Export limit exceeded: 12099 CVEs match your query. Please refine your search to export 10,000 CVEs or fewer.
Search
Search Results (12099 CVEs found)
| CVE | Vendors | Products | Updated | CVSS v3.1 |
|---|---|---|---|---|
| CVE-2026-31426 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 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-2026-31406 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 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-2026-31408 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 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-2026-43481 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: net-shapers: don't free reply skb after genlmsg_reply() genlmsg_reply() hands the reply skb to netlink, and netlink_unicast() consumes it on all return paths, whether the skb is queued successfully or freed on an error path. net_shaper_nl_get_doit() and net_shaper_nl_cap_get_doit() currently jump to free_msg after genlmsg_reply() fails and call nlmsg_free(msg), which can hit the same skb twice. Return the genlmsg_reply() error directly and keep free_msg only for pre-reply failures. | ||||
| CVE-2026-43380 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: hwmon: (pmbus/q54sj108a2) fix stack overflow in debugfs read The q54sj108a2_debugfs_read function suffers from a stack buffer overflow due to incorrect arguments passed to bin2hex(). The function currently passes 'data' as the destination and 'data_char' as the source. Because bin2hex() converts each input byte into two hex characters, a 32-byte block read results in 64 bytes of output. Since 'data' is only 34 bytes (I2C_SMBUS_BLOCK_MAX + 2), this writes 30 bytes past the end of the buffer onto the stack. Additionally, the arguments were swapped: it was reading from the zero-initialized 'data_char' and writing to 'data', resulting in all-zero output regardless of the actual I2C read. Fix this by: 1. Expanding 'data_char' to 66 bytes to safely hold the hex output. 2. Correcting the bin2hex() argument order and using the actual read count. 3. Using a pointer to select the correct output buffer for the final simple_read_from_buffer call. | ||||
| CVE-2026-31413 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 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-2026-23461 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 8.8 High |
| 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. | ||||
| CVE-2026-23462 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 8.8 High |
| 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_sync.c:5360) [ 97.810180] ? __pfx_hci_dev_close_sync (net/bluetooth/hci_sync.c:5285) [ 97.810212] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810242] ? up_write (./arch/x86/include/asm/atomic64_64.h:87 (discriminator 5) ./include/linux/atomic/atomic-arch-fallback.h:2852 (discriminator 5) ./include/linux/atomic/atomic-long.h:268 (discriminator 5) ./include/linux/atomic/atomic-instrumented.h:3391 (discriminator 5) kernel/locking/rwsem.c:1385 (discriminator 5) kernel/locking/rwsem.c:1643 (discriminator 5)) [ 97.810267] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810290] ? rcu_is_watching (./arch/x86/include/asm/atomic.h:23 ./include/linux/atomic/atomic-arch-fallback.h:457 ./include/linux/context_tracking.h:128 kernel/rcu/tree.c:752) [ 97.810320] hci_unregister_dev (net/bluetooth/hci_core.c:504 net/bluetooth/hci_core.c:2716) [ 97.810346] vhci_release (drivers/bluetooth/hci_vhci.c:691) [ 97.810375] ? __pfx_vhci_release (drivers/bluetooth/hci_vhci.c:678) [ 97.810404] __fput (fs/file_table.c:470) [ 97.810430] task_work_run (kernel/task_work.c:235) [ 97.810451] ? __pfx_task_work_run (kernel/task_work.c:201) [ 97.810472] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810495] ? do_raw_spin_unlock (./include/asm-generic/qspinlock.h:128 (discriminator 5) kernel/locking/spinlock_debug.c:142 (discriminator 5)) [ 97.810527] do_exit (kernel/exit.c:972) [ 97.810547] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810574] ? __pfx_do_exit (kernel/exit.c:897) [ 97.810594] ? lock_acquire (kernel/locking/lockdep.c:470 (discriminator 6) kernel/locking/lockdep.c:5870 (discriminator 6) kernel/locking/lockdep.c:5825 (discriminator 6)) [ 97.810616] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810639] ? do_raw_spin_lock (kernel/locking/spinlock_debug.c:95 (discriminator 4) kernel/locking/spinlock_debug.c:118 (discriminator 4)) [ 97.810664] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810688] ? find_held_lock (kernel/locking/lockdep.c:5350 (discriminator 1)) [ 97.810721] do_group_exit (kernel/exit.c:1093) [ 97.810745] get_signal (kernel/signal.c:3007 (discriminator 1)) [ 97.810772] ? security_file_permission (./arch/x86/include/asm/jump_label.h:37 security/security.c:2366) [ 97.810803] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810826] ? vfs_read (fs/read_write.c:555) [ 97.810854] ? __pfx_get_signal (kernel/signal.c:2800) [ 97.810880] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810905] ? __pfx_vfs_read (fs/read_write.c:555) [ 97.810932] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810960] arch_do_signal_or_restart (arch/ ---truncated--- | ||||
| CVE-2026-23466 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| 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) | ||||
| CVE-2026-31389 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| 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. | ||||
| CVE-2026-31396 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 7.8 High |
| 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 net/ethtool/ioctl.c:2367 [inline] __dev_ethtool net/ethtool/ioctl.c:3017 [inline] dev_ethtool+0x2b05/0x6290 net/ethtool/ioctl.c:3095 dev_ioctl+0x637/0x1070 net/core/dev_ioctl.c:510 sock_do_ioctl+0x20d/0x2c0 net/socket.c:1215 sock_ioctl+0x577/0x6d0 net/socket.c:1320 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x18c/0x210 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:46 [inline] do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 </TASK> Allocated by task 457: kmalloc include/linux/slab.h:563 [inline] kzalloc include/linux/slab.h:699 [inline] ptp_clock_register+0x144/0x10e0 drivers/ptp/ptp_clock.c:235 gem_ptp_init+0x46f/0x930 drivers/net/ethernet/cadence/macb_ptp.c:375 macb_open+0x901/0xd10 drivers/net/ethernet/cadence/macb_main.c:2920 __dev_open+0x2ce/0x500 net/core/dev.c:1501 __dev_change_flags+0x56a/0x740 net/core/dev.c:8651 dev_change_flags+0x92/0x170 net/core/dev.c:8722 do_setlink+0xaf8/0x3a80 net/core/rtnetlink.c:2833 __rtnl_newlink+0xbf4/0x1940 net/core/rtnetlink.c:3608 rtnl_newlink+0x63/0xa0 net/core/rtnetlink.c:3655 rtnetlink_rcv_msg+0x3c6/0xed0 net/core/rtnetlink.c:6150 netlink_rcv_skb+0x15d/0x430 net/netlink/af_netlink.c:2511 netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline] netlink_unicast+0x6d7/0xa30 net/netlink/af_netlink.c:1344 netlink_sendmsg+0x97e/0xeb0 net/netlink/af_netlink.c:1872 sock_sendmsg_nosec net/socket.c:718 [inline] __sock_sendmsg+0x14b/0x180 net/socket.c:730 __sys_sendto+0x320/0x3b0 net/socket.c:2152 __do_sys_sendto net/socket.c:2164 [inline] __se_sys_sendto net/socket.c:2160 [inline] __x64_sys_sendto+0xdc/0x1b0 net/socket.c:2160 do_syscall_x64 arch/x86/entry/common.c:46 [inline] do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Freed by task 938: kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1729 [inline] slab_free_freelist_hook mm/slub.c:1755 [inline] slab_free mm/slub.c:3687 [inline] __kmem_cache_free+0xbc/0x320 mm/slub.c:3700 device_release+0xa0/0x240 drivers/base/core.c:2507 kobject_cleanup lib/kobject.c:681 [inline] kobject_release lib/kobject.c:712 [inline] kref_put include/linux/kref.h:65 [inline] kobject_put+0x1cd/0x350 lib/kobject.c:729 put_device+0x1b/0x30 drivers/base/core.c:3805 ptp_clock_unregister+0x171/0x270 drivers/ptp/ptp_clock.c:391 gem_ptp_remove+0x4e/0x1f0 drivers/net/ethernet/cadence/macb_ptp.c:404 macb_close+0x1c8/0x270 drivers/net/ethernet/cadence/macb_main.c:2966 __dev_close_many+0x1b9/0x310 net/core/dev.c:1585 __dev_close net/core/dev.c:1597 [inline] __dev_change_flags+0x2bb/0x740 net/core/dev.c:8649 dev_change_fl ---truncated--- | ||||
| CVE-2026-31397 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 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. | ||||
| CVE-2026-31398 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 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-2026-31401 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 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-2026-31403 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 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-2026-31404 | 1 Linux | 1 Linux Kernel | 2026-05-20 | 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-2025-68065 | 2 Liquidthemes, Wordpress | 2 Hub, Wordpress | 2026-05-20 | 7.5 High |
| Improper Control of Filename for Include/Require Statement in PHP Program ('PHP Remote File Inclusion') vulnerability in LiquidThemes Hub Core allows PHP Local File Inclusion. This issue affects Hub Core: from n/a before 6.0.2. | ||||
| CVE-2026-43091 | 1 Linux | 1 Linux Kernel | 2026-05-19 | 7.8 High |
| In the Linux kernel, the following vulnerability has been resolved: xfrm: Wait for RCU readers during policy netns exit xfrm_policy_fini() frees the policy_bydst hash tables after flushing the policy work items and deleting all policies, but it does not wait for concurrent RCU readers to leave their read-side critical sections first. The policy_bydst tables are published via rcu_assign_pointer() and are looked up through rcu_dereference_check(), so netns teardown must also wait for an RCU grace period before freeing the table memory. Fix this by adding synchronize_rcu() before freeing the policy hash tables. | ||||
| CVE-2026-31435 | 1 Linux | 1 Linux Kernel | 2026-05-19 | 8.8 High |
| 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. | ||||
| CVE-2022-21840 | 1 Microsoft | 10 365 Apps, Excel, Office and 7 more | 2026-05-19 | 8.8 High |
| Microsoft Office Remote Code Execution Vulnerability | ||||