Export limit exceeded: 347343 CVEs match your query. Please refine your search to export 10,000 CVEs or fewer.
Search
Search Results (347343 CVEs found)
| CVE | Vendors | Products | Updated | CVSS v3.1 |
|---|---|---|---|---|
| CVE-2026-31454 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| 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. | ||||
| CVE-2026-31453 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| 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. | ||||
| CVE-2026-31448 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 9.4 Critical |
| 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] | ||||
| CVE-2026-31447 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| 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. | ||||
| CVE-2026-31436 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 9.8 Critical |
| 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. | ||||
| CVE-2026-31432 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 8.8 High |
| 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. | ||||
| CVE-2026-31426 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7 High |
| 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: <TASK> 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) </TASK> 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 | ||||
| CVE-2026-31417 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.5 High |
| 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()`. | ||||
| CVE-2026-31413 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| 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. | ||||
| CVE-2026-31409 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 8.8 High |
| 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. | ||||
| CVE-2026-31408 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 8.8 High |
| 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. | ||||
| CVE-2026-31407 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.1 High |
| 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. | ||||
| CVE-2026-31406 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| 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(). | ||||
| CVE-2026-31405 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 9.8 Critical |
| 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. | ||||
| CVE-2026-31404 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: NFSD: Defer sub-object cleanup in export put callbacks svc_export_put() calls path_put() and auth_domain_put() immediately when the last reference drops, before the RCU grace period. RCU readers in e_show() and c_show() access both ex_path (via seq_path/d_path) and ex_client->name (via seq_escape) without holding a reference. If cache_clean removes the entry and drops the last reference concurrently, the sub-objects are freed while still in use, producing a NULL pointer dereference in d_path. Commit 2530766492ec ("nfsd: fix UAF when access ex_uuid or ex_stats") moved kfree of ex_uuid and ex_stats into the call_rcu callback, but left path_put() and auth_domain_put() running before the grace period because both may sleep and call_rcu callbacks execute in softirq context. Replace call_rcu/kfree_rcu with queue_rcu_work(), which defers the callback until after the RCU grace period and executes it in process context where sleeping is permitted. This allows path_put() and auth_domain_put() to be moved into the deferred callback alongside the other resource releases. Apply the same fix to expkey_put(), which has the identical pattern with ek_path and ek_client. A dedicated workqueue scopes the shutdown drain to only NFSD export release work items; flushing the shared system_unbound_wq would stall on unrelated work from other subsystems. nfsd_export_shutdown() uses rcu_barrier() followed by flush_workqueue() to ensure all deferred release callbacks complete before the export caches are destroyed. Reviwed-by: Jeff Layton <jlayton@kernel.org> | ||||
| CVE-2026-31403 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| 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. | ||||
| CVE-2026-31402 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 9.8 Critical |
| In the Linux kernel, the following vulnerability has been resolved: nfsd: fix heap overflow in NFSv4.0 LOCK replay cache The NFSv4.0 replay cache uses a fixed 112-byte inline buffer (rp_ibuf[NFSD4_REPLAY_ISIZE]) to store encoded operation responses. This size was calculated based on OPEN responses and does not account for LOCK denied responses, which include the conflicting lock owner as a variable-length field up to 1024 bytes (NFS4_OPAQUE_LIMIT). When a LOCK operation is denied due to a conflict with an existing lock that has a large owner, nfsd4_encode_operation() copies the full encoded response into the undersized replay buffer via read_bytes_from_xdr_buf() with no bounds check. This results in a slab-out-of-bounds write of up to 944 bytes past the end of the buffer, corrupting adjacent heap memory. This can be triggered remotely by an unauthenticated attacker with two cooperating NFSv4.0 clients: one sets a lock with a large owner string, then the other requests a conflicting lock to provoke the denial. We could fix this by increasing NFSD4_REPLAY_ISIZE to allow for a full opaque, but that would increase the size of every stateowner, when most lockowners are not that large. Instead, fix this by checking the encoded response length against NFSD4_REPLAY_ISIZE before copying into the replay buffer. If the response is too large, set rp_buflen to 0 to skip caching the replay payload. The status is still cached, and the client already received the correct response on the original request. | ||||
| CVE-2026-31401 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| 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. | ||||
| CVE-2026-31398 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: mm/rmap: fix incorrect pte restoration for lazyfree folios We batch unmap anonymous lazyfree folios by folio_unmap_pte_batch. If the batch has a mix of writable and non-writable bits, we may end up setting the entire batch writable. Fix this by respecting writable bit during batching. Although on a successful unmap of a lazyfree folio, the soft-dirty bit is lost, preserve it on pte restoration by respecting the bit during batching, to make the fix consistent w.r.t both writable bit and soft-dirty bit. I was able to write the below reproducer and crash the kernel. Explanation of reproducer (set 64K mTHP to always): Fault in a 64K large folio. Split the VMA at mid-point with MADV_DONTFORK. fork() - parent points to the folio with 8 writable ptes and 8 non-writable ptes. Merge the VMAs with MADV_DOFORK so that folio_unmap_pte_batch() can determine all the 16 ptes as a batch. Do MADV_FREE on the range to mark the folio as lazyfree. Write to the memory to dirty the pte, eventually rmap will dirty the folio. Then trigger reclaim, we will hit the pte restoration path, and the kernel will crash with the trace given below. The BUG happens at: BUG_ON(atomic_inc_return(&ptc->anon_map_count) > 1 && rw); The code path is asking for anonymous page to be mapped writable into the pagetable. The BUG_ON() firing implies that such a writable page has been mapped into the pagetables of more than one process, which breaks anonymous memory/CoW semantics. [ 21.134473] kernel BUG at mm/page_table_check.c:118! [ 21.134497] Internal error: Oops - BUG: 00000000f2000800 [#1] SMP [ 21.135917] Modules linked in: [ 21.136085] CPU: 1 UID: 0 PID: 1735 Comm: dup-lazyfree Not tainted 7.0.0-rc1-00116-g018018a17770 #1028 PREEMPT [ 21.136858] Hardware name: linux,dummy-virt (DT) [ 21.137019] pstate: 21400005 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) [ 21.137308] pc : page_table_check_set+0x28c/0x2a8 [ 21.137607] lr : page_table_check_set+0x134/0x2a8 [ 21.137885] sp : ffff80008a3b3340 [ 21.138124] x29: ffff80008a3b3340 x28: fffffdffc3d14400 x27: ffffd1a55e03d000 [ 21.138623] x26: 0040000000000040 x25: ffffd1a55f7dd000 x24: 0000000000000001 [ 21.139045] x23: 0000000000000001 x22: 0000000000000001 x21: ffffd1a55f217f30 [ 21.139629] x20: 0000000000134521 x19: 0000000000134519 x18: 005c43e000040000 [ 21.140027] x17: 0001400000000000 x16: 0001700000000000 x15: 000000000000ffff [ 21.140578] x14: 000000000000000c x13: 005c006000000000 x12: 0000000000000020 [ 21.140828] x11: 0000000000000000 x10: 005c000000000000 x9 : ffffd1a55c079ee0 [ 21.141077] x8 : 0000000000000001 x7 : 005c03e000040000 x6 : 000000004000ffff [ 21.141490] x5 : ffff00017fffce00 x4 : 0000000000000001 x3 : 0000000000000002 [ 21.141741] x2 : 0000000000134510 x1 : 0000000000000000 x0 : ffff0000c08228c0 [ 21.141991] Call trace: [ 21.142093] page_table_check_set+0x28c/0x2a8 (P) [ 21.142265] __page_table_check_ptes_set+0x144/0x1e8 [ 21.142441] __set_ptes_anysz.constprop.0+0x160/0x1a8 [ 21.142766] contpte_set_ptes+0xe8/0x140 [ 21.142907] try_to_unmap_one+0x10c4/0x10d0 [ 21.143177] rmap_walk_anon+0x100/0x250 [ 21.143315] try_to_unmap+0xa0/0xc8 [ 21.143441] shrink_folio_list+0x59c/0x18a8 [ 21.143759] shrink_lruvec+0x664/0xbf0 [ 21.144043] shrink_node+0x218/0x878 [ 21.144285] __node_reclaim.constprop.0+0x98/0x338 [ 21.144763] user_proactive_reclaim+0x2a4/0x340 [ 21.145056] reclaim_store+0x3c/0x60 [ 21.145216] dev_attr_store+0x20/0x40 [ 21.145585] sysfs_kf_write+0x84/0xa8 [ 21.145835] kernfs_fop_write_iter+0x130/0x1c8 [ 21.145994] vfs_write+0x2b8/0x368 [ 21.146119] ksys_write+0x70/0x110 [ 21.146240] __arm64_sys_write+0x24/0x38 [ 21.146380] invoke_syscall+0x50/0x120 [ 21.146513] el0_svc_common.constprop.0+0x48/0xf8 [ 21.146679] do_el0_svc+0x28/0x40 [ 21.146798] el0_svc+0x34/0x110 [ 21.146926] el0t ---truncated--- | ||||
| CVE-2026-31397 | 1 Linux | 1 Linux Kernel | 2026-04-27 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: mm/huge_memory: fix use of NULL folio in move_pages_huge_pmd() move_pages_huge_pmd() handles UFFDIO_MOVE for both normal THPs and huge zero pages. For the huge zero page path, src_folio is explicitly set to NULL, and is used as a sentinel to skip folio operations like lock and rmap. In the huge zero page branch, src_folio is NULL, so folio_mk_pmd(NULL, pgprot) passes NULL through folio_pfn() and page_to_pfn(). With SPARSEMEM_VMEMMAP this silently produces a bogus PFN, installing a PMD pointing to non-existent physical memory. On other memory models it is a NULL dereference. Use page_folio(src_page) to obtain the valid huge zero folio from the page, which was obtained from pmd_page() and remains valid throughout. After commit d82d09e48219 ("mm/huge_memory: mark PMD mappings of the huge zero folio special"), moved huge zero PMDs must remain special so vm_normal_page_pmd() continues to treat them as special mappings. move_pages_huge_pmd() currently reconstructs the destination PMD in the huge zero page branch, which drops PMD state such as pmd_special() on architectures with CONFIG_ARCH_HAS_PTE_SPECIAL. As a result, vm_normal_page_pmd() can treat the moved huge zero PMD as a normal page and corrupt its refcount. Instead of reconstructing the PMD from the folio, derive the destination entry from src_pmdval after pmdp_huge_clear_flush(), then handle the PMD metadata the same way move_huge_pmd() does for moved entries by marking it soft-dirty and clearing uffd-wp. | ||||