drop the reference from the RCU callback, matching the non-tunnel destroy path and avoiding additional synchronization under RTNL.

Published: 2026-04-25Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31679

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: openvswitch: validate MPLS set/set_masked payload length validate_set() accepted OVS_KEY_ATTR_MPLS as variable-sized payload for SET/SET_MASKED actions. In action handling, OVS expects fixed-size MPLS key data (struct ovs_key_mpls). Use the already normalized key_len (masked case included) and reject non-matching MPLS action key sizes. Reject invalid MPLS action payload lengths early.

Published: 2026-04-25Modified: 2026-06-17

CVSS 3.xHIGH 7.1

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

References

CVE-2026-31680

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: ipv6: flowlabel: defer exclusive option free until RCU teardown `ip6fl_seq_show()` walks the global flowlabel hash under the seq-file RCU read-side lock and prints `fl->opt->opt_nflen` when an option block is present. Exclusive flowlabels currently free `fl->opt` as soon as `fl->users` drops to zero in `fl_release()`. However, the surrounding `struct ip6_flowlabel` remains visible in the global hash table until later garbage collection removes it and `fl_free_rcu()` finally tears it down. A concurrent `/proc/net/ip6_flowlabel` reader can therefore race that early `kfree()` and dereference freed option state, triggering a crash in `ip6fl_seq_show()`. Fix this by keeping `fl->opt` alive until `fl_free_rcu()`. That matches the lifetime already required for the enclosing flowlabel while readers can still reach it under RCU.

Published: 2026-04-25Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31682

CRITICAL9.1

In the Linux kernel, the following vulnerability has been resolved: bridge: br_nd_send: linearize skb before parsing ND options br_nd_send() parses neighbour discovery options from ns->opt[] and assumes that these options are in the linear part of request. Its callers only guarantee that the ICMPv6 header and target address are available, so the option area can still be non-linear. Parsing ns->opt[] in that case can access data past the linear buffer. Linearize request before option parsing and derive ns from the linear network header.

Published: 2026-04-25Modified: 2026-06-17

CVSS 3.xCRITICAL 9.1

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

References

CVE-2026-31695

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: wifi: virt_wifi: remove SET_NETDEV_DEV to avoid use-after-free Currently we execute `SET_NETDEV_DEV(dev, &priv->lowerdev->dev)` for the virt_wifi net devices. However, unregistering a virt_wifi device in netdev_run_todo() can happen together with the device referenced by SET_NETDEV_DEV(). It can result in use-after-free during the ethtool operations performed on a virt_wifi device that is currently being unregistered. Such a net device can have the `dev.parent` field pointing to the freed memory, but ethnl_ops_begin() calls `pm_runtime_get_sync(dev->dev.parent)`. Let's remove SET_NETDEV_DEV for virt_wifi to avoid bugs like this: ================================================================== BUG: KASAN: slab-use-after-free in __pm_runtime_resume+0xe2/0xf0 Read of size 2 at addr ffff88810cfc46f8 by task pm/606 Call Trace: dump_stack_lvl+0x4d/0x70 print_report+0x170/0x4f3 ? pfxraw_spin_lock_irqsave+0x10/0x10 kasan_report+0xda/0x110 ? __pm_runtime_resume+0xe2/0xf0 ? __pm_runtime_resume+0xe2/0xf0 __pm_runtime_resume+0xe2/0xf0 ethnl_ops_begin+0x49/0x270 ethnl_set_features+0x23c/0xab0 ? __pfx_ethnl_set_features+0x10/0x10 ? kvm_sched_clock_read+0x11/0x20 ? local_clock_noinstr+0xf/0xf0 ? local_clock+0x10/0x30 ? kasan_save_track+0x25/0x60 ? __kasan_kmalloc+0x7f/0x90 ? genl_family_rcv_msg_attrs_parse.isra.0+0x150/0x2c0 genl_family_rcv_msg_doit+0x1e7/0x2c0 ? __pfx_genl_family_rcv_msg_doit+0x10/0x10 ? __pfx_cred_has_capability.isra.0+0x10/0x10 ? stack_trace_save+0x8e/0xc0 genl_rcv_msg+0x411/0x660 ? __pfx_genl_rcv_msg+0x10/0x10 ? __pfx_ethnl_set_features+0x10/0x10 netlink_rcv_skb+0x121/0x380 ? __pfx_genl_rcv_msg+0x10/0x10 ? __pfx_netlink_rcv_skb+0x10/0x10 ? __pfx_down_read+0x10/0x10 genl_rcv+0x23/0x30 netlink_unicast+0x60f/0x830 ? __pfx_netlink_unicast+0x10/0x10 ? pfx_alloc_skb+0x10/0x10 netlink_sendmsg+0x6ea/0xbc0 ? __pfx_netlink_sendmsg+0x10/0x10 ? __futex_queue+0x10b/0x1f0 ____sys_sendmsg+0x7a2/0x950 ? copy_msghdr_from_user+0x26b/0x430 ? pfx___sys_sendmsg+0x10/0x10 ? __pfx_copy_msghdr_from_user+0x10/0x10 ___sys_sendmsg+0xf8/0x180 ? pfx__sys_sendmsg+0x10/0x10 ? __pfx_futex_wait+0x10/0x10 ? fdget+0x2e4/0x4a0 __sys_sendmsg+0x11f/0x1c0 ? pfx_sys_sendmsg+0x10/0x10 do_syscall_64+0xe2/0x570 ? exc_page_fault+0x66/0xb0 entry_SYSCALL_64_after_hwframe+0x77/0x7f This fix may be combined with another one in the ethtool subsystem: https://lore.kernel.org/all/20260322075917.254874-1-alex.popov@linux.com/T/#u

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31720

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_uac1_legacy: validate control request size f_audio_complete() copies req->length bytes into a 4-byte stack variable: u32 data = 0; memcpy(&data, req->buf, req->length); req->length is derived from the host-controlled USB request path, which can lead to a stack out-of-bounds write. Validate req->actual against the expected payload size for the supported control selectors and decode only the expected amount of data. This avoids copying a host-influenced length into a fixed-size stack object.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31721

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_hid: move list and spinlock inits from bind to alloc There was an issue when you did the following: - setup and bind an hid gadget - open /dev/hidg0 - use the resulting fd in EPOLL_CTL_ADD - unbind the UDC - bind the UDC - use the fd in EPOLL_CTL_DEL When CONFIG_DEBUG_LIST was enabled, a list_del corruption was reported within remove_wait_queue (via ep_remove_wait_queue). After some debugging I found out that the queues, which f_hid registers via poll_wait were the problem. These were initialized using init_waitqueue_head inside hidg_bind. So effectively, the bind function re-initialized the queues while there were still items in them. The solution is to move the initialization from hidg_bind to hidg_alloc to extend their lifetimes to the lifetime of the function instance. Additionally, I found many other possibly problematic init calls in the bind function, which I moved as well.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31722

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_rndis: Fix net_device lifecycle with device_move The net_device is allocated during function instance creation and registered during the bind phase with the gadget device as its sysfs parent. When the function unbinds, the parent device is destroyed, but the net_device survives, resulting in dangling sysfs symlinks: console:/ # ls -l /sys/class/net/usb0 lrwxrwxrwx ... /sys/class/net/usb0 -> /sys/devices/platform/.../gadget.0/net/usb0 console:/ # ls -l /sys/devices/platform/.../gadget.0/net/usb0 ls: .../gadget.0/net/usb0: No such file or directory Use device_move() to reparent the net_device between the gadget device tree and /sys/devices/virtual across bind and unbind cycles. During the final unbind, calling device_move(NULL) moves the net_device to the virtual device tree before the gadget device is destroyed. On rebinding, device_move() reparents the device back under the new gadget, ensuring proper sysfs topology and power management ordering. To maintain compatibility with legacy composite drivers (e.g., multi.c), the borrowed_net flag is used to indicate whether the network device is shared and pre-registered during the legacy driver's bind phase.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31723

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_subset: Fix net_device lifecycle with device_move The net_device is allocated during function instance creation and registered during the bind phase with the gadget device as its sysfs parent. When the function unbinds, the parent device is destroyed, but the net_device survives, resulting in dangling sysfs symlinks: console:/ # ls -l /sys/class/net/usb0 lrwxrwxrwx ... /sys/class/net/usb0 -> /sys/devices/platform/.../gadget.0/net/usb0 console:/ # ls -l /sys/devices/platform/.../gadget.0/net/usb0 ls: .../gadget.0/net/usb0: No such file or directory Use device_move() to reparent the net_device between the gadget device tree and /sys/devices/virtual across bind and unbind cycles. During the final unbind, calling device_move(NULL) moves the net_device to the virtual device tree before the gadget device is destroyed. On rebinding, device_move() reparents the device back under the new gadget, ensuring proper sysfs topology and power management ordering. To maintain compatibility with legacy composite drivers (e.g., multi.c), the bound flag is used to indicate whether the network device is shared and pre-registered during the legacy driver's bind phase.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31724

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_eem: Fix net_device lifecycle with device_move The net_device is allocated during function instance creation and registered during the bind phase with the gadget device as its sysfs parent. When the function unbinds, the parent device is destroyed, but the net_device survives, resulting in dangling sysfs symlinks: console:/ # ls -l /sys/class/net/usb0 lrwxrwxrwx ... /sys/class/net/usb0 -> /sys/devices/platform/.../gadget.0/net/usb0 console:/ # ls -l /sys/devices/platform/.../gadget.0/net/usb0 ls: .../gadget.0/net/usb0: No such file or directory Use device_move() to reparent the net_device between the gadget device tree and /sys/devices/virtual across bind and unbind cycles. During the final unbind, calling device_move(NULL) moves the net_device to the virtual device tree before the gadget device is destroyed. On rebinding, device_move() reparents the device back under the new gadget, ensuring proper sysfs topology and power management ordering. To maintain compatibility with legacy composite drivers (e.g., multi.c), the bound flag is used to indicate whether the network device is shared and pre-registered during the legacy driver's bind phase.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31725

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_ecm: Fix net_device lifecycle with device_move The net_device is allocated during function instance creation and registered during the bind phase with the gadget device as its sysfs parent. When the function unbinds, the parent device is destroyed, but the net_device survives, resulting in dangling sysfs symlinks: console:/ # ls -l /sys/class/net/usb0 lrwxrwxrwx ... /sys/class/net/usb0 -> /sys/devices/platform/.../gadget.0/net/usb0 console:/ # ls -l /sys/devices/platform/.../gadget.0/net/usb0 ls: .../gadget.0/net/usb0: No such file or directory Use device_move() to reparent the net_device between the gadget device tree and /sys/devices/virtual across bind and unbind cycles. During the final unbind, calling device_move(NULL) moves the net_device to the virtual device tree before the gadget device is destroyed. On rebinding, device_move() reparents the device back under the new gadget, ensuring proper sysfs topology and power management ordering. To maintain compatibility with legacy composite drivers (e.g., multi.c), the bound flag is used to indicate whether the network device is shared and pre-registered during the legacy driver's bind phase.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31726

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: uvc: fix NULL pointer dereference during unbind race Commit b81ac4395bbe ("usb: gadget: uvc: allow for application to cleanly shutdown") introduced two stages of synchronization waits totaling 1500ms in uvc_function_unbind() to prevent several types of kernel panics. However, this timing-based approach is insufficient during power management (PM) transitions. When the PM subsystem starts freezing user space processes, the wait_event_interruptible_timeout() is aborted early, which allows the unbind thread to proceed and nullify the gadget pointer (cdev->gadget = NULL): [ 814.123447][ T947] configfs-gadget.g1 gadget.0: uvc: uvc_function_unbind() [ 814.178583][ T3173] PM: suspend entry (deep) [ 814.192487][ T3173] Freezing user space processes [ 814.197668][ T947] configfs-gadget.g1 gadget.0: uvc: uvc_function_unbind no clean disconnect, wait for release When the PM subsystem resumes or aborts the suspend and tasks are restarted, the V4L2 release path is executed and attempts to access the already nullified gadget pointer, triggering a kernel panic: [ 814.292597][ C0] PM: pm_system_irq_wakeup: 479 triggered dhdpcie_host_wake [ 814.386727][ T3173] Restarting tasks ... [ 814.403522][ T4558] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000030 [ 814.404021][ T4558] pc : usb_gadget_deactivate+0x14/0xf4 [ 814.404031][ T4558] lr : usb_function_deactivate+0x54/0x94 [ 814.404078][ T4558] Call trace: [ 814.404080][ T4558] usb_gadget_deactivate+0x14/0xf4 [ 814.404083][ T4558] usb_function_deactivate+0x54/0x94 [ 814.404087][ T4558] uvc_function_disconnect+0x1c/0x5c [ 814.404092][ T4558] uvc_v4l2_release+0x44/0xac [ 814.404095][ T4558] v4l2_release+0xcc/0x130 Address the race condition and NULL pointer dereference by: 1. State Synchronization (flag + mutex) Introduce a 'func_unbound' flag in struct uvc_device. This allows uvc_function_disconnect() to safely skip accessing the nullified cdev->gadget pointer. As suggested by Alan Stern, this flag is protected by a new mutex (uvc->lock) to ensure proper memory ordering and prevent instruction reordering or speculative loads. This mutex is also used to protect 'func_connected' for consistent state management. 2. Explicit Synchronization (completion) Use a completion to synchronize uvc_function_unbind() with the uvc_vdev_release() callback. This prevents Use-After-Free (UAF) by ensuring struct uvc_device is freed after all video device resources are released.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31727

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: u_ether: Fix NULL pointer deref in eth_get_drvinfo Commit ec35c1969650 ("usb: gadget: f_ncm: Fix net_device lifecycle with device_move") reparents the gadget device to /sys/devices/virtual during unbind, clearing the gadget pointer. If the userspace tool queries on the surviving interface during this detached window, this leads to a NULL pointer dereference. Unable to handle kernel NULL pointer dereference Call trace: eth_get_drvinfo+0x50/0x90 ethtool_get_drvinfo+0x5c/0x1f0 __dev_ethtool+0xaec/0x1fe0 dev_ethtool+0x134/0x2e0 dev_ioctl+0x338/0x560 Add a NULL check for dev->gadget in eth_get_drvinfo(). When detached, skip copying the fw_version and bus_info strings, which is natively handled by ethtool_get_drvinfo for empty strings.

Published: 2026-05-01Modified: 2026-06-19

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31728

MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: u_ether: Fix race between gether_disconnect and eth_stop A race condition between gether_disconnect() and eth_stop() leads to a NULL pointer dereference. Specifically, if eth_stop() is triggered concurrently while gether_disconnect() is tearing down the endpoints, eth_stop() attempts to access the cleared endpoint descriptor, causing the following NPE: Unable to handle kernel NULL pointer dereference Call trace: __dwc3_gadget_ep_enable+0x60/0x788 dwc3_gadget_ep_enable+0x70/0xe4 usb_ep_enable+0x60/0x15c eth_stop+0xb8/0x108 Because eth_stop() crashes while holding the dev->lock, the thread running gether_disconnect() fails to acquire the same lock and spins forever, resulting in a hardlockup: Core - Debugging Information for Hardlockup core(7) Call trace: queued_spin_lock_slowpath+0x94/0x488 _raw_spin_lock+0x64/0x6c gether_disconnect+0x19c/0x1e8 ncm_set_alt+0x68/0x1a0 composite_setup+0x6a0/0xc50 The root cause is that the clearing of dev->port_usb in gether_disconnect() is delayed until the end of the function. Move the clearing of dev->port_usb to the very beginning of gether_disconnect() while holding dev->lock. This cuts off the link immediately, ensuring eth_stop() will see dev->port_usb as NULL and safely bail out.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 4.7

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

References

CVE-2026-31729

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: usb: typec: ucsi: validate connector number in ucsi_notify_common() The connector number extracted from CCI via UCSI_CCI_CONNECTOR() is a 7-bit field (0-127) that is used to index into the connector array in ucsi_connector_change(). However, the array is only allocated for the number of connectors reported by the device (typically 2-4 entries). A malicious or malfunctioning device could report an out-of-range connector number in the CCI, causing an out-of-bounds array access in ucsi_connector_change(). Add a bounds check in ucsi_notify_common(), the central point where CCI is parsed after arriving from hardware, so that bogus connector numbers are rejected before they propagate further.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31730

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: misc: fastrpc: possible double-free of cctx->remote_heap fastrpc_init_create_static_process() may free cctx->remote_heap on the err_map path but does not clear the pointer. Later, fastrpc_rpmsg_remove() frees cctx->remote_heap again if it is non-NULL, which can lead to a double-free if the INIT_CREATE_STATIC ioctl hits the error path and the rpmsg device is subsequently removed/unbound. Clear cctx->remote_heap after freeing it in the error path to prevent the later cleanup from freeing it again. This issue was found by an in-house analysis workflow that extracts AST-based information and runs static checks, with LLM assistance for triage, and was confirmed by manual code review. No hardware testing was performed.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31731

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: thermal: core: Address thermal zone removal races with resume Since thermal_zone_pm_complete() and thermal_zone_device_resume() re-initialize the poll_queue delayed work for the given thermal zone, the cancel_delayed_work_sync() in thermal_zone_device_unregister() may miss some already running work items and the thermal zone may be freed prematurely [1]. There are two failing scenarios that both start with running thermal_pm_notify_complete() right before invoking thermal_zone_device_unregister() for one of the thermal zones. In the first scenario, there is a work item already running for the given thermal zone when thermal_pm_notify_complete() calls thermal_zone_pm_complete() for that thermal zone and it continues to run when thermal_zone_device_unregister() starts. Since the poll_queue delayed work has been re-initialized by thermal_pm_notify_complete(), the running work item will be missed by the cancel_delayed_work_sync() in thermal_zone_device_unregister() and if it continues to run past the freeing of the thermal zone object, a use-after-free will occur. In the second scenario, thermal_zone_device_resume() queued up by thermal_pm_notify_complete() runs right after the thermal_zone_exit() called by thermal_zone_device_unregister() has returned. The poll_queue delayed work is re-initialized by it before cancel_delayed_work_sync() is called by thermal_zone_device_unregister(), so it may continue to run after the freeing of the thermal zone object, which also leads to a use-after-free. Address the first failing scenario by ensuring that no thermal work items will be running when thermal_pm_notify_complete() is called. For this purpose, first move the cancel_delayed_work() call from thermal_zone_pm_complete() to thermal_zone_pm_prepare() to prevent new work from entering the workqueue going forward. Next, switch over to using a dedicated workqueue for thermal events and update the code in thermal_pm_notify() to flush that workqueue after thermal_pm_notify_prepare() has returned which will take care of all leftover thermal work already on the workqueue (that leftover work would do nothing useful anyway because all of the thermal zones have been flagged as suspended). The second failing scenario is addressed by adding a tz->state check to thermal_zone_device_resume() to prevent it from re-initializing the poll_queue delayed work if the thermal zone is going away. Note that the above changes will also facilitate relocating the suspend and resume of thermal zones closer to the suspend and resume of devices, respectively.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31732

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: gpio: Fix resource leaks on errors in gpiochip_add_data_with_key() Since commit aab5c6f20023 ("gpio: set device type for GPIO chips"), `gdev->dev.release` is unset. As a result, the reference count to `gdev->dev` isn't dropped on the error handling paths. Drop the reference on errors. Also reorder the instructions to make the error handling simpler. Now gpiochip_add_data_with_key() roughly looks like: >>> Some memory allocation. Go to ERR ZONE 1 on errors. >>> device_initialize(). gpiodev_release() takes over the responsibility for freeing the resources of `gdev->dev`. The subsequent error handling paths shouldn't go through ERR ZONE 1 again which leads to double free. >>> Some initialization mainly on `gdev`. >>> The rest of initialization. Go to ERR ZONE 2 on errors. >>> Chip registration success and exit. >>> ERR ZONE 2. gpio_device_put() and exit. >>> ERR ZONE 1.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31733

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: sched_ext: Fix stale direct dispatch state in ddsp_dsq_id @p->scx.ddsp_dsq_id can be left set (non-SCX_DSQ_INVALID) triggering a spurious warning in mark_direct_dispatch() when the next wakeup's ops.select_cpu() calls scx_bpf_dsq_insert(), such as: WARNING: kernel/sched/ext.c:1273 at scx_dsq_insert_commit+0xcd/0x140 The root cause is that ddsp_dsq_id was only cleared in dispatch_enqueue(), which is not reached in all paths that consume or cancel a direct dispatch verdict. Fix it by clearing it at the right places: - direct_dispatch(): cache the direct dispatch state in local variables and clear it before dispatch_enqueue() on the synchronous path. For the deferred path, the direct dispatch state must remain set until process_ddsp_deferred_locals() consumes them. - process_ddsp_deferred_locals(): cache the dispatch state in local variables and clear it before calling dispatch_to_local_dsq(), which may migrate the task to another rq. - do_enqueue_task(): clear the dispatch state on the enqueue path (local/global/bypass fallbacks), where the direct dispatch verdict is ignored. - dequeue_task_scx(): clear the dispatch state after dispatch_dequeue() to handle both the deferred dispatch cancellation and the holding_cpu race, covering all cases where a pending direct dispatch is cancelled. - scx_disable_task(): clear the direct dispatch state when transitioning a task out of the current scheduler. Waking tasks may have had the direct dispatch state set by the outgoing scheduler's ops.select_cpu() and then been queued on a wake_list via ttwu_queue_wakelist(), when SCX_OPS_ALLOW_QUEUED_WAKEUP is set. Such tasks are not on the runqueue and are not iterated by scx_bypass(), so their direct dispatch state won't be cleared. Without this clear, any subsequent SCX scheduler that tries to direct dispatch the task will trigger the WARN_ON_ONCE() in mark_direct_dispatch().

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31734

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: sched_ext: Fix is_bpf_migration_disabled() false negative on non-PREEMPT_RCU Since commit 8e4f0b1ebcf2 ("bpf: use rcu_read_lock_dont_migrate() for trampoline.c"), the BPF prolog (__bpf_prog_enter) calls migrate_disable() only when CONFIG_PREEMPT_RCU is enabled, via rcu_read_lock_dont_migrate(). Without CONFIG_PREEMPT_RCU, the prolog never touches migration_disabled, so migration_disabled == 1 always means the task is truly migration-disabled regardless of whether it is the current task. The old unconditional p == current check was a false negative in this case, potentially allowing a migration-disabled task to be dispatched to a remote CPU and triggering scx_error in task_can_run_on_remote_rq(). Only apply the p == current disambiguation when CONFIG_PREEMPT_RCU is enabled, where the ambiguity with the BPF prolog still exists.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31736

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: ethernet: mtk_ppe: avoid NULL deref when gmac0 is disabled If the gmac0 is disabled, the precheck for a valid ingress device will cause a NULL pointer deref and crash the system. This happens because eth->netdev[0] will be NULL but the code will directly try to access netdev_ops. Instead of just checking for the first net_device, it must be checked if any of the mtk_eth net_devices is matching the netdev_ops of the ingress device.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31737

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: ftgmac100: fix ring allocation unwind on open failure ftgmac100_alloc_rings() allocates rx_skbs, tx_skbs, rxdes, txdes, and rx_scratch in stages. On intermediate failures it returned -ENOMEM directly, leaking resources allocated earlier in the function. Rework the failure path to use staged local unwind labels and free allocated resources in reverse order before returning -ENOMEM. This matches common netdev allocation cleanup style.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31738

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: vxlan: validate ND option lengths in vxlan_na_create vxlan_na_create() walks ND options according to option-provided lengths. A malformed option can make the parser advance beyond the computed option span or use a too-short source LLADDR option payload. Validate option lengths against the remaining NS option area before advancing, and only read source LLADDR when the option is large enough for an Ethernet address.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31739

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: crypto: tegra - Add missing CRYPTO_ALG_ASYNC The tegra crypto driver failed to set the CRYPTO_ALG_ASYNC on its asynchronous algorithms, causing the crypto API to select them for users that request only synchronous algorithms. This causes crashes (at least). Fix this by adding the flag like what the other drivers do. Also remove the unnecessary CRYPTO_ALG_TYPE_* flags, since those just get ignored and overridden by the registration function anyway.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 8.8

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

References

CVE-2026-31740

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: counter: rz-mtu3-cnt: do not use struct rz_mtu3_channel's dev member The counter driver can use HW channels 1 and 2, while the PWM driver can use HW channels 0, 1, 2, 3, 4, 6, 7. The dev member is assigned both by the counter driver and the PWM driver for channels 1 and 2, to their own struct device instance, overwriting the previous value. The sub-drivers race to assign their own struct device pointer to the same struct rz_mtu3_channel's dev member. The dev member of struct rz_mtu3_channel is used by the counter sub-driver for runtime PM. Depending on the probe order of the counter and PWM sub-drivers, the dev member may point to the wrong struct device instance, causing the counter sub-driver to do runtime PM actions on the wrong device. To fix this, use the parent pointer of the counter, which is assigned during probe to the correct struct device, not the struct device pointer inside the shared struct rz_mtu3_channel.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31741

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: counter: rz-mtu3-cnt: prevent counter from being toggled multiple times Runtime PM counter is incremented / decremented each time the sysfs enable file is written to. If user writes 0 to the sysfs enable file multiple times, runtime PM usage count underflows, generating the following message. rz-mtu3-counter rz-mtu3-counter.0: Runtime PM usage count underflow! At the same time, hardware registers end up being accessed with clocks off in rz_mtu3_terminate_counter() to disable an already disabled channel. If user writes 1 to the sysfs enable file multiple times, runtime PM usage count will be incremented each time, requiring the same number of 0 writes to get it back to 0. If user writes 0 to the sysfs enable file while PWM is in progress, PWM is stopped without counter being the owner of the underlying MTU3 channel. Check against the cached count_is_enabled value and exit if the user is trying to set the same enable value.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31742

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: vt: discard stale unicode buffer on alt screen exit after resize When enter_alt_screen() saves vc_uni_lines into vc_saved_uni_lines and sets vc_uni_lines to NULL, a subsequent console resize via vc_do_resize() skips reallocating the unicode buffer because vc_uni_lines is NULL. However, vc_saved_uni_lines still points to the old buffer allocated for the original dimensions. When leave_alt_screen() later restores vc_saved_uni_lines, the buffer dimensions no longer match vc_rows/vc_cols. Any operation that iterates over the unicode buffer using the current dimensions (e.g. csi_J clearing the screen) will access memory out of bounds, causing a kernel oops: BUG: unable to handle page fault for address: 0x0000002000000020 RIP: 0010:csi_J+0x133/0x2d0 The faulting address 0x0000002000000020 is two adjacent u32 space characters (0x20) interpreted as a pointer, read from the row data area past the end of the 25-entry pointer array in a buffer allocated for 80x25 but accessed with 240x67 dimensions. Fix this by checking whether the console dimensions changed while in the alternate screen. If they did, free the stale saved buffer instead of restoring it. The unicode screen will be lazily rebuilt via vc_uniscr_check() when next needed.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31743

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: nvmem: zynqmp_nvmem: Fix buffer size in DMA and memcpy Buffer size used in dma allocation and memcpy is wrong. It can lead to undersized DMA buffer access and possible memory corruption. use correct buffer size in dma_alloc_coherent and memcpy.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31746

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: s390/zcrypt: Fix memory leak with CCA cards used as accelerator Tests showed that there is a memory leak if CCA cards are used as accelerator for clear key RSA requests (ME and CRT). With the last rework for the memory allocation the AP messages are allocated by ap_init_apmsg() but for some reason on two places (ME and CRT) the older allocation was still in place. So the first allocation simple was never freed.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31747

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: comedi: me4000: Fix potential overrun of firmware buffer `me4000_xilinx_download()` loads the firmware that was requested by `request_firmware()`. It is possible for it to overrun the source buffer because it blindly trusts the file format. It reads a data stream length from the first 4 bytes into variable `file_length` and reads the data stream contents of length `file_length` from offset 16 onwards. Add a test to ensure that the supplied firmware is long enough to contain the header and the data stream. On failure, log an error and return `-EINVAL`. Note: The firmware loading was totally broken before commit ac584af59945 ("staging: comedi: me4000: fix firmware downloading"), but that is the most sensible target for this fix.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31748

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: comedi: me_daq: Fix potential overrun of firmware buffer `me2600_xilinx_download()` loads the firmware that was requested by `request_firmware()`. It is possible for it to overrun the source buffer because it blindly trusts the file format. It reads a data stream length from the first 4 bytes into variable `file_length` and reads the data stream contents of length `file_length` from offset 16 onwards. Although it checks that the supplied firmware is at least 16 bytes long, it does not check that it is long enough to contain the data stream. Add a test to ensure that the supplied firmware is long enough to contain the header and the data stream. On failure, log an error and return `-EINVAL`.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31749

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: comedi: ni_atmio16d: Fix invalid clean-up after failed attach If the driver's COMEDI "attach" handler function (`atmio16d_attach()`) returns an error, the COMEDI core will call the driver's "detach" handler function (`atmio16d_detach()`) to clean up. This calls `reset_atmio16d()` unconditionally, but depending on where the error occurred in the attach handler, the device may not have been sufficiently initialized to call `reset_atmio16d()`. It uses `dev->iobase` as the I/O port base address and `dev->private` as the pointer to the COMEDI device's private data structure. `dev->iobase` may still be set to its initial value of 0, which would result in undesired writes to low I/O port addresses. `dev->private` may still be `NULL`, which would result in null pointer dereferences. Fix `atmio16d_detach()` by checking that `dev->private` is valid (non-null) before calling `reset_atmio16d()`. This implies that `dev->iobase` was set correctly since that is set up before `dev->private`.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31751

MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: comedi: dt2815: add hardware detection to prevent crash The dt2815 driver crashes when attached to I/O ports without actual hardware present. This occurs because syzkaller or users can attach the driver to arbitrary I/O addresses via COMEDI_DEVCONFIG ioctl. When no hardware exists at the specified port, inb() operations return 0xff (floating bus), but outb() operations can trigger page faults due to undefined behavior, especially under race conditions: BUG: unable to handle page fault for address: 000000007fffff90 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page RIP: 0010:dt2815_attach+0x6e0/0x1110 Add hardware detection by reading the status register before attempting any write operations. If the read returns 0xff, assume no hardware is present and fail the attach with -ENODEV. This prevents crashes from outb() operations on non-existent hardware.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 4.7

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

References

CVE-2026-31752

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: bridge: br_nd_send: validate ND option lengths br_nd_send() walks ND options according to option-provided lengths. A malformed option can make the parser advance beyond the computed option span or use a too-short source LLADDR option payload. Validate option lengths against the remaining NS option area before advancing, and only read source LLADDR when the option is large enough for an Ethernet address.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31754

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: cdns3: gadget: fix state inconsistency on gadget init failure When cdns3_gadget_start() fails, the DRD hardware is left in gadget mode while software state remains INACTIVE, creating hardware/software state inconsistency. When switching to host mode via sysfs: echo host > /sys/class/usb_role/13180000.usb-role-switch/role The role state is not set to CDNS_ROLE_STATE_ACTIVE due to the error, so cdns_role_stop() skips cleanup because state is still INACTIVE. This violates the DRD controller design specification (Figure22), which requires returning to idle state before switching roles. This leads to a synchronous external abort in xhci_gen_setup() when setting up the host controller: [ 516.440698] configfs-gadget 13180000.usb: failed to start g1: -19 [ 516.442035] cdns-usb3 13180000.usb: Failed to add gadget [ 516.443278] cdns-usb3 13180000.usb: set role 2 has failed ... [ 1301.375722] xhci-hcd xhci-hcd.1.auto: xHCI Host Controller [ 1301.377716] Internal error: synchronous external abort: 96000010 [#1] PREEMPT SMP [ 1301.382485] pc : xhci_gen_setup+0xa4/0x408 [ 1301.393391] backtrace: ... xhci_gen_setup+0xa4/0x408 <-- CRASH xhci_plat_setup+0x44/0x58 usb_add_hcd+0x284/0x678 ... cdns_role_set+0x9c/0xbc <-- Role switch Fix by calling cdns_drd_gadget_off() in the error path to properly clean up the DRD gadget state.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31755

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: cdns3: gadget: fix NULL pointer dereference in ep_queue When the gadget endpoint is disabled or not yet configured, the ep->desc pointer can be NULL. This leads to a NULL pointer dereference when __cdns3_gadget_ep_queue() is called, causing a kernel crash. Add a check to return -ESHUTDOWN if ep->desc is NULL, which is the standard return code for unconfigured endpoints. This prevents potential crashes when ep_queue is called on endpoints that are not ready.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31756

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: dwc2: gadget: Fix spin_lock/unlock mismatch in dwc2_hsotg_udc_stop() dwc2_gadget_exit_clock_gating() internally calls call_gadget() macro, which expects hsotg->lock to be held since it does spin_unlock/spin_lock around the gadget driver callback invocation. However, dwc2_hsotg_udc_stop() calls dwc2_gadget_exit_clock_gating() without holding the lock. This leads to: - spin_unlock on a lock that is not held (undefined behavior) - The lock remaining held after dwc2_gadget_exit_clock_gating() returns, causing a deadlock when spin_lock_irqsave() is called later in the same function. Fix this by acquiring hsotg->lock before calling dwc2_gadget_exit_clock_gating() and releasing it afterwards, which satisfies the locking requirement of the call_gadget() macro.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31757

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: misc: usbio: Fix URB memory leak on submit failure When usb_submit_urb() fails in usbio_probe(), the previously allocated URB is never freed, causing a memory leak. Fix this by jumping to err_free_urb label to properly release the URB on the error path.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31758

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: usb: usbtmc: Flush anchored URBs in usbtmc_release When calling usbtmc_release, pending anchored URBs must be flushed or killed to prevent use-after-free errors (e.g. in the HCD giveback path). Call usbtmc_draw_down() to allow anchored URBs to be completed.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31759

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: usb: ulpi: fix double free in ulpi_register_interface() error path When device_register() fails, ulpi_register() calls put_device() on ulpi->dev. The device release callback ulpi_dev_release() drops the OF node reference and frees ulpi, but the current error path in ulpi_register_interface() then calls kfree(ulpi) again, causing a double free. Let put_device() handle the cleanup through ulpi_dev_release() and avoid freeing ulpi again in ulpi_register_interface().

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31760

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: gpib: lpvo_usb: fix memory leak on disconnect The driver iterates over the registered USB interfaces during GPIB attach and takes a reference to their USB devices until a match is found. These references are never released which leads to a memory leak when devices are disconnected. Fix the leak by dropping the unnecessary references.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31761

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: iio: gyro: mpu3050: Move iio_device_register() to correct location iio_device_register() should be at the end of the probe function to prevent race conditions. Place iio_device_register() at the end of the probe function and place iio_device_unregister() accordingly.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31762

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: iio: gyro: mpu3050: Fix irq resource leak The interrupt handler is setup but only a few lines down if iio_trigger_register() fails the function returns without properly releasing the handler. Add cleanup goto to resolve resource leak. Detected by Smatch: drivers/iio/gyro/mpu3050-core.c:1128 mpu3050_trigger_probe() warn: 'irq' from request_threaded_irq() not released on lines: 1124.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31763

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: iio: gyro: mpu3050: Fix incorrect free_irq() variable The handler for the IRQ part of this driver is mpu3050->trig but, in the teardown free_irq() is called with handler mpu3050. Use correct IRQ handler when calling free_irq().

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31765

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Change AMDGPU_VA_RESERVED_TRAP_SIZE to 64KB Currently, AMDGPU_VA_RESERVED_TRAP_SIZE is hardcoded to 8KB, while KFD_CWSR_TBA_TMA_SIZE is defined as 2 * PAGE_SIZE. On systems with 4K pages, both values match (8KB), so allocation and reserved space are consistent. However, on 64K page-size systems, KFD_CWSR_TBA_TMA_SIZE becomes 128KB, while the reserved trap area remains 8KB. This mismatch causes the kernel to crash when running rocminfo or rccl unit tests. Kernel attempted to read user page (2) - exploit attempt? (uid: 1001) BUG: Kernel NULL pointer dereference on read at 0x00000002 Faulting instruction address: 0xc0000000002c8a64 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries CPU: 34 UID: 1001 PID: 9379 Comm: rocminfo Tainted: G E 6.19.0-rc4-amdgpu-00320-gf23176405700 #56 VOLUNTARY Tainted: [E]=UNSIGNED_MODULE Hardware name: IBM,9105-42A POWER10 (architected) 0x800200 0xf000006 of:IBM,FW1060.30 (ML1060_896) hv:phyp pSeries NIP: c0000000002c8a64 LR: c00000000125dbc8 CTR: c00000000125e730 REGS: c0000001e0957580 TRAP: 0300 Tainted: G E MSR: 8000000000009033 CR: 24008268 XER: 00000036 CFAR: c00000000125dbc4 DAR: 0000000000000002 DSISR: 40000000 IRQMASK: 1 GPR00: c00000000125d908 c0000001e0957820 c0000000016e8100 c00000013d814540 GPR04: 0000000000000002 c00000013d814550 0000000000000045 0000000000000000 GPR08: c00000013444d000 c00000013d814538 c00000013d814538 0000000084002268 GPR12: c00000000125e730 c000007e2ffd5f00 ffffffffffffffff 0000000000020000 GPR16: 0000000000000000 0000000000000002 c00000015f653000 0000000000000000 GPR20: c000000138662400 c00000013d814540 0000000000000000 c00000013d814500 GPR24: 0000000000000000 0000000000000002 c0000001e0957888 c0000001e0957878 GPR28: c00000013d814548 0000000000000000 c00000013d814540 c0000001e0957888 NIP [c0000000002c8a64] __mutex_add_waiter+0x24/0xc0 LR [c00000000125dbc8] __mutex_lock.constprop.0+0x318/0xd00 Call Trace: 0xc0000001e0957890 (unreliable) __mutex_lock.constprop.0+0x58/0xd00 amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x6fc/0xb60 [amdgpu] kfd_process_alloc_gpuvm+0x54/0x1f0 [amdgpu] kfd_process_device_init_cwsr_dgpu+0xa4/0x1a0 [amdgpu] kfd_process_device_init_vm+0xd8/0x2e0 [amdgpu] kfd_ioctl_acquire_vm+0xd0/0x130 [amdgpu] kfd_ioctl+0x514/0x670 [amdgpu] sys_ioctl+0x134/0x180 system_call_exception+0x114/0x300 system_call_vectored_common+0x15c/0x2ec This patch changes AMDGPU_VA_RESERVED_TRAP_SIZE to 64 KB and KFD_CWSR_TBA_TMA_SIZE to the AMD GPU page size. This means we reserve 64 KB for the trap in the address space, but only allocate 8 KB within it. With this approach, the allocation size never exceeds the reserved area. (cherry picked from commit 31b8de5e55666f26ea7ece5f412b83eab3f56dbb)

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31766

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: validate doorbell_offset in user queue creation amdgpu_userq_get_doorbell_index() passes the user-provided doorbell_offset to amdgpu_doorbell_index_on_bar() without bounds checking. An arbitrarily large doorbell_offset can cause the calculated doorbell index to fall outside the allocated doorbell BO, potentially corrupting kernel doorbell space. Validate that doorbell_offset falls within the doorbell BO before computing the BAR index, using u64 arithmetic to prevent overflow. (cherry picked from commit de1ef4ffd70e1d15f0bf584fd22b1f28cbd5e2ec)

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.1

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

References

CVE-2026-31767

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/i915/dsi: Don't do DSC horizontal timing adjustments in command mode Stop adjusting the horizontal timing values based on the compression ratio in command mode. Bspec seems to be telling us to do this only in video mode, and this is also how the Windows driver does things. This should also fix a div-by-zero on some machines because the adjusted htotal ends up being so small that we end up with line_time_us==0 when trying to determine the vtotal value in command mode. Note that this doesn't actually make the display on the Huawei Matebook E work, but at least the kernel no longer explodes when the driver loads. (cherry picked from commit 0b475e91ecc2313207196c6d7fd5c53e1a878525)

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31768

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: iio: adc: ti-adc161s626: use DMA-safe memory for spi_read() Add a DMA-safe buffer and use it for spi_read() instead of a stack memory. All SPI buffers must be DMA-safe. Since we only need up to 3 bytes, we just use a u8[] instead of be16 and be32 and change the conversion functions appropriately.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31769

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: gpib: fix use-after-free in IO ioctl handlers The IBRD, IBWRT, IBCMD, and IBWAIT ioctl handlers use a gpib_descriptor pointer after board->big_gpib_mutex has been released. A concurrent IBCLOSEDEV ioctl can free the descriptor via close_dev_ioctl() during this window, causing a use-after-free. The IO handlers (read_ioctl, write_ioctl, command_ioctl) explicitly release big_gpib_mutex before calling their handler. wait_ioctl() is called with big_gpib_mutex held, but ibwait() releases it internally when wait_mask is non-zero. In all four cases, the descriptor pointer obtained from handle_to_descriptor() becomes unprotected. Fix this by introducing a kernel-only descriptor_busy reference count in struct gpib_descriptor. Each handler atomically increments descriptor_busy under file_priv->descriptors_mutex before releasing the lock, and decrements it when done. close_dev_ioctl() checks descriptor_busy under the same lock and rejects the close with -EBUSY if the count is non-zero. A reference count rather than a simple flag is necessary because multiple handlers can operate on the same descriptor concurrently (e.g. IBRD and IBWAIT on the same handle from different threads). A separate counter is needed because io_in_progress can be cleared from unprivileged userspace via the IBWAIT ioctl (through general_ibstatus() with set_mask containing CMPL), which would allow an attacker to bypass a check based solely on io_in_progress. The new descriptor_busy counter is only modified by the kernel IO paths. The lock ordering is consistent (big_gpib_mutex -> descriptors_mutex) and the handlers only hold descriptors_mutex briefly during the lookup, so there is no deadlock risk and no impact on IO throughput.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31770

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: hwmon: (occ) Fix division by zero in occ_show_power_1() In occ_show_power_1() case 1, the accumulator is divided by update_tag without checking for zero. If no samples have been collected yet (e.g. during early boot when the sensor block is included but hasn't been updated), update_tag is zero, causing a kernel divide-by-zero crash. The 2019 fix in commit 211186cae14d ("hwmon: (occ) Fix division by zero issue") only addressed occ_get_powr_avg() used by occ_show_power_2() and occ_show_power_a0(). This separate code path in occ_show_power_1() was missed. Fix this by reusing the existing occ_get_powr_avg() helper, which already handles the zero-sample case and uses mul_u64_u32_div() to multiply before dividing for better precision. Move the helper above occ_show_power_1() so it is visible at the call site. [groeck: Fix alignment problems reported by checkpatch]

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31772

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_sync: fix stack buffer overflow in hci_le_big_create_sync hci_le_big_create_sync() uses DEFINE_FLEX to allocate a struct hci_cp_le_big_create_sync on the stack with room for 0x11 (17) BIS entries. However, conn->num_bis can hold up to HCI_MAX_ISO_BIS (31) entries — validated against ISO_MAX_NUM_BIS (0x1f) in the caller hci_conn_big_create_sync(). When conn->num_bis is between 18 and 31, the memcpy that copies conn->bis into cp->bis writes up to 14 bytes past the stack buffer, corrupting adjacent stack memory. This is trivially reproducible: binding an ISO socket with bc_num_bis = ISO_MAX_NUM_BIS (31) and calling listen() will eventually trigger hci_le_big_create_sync() from the HCI command sync worker, causing a KASAN-detectable stack-out-of-bounds write: BUG: KASAN: stack-out-of-bounds in hci_le_big_create_sync+0x256/0x3b0 Write of size 31 at addr ffffc90000487b48 by task kworker/u9:0/71 Fix this by changing the DEFINE_FLEX count from the incorrect 0x11 to HCI_MAX_ISO_BIS, which matches the maximum number of BIS entries that conn->bis can actually carry.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31773

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: SMP: derive legacy responder STK authentication from MITM state The legacy responder path in smp_random() currently labels the stored STK as authenticated whenever pending_sec_level is BT_SECURITY_HIGH. That reflects what the local service requested, not what the pairing flow actually achieved. For Just Works/Confirm legacy pairing, SMP_FLAG_MITM_AUTH stays clear and the resulting STK should remain unauthenticated even if the local side requested HIGH security. Use the established MITM state when storing the responder STK so the key metadata matches the pairing result. This also keeps the legacy path aligned with the Secure Connections code, which already treats JUST_WORKS/JUST_CFM as unauthenticated.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 8.8

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

References

CVE-2026-31774

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: io_uring/net: fix slab-out-of-bounds read in io_bundle_nbufs() sqe->len is __u32 but gets stored into sr->len which is int. When userspace passes sqe->len values exceeding INT_MAX (e.g. 0xFFFFFFFF), sr->len overflows to a negative value. This negative value propagates through the bundle recv/send path: 1. io_recv(): sel.val = sr->len (ssize_t gets -1) 2. io_recv_buf_select(): arg.max_len = sel->val (size_t gets 0xFFFFFFFFFFFFFFFF) 3. io_ring_buffers_peek(): buf->len is not clamped because max_len is astronomically large 4. iov[].iov_len = 0xFFFFFFFF flows into io_bundle_nbufs() 5. io_bundle_nbufs(): min_t(int, 0xFFFFFFFF, ret) yields -1, causing ret to increase instead of decrease, creating an infinite loop that reads past the allocated iov[] array This results in a slab-out-of-bounds read in io_bundle_nbufs() from the kmalloc-64 slab, as nbufs increments past the allocated iovec entries. BUG: KASAN: slab-out-of-bounds in io_bundle_nbufs+0x128/0x160 Read of size 8 at addr ffff888100ae05c8 by task exp/145 Call Trace: io_bundle_nbufs+0x128/0x160 io_recv_finish+0x117/0xe20 io_recv+0x2db/0x1160 Fix this by rejecting negative sr->len values early in both io_sendmsg_prep() and io_recvmsg_prep(). Since sqe->len is __u32, any value > INT_MAX indicates overflow and is not a valid length.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.1

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

References

CVE-2026-31778

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: ALSA: caiaq: fix stack out-of-bounds read in init_card The loop creates a whitespace-stripped copy of the card shortname where `len < sizeof(card->id)` is used for the bounds check. Since sizeof(card->id) is 16 and the local id buffer is also 16 bytes, writing 16 non-space characters fills the entire buffer, overwriting the terminating nullbyte. When this non-null-terminated string is later passed to snd_card_set_id() -> copy_valid_id_string(), the function scans forward with `while (*nid && ...)` and reads past the end of the stack buffer, reading the contents of the stack. A USB device with a product name containing many non-ASCII, non-space characters (e.g. multibyte UTF-8) will reliably trigger this as follows: BUG: KASAN: stack-out-of-bounds in copy_valid_id_string sound/core/init.c:696 [inline] BUG: KASAN: stack-out-of-bounds in snd_card_set_id_no_lock+0x698/0x74c sound/core/init.c:718 The off-by-one has been present since commit bafeee5b1f8d ("ALSA: snd_usb_caiaq: give better shortname") from June 2009 (v2.6.31-rc1), which first introduced this whitespace-stripping loop. The original code never accounted for the null terminator when bounding the copy. Fix this by changing the loop bound to `sizeof(card->id) - 1`, ensuring at least one byte remains as the null terminator.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.1

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

References

CVE-2026-31779

HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: mvm: fix potential out-of-bounds read in iwl_mvm_nd_match_info_handler() The memcpy function assumes the dynamic array notif->matches is at least as large as the number of bytes to copy. Otherwise, results->matches may contain unwanted data. To guarantee safety, extend the validation in one of the checks to ensure sufficient packet length. Found by Linux Verification Center (linuxtesting.org) with SVACE.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 8.1

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

References

CVE-2026-31780

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: wifi: wilc1000: fix u8 overflow in SSID scan buffer size calculation The variable valuesize is declared as u8 but accumulates the total length of all SSIDs to scan. Each SSID contributes up to 33 bytes (IEEE80211_MAX_SSID_LEN + 1), and with WILC_MAX_NUM_PROBED_SSID (10) SSIDs the total can reach 330, which wraps around to 74 when stored in a u8. This causes kmalloc to allocate only 75 bytes while the subsequent memcpy writes up to 331 bytes into the buffer, resulting in a 256-byte heap buffer overflow. Widen valuesize from u8 to u32 to accommodate the full range.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31781

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/ioc32: stop speculation on the drm_compat_ioctl path The drm compat ioctl path takes a user controlled pointer, and then dereferences it into a table of function pointers, the signature method of spectre problems. Fix this up by calling array_index_nospec() on the index to the function pointer list.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31782

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: perf/x86: Fix potential bad container_of in intel_pmu_hw_config Auto counter reload may have a group of events with software events present within it. The software event PMU isn't the x86_hybrid_pmu and a container_of operation in intel_pmu_set_acr_caused_constr (via the hybrid helper) could cause out of bound memory reads. Avoid this by guarding the call to intel_pmu_set_acr_caused_constr with an is_x86_event check.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-31783

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: spi: amlogic: spifc-a4: unregister ECC engine on probe failure and remove() callback aml_sfc_probe() registers the on-host NAND ECC engine, but teardown was missing from both probe unwind and remove-time cleanup. Add a devm cleanup action after successful registration so nand_ecc_unregister_on_host_hw_engine() runs automatically on probe failures and during device removal.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-31784

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/xe/pxp: Clear restart flag in pxp_start after jumping back If we don't clear the flag we'll keep jumping back at the beginning of the function once we reach the end. (cherry picked from commit 0850ec7bb2459602351639dccf7a68a03c9d1ee0)

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43004

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: spi: stm32-ospi: Fix resource leak in remove() callback The remove() callback returned early if pm_runtime_resume_and_get() failed, skipping the cleanup of spi controller and other resources. Remove the early return so cleanup completes regardless of PM resume result.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43005

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: hwmon: (tps53679) Fix array access with zero-length block read i2c_smbus_read_block_data() can return 0, indicating a zero-length read. When this happens, tps53679_identify_chip() accesses buf[ret - 1] which is buf[-1], reading one byte before the buffer on the stack. Fix by changing the check from "ret < 0" to "ret <= 0", treating a zero-length read as an error (-EIO), which prevents the out-of-bounds array access. Also fix a typo in the adjacent comment: "if present" instead of duplicate "if".

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.1

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

References

CVE-2026-43006

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: io_uring/rsrc: reject zero-length fixed buffer import validate_fixed_range() admits buf_addr at the exact end of the registered region when len is zero, because the check uses strict greater-than (buf_end > imu->ubuf + imu->len). io_import_fixed() then computes offset == imu->len, which causes the bvec skip logic to advance past the last bio_vec entry and read bv_offset from out-of-bounds slab memory. Return early from io_import_fixed() when len is zero. A zero-length import has no data to transfer and should not walk the bvec array at all. BUG: KASAN: slab-out-of-bounds in io_import_reg_buf+0x697/0x7f0 Read of size 4 at addr ffff888002bcc254 by task poc/103 Call Trace: io_import_reg_buf+0x697/0x7f0 io_write_fixed+0xd9/0x250 __io_issue_sqe+0xad/0x710 io_issue_sqe+0x7d/0x1100 io_submit_sqes+0x86a/0x23c0 __do_sys_io_uring_enter+0xa98/0x1590 Allocated by task 103: The buggy address is located 12 bytes to the right of allocated 584-byte region [ffff888002bcc000, ffff888002bcc248)

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.1

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

References

CVE-2026-43007

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: accel/qaic: Handle DBC deactivation if the owner went away When a DBC is released, the device sends a QAIC_TRANS_DEACTIVATE_FROM_DEV transaction to the host over the QAIC_CONTROL MHI channel. QAIC handles this by calling decode_deactivate() to release the resources allocated for that DBC. Since that handling is done in the qaic_manage_ioctl() context, if the user goes away before receiving and handling the deactivation, the host will be out-of-sync with the DBCs available for use, and the DBC resources will not be freed unless the device is removed. If another user loads and requests to activate a network, then the device assigns the same DBC to that network, QAIC will "indefinitely" wait for dbc->in_use = false, leading the user process to hang. As a solution to this, handle QAIC_TRANS_DEACTIVATE_FROM_DEV transactions that are received after the user has gone away.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43010

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: bpf: Reject sleepable kprobe_multi programs at attach time kprobe.multi programs run in atomic/RCU context and cannot sleep. However, bpf_kprobe_multi_link_attach() did not validate whether the program being attached had the sleepable flag set, allowing sleepable helpers such as bpf_copy_from_user() to be invoked from a non-sleepable context. This causes a "sleeping function called from invalid context" splat: BUG: sleeping function called from invalid context at ./include/linux/uaccess.h:169 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1787, name: sudo preempt_count: 1, expected: 0 RCU nest depth: 2, expected: 0 Fix this by rejecting sleepable programs early in bpf_kprobe_multi_link_attach(), before any further processing.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43011

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: net/x25: Fix potential double free of skb When alloc_skb fails in x25_queue_rx_frame it calls kfree_skb(skb) at line 48 and returns 1 (error). This error propagates back through the call chain: x25_queue_rx_frame returns 1 | v x25_state3_machine receives the return value 1 and takes the else branch at line 278, setting queued=0 and returning 0 | v x25_process_rx_frame returns queued=0 | v x25_backlog_rcv at line 452 sees queued=0 and calls kfree_skb(skb) again This would free the same skb twice. Looking at x25_backlog_rcv: net/x25/x25_in.c:x25_backlog_rcv() { ... queued = x25_process_rx_frame(sk, skb); ... if (!queued) kfree_skb(skb); }

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xCRITICAL 9.8

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

References

CVE-2026-43012

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Fix switchdev mode rollback in case of failure If for some internal reason switchdev mode fails, we rollback to legacy mode, before this patch, rollback will unregister the uplink netdev and leave it unregistered causing the below kernel bug. To fix this, we need to avoid netdev unregister by setting the proper rollback flag 'MLX5_PRIV_FLAGS_SWITCH_LEGACY' to indicate legacy mode. devlink (431) used greatest stack depth: 11048 bytes left mlx5_core 0000:00:03.0: E-Switch: Disable: mode(LEGACY), nvfs(0), \ necvfs(0), active vports(0) mlx5_core 0000:00:03.0: E-Switch: Supported tc chains and prios offload mlx5_core 0000:00:03.0: Loading uplink representor for vport 65535 mlx5_core 0000:00:03.0: mlx5_cmd_out_err:816:(pid 456): \ QUERY_HCA_CAP(0x100) op_mod(0x0) failed, \ status bad parameter(0x3), syndrome (0x3a3846), err(-22) mlx5_core 0000:00:03.0 enp0s3np0 (unregistered): Unloading uplink \ representor for vport 65535 ------------[ cut here ]------------ kernel BUG at net/core/dev.c:12070! Oops: invalid opcode: 0000 [#1] SMP NOPTI CPU: 2 UID: 0 PID: 456 Comm: devlink Not tainted 6.16.0-rc3+ \ #9 PREEMPT(voluntary) RIP: 0010:unregister_netdevice_many_notify+0x123/0xae0 ... Call Trace: [ 90.923094] unregister_netdevice_queue+0xad/0xf0 [ 90.923323] unregister_netdev+0x1c/0x40 [ 90.923522] mlx5e_vport_rep_unload+0x61/0xc6 [ 90.923736] esw_offloads_enable+0x8e6/0x920 [ 90.923947] mlx5_eswitch_enable_locked+0x349/0x430 [ 90.924182] ? is_mp_supported+0x57/0xb0 [ 90.924376] mlx5_devlink_eswitch_mode_set+0x167/0x350 [ 90.924628] devlink_nl_eswitch_set_doit+0x6f/0xf0 [ 90.924862] genl_family_rcv_msg_doit+0xe8/0x140 [ 90.925088] genl_rcv_msg+0x18b/0x290 [ 90.925269] ? __pfx_devlink_nl_pre_doit+0x10/0x10 [ 90.925506] ? __pfx_devlink_nl_eswitch_set_doit+0x10/0x10 [ 90.925766] ? __pfx_devlink_nl_post_doit+0x10/0x10 [ 90.926001] ? __pfx_genl_rcv_msg+0x10/0x10 [ 90.926206] netlink_rcv_skb+0x52/0x100 [ 90.926393] genl_rcv+0x28/0x40 [ 90.926557] netlink_unicast+0x27d/0x3d0 [ 90.926749] netlink_sendmsg+0x1f7/0x430 [ 90.926942] __sys_sendto+0x213/0x220 [ 90.927127] ? __sys_recvmsg+0x6a/0xd0 [ 90.927312] __x64_sys_sendto+0x24/0x30 [ 90.927504] do_syscall_64+0x50/0x1c0 [ 90.927687] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 90.927929] RIP: 0033:0x7f7d0363e047

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43013

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net/mlx5: lag: Check for LAG device before creating debugfs __mlx5_lag_dev_add_mdev() may return 0 (success) even when an error occurs that is handled gracefully. Consequently, the initialization flow proceeds to call mlx5_ldev_add_debugfs() even when there is no valid LAG context. mlx5_ldev_add_debugfs() blindly created the debugfs directory and attributes. This exposed interfaces (like the members file) that rely on a valid ldev pointer, leading to potential NULL pointer dereferences if accessed when ldev is NULL. Add a check to verify that mlx5_lag_dev(dev) returns a valid pointer before attempting to create the debugfs entries.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43014

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: macb: properly unregister fixed rate clocks The additional resources allocated with clk_register_fixed_rate() need to be released with clk_unregister_fixed_rate(), otherwise they are lost.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43015

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: macb: fix clk handling on PCI glue driver removal platform_device_unregister() may still want to use the registered clks during runtime resume callback. Note that there is a commit d82d5303c4c5 ("net: macb: fix use after free on rmmod") that addressed the similar problem of clk vs platform device unregistration but just moved the bug to another place. Save the pointers to clks into local variables for reuse after platform device is unregistered. BUG: KASAN: use-after-free in clk_prepare+0x5a/0x60 Read of size 8 at addr ffff888104f85e00 by task modprobe/597 CPU: 2 PID: 597 Comm: modprobe Not tainted 6.1.164+ #114 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.1-0-g3208b098f51a-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack_lvl+0x8d/0xba print_report+0x17f/0x496 kasan_report+0xd9/0x180 clk_prepare+0x5a/0x60 macb_runtime_resume+0x13d/0x410 [macb] pm_generic_runtime_resume+0x97/0xd0 __rpm_callback+0xc8/0x4d0 rpm_callback+0xf6/0x230 rpm_resume+0xeeb/0x1a70 __pm_runtime_resume+0xb4/0x170 bus_remove_device+0x2e3/0x4b0 device_del+0x5b3/0xdc0 platform_device_del+0x4e/0x280 platform_device_unregister+0x11/0x50 pci_device_remove+0xae/0x210 device_remove+0xcb/0x180 device_release_driver_internal+0x529/0x770 driver_detach+0xd4/0x1a0 bus_remove_driver+0x135/0x260 driver_unregister+0x72/0xb0 pci_unregister_driver+0x26/0x220 __do_sys_delete_module+0x32e/0x550 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Allocated by task 519: kasan_save_stack+0x2c/0x50 kasan_set_track+0x21/0x30 __kasan_kmalloc+0x8e/0x90 __clk_register+0x458/0x2890 clk_hw_register+0x1a/0x60 __clk_hw_register_fixed_rate+0x255/0x410 clk_register_fixed_rate+0x3c/0xa0 macb_probe+0x1d8/0x42e [macb_pci] local_pci_probe+0xd7/0x190 pci_device_probe+0x252/0x600 really_probe+0x255/0x7f0 __driver_probe_device+0x1ee/0x330 driver_probe_device+0x4c/0x1f0 __driver_attach+0x1df/0x4e0 bus_for_each_dev+0x15d/0x1f0 bus_add_driver+0x486/0x5e0 driver_register+0x23a/0x3d0 do_one_initcall+0xfd/0x4d0 do_init_module+0x18b/0x5a0 load_module+0x5663/0x7950 __do_sys_finit_module+0x101/0x180 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Freed by task 597: kasan_save_stack+0x2c/0x50 kasan_set_track+0x21/0x30 kasan_save_free_info+0x2a/0x50 __kasan_slab_free+0x106/0x180 __kmem_cache_free+0xbc/0x320 clk_unregister+0x6de/0x8d0 macb_remove+0x73/0xc0 [macb_pci] pci_device_remove+0xae/0x210 device_remove+0xcb/0x180 device_release_driver_internal+0x529/0x770 driver_detach+0xd4/0x1a0 bus_remove_driver+0x135/0x260 driver_unregister+0x72/0xb0 pci_unregister_driver+0x26/0x220 __do_sys_delete_module+0x32e/0x550 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43016

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bpf: sockmap: Fix use-after-free of sk->sk_socket in sk_psock_verdict_data_ready(). syzbot reported use-after-free of AF_UNIX socket's sk->sk_socket in sk_psock_verdict_data_ready(). [0] In unix_stream_sendmsg(), the peer socket's ->sk_data_ready() is called after dropping its unix_state_lock(). Although the sender socket holds the peer's refcount, it does not prevent the peer's sock_orphan(), and the peer's sk_socket might be freed after one RCU grace period. Let's fetch the peer's sk->sk_socket and sk->sk_socket->ops under RCU in sk_psock_verdict_data_ready(). [0]: BUG: KASAN: slab-use-after-free in sk_psock_verdict_data_ready+0xec/0x590 net/core/skmsg.c:1278 Read of size 8 at addr ffff8880594da860 by task syz.4.1842/11013 CPU: 1 UID: 0 PID: 11013 Comm: syz.4.1842 Not tainted syzkaller #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2026 Call Trace: dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xba/0x230 mm/kasan/report.c:482 kasan_report+0x117/0x150 mm/kasan/report.c:595 sk_psock_verdict_data_ready+0xec/0x590 net/core/skmsg.c:1278 unix_stream_sendmsg+0x8a3/0xe80 net/unix/af_unix.c:2482 sock_sendmsg_nosec net/socket.c:721 [inline] __sock_sendmsg net/socket.c:736 [inline] ____sys_sendmsg+0x972/0x9f0 net/socket.c:2585 ___sys_sendmsg+0x2a5/0x360 net/socket.c:2639 __sys_sendmsg net/socket.c:2671 [inline] __do_sys_sendmsg net/socket.c:2676 [inline] __se_sys_sendmsg net/socket.c:2674 [inline] __x64_sys_sendmsg+0x1bd/0x2a0 net/socket.c:2674 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7facf899c819 Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007facf9827028 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007facf8c15fa0 RCX: 00007facf899c819 RDX: 0000000000000000 RSI: 0000200000000500 RDI: 0000000000000004 RBP: 00007facf8a32c91 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007facf8c16038 R14: 00007facf8c15fa0 R15: 00007ffd41b01c78 Allocated by task 11013: kasan_save_stack mm/kasan/common.c:57 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:78 unpoison_slab_object mm/kasan/common.c:340 [inline] __kasan_slab_alloc+0x6c/0x80 mm/kasan/common.c:366 kasan_slab_alloc include/linux/kasan.h:253 [inline] slab_post_alloc_hook mm/slub.c:4538 [inline] slab_alloc_node mm/slub.c:4866 [inline] kmem_cache_alloc_lru_noprof+0x2b8/0x640 mm/slub.c:4885 sock_alloc_inode+0x28/0xc0 net/socket.c:316 alloc_inode+0x6a/0x1b0 fs/inode.c:347 new_inode_pseudo include/linux/fs.h:3003 [inline] sock_alloc net/socket.c:631 [inline] __sock_create+0x12d/0x9d0 net/socket.c:1562 sock_create net/socket.c:1656 [inline] __sys_socketpair+0x1c4/0x560 net/socket.c:1803 __do_sys_socketpair net/socket.c:1856 [inline] __se_sys_socketpair net/socket.c:1853 [inline] __x64_sys_socketpair+0x9b/0xb0 net/socket.c:1853 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f Freed by task 15: kasan_save_stack mm/kasan/common.c:57 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:78 kasan_save_free_info+0x46/0x50 mm/kasan/generic.c:584 poison_slab_object mm/kasan/common.c:253 [inline] __kasan_slab_free+0x5c/0x80 mm/kasan/common.c:285 kasan_slab_free include/linux/kasan.h:235 [inline] slab_free_hook mm/slub.c:2685 [inline] slab_free mm/slub.c:6165 [inline] kmem_cache_free+0x187/0x630 mm/slub.c:6295 rcu_do_batch kernel/rcu/tree.c: ---truncated---

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43017

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: MGMT: validate mesh send advertising payload length mesh_send() currently bounds MGMT_OP_MESH_SEND by total command length, but it never verifies that the bytes supplied for the flexible adv_data[] array actually match the embedded adv_data_len field. MGMT_MESH_SEND_SIZE only covers the fixed header, so a truncated command can still pass the existing 20..50 byte range check and later drive the async mesh send path past the end of the queued command buffer. Keep rejecting zero-length and oversized advertising payloads, but validate adv_data_len explicitly and require the command length to exactly match the flexible array size before queueing the request.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43018

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_event: fix potential UAF in hci_le_remote_conn_param_req_evt hci_conn lookup and field access must be covered by hdev lock in hci_le_remote_conn_param_req_evt, otherwise it's possible it is freed concurrently. Extend the hci_dev_lock critical section to cover all conn usage.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 8.8

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

References

CVE-2026-43019

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_conn: fix potential UAF in set_cig_params_sync hci_conn lookup and field access must be covered by hdev lock in set_cig_params_sync, otherwise it's possible it is freed concurrently. Take hdev lock to prevent hci_conn from being deleted or modified concurrently. Just RCU lock is not suitable here, as we also want to avoid "tearing" in the configuration.

Published: 2026-05-01Modified: 2026-06-19

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43020

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: MGMT: validate LTK enc_size on load Load Long Term Keys stores the user-provided enc_size and later uses it to size fixed-size stack operations when replying to LE LTK requests. An enc_size larger than the 16-byte key buffer can therefore overflow the reply stack buffer. Reject oversized enc_size values while validating the management LTK record so invalid keys never reach the stored key state.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43023

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: SCO: fix race conditions in sco_sock_connect() sco_sock_connect() checks sk_state and sk_type without holding the socket lock. Two concurrent connect() syscalls on the same socket can both pass the check and enter sco_connect(), leading to use-after-free. The buggy scenario involves three participants and was confirmed with additional logging instrumentation: Thread A (connect): HCI disconnect: Thread B (connect): sco_sock_connect(sk) sco_sock_connect(sk) sk_state==BT_OPEN sk_state==BT_OPEN (pass, no lock) (pass, no lock) sco_connect(sk): sco_connect(sk): hci_dev_lock hci_dev_lock hci_connect_sco <- blocked -> hcon1 sco_conn_add->conn1 lock_sock(sk) sco_chan_add: conn1->sk = sk sk->conn = conn1 sk_state=BT_CONNECT release_sock hci_dev_unlock hci_dev_lock sco_conn_del: lock_sock(sk) sco_chan_del: sk->conn=NULL conn1->sk=NULL sk_state= BT_CLOSED SOCK_ZAPPED release_sock hci_dev_unlock (unblocked) hci_connect_sco -> hcon2 sco_conn_add -> conn2 lock_sock(sk) sco_chan_add: sk->conn=conn2 sk_state= BT_CONNECT // zombie sk! release_sock hci_dev_unlock Thread B revives a BT_CLOSED + SOCK_ZAPPED socket back to BT_CONNECT. Subsequent cleanup triggers double sock_put() and use-after-free. Meanwhile conn1 is leaked as it was orphaned when sco_conn_del() cleared the association. Fix this by: - Moving lock_sock() before the sk_state/sk_type checks in sco_sock_connect() to serialize concurrent connect attempts - Fixing the sk_type != SOCK_SEQPACKET check to actually return the error instead of just assigning it - Adding a state re-check in sco_connect() after lock_sock() to catch state changes during the window between the locks - Adding sco_pi(sk)->conn check in sco_chan_add() to prevent double-attach of a socket to multiple connections - Adding hci_conn_drop() on sco_chan_add failure to prevent HCI connection leaks

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43024

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: reject immediate NF_QUEUE verdict nft_queue is always used from userspace nftables to deliver the NF_QUEUE verdict. Immediately emitting an NF_QUEUE verdict is never used by the userspace nft tools, so reject immediate NF_QUEUE verdicts. The arp family does not provide queue support, but such an immediate verdict is still reachable. Globally reject NF_QUEUE immediate verdicts to address this issue.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43025

HIGH7.3

In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: ignore explicit helper on new expectations Use the existing master conntrack helper, anything else is not really supported and it just makes validation more complicated, so just ignore what helper userspace suggests for this expectation. This was uncovered when validating CTA_EXPECT_CLASS via different helper provided by userspace than the existing master conntrack helper: BUG: KASAN: slab-out-of-bounds in nf_ct_expect_related_report+0x2479/0x27c0 Read of size 4 at addr ffff8880043fe408 by task poc/102 Call Trace: nf_ct_expect_related_report+0x2479/0x27c0 ctnetlink_create_expect+0x22b/0x3b0 ctnetlink_new_expect+0x4bd/0x5c0 nfnetlink_rcv_msg+0x67a/0x950 netlink_rcv_skb+0x120/0x350 Allowing to read kernel memory bytes off the expectation boundary. CTA_EXPECT_HELP_NAME is still used to offer the helper name to userspace via netlink dump.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.3

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

References

CVE-2026-43026

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: zero expect NAT fields when CTA_EXPECT_NAT absent ctnetlink_alloc_expect() allocates expectations from a non-zeroing slab cache via nf_ct_expect_alloc(). When CTA_EXPECT_NAT is not present in the netlink message, saved_addr and saved_proto are never initialized. Stale data from a previous slab occupant can then be dumped to userspace by ctnetlink_exp_dump_expect(), which checks these fields to decide whether to emit CTA_EXPECT_NAT. The safe sibling nf_ct_expect_init(), used by the packet path, explicitly zeroes these fields. Zero saved_addr, saved_proto and dir in the else branch, guarded by IS_ENABLED(CONFIG_NF_NAT) since these fields only exist when NAT is enabled. Confirmed by priming the expect slab with NAT-bearing expectations, freeing them, creating a new expectation without CTA_EXPECT_NAT, and observing that the ctnetlink dump emits a spurious CTA_EXPECT_NAT containing stale data from the prior allocation.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43027

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_helper: pass helper to expect cleanup nf_conntrack_helper_unregister() calls nf_ct_expect_iterate_destroy() to remove expectations belonging to the helper being unregistered. However, it passes NULL instead of the helper pointer as the data argument, so expect_iter_me() never matches any expectation and all of them survive the cleanup. After unregister returns, nfnl_cthelper_del() frees the helper object immediately. Subsequent expectation dumps or packet-driven init_conntrack() calls then dereference the freed exp->helper, causing a use-after-free. Pass the actual helper pointer so expectations referencing it are properly destroyed before the helper object is freed. BUG: KASAN: slab-use-after-free in string+0x38f/0x430 Read of size 1 at addr ffff888003b14d20 by task poc/103 Call Trace: string+0x38f/0x430 vsnprintf+0x3cc/0x1170 seq_printf+0x17a/0x240 exp_seq_show+0x2e5/0x560 seq_read_iter+0x419/0x1280 proc_reg_read+0x1ac/0x270 vfs_read+0x179/0x930 ksys_read+0xef/0x1c0 Freed by task 103: The buggy address is located 32 bytes inside of freed 192-byte region [ffff888003b14d00, ffff888003b14dc0)

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43028

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: netfilter: x_tables: ensure names are nul-terminated Reject names that lack a \0 character before feeding them to functions that expect c-strings. Fixes tag is the most recent commit that needs this change.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.1

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

References

CVE-2026-43029

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: mptcp: fix soft lockup in mptcp_recvmsg() syzbot reported a soft lockup in mptcp_recvmsg() [0]. When receiving data with MSG_PEEK | MSG_WAITALL flags, the skb is not removed from the sk_receive_queue. This causes sk_wait_data() to always find available data and never perform actual waiting, leading to a soft lockup. Fix this by adding a 'last' parameter to track the last peeked skb. This allows sk_wait_data() to make informed waiting decisions and prevent infinite loops when MSG_PEEK is used. [0]: watchdog: BUG: soft lockup - CPU#2 stuck for 156s! [server:1963] Modules linked in: CPU: 2 UID: 0 PID: 1963 Comm: server Not tainted 6.19.0-rc8 #61 PREEMPT(none) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 RIP: 0010:sk_wait_data+0x15/0x190 Code: 80 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 41 56 41 55 41 54 49 89 f4 55 48 89 d5 53 48 89 fb <48> 83 ec 30 65 48 8b 05 17 a4 6b 01 48 89 44 24 28 31 c0 65 48 8b RSP: 0018:ffffc90000603ca0 EFLAGS: 00000246 RAX: 0000000000000000 RBX: ffff888102bf0800 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffffc90000603d18 RDI: ffff888102bf0800 RBP: 0000000000000000 R08: 0000000000000002 R09: 0000000000000101 R10: 0000000000000000 R11: 0000000000000075 R12: ffffc90000603d18 R13: ffff888102bf0800 R14: ffff888102bf0800 R15: 0000000000000000 FS: 00007f6e38b8c4c0(0000) GS:ffff8881b877e000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055aa7bff1680 CR3: 0000000105cbe000 CR4: 00000000000006f0 Call Trace: mptcp_recvmsg+0x547/0x8c0 net/mptcp/protocol.c:2329 inet_recvmsg+0x11f/0x130 net/ipv4/af_inet.c:891 sock_recvmsg+0x94/0xc0 net/socket.c:1100 __sys_recvfrom+0xb2/0x130 net/socket.c:2256 __x64_sys_recvfrom+0x1f/0x30 net/socket.c:2267 do_syscall_64+0x59/0x2d0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e arch/x86/entry/entry_64.S:131 RIP: 0033:0x7f6e386a4a1d Code: 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 8d 05 f1 de 2c 00 41 89 ca 8b 00 85 c0 75 20 45 31 c9 45 31 c0 b8 2d 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 6b f3 c3 66 0f 1f 84 00 00 00 00 00 41 56 41 RSP: 002b:00007ffc3c4bb078 EFLAGS: 00000246 ORIG_RAX: 000000000000002d RAX: ffffffffffffffda RBX: 000000000000861e RCX: 00007f6e386a4a1d RDX: 00000000000003ff RSI: 00007ffc3c4bb150 RDI: 0000000000000004 RBP: 00007ffc3c4bb570 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000103 R11: 0000000000000246 R12: 00005605dbc00be0 R13: 00007ffc3c4bb650 R14: 0000000000000000 R15: 0000000000000000

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.5

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

References

CVE-2026-43030

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix regsafe() for pointers to packet In case rold->reg->range == BEYOND_PKT_END && rcur->reg->range == N regsafe() may return true which may lead to current state with valid packet range not being explored. Fix the bug.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43031

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: net: xilinx: axienet: Fix BQL accounting for multi-BD TX packets When a TX packet spans multiple buffer descriptors (scatter-gather), axienet_free_tx_chain sums the per-BD actual length from descriptor status into a caller-provided accumulator. That sum is reset on each NAPI poll. If the BDs for a single packet complete across different polls, the earlier bytes are lost and never credited to BQL. This causes BQL to think bytes are permanently in-flight, eventually stalling the TX queue. The SKB pointer is stored only on the last BD of a packet. When that BD completes, use skb->len for the byte count instead of summing per-BD status lengths. This matches netdev_sent_queue(), which debits skb->len, and naturally survives across polls because no partial packet contributes to the accumulator.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.5

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

References

CVE-2026-43032

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: NFC: pn533: bound the UART receive buffer pn532_receive_buf() appends every incoming byte to dev->recv_skb and only resets the buffer after pn532_uart_rx_is_frame() recognizes a complete frame. A continuous stream of bytes without a valid PN532 frame header therefore keeps growing the skb until skb_put_u8() hits the tail limit. Drop the accumulated partial frame once the fixed receive buffer is full so malformed UART traffic cannot grow the skb past PN532_UART_SKB_BUFF_LEN.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43033

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: crypto: authencesn - Do not place hiseq at end of dst for out-of-place decryption When decrypting data that is not in-place (src != dst), there is no need to save the high-order sequence bits in dst as it could simply be re-copied from the source. However, the data to be hashed need to be rearranged accordingly. Thanks,

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43034

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: bnxt_en: set backing store type from query type bnxt_hwrm_func_backing_store_qcaps_v2() stores resp->type from the firmware response in ctxm->type and later uses that value to index fixed backing-store metadata arrays such as ctx_arr[] and bnxt_bstore_to_trace[]. ctxm->type is fixed by the current backing-store query type and matches the array index of ctx->ctx_arr. Set ctxm->type from the current loop variable instead of depending on resp->type. Also update the loop to advance type from next_valid_type in the for statement, which keeps the control flow simpler for non-valid and unchanged entries.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43035

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: sched: cls_api: fix tc_chain_fill_node to initialize tcm_info to zero to prevent an info-leak When building netlink messages, tc_chain_fill_node() never initializes the tcm_info field of struct tcmsg. Since the allocation is not zeroed, kernel heap memory is leaked to userspace through this 4-byte field. The fix simply zeroes tcm_info alongside the other fields that are already initialized.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43036

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: use skb_header_pointer() for TCPv4 GSO frag_off check Syzbot reported a KMSAN uninit-value warning in gso_features_check() called from netif_skb_features() [1]. gso_features_check() reads iph->frag_off to decide whether to clear mangleid_features. Accessing the IPv4 header via ip_hdr()/inner_ip_hdr() can rely on skb header offsets that are not always safe for direct dereference on packets injected from PF_PACKET paths. Use skb_header_pointer() for the TCPv4 frag_off check so the header read is robust whether data is already linear or needs copying. [1] https://syzkaller.appspot.com/bug?extid=1543a7d954d9c6d00407

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43037

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ip6_tunnel: clear skb2->cb[] in ip4ip6_err() Oskar Kjos reported the following problem. ip4ip6_err() calls icmp_send() on a cloned skb whose cb[] was written by the IPv6 receive path as struct inet6_skb_parm. icmp_send() passes IPCB(skb2) to __ip_options_echo(), which interprets that cb[] region as struct inet_skb_parm (IPv4). The layouts differ: inet6_skb_parm.nhoff at offset 14 overlaps inet_skb_parm.opt.rr, producing a non-zero rr value. __ip_options_echo() then reads optlen from attacker-controlled packet data at sptr[rr+1] and copies that many bytes into dopt->__data, a fixed 40-byte stack buffer (IP_OPTIONS_DATA_FIXED_SIZE). To fix this we clear skb2->cb[], as suggested by Oskar Kjos. Also add minimal IPv4 header validation (version == 4, ihl >= 5).

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xCRITICAL 9.8

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

References

CVE-2026-43038

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ipv6: icmp: clear skb2->cb[] in ip6_err_gen_icmpv6_unreach() Sashiko AI-review observed: In ip6_err_gen_icmpv6_unreach(), the skb is an outer IPv4 ICMP error packet where its cb contains an IPv4 inet_skb_parm. When skb is cloned into skb2 and passed to icmp6_send(), it uses IP6CB(skb2). IP6CB interprets the IPv4 inet_skb_parm as an inet6_skb_parm. The cipso offset in inet_skb_parm.opt directly overlaps with dsthao in inet6_skb_parm at offset 18. If an attacker sends a forged ICMPv4 error with a CIPSO IP option, dsthao would be a non-zero offset. Inside icmp6_send(), mip6_addr_swap() is called and uses ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO). This would scan the inner, attacker-controlled IPv6 packet starting at that offset, potentially returning a fake TLV without checking if the remaining packet length can hold the full 18-byte struct ipv6_destopt_hao. Could mip6_addr_swap() then perform a 16-byte swap that extends past the end of the packet data into skb_shared_info? Should the cb array also be cleared in ip6_err_gen_icmpv6_unreach() and ip6ip6_err() to prevent this? This patch implements the first suggestion. I am not sure if ip6ip6_err() needs to be changed. A separate patch would be better anyway.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xCRITICAL 9.8

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

References

CVE-2026-43040

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: net: ipv6: ndisc: fix ndisc_ra_useropt to initialize nduseropt_padX fields to zero to prevent an info-leak When processing Router Advertisements with user options the kernel builds an RTM_NEWNDUSEROPT netlink message. The nduseroptmsg struct has three padding fields that are never zeroed and can leak kernel data The fix is simple, just zeroes the padding fields.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.1

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

References

CVE-2026-43041

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: net: qrtr: replace qrtr_tx_flow radix_tree with xarray to fix memory leak __radix_tree_create() allocates and links intermediate nodes into the tree one by one. If a subsequent allocation fails, the already-linked nodes remain in the tree with no corresponding leaf entry. These orphaned internal nodes are never reclaimed because radix_tree_for_each_slot() only visits slots containing leaf values. The radix_tree API is deprecated in favor of xarray. As suggested by Matthew Wilcox, migrate qrtr_tx_flow from radix_tree to xarray instead of fixing the radix_tree itself [1]. xarray properly handles cleanup of internal nodes — xa_destroy() frees all internal xarray nodes when the qrtr_node is released, preventing the leak. [1] https://lore.kernel.org/all/20260225071623.41275-1-jiayuan.chen@linux.dev/T/

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43043

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: crypto: af-alg - fix NULL pointer dereference in scatterwalk The AF_ALG interface fails to unmark the end of a Scatter/Gather List (SGL) when chaining a new af_alg_tsgl structure. If a sendmsg() fills an SGL exactly to MAX_SGL_ENTS, the last entry is marked as the end. A subsequent sendmsg() allocates a new SGL and chains it, but fails to clear the end marker on the previous SGL's last data entry. This causes the crypto scatterwalk to hit a premature end, returning NULL on sg_next() and leading to a kernel panic during dereference. Fix this by explicitly unmarking the end of the previous SGL when performing sg_chain() in af_alg_alloc_tsgl().

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43044

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: crypto: caam - fix DMA corruption on long hmac keys When a key longer than block size is supplied, it is copied and then hashed into the real key. The memory allocated for the copy needs to be rounded to DMA cache alignment, as otherwise the hashed key may corrupt neighbouring memory. The rounding was performed, but never actually used for the allocation. Fix this by replacing kmemdup with kmalloc for a larger buffer, followed by memcpy.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43046

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: btrfs: reject root items with drop_progress and zero drop_level [BUG] When recovering relocation at mount time, merge_reloc_root() and btrfs_drop_snapshot() both use BUG_ON(level == 0) to guard against an impossible state: a non-zero drop_progress combined with a zero drop_level in a root_item, which can be triggered: ------------[ cut here ]------------ kernel BUG at fs/btrfs/relocation.c:1545! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI CPU: 1 UID: 0 PID: 283 ... Tainted: 6.18.0+ #16 PREEMPT(voluntary) Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Hardware name: QEMU Ubuntu 24.04 PC v2, BIOS 1.16.3-debian-1.16.3-2 RIP: 0010:merge_reloc_root+0x1266/0x1650 fs/btrfs/relocation.c:1545 Code: ffff0000 00004589 d7e9acfa ffffe8a1 79bafebe 02000000 Call Trace: merge_reloc_roots+0x295/0x890 fs/btrfs/relocation.c:1861 btrfs_recover_relocation+0xd6e/0x11d0 fs/btrfs/relocation.c:4195 btrfs_start_pre_rw_mount+0xa4d/0x1810 fs/btrfs/disk-io.c:3130 open_ctree+0x5824/0x5fe0 fs/btrfs/disk-io.c:3640 btrfs_fill_super fs/btrfs/super.c:987 [inline] btrfs_get_tree_super fs/btrfs/super.c:1951 [inline] btrfs_get_tree_subvol fs/btrfs/super.c:2094 [inline] btrfs_get_tree+0x111c/0x2190 fs/btrfs/super.c:2128 vfs_get_tree+0x9a/0x370 fs/super.c:1758 fc_mount fs/namespace.c:1199 [inline] do_new_mount_fc fs/namespace.c:3642 [inline] do_new_mount fs/namespace.c:3718 [inline] path_mount+0x5b8/0x1ea0 fs/namespace.c:4028 do_mount fs/namespace.c:4041 [inline] __do_sys_mount fs/namespace.c:4229 [inline] __se_sys_mount fs/namespace.c:4206 [inline] __x64_sys_mount+0x282/0x320 fs/namespace.c:4206 ... RIP: 0033:0x7f969c9a8fde Code: 0f1f4000 48c7c2b0 fffffff7 d8648902 b8ffffff ffc3660f ---[ end trace 0000000000000000 ]--- The bug is reproducible on 7.0.0-rc2-next-20260310 with our dynamic metadata fuzzing tool that corrupts btrfs metadata at runtime. [CAUSE] A non-zero drop_progress.objectid means an interrupted btrfs_drop_snapshot() left a resume point on disk, and in that case drop_level must be greater than 0 because the checkpoint is only saved at internal node levels. Although this invariant is enforced when the kernel writes the root item, it is not validated when the root item is read back from disk. That allows on-disk corruption to provide an invalid state with drop_progress.objectid != 0 and drop_level == 0. When relocation recovery later processes such a root item, merge_reloc_root() reads drop_level and hits BUG_ON(level == 0). The same invalid metadata can also trigger the corresponding BUG_ON() in btrfs_drop_snapshot(). [FIX] Fix this by validating the root_item invariant in tree-checker when reading root items from disk: if drop_progress.objectid is non-zero, drop_level must also be non-zero. Reject such malformed metadata with -EUCLEAN before it reaches merge_reloc_root() or btrfs_drop_snapshot() and triggers the BUG_ON. After the fix, the same corruption is correctly rejected by tree-checker and the BUG_ON is no longer triggered.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43047

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: HID: multitouch: Check to ensure report responses match the request It is possible for a malicious (or clumsy) device to respond to a specific report's feature request using a completely different report ID. This can cause confusion in the HID core resulting in nasty side-effects such as OOB writes. Add a check to ensure that the report ID in the response, matches the one that was requested. If it doesn't, omit reporting the raw event and return early.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43048

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: HID: core: Mitigate potential OOB by removing bogus memset() The memset() in hid_report_raw_event() has the good intention of clearing out bogus data by zeroing the area from the end of the incoming data string to the assumed end of the buffer. However, as we have previously seen, doing so can easily result in OOB reads and writes in the subsequent thread of execution. The current suggestion from one of the HID maintainers is to remove the memset() and simply return if the incoming event buffer size is not large enough to fill the associated report. Suggested-by Benjamin Tissoires [bentiss: changed the return value]

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 8.8

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

References

CVE-2026-43049

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: HID: logitech-hidpp: Prevent use-after-free on force feedback initialisation failure Presently, if the force feedback initialisation fails when probing the Logitech G920 Driving Force Racing Wheel for Xbox One, an error number will be returned and propagated before the userspace infrastructure (sysfs and /dev/input) has been torn down. If userspace ignores the errors and continues to use its references to these dangling entities, a UAF will promptly follow. We have 2 options; continue to return the error, but ensure that all of the infrastructure is torn down accordingly or continue to treat this condition as a warning by emitting the message but returning success. It is thought that the original author's intention was to emit the warning but keep the device functional, less the force feedback feature, so let's go with that.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43050

HIGH7.0

In the Linux kernel, the following vulnerability has been resolved: atm: lec: fix use-after-free in sock_def_readable() A race condition exists between lec_atm_close() setting priv->lecd to NULL and concurrent access to priv->lecd in send_to_lecd(), lec_handle_bridge(), and lec_atm_send(). When the socket is freed via RCU while another thread is still using it, a use-after-free occurs in sock_def_readable() when accessing the socket's wait queue. The root cause is that lec_atm_close() clears priv->lecd without any synchronization, while callers dereference priv->lecd without any protection against concurrent teardown. Fix this by converting priv->lecd to an RCU-protected pointer: - Mark priv->lecd as __rcu in lec.h - Use rcu_assign_pointer() in lec_atm_close() and lecd_attach() for safe pointer assignment - Use rcu_access_pointer() for NULL checks that do not dereference the pointer in lec_start_xmit(), lec_push(), send_to_lecd() and lecd_attach() - Use rcu_read_lock/rcu_dereference/rcu_read_unlock in send_to_lecd(), lec_handle_bridge() and lec_atm_send() to safely access lecd - Use rcu_assign_pointer() followed by synchronize_rcu() in lec_atm_close() to ensure all readers have completed before proceeding. This is safe since lec_atm_close() is called from vcc_release() which holds lock_sock(), a sleeping lock. - Remove the manual sk_receive_queue drain from lec_atm_close() since vcc_destroy_socket() already drains it after lec_atm_close() returns. v2: Switch from spinlock + sock_hold/put approach to RCU to properly fix the race. The v1 spinlock approach had two issues pointed out by Eric Dumazet: 1. priv->lecd was still accessed directly after releasing the lock instead of using a local copy. 2. The spinlock did not prevent packets being queued after lec_atm_close() drains sk_receive_queue since timer and workqueue paths bypass netif_stop_queue(). Note: Syzbot patch testing was attempted but the test VM terminated unexpectedly with "Connection to localhost closed by remote host", likely due to a QEMU AHCI emulation issue unrelated to this fix. Compile testing with "make W=1 net/atm/lec.o" passes cleanly.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.0

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

References

CVE-2026-43051

HIGH8.1

In the Linux kernel, the following vulnerability has been resolved: HID: wacom: fix out-of-bounds read in wacom_intuos_bt_irq The wacom_intuos_bt_irq() function processes Bluetooth HID reports without sufficient bounds checking. A maliciously crafted short report can trigger an out-of-bounds read when copying data into the wacom structure. Specifically, report 0x03 requires at least 22 bytes to safely read the processed data and battery status, while report 0x04 (which falls through to 0x03) requires 32 bytes. Add explicit length checks for these report IDs and log a warning if a short report is received.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 8.1

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

References

CVE-2026-43052

HIGH7.1

In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: check tdls flag in ieee80211_tdls_oper When NL80211_TDLS_ENABLE_LINK is called, the code only checks if the station exists but not whether it is actually a TDLS station. This allows the operation to proceed for non-TDLS stations, causing unintended side effects like modifying channel context and HT protection before failing. Add a check for sta->sta.tdls early in the ENABLE_LINK case, before any side effects occur, to ensure the operation is only allowed for actual TDLS peers.

Published: 2026-05-01Modified: 2026-06-19

CVSS 3.xHIGH 7.1

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

References

CVE-2026-43054

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: scsi: target: tcm_loop: Drain commands in target_reset handler tcm_loop_target_reset() violates the SCSI EH contract: it returns SUCCESS without draining any in-flight commands. The SCSI EH documentation (scsi_eh.rst) requires that when a reset handler returns SUCCESS the driver has made lower layers "forget about timed out scmds" and is ready for new commands. Every other SCSI LLD (virtio_scsi, mpt3sas, ipr, scsi_debug, mpi3mr) enforces this by draining or completing outstanding commands before returning SUCCESS. Because tcm_loop_target_reset() doesn't drain, the SCSI EH reuses in-flight scsi_cmnd structures for recovery commands (e.g. TUR) while the target core still has async completion work queued for the old se_cmd. The memset in queuecommand zeroes se_lun and lun_ref_active, causing transport_lun_remove_cmd() to skip its percpu_ref_put(). The leaked LUN reference prevents transport_clear_lun_ref() from completing, hanging configfs LUN unlink forever in D-state: INFO: task rm:264 blocked for more than 122 seconds. rm D 0 264 258 0x00004000 Call Trace: __schedule+0x3d0/0x8e0 schedule+0x36/0xf0 transport_clear_lun_ref+0x78/0x90 [target_core_mod] core_tpg_remove_lun+0x28/0xb0 [target_core_mod] target_fabric_port_unlink+0x50/0x60 [target_core_mod] configfs_unlink+0x156/0x1f0 [configfs] vfs_unlink+0x109/0x290 do_unlinkat+0x1d5/0x2d0 Fix this by making tcm_loop_target_reset() actually drain commands: 1. Issue TMR_LUN_RESET via tcm_loop_issue_tmr() to drain all commands that the target core knows about (those not yet CMD_T_COMPLETE). 2. Use blk_mq_tagset_busy_iter() to iterate all started requests and flush_work() on each se_cmd — this drains any deferred completion work for commands that already had CMD_T_COMPLETE set before the TMR (which the TMR skips via __target_check_io_state()). This is the same pattern used by mpi3mr, scsi_debug, and libsas to drain outstanding commands during reset.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43055

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: scsi: target: file: Use kzalloc_flex for aio_cmd The target_core_file doesn't initialize the aio_cmd->iocb for the ki_write_stream. When a write command fd_execute_rw_aio() is executed, we may get a bogus ki_write_stream value, causing unintended write failure status when checking iocb->ki_write_stream > max_write_streams in the block device. Let's just use kzalloc_flex when allocating the aio_cmd and let ki_write_stream=0 to fix this issue.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.5

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

References

CVE-2026-43056

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: net: mana: fix use-after-free in add_adev() error path If auxiliary_device_add() fails, add_adev() jumps to add_fail and calls auxiliary_device_uninit(adev). The auxiliary device has its release callback set to adev_release(), which frees the containing struct mana_adev. Since adev is embedded in struct mana_adev, the subsequent fall-through to init_fail and access to adev->id may result in a use-after-free. Fix this by saving the allocated auxiliary device id in a local variable before calling auxiliary_device_add(), and use that saved id in the cleanup path after auxiliary_device_uninit().

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43057

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: net: correctly handle tunneled traffic on IPV6_CSUM GSO fallback NETIF_F_IPV6_CSUM only advertises support for checksum offload of packets without IPv6 extension headers. Packets with extension headers must fall back onto software checksumming. Since TSO depends on checksum offload, those must revert to GSO. The below commit introduces that fallback. It always checks network header length. For tunneled packets, the inner header length must be checked instead. Extend the check accordingly. A special case is tunneled packets without inner IP protocol. Such as RFC 6951 SCTP in UDP. Those are not standard IPv6 followed by transport header either, so also must revert to the software GSO path.

Published: 2026-05-01Modified: 2026-06-17

CVSS 3.xHIGH 7.5

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

References

CVE-2026-43063

HIGH7.8

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

Published: 2026-05-05Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43064

MEDIUM5.5

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

Published: 2026-05-05Modified: 2026-06-19

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43065

MEDIUM5.5

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

Published: 2026-05-05Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43066

MEDIUM5.5

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

Published: 2026-05-05Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43067

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: ext4: handle wraparound when searching for blocks for indirect mapped blocks Commit 4865c768b563 ("ext4: always allocate blocks only from groups inode can use") restricts what blocks will be allocated for indirect block based files to block numbers that fit within 32-bit block numbers. However, when using a review bot running on the latest Gemini LLM to check this commit when backporting into an LTS based kernel, it raised this concern: If ac->ac_g_ex.fe_group is >= ngroups (for instance, if the goal group was populated via stream allocation from s_mb_last_groups), then start will be >= ngroups. Does this allow allocating blocks beyond the 32-bit limit for indirect block mapped files? The commit message mentions that ext4_mb_scan_groups_linear() takes care to not select unsupported groups. However, its loop uses group = *start, and the very first iteration will call ext4_mb_scan_group() with this unsupported group because next_linear_group() is only called at the end of the iteration. After reviewing the code paths involved and considering the LLM review, I determined that this can happen when there is a file system where some files/directories are extent-mapped and others are indirect-block mapped. To address this, add a safety clamp in ext4_mb_scan_groups().

Published: 2026-05-05Modified: 2026-06-17

CVSS 3.xCRITICAL 9.8

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

References

CVE-2026-43068

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: ext4: avoid allocate block from corrupted group in ext4_mb_find_by_goal() There's issue as follows: ... EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 206 at logical offset 0 with max blocks 1 with error 117 EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 206 at logical offset 0 with max blocks 1 with error 117 EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 206 at logical offset 0 with max blocks 1 with error 117 EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 206 at logical offset 0 with max blocks 1 with error 117 EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 2243 at logical offset 0 with max blocks 1 with error 117 EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 2239 at logical offset 0 with max blocks 1 with error 117 EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost EXT4-fs (mmcblk0p1): error count since last fsck: 1 EXT4-fs (mmcblk0p1): initial error at time 1765597433: ext4_mb_generate_buddy:760 EXT4-fs (mmcblk0p1): last error at time 1765597433: ext4_mb_generate_buddy:760 ... According to the log analysis, blocks are always requested from the corrupted block group. This may happen as follows: ext4_mb_find_by_goal ext4_mb_load_buddy ext4_mb_load_buddy_gfp ext4_mb_init_cache ext4_read_block_bitmap_nowait ext4_wait_block_bitmap ext4_validate_block_bitmap if (!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) return -EFSCORRUPTED; // There's no logs. if (err) return err; // Will return error ext4_lock_group(ac->ac_sb, group); if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) // Unreachable goto out; After commit 9008a58e5dce ("ext4: make the bitmap read routines return real error codes") merged, Commit 163a203ddb36 ("ext4: mark block group as corrupt on block bitmap error") is no real solution for allocating blocks from corrupted block groups. This is because if 'EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)' is true, then 'ext4_mb_load_buddy()' may return an error. This means that the block allocation will fail. Therefore, check block group if corrupted when ext4_mb_load_buddy() returns error.

Published: 2026-05-05Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43069

MEDIUM5.5

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

Published: 2026-05-05Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43070

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: bpf: Reset register ID for BPF_END value tracking When a register undergoes a BPF_END (byte swap) operation, its scalar value is mutated in-place. If this register previously shared a scalar ID with another register (e.g., after an `r1 = r0` assignment), this tie must be broken. Currently, the verifier misses resetting `dst_reg->id` to 0 for BPF_END. Consequently, if a conditional jump checks the swapped register, the verifier incorrectly propagates the learned bounds to the linked register, leading to false confidence in the linked register's value and potentially allowing out-of-bounds memory accesses. Fix this by explicitly resetting `dst_reg->id` to 0 in the BPF_END case to break the scalar tie, similar to how BPF_NEG handles it via `__mark_reg_known`.

Published: 2026-05-05Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43323

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: sched/fair: Fix zero_vruntime tracking fix John reported that stress-ng-yield could make his machine unhappy and managed to bisect it to commit b3d99f43c72b ("sched/fair: Fix zero_vruntime tracking"). The combination of yield and that commit was specific enough to hypothesize the following scenario: Suppose we have 2 runnable tasks, both doing yield. Then one will be eligible and one will not be, because the average position must be in between these two entities. Therefore, the runnable task will be eligible, and be promoted a full slice (all the tasks do is yield after all). This causes it to jump over the other task and now the other task is eligible and current is no longer. So we schedule. Since we are runnable, there is no {de,en}queue. All we have is the __{en,de}queue_entity() from {put_prev,set_next}_task(). But per the fingered commit, those two no longer move zero_vruntime. All that moves zero_vruntime are tick and full {de,en}queue. This means, that if the two tasks playing leapfrog can reach the critical speed to reach the overflow point inside one tick's worth of time, we're up a creek. Additionally, when multiple cgroups are involved, there is no guarantee the tick will in fact hit every cgroup in a timely manner. Statistically speaking it will, but that same statistics does not rule out the possibility of one cgroup not getting a tick for a significant amount of time -- however unlikely. Therefore, just like with the yield() case, force an update at the end of every slice. This ensures the update is never more than a single slice behind and the whole thing is within 2 lag bounds as per the comment on entity_key().

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43324

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: USB: dummy-hcd: Fix interrupt synchronization error This fixes an error in synchronization in the dummy-hcd driver. The error has a somewhat involved history. The synchronization mechanism was introduced by commit 7dbd8f4cabd9 ("USB: dummy-hcd: Fix erroneous synchronization change"), which added an emulated "interrupts enabled" flag together with code emulating synchronize_irq() (it waits until all current handler callbacks have returned). But the emulated interrupt-disable occurred too late, after the driver containing the handler callback routines had been told that it was unbound and no more callbacks would occur. Commit 4a5d797a9f9c ("usb: gadget: dummy_hcd: fix gpf in gadget_setup") tried to fix this by moving the synchronize_irq() emulation code from dummy_stop() to dummy_pullup(), which runs before the unbind callback. There still were races, though, because the emulated interrupt-disable still occurred too late. It couldn't be moved to dummy_pullup(), because that routine can be called for reasons other than an impending unbind. Therefore commits 7dc0c55e9f30 ("USB: UDC core: Add udc_async_callbacks gadget op") and 04145a03db9d ("USB: UDC: Implement udc_async_callbacks in dummy-hcd") added an API allowing the UDC core to tell dummy-hcd exactly when emulated interrupts and their callbacks should be disabled. That brings us to the current state of things, which is still wrong because the emulated synchronize_irq() occurs before the emulated interrupt-disable! That's no good, beause it means that more emulated interrupts can occur after the synchronize_irq() emulation has run, leading to the possibility that a callback handler may be running when the gadget driver is unbound. To fix this, we have to move the synchronize_irq() emulation code yet again, to the dummy_udc_async_callbacks() routine, which takes care of enabling and disabling emulated interrupt requests. The synchronization will now run immediately after emulated interrupts are disabled, which is where it belongs.

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43325

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: mvm: don't send a 6E related command when not supported MCC_ALLOWED_AP_TYPE_CMD is related to 6E support. Do not send it if the device doesn't support 6E. Apparently, the firmware is mistakenly advertising support for this command even on AX201 which does not support 6E and then the firmware crashes.

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43327

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: USB: dummy-hcd: Fix locking/synchronization error Syzbot testing was able to provoke an addressing exception and crash in the usb_gadget_udc_reset() routine in drivers/usb/gadgets/udc/core.c, resulting from the fact that the routine was called with a second ("driver") argument of NULL. The bad caller was set_link_state() in dummy_hcd.c, and the problem arose because of a race between a USB reset and driver unbind. These sorts of races were not supposed to be possible; commit 7dbd8f4cabd9 ("USB: dummy-hcd: Fix erroneous synchronization change"), along with a few followup commits, was written specifically to prevent them. As it turns out, there are (at least) two errors remaining in the code. Another patch will address the second error; this one is concerned with the first. The error responsible for the syzbot crash occurred because the stop_activity() routine will sometimes drop and then re-acquire the dum->lock spinlock. A call to stop_activity() occurs in set_link_state() when handling an emulated USB reset, after the test of dum->ints_enabled and before the increment of dum->callback_usage. This allowed another thread (doing a driver unbind) to sneak in and grab the spinlock, and then clear dum->ints_enabled and dum->driver. Normally this other thread would have to wait for dum->callback_usage to go down to 0 before it would clear dum->driver, but in this case it didn't have to wait since dum->callback_usage had not yet been incremented. The fix is to increment dum->callback_usage _before_ calling stop_activity() instead of after. Then the thread doing the unbind will not clear dum->driver until after the call to usb_gadget_udc_reset() safely returns and dum->callback_usage has been decremented again.

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43328

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: cpufreq: governor: fix double free in cpufreq_dbs_governor_init() error path When kobject_init_and_add() fails, cpufreq_dbs_governor_init() calls kobject_put(&dbs_data->attr_set.kobj). The kobject release callback cpufreq_dbs_data_release() calls gov->exit(dbs_data) and kfree(dbs_data), but the current error path then calls gov->exit(dbs_data) and kfree(dbs_data) again, causing a double free. Keep the direct kfree(dbs_data) for the gov->init() failure path, but after kobject_init_and_add() has been called, let kobject_put() handle the cleanup through cpufreq_dbs_data_release().

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43329

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: netfilter: flowtable: strictly check for maximum number of actions The maximum number of flowtable hardware offload actions in IPv6 is: * ethernet mangling (4 payload actions, 2 for each ethernet address) * SNAT (4 payload actions) * DNAT (4 payload actions) * Double VLAN (4 vlan actions, 2 for popping vlan, and 2 for pushing) for QinQ. * Redirect (1 action) Which makes 17, while the maximum is 16. But act_ct supports for tunnels actions too. Note that payload action operates at 32-bit word level, so mangling an IPv6 address takes 4 payload actions. Update flow_action_entry_next() calls to check for the maximum number of supported actions. While at it, rise the maximum number of actions per flow from 16 to 24 so this works fine with IPv6 setups.

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43330

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: crypto: caam - fix overflow on long hmac keys When a key longer than block size is supplied, it is copied and then hashed into the real key. The memory allocated for the copy needs to be rounded to DMA cache alignment, as otherwise the hashed key may corrupt neighbouring memory. The copying is performed using kmemdup, however this leads to an overflow: reading more bytes (aligned_len - keylen) from the keylen source buffer. Fix this by replacing kmemdup with kmalloc, followed by memcpy.

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43331

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: x86/kexec: Disable KCOV instrumentation after load_segments() The load_segments() function changes segment registers, invalidating GS base (which KCOV relies on for per-cpu data). When CONFIG_KCOV is enabled, any subsequent instrumented C code call (e.g. native_gdt_invalidate()) begins crashing the kernel in an endless loop. To reproduce the problem, it's sufficient to do kexec on a KCOV-instrumented kernel: $ kexec -l /boot/otherKernel $ kexec -e The real-world context for this problem is enabling crash dump collection in syzkaller. For this, the tool loads a panic kernel before fuzzing and then calls makedumpfile after the panic. This workflow requires both CONFIG_KEXEC and CONFIG_KCOV to be enabled simultaneously. Adding safeguards directly to the KCOV fast-path (__sanitizer_cov_trace_pc()) is also undesirable as it would introduce an extra performance overhead. Disabling instrumentation for the individual functions would be too fragile, so disable KCOV instrumentation for the entire machine_kexec_64.c and physaddr.c. If coverage-guided fuzzing ever needs these components in the future, other approaches should be considered. The problem is not relevant for 32 bit kernels as CONFIG_KCOV is not supported there. [ bp: Space out comment for better readability. ]

Published: 2026-05-08Modified: 2026-06-19

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43332

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: thermal: core: Fix thermal zone device registration error path If thermal_zone_device_register_with_trips() fails after registering a thermal zone device, it needs to wait for the tz->removal completion like thermal_zone_device_unregister(), in case user space has managed to take a reference to the thermal zone device's kobject, in which case thermal_release() may not be called by the error path itself and tz may be freed prematurely. Add the missing wait_for_completion() call to the thermal zone device registration error path.

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43333

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: bpf: reject direct access to nullable PTR_TO_BUF pointers check_mem_access() matches PTR_TO_BUF via base_type() which strips PTR_MAYBE_NULL, allowing direct dereference without a null check. Map iterator ctx->key and ctx->value are PTR_TO_BUF | PTR_MAYBE_NULL. On stop callbacks these are NULL, causing a kernel NULL dereference. Add a type_may_be_null() guard to the PTR_TO_BUF branch, matching the existing PTR_TO_BTF_ID pattern.

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43334

HIGH8.8

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: SMP: force responder MITM requirements before building the pairing response smp_cmd_pairing_req() currently builds the pairing response from the initiator auth_req before enforcing the local BT_SECURITY_HIGH requirement. If the initiator omits SMP_AUTH_MITM, the response can also omit it even though the local side still requires MITM. tk_request() then sees an auth value without SMP_AUTH_MITM and may select JUST_CFM, making method selection inconsistent with the pairing policy the responder already enforces. When the local side requires HIGH security, first verify that MITM can be achieved from the IO capabilities and then force SMP_AUTH_MITM in the response in both rsp.auth_req and auth. This keeps the responder auth bits and later method selection aligned.

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xHIGH 8.8

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

References

CVE-2026-43336

HIGH7.5

In the Linux kernel, the following vulnerability has been resolved: lib/crypto: chacha: Zeroize permuted_state before it leaves scope Since the ChaCha permutation is invertible, the local variable 'permuted_state' is sufficient to compute the original 'state', and thus the key, even after the permutation has been done. While the kernel is quite inconsistent about zeroizing secrets on the stack (and some prominent userspace crypto libraries don't bother at all since it's not guaranteed to work anyway), the kernel does try to do it as a best practice, especially in cases involving the RNG. Thus, explicitly zeroize 'permuted_state' before it goes out of scope.

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xHIGH 7.5

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

References

CVE-2026-43337

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix NULL pointer dereference in dcn401_init_hw() dcn401_init_hw() assumes that update_bw_bounding_box() is valid when entering the update path. However, the existing condition: ((!fams2_enable && update_bw_bounding_box) || freq_changed) does not guarantee this, as the freq_changed branch can evaluate to true independently of the callback pointer. This can result in calling update_bw_bounding_box() when it is NULL. Fix this by separating the update condition from the pointer checks and ensuring the callback, dc->clk_mgr, and bw_params are validated before use. Fixes the below: ../dc/hwss/dcn401/dcn401_hwseq.c:367 dcn401_init_hw() error: we previously assumed 'dc->res_pool->funcs->update_bw_bounding_box' could be null (see line 362) (cherry picked from commit 86117c5ab42f21562fedb0a64bffea3ee5fcd477)

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43338

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: btrfs: reserve enough transaction items for qgroup ioctls Currently our qgroup ioctls don't reserve any space, they just do a transaction join, which does not reserve any space, neither for the quota tree updates nor for the delayed refs generated when updating the quota tree. The quota root uses the global block reserve, which is fine most of the time since we don't expect a lot of updates to the quota root, or to be too close to -ENOSPC such that other critical metadata updates need to resort to the global reserve. However this is not optimal, as not reserving proper space may result in a transaction abort due to not reserving space for delayed refs and then abusing the use of the global block reserve. For example, the following reproducer (which is unlikely to model any real world use case, but just to illustrate the problem), triggers such a transaction abort due to -ENOSPC when running delayed refs: $ cat test.sh #!/bin/bash DEV=/dev/nullb0 MNT=/mnt/nullb0 umount $DEV &> /dev/null # Limit device to 1G so that it's much faster to reproduce the issue. mkfs.btrfs -f -b 1G $DEV mount -o commit=600 $DEV $MNT fallocate -l 800M $MNT/filler btrfs quota enable $MNT for ((i = 1; i <= 400000; i++)); do btrfs qgroup create 1/$i $MNT done umount $MNT When running this, we can see in dmesg/syslog that a transaction abort happened: [436.490] BTRFS error (device nullb0): failed to run delayed ref for logical 30408704 num_bytes 16384 type 176 action 1 ref_mod 1: -28 [436.493] ------------[ cut here ]------------ [436.494] BTRFS: Transaction aborted (error -28) [436.495] WARNING: fs/btrfs/extent-tree.c:2247 at btrfs_run_delayed_refs+0xd9/0x110 [btrfs], CPU#4: umount/2495372 [436.497] Modules linked in: btrfs loop (...) [436.508] CPU: 4 UID: 0 PID: 2495372 Comm: umount Tainted: G W 6.19.0-rc8-btrfs-next-225+ #1 PREEMPT(full) [436.510] Tainted: [W]=WARN [436.511] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014 [436.513] RIP: 0010:btrfs_run_delayed_refs+0xdf/0x110 [btrfs] [436.514] Code: 0f 82 ea (...) [436.518] RSP: 0018:ffffd511850b7d78 EFLAGS: 00010292 [436.519] RAX: 00000000ffffffe4 RBX: ffff8f120dad37e0 RCX: 0000000002040001 [436.520] RDX: 0000000000000002 RSI: 00000000ffffffe4 RDI: ffffffffc090fd80 [436.522] RBP: 0000000000000000 R08: 0000000000000001 R09: ffffffffc04d1867 [436.523] R10: ffff8f18dc1fffa8 R11: 0000000000000003 R12: ffff8f173aa89400 [436.524] R13: 0000000000000000 R14: ffff8f173aa89400 R15: 0000000000000000 [436.526] FS: 00007fe59045d840(0000) GS:ffff8f192e22e000(0000) knlGS:0000000000000000 [436.527] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [436.528] CR2: 00007fe5905ff2b0 CR3: 000000060710a002 CR4: 0000000000370ef0 [436.530] Call Trace: [436.530] [436.530] btrfs_commit_transaction+0x73/0xc00 [btrfs] [436.531] ? btrfs_attach_transaction_barrier+0x1e/0x70 [btrfs] [436.532] sync_filesystem+0x7a/0x90 [436.533] generic_shutdown_super+0x28/0x180 [436.533] kill_anon_super+0x12/0x40 [436.534] btrfs_kill_super+0x12/0x20 [btrfs] [436.534] deactivate_locked_super+0x2f/0xb0 [436.534] cleanup_mnt+0xea/0x180 [436.535] task_work_run+0x58/0xa0 [436.535] exit_to_user_mode_loop+0xed/0x480 [436.536] ? __x64_sys_umount+0x68/0x80 [436.536] do_syscall_64+0x2a5/0xf20 [436.537] entry_SYSCALL_64_after_hwframe+0x76/0x7e [436.537] RIP: 0033:0x7fe5906b6217 [436.538] Code: 0d 00 f7 (...) [436.540] RSP: 002b:00007ffcd87a61f8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 [436.541] RAX: 0000000000000000 RBX: 00005618b9ecadc8 RCX: 00007fe5906b6217 [436.541] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 00005618b9ecb100 [436.542] RBP: 0000000000000000 R08: 00007ffcd87a4fe0 R09: 00000000ffffffff [436.544] R10: 0000000000000103 R11: ---truncated---

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43339

HIGH7.8

In the Linux kernel, the following vulnerability has been resolved: ipv6: prevent possible UaF in addrconf_permanent_addr() The mentioned helper try to warn the user about an exceptional condition, but the message is delivered too late, accessing the ipv6 after its possible deletion. Reorder the statement to avoid the possible UaF; while at it, place the warning outside the idev->lock as it needs no protection.

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xHIGH 7.8

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

References

CVE-2026-43340

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: comedi: Reinit dev->spinlock between attachments to low-level drivers `struct comedi_device` is the main controlling structure for a COMEDI device created by the COMEDI subsystem. It contains a member `spinlock` containing a spin-lock that is initialized by the COMEDI subsystem, but is reserved for use by a low-level driver attached to the COMEDI device (at least since commit 25436dc9d84f ("Staging: comedi: remove RT code")). Some COMEDI devices (those created on initialization of the COMEDI subsystem when the "comedi.comedi_num_legacy_minors" parameter is non-zero) can be attached to different low-level drivers over their lifetime using the `COMEDI_DEVCONFIG` ioctl command. This can result in inconsistent lock states being reported when there is a mismatch in the spin-lock locking levels used by each low-level driver to which the COMEDI device has been attached. Fix it by reinitializing `dev->spinlock` before calling the low-level driver's `attach` function pointer if `CONFIG_LOCKDEP` is enabled.

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

CVE-2026-43341

CRITICAL9.8

In the Linux kernel, the following vulnerability has been resolved: net/ipv6: ioam6: prevent schema length wraparound in trace fill ioam6_fill_trace_data() stores the schema contribution to the trace length in a u8. With bit 22 enabled and the largest schema payload, sclen becomes 1 + 1020 / 4, wraps from 256 to 0, and bypasses the remaining-space check. __ioam6_fill_trace_data() then positions the write cursor without reserving the schema area but still copies the 4-byte schema header and the full schema payload, overrunning the trace buffer. Keep sclen in an unsigned int so the remaining-space check and the write cursor calculation both see the full schema length.

Published: 2026-05-08Modified: 2026-06-19

CVSS 3.xCRITICAL 9.8

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

References

CVE-2026-43342

MEDIUM4.7

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_rndis: Protect RNDIS options with mutex The class/subclass/protocol options are suspectible to race conditions as they can be accessed concurrently through configfs. Use existing mutex to protect these options. This issue was identified during code inspection.

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xMEDIUM 4.7

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

References

CVE-2026-43343

MEDIUM5.5

In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_subset: Fix unbalanced refcnt in geth_free geth_alloc() increments the reference count, but geth_free() fails to decrement it. This prevents the configuration of attributes via configfs after unlinking the function. Decrement the reference count in geth_free() to ensure proper cleanup.

Published: 2026-05-08Modified: 2026-06-17

CVSS 3.xMEDIUM 5.5

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

References

GHSA-m38g-vww2-mvgx

HIGH7.5

Talos Linux has a local privilege escalation from untrusted workloads

Published: 2026-05-07Modified: 2026-06-08

CVSS 3.xHIGH 7.5

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

References

Package update kernel-image-6.18 in branch p11

Closed issues (295)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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").

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.

In the Linux kernel, the following vulnerability has been resolved: iio: gyro: mpu3050: Fix incorrect free_irq() variable The handler for the IRQ part of this driver is mpu3050->trig but, in the teardown free_irq() is called with handler mpu3050. Use correct IRQ handler when calling free_irq().

In the Linux kernel, the following vulnerability has been resolved: net: macb: properly unregister fixed rate clocks The additional resources allocated with clk_register_fixed_rate() need to be released with clk_unregister_fixed_rate(), otherwise they are lost.

In the Linux kernel, the following vulnerability has been resolved: netfilter: x_tables: ensure names are nul-terminated Reject names that lack a \0 character before feeding them to functions that expect c-strings. Fixes tag is the most recent commit that needs this change.

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix regsafe() for pointers to packet In case rold->reg->range == BEYOND_PKT_END && rcur->reg->range == N regsafe() may return true which may lead to current state with valid packet range not being explored. Fix the bug.

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

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

Talos Linux has a local privilege escalation from untrusted workloads