Vulnerability database

25,393 results · page 161 of 508

• Apr 13, 2026In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_expect: use expect->helper Use expect->helper in ctnetlink and /prCVE-2026-31414 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Critical 9.8

  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.

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 13, 2026UAF vulnerability in the kernel module.CVE-2026-34859 · Other software · Huawei · reported by psirt@huawei.comMedium 5.9

  UAF vulnerability in the kernel module. Impact: Successful exploitation of this vulnerability will affect availability and confidentiality.

  Product

  HarmonyOS

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordconsumer.huawei.comconsumer.huawei.com

• Apr 13, 2026Out-of-bounds write vulnerability in the kernel module.CVE-2026-34855 · Other software · Huawei · reported by psirt@huawei.comMedium 5.7

  Out-of-bounds write vulnerability in the kernel module. Impact: Successful exploitation of this vulnerability will affect availability and confidentiality.

  Product

  HarmonyOS

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordconsumer.huawei.com

• Apr 13, 2026UAF vulnerability in the kernel module.CVE-2026-34854 · Other software · Huawei · reported by psirt@huawei.comMedium 5.7

  UAF vulnerability in the kernel module. Impact: Successful exploitation of this vulnerability will affect availability and confidentiality.

  Product

  HarmonyOS

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordconsumer.huawei.com

• Apr 12, 2026In the Linux kernel, the following vulnerability has been resolved: bpf: Fix unsound scalar forking in maybe_fork_scalars() for BPF_OR maybe_fork_scalars() isCVE-2026-31413 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7.8

  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.

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 10, 2026In udev in systemd before 260, local root execution can occur via malicious hardware devices and unsanitized kernel output.CVE-2026-40225 · Other software · systemd · reported by MITREMedium 6.4

  In udev in systemd before 260, local root execution can occur via malicious hardware devices and unsanitized kernel output.

  Product

  systemd

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgithub.com

• Apr 10, 2026In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_mass_storage: Fix potential integer overflow in check_command_size_in_blocksCVE-2026-31412 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 8, 2026In the Linux kernel, the following vulnerability has been resolved: net: atm: fix crash due to unvalidated vcc pointer in sigd_send() Reproducer available at CVE-2026-31411 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

  In the Linux kernel, the following vulnerability has been resolved: net: atm: fix crash due to unvalidated vcc pointer in sigd_send() Reproducer available at [1]. The ATM send path (sendmsg -> vcc_sendmsg -> sigd_send) reads the vcc pointer from msg->vcc and uses it directly without any validation. This pointer comes from userspace via sendmsg() and can be arbitrarily forged: int fd = socket(AF_ATMSVC, SOCK_DGRAM, 0); ioctl(fd, ATMSIGD_CTRL); // become ATM signaling daemon struct msghdr msg = { .msg_iov = &iov, ... }; *(unsigned long *)(buf + 4) = 0xdeadbeef; // fake vcc pointer sendmsg(fd, &msg, 0); // kernel dereferences 0xdeadbeef In normal operation, the kernel sends the vcc pointer to the signaling daemon via sigd_enq() when processing operations like connect(), bind(), or listen(). The daemon is expected to return the same pointer when responding. However, a malicious daemon can send arbitrary pointer values. Fix this by introducing find_get_vcc() which validates the pointer by searching through vcc_hash (similar to how sigd_close() iterates over all VCCs), and acquires a reference via sock_hold() if found. Since struct atm_vcc embeds struct sock

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 7, 2026Generation of Predictable Numbers or Identifiers vulnerability in Erlang/OTP kernel (inet_res, inet_db modules) allows DNS Cache Poisoning.CVE-2026-28810 · Other software · Erlang · reported by 6b3ad84c-e1a6-4bf7-a703-f496b71e49dbMedium 6.3

  Generation of Predictable Numbers or Identifiers vulnerability in Erlang/OTP kernel (inet_res, inet_db modules) allows DNS Cache Poisoning. The built-in DNS resolver (inet_res) uses a sequential, process-global 16-bit transaction ID for UDP queries and does not implement source port randomization. Response validation relies almost entirely on this ID, making DNS cache poisoning practical for an attacker who can observe one query or predict the next ID. This conflicts with RFC 5452 recommendations for mitigating forged DNS answers. inet_res is intended for use in trusted network environments and with trusted recursive resolvers. Earlier documentation did not clearly state this deployment assumption, which could lead users to deploy the resolver in environments where spoofed DNS responses are possible. This vulnerability is associated with program files lib/kernel/src/inet_db.erl and lib/kernel/src/inet_res.erl. This issue affects OTP from OTP 17.0 before OTP 28.4.2, OTP 27.3.4.10 and OTP 26.2.5.19, corresponding to kernel from 3.0 before 10.6.2, 10.2.7.4 and 9.2.4.11.

  Product

  OTP

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordcna.erlef.orggithub.com

• Apr 6, 2026In the Linux kernel, the following vulnerability has been resolved: ksmbd: use volume UUID in FS_OBJECT_ID_INFORMATION Use sb->s_uuid for a proper volume idenCVE-2026-31410 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 6, 2026In the Linux kernel, the following vulnerability has been resolved: ksmbd: unset conn->binding on failed binding request When a multichannel SMB2_SESSION_SETUCVE-2026-31409 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 8.8

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 6, 2026In 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_fCVE-2026-31408 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 8.8

  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.

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 6, 2026In the Linux kernel, the following vulnerability has been resolved: netfilter: conntrack: add missing netlink policy validations Hyunwoo Kim reports out-of-boCVE-2026-31407 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7.1

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 6, 2026In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini() After cancel_delaCVE-2026-31406 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7.8

  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, ca

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 6, 2026In the Linux kernel, the following vulnerability has been resolved: media: dvb-net: fix OOB access in ULE extension header tables The ule_mandatory_ext_handleCVE-2026-31405 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Critical 9.8

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: NFSD: Hold net reference for the lifetime of /proc/fs/nfs/exports fd The /proc/fs/nfs/expoCVE-2026-31403 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7.8

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: nfsd: fix heap overflow in NFSv4.0 LOCK replay cache The NFSv4.0 replay cache uses a fixedCVE-2026-31402 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Critical 9.8

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: HID: bpf: prevent buffer overflow in hid_hw_request right now the returned value is considCVE-2026-31401 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7.8

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: sunrpc: fix cache_request leak in cache_release When a reader's file descriptor is closed CVE-2026-31400 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: nvdimm/bus: Fix potential use after free in asynchronous initialization Dingisoul with KASCVE-2026-31399 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7.8

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: mm/rmap: fix incorrect pte restoration for lazyfree folios We batch unmap anonymous lazyfrCVE-2026-31398 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7.8

  In the Linux kernel, the following vulnerability has been resolved: mm/rmap: fix incorrect pte restoration for lazyfree folios We batch unmap anonymous lazyfree folios by folio_unmap_pte_batch. If the batch has a mix of writable and non-writable bits, we may end up setting the entire batch writable. Fix this by respecting writable bit during batching. Although on a successful unmap of a lazyfree folio, the soft-dirty bit is lost, preserve it on pte restoration by respecting the bit during batching, to make the fix consistent w.r.t both writable bit and soft-dirty bit. I was able to write the below reproducer and crash the kernel. Explanation of reproducer (set 64K mTHP to always): Fault in a 64K large folio. Split the VMA at mid-point with MADV_DONTFORK. fork() - parent points to the folio with 8 writable ptes and 8 non-writable ptes. Merge the VMAs with MADV_DOFORK so that folio_unmap_pte_batch() can determine all the 16 ptes as a batch. Do MADV_FREE on the range to mark the folio as lazyfree. Write to the memory to dirty the pte, eventually rmap will dirty the folio. Then trigger reclaim, we will hit the pte restoration path, and the kernel will crash with the trace

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: mm/huge_memory: fix use of NULL folio in move_pages_huge_pmd() move_pages_huge_pmd() handlCVE-2026-31397 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7.8

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: net: macb: fix use-after-free access to PTP clock PTP clock is registered on every openingCVE-2026-31396 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7.8

  In the Linux kernel, the following vulnerability has been resolved: net: macb: fix use-after-free access to PTP clock PTP clock is registered on every opening of the interface and destroyed on every closing. However it may be accessed via get_ts_info ethtool call which is possible while the interface is just present in the kernel. BUG: KASAN: use-after-free in ptp_clock_index+0x47/0x50 drivers/ptp/ptp_clock.c:426 Read of size 4 at addr ffff8880194345cc by task syz.0.6/948 CPU: 1 PID: 948 Comm: syz.0.6 Not tainted 6.1.164+ #109 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.1-0-g3208b098f51a-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x8d/0xba lib/dump_stack.c:106 print_address_description mm/kasan/report.c:316 [inline] print_report+0x17f/0x496 mm/kasan/report.c:420 kasan_report+0xd9/0x180 mm/kasan/report.c:524 ptp_clock_index+0x47/0x50 drivers/ptp/ptp_clock.c:426 gem_get_ts_info+0x138/0x1e0 drivers/net/ethernet/cadence/macb_main.c:3349 macb_get_ts_info+0x68/0xb0 drivers/net/ethernet/cadence/macb_main.c:3371 __ethtool_get_ts_info+0x17c/0x260 net/ethtool/common.c:558 ethtool_get_ts_info n

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: bnxt_en: fix OOB access in DBG_BUF_PRODUCER async event handler The ASYNC_EVENT_CMPL_EVENTCVE-2026-31395 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7.1

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: mac80211: fix crash in ieee80211_chan_bw_change for AP_VLAN stations ieee80211_chan_bw_chaCVE-2026-31394 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Validate L2CAP_INFO_RSP payload length before access l2cap_information_rCVE-2026-31393 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 8.1

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: smb: client: fix krb5 mount with username option Customer reported that some of their krb5CVE-2026-31392 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 8.1

  In the Linux kernel, the following vulnerability has been resolved: smb: client: fix krb5 mount with username option Customer reported that some of their krb5 mounts were failing against a single server as the client was trying to mount the shares with wrong credentials. It turned out the client was reusing SMB session from first mount to try mounting the other shares, even though a different username= option had been specified to the other mounts. By using username mount option along with sec=krb5 to search for principals from keytab is supported by cifs.upcall(8) since cifs-utils-4.8. So fix this by matching username mount option in match_session() even with Kerberos. For example, the second mount below should fail with -ENOKEY as there is no 'foobar' principal in keytab (/etc/krb5.keytab). The client ends up reusing SMB session from first mount to perform the second one, which is wrong. ``` $ ktutil ktutil: add_entry -password -p testuser -k 1 -e aes256-cts Password for testuser@ZELDA.TEST: ktutil: write_kt /etc/krb5.keytab ktutil: quit $ klist -ke Keytab name: FILE:/etc/krb5.keytab KVNO Principal ---- ----------------------------------------------------------------

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: crypto: atmel-sha204a - Fix OOM ->tfm_count leak If memory allocation fails, decrement ->tCVE-2026-31391 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: drm/xe: Fix memory leak in xe_vm_madvise_ioctl When check_bo_args_are_sane() validation faCVE-2026-31390 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

  In the Linux kernel, the following vulnerability has been resolved: drm/xe: Fix memory leak in xe_vm_madvise_ioctl When check_bo_args_are_sane() validation fails, jump to the new free_vmas cleanup label to properly free the allocated resources. This ensures proper cleanup in this error path. (cherry picked from commit 29bd06faf727a4b76663e4be0f7d770e2d2a7965)

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: spi: fix use-after-free on controller registration failure Make sure to deregister from drCVE-2026-31389 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7.8

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: spi: fix statistics allocation The controller per-cpu statistics is not allocated until afCVE-2026-23475 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: mtd: Avoid boot crash in RedBoot partition table parser Given CONFIG_FORTIFY_SOURCE=y and CVE-2026-23474 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: serial: core: fix infinite loop in handle_tx() for PORT_UNKNOWN uart_write_room() and uartCVE-2026-23472 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

  In the Linux kernel, the following vulnerability has been resolved: serial: core: fix infinite loop in handle_tx() for PORT_UNKNOWN uart_write_room() and uart_write() behave inconsistently when xmit_buf is NULL (which happens for PORT_UNKNOWN ports that were never properly initialized): - uart_write_room() returns kfifo_avail() which can be > 0 - uart_write() checks xmit_buf and returns 0 if NULL This inconsistency causes an infinite loop in drivers that rely on tty_write_room() to determine if they can write: while (tty_write_room(tty) > 0) { written = tty->ops->write(...); // written is always 0, loop never exits } For example, caif_serial's handle_tx() enters an infinite loop when used with PORT_UNKNOWN serial ports, causing system hangs. Fix by making uart_write_room() also check xmit_buf and return 0 if it's NULL, consistent with uart_write(). Reproducer: https://gist.github.com/mrpre/d9a694cc0e19828ee3bc3b37983fde13

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: drm/imagination: Fix deadlock in soft reset sequence The soft reset sequence is currently CVE-2026-23470 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: drm/imagination: Synchronize interrupts before suspending the GPU The runtime PM suspend cCVE-2026-23469 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 4.7

  In the Linux kernel, the following vulnerability has been resolved: drm/imagination: Synchronize interrupts before suspending the GPU The runtime PM suspend callback doesn't know whether the IRQ handler is in progress on a different CPU core and doesn't wait for it to finish. Depending on timing, the IRQ handler could be running while the GPU is suspended, leading to kernel crashes when trying to access GPU registers. See example signature below. In a power off sequence initiated by the runtime PM suspend callback, wait for any IRQ handlers in progress on other CPU cores to finish, by calling synchronize_irq(). At the same time, remove the runtime PM resume/put calls in the threaded IRQ handler. On top of not being the right approach to begin with, and being at the wrong place as they should have wrapped all GPU register accesses, the driver would hit a deadlock between synchronize_irq() being called from a runtime PM suspend callback, holding the device power lock, and the resume callback requiring the same. Example crash signature on a TI AM68 SK platform: [ 337.241218] SError Interrupt on CPU0, code 0x00000000bf000000 -- SError [ 337.241239] CPU: 0 UID: 0 PID: 112 C

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Limit BO list entry count to prevent resource exhaustion Userspace can pass anCVE-2026-23468 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: drm/i915/dmc: Fix an unlikely NULL pointer deference at probe intel_dmc_update_dc6_allowedCVE-2026-23467 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

  In the Linux kernel, the following vulnerability has been resolved: drm/i915/dmc: Fix an unlikely NULL pointer deference at probe intel_dmc_update_dc6_allowed_count() oopses when DMC hasn't been initialized, and dmc is thus NULL. That would be the case when the call path is intel_power_domains_init_hw() -> {skl,bxt,icl}_display_core_init() -> gen9_set_dc_state() -> intel_dmc_update_dc6_allowed_count(), as intel_power_domains_init_hw() is called *before* intel_dmc_init(). However, gen9_set_dc_state() calls intel_dmc_update_dc6_allowed_count() conditionally, depending on the current and target DC states. At probe, the target is disabled, but if DC6 is enabled, the function is called, and an oops follows. Apparently it's quite unlikely that DC6 is enabled at probe, as we haven't seen this failure mode before. It is also strange to have DC6 enabled at boot, since that would require the DMC firmware (loaded by BIOS); the BIOS loading the DMC firmware and the driver stopping / reprogramming the firmware is a poorly specified sequence and as such unlikely an intentional BIOS behaviour. It's more likely that BIOS is leaving an unintentionally enabled DC6 HW state behind (without actua

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: drm/xe: Open-code GGTT MMIO access protection GGTT MMIO access is currently protected by hCVE-2026-23466 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7.8

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: btrfs: log new dentries when logging parent dir of a conflicting inode If we log the parenCVE-2026-23465 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

  In the Linux kernel, the following vulnerability has been resolved: btrfs: log new dentries when logging parent dir of a conflicting inode If we log the parent directory of a conflicting inode, we are not logging the new dentries of the directory, so when we finish we have the parent directory's inode marked as logged but we did not log its new dentries. As a consequence if the parent directory is explicitly fsynced later and it does not have any new changes since we logged it, the fsync is a no-op and after a power failure the new dentries are missing. Example scenario: $ mkdir foo $ sync $rmdir foo $ mkdir dir1 $ mkdir dir2 # A file with the same name and parent as the directory we just deleted # and was persisted in a past transaction. So the deleted directory's # inode is a conflicting inode of this new file's inode. $ touch foo $ ln foo dir2/link # The fsync on dir2 will log the parent directory (".") because the # conflicting inode (deleted directory) does not exists anymore, but it # it does not log its new dentries (dir1). $ xfs_io -c "fsync" dir2 # This fsync on the parent directory is no-op, since the previous fsync # logged it (

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: soc: microchip: mpfs: Fix memory leak in mpfs_sys_controller_probe() In mpfs_sys_controlleCVE-2026-23464 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: soc: fsl: qbman: fix race condition in qman_destroy_fq When QMAN_FQ_FLAG_DYNAMIC_FQID is sCVE-2026-23463 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 4.7

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: Bluetooth: HIDP: Fix possible UAF This fixes the following trace caused by not dropping l2CVE-2026-23462 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 8.8

  In the Linux kernel, the following vulnerability has been resolved: Bluetooth: HIDP: Fix possible UAF This fixes the following trace caused by not dropping l2cap_conn reference when user->remove callback is called: [ 97.809249] l2cap_conn_free: freeing conn ffff88810a171c00 [ 97.809907] CPU: 1 UID: 0 PID: 1419 Comm: repro_standalon Not tainted 7.0.0-rc1-dirty #14 PREEMPT(lazy) [ 97.809935] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014 [ 97.809947] Call Trace: [ 97.809954] <TASK> [ 97.809961] dump_stack_lvl (lib/dump_stack.c:122) [ 97.809990] l2cap_conn_free (net/bluetooth/l2cap_core.c:1808) [ 97.810017] l2cap_conn_del (./include/linux/kref.h:66 net/bluetooth/l2cap_core.c:1821 net/bluetooth/l2cap_core.c:1798) [ 97.810055] l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7347 (discriminator 1) net/bluetooth/l2cap_core.c:7340 (discriminator 1)) [ 97.810086] ? __pfx_l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7341) [ 97.810117] hci_conn_hash_flush (./include/net/bluetooth/hci_core.h:2152 (discriminator 2) net/bluetooth/hci_conn.c:2644 (discriminator 2)) [ 97.810148] hci_dev_close_sync (net/bluetooth/hci_s

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix use-after-free in l2cap_unregister_user After commit ab4eedb790ca ("CVE-2026-23461 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 8.8

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: net/rose: fix NULL pointer dereference in rose_transmit_link on reconnect syzkaller reportCVE-2026-23460 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Medium 5.5

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: ip_tunnel: adapt iptunnel_xmit_stats() to NETDEV_PCPU_STAT_DSTATS Blamed commits forgot thCVE-2026-23459 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 8.2

  In the Linux kernel, the following vulnerability has been resolved: ip_tunnel: adapt iptunnel_xmit_stats() to NETDEV_PCPU_STAT_DSTATS Blamed commits forgot that vxlan/geneve use udp_tunnel[6]_xmit_skb() which call iptunnel_xmit_stats(). iptunnel_xmit_stats() was assuming tunnels were only using NETDEV_PCPU_STAT_TSTATS. @syncp offset in pcpu_sw_netstats and pcpu_dstats is different. 32bit kernels would either have corruptions or freezes if the syncp sequence was overwritten. This patch also moves pcpu_stat_type closer to dev->{t,d}stats to avoid a potential cache line miss since iptunnel_xmit_stats() needs to read it.

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: fix use-after-free in ctnetlink_dump_exp_ct() ctnetlink_dump_exp_ct(CVE-2026-23458 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7.8

  In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: fix use-after-free in ctnetlink_dump_exp_ct() ctnetlink_dump_exp_ct() stores a conntrack pointer in cb->data for the netlink dump callback ctnetlink_exp_ct_dump_table(), but drops the conntrack reference immediately after netlink_dump_start(). When the dump spans multiple rounds, the second recvmsg() triggers the dump callback which dereferences the now-freed conntrack via nfct_help(ct), leading to a use-after-free on ct->ext. The bug is that the netlink_dump_control has no .start or .done callbacks to manage the conntrack reference across dump rounds. Other dump functions in the same file (e.g. ctnetlink_get_conntrack) properly use .start/.done callbacks for this purpose. Fix this by adding .start and .done callbacks that hold and release the conntrack reference for the duration of the dump, and move the nfct_help() call after the cb->args[0] early-return check in the dump callback to avoid dereferencing ct->ext unnecessarily. BUG: KASAN: slab-use-after-free in ctnetlink_exp_ct_dump_table+0x4f/0x2e0 Read of size 8 at addr ffff88810597ebf0 by task ctnetlink_poc/133 CPU: 1 UID: 0 PID

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_sip: fix Content-Length u32 truncation in sip_help_tcp() sip_help_CVE-2026-23457 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 8.6

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_h323: fix OOB read in decode_int() CONS case In decode_int(), the CVE-2026-23456 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 8.2

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_h323: check for zero length in DecodeQ931() In DecodeQ931(), the UCVE-2026-23455 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67Critical 9.1

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

• Apr 3, 2026In the Linux kernel, the following vulnerability has been resolved: net: mana: fix use-after-free in mana_hwc_destroy_channel() by reordering teardown A potenCVE-2026-23454 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 7

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

  Product

  Linux

  What to do

  Apply the vendor’s update. The NVD record links to the advisory.

  Full record and what to do →NVD recordgit.kernel.orggit.kernel.org

Where this comes from: the exploited list is CISA’s Known Exploited Vulnerabilities catalog. Everything else is the whole National Vulnerability Database, where each record is published by the team that found the bug (Wordfence, Patchstack, WPScan, the vendors themselves and others); we show who. Exploit odds are FIRST’s EPSS, updated daily. Titles and categories are ours, so check the linked record before acting on a detail. For a write-up of the big ones, see our advisories. Every vendor, and every WordPress plugin and theme with a recorded flaw, also has its own page. All of it is free to reuse as JSON, CSV or RSS.