Total
19304 CVE
| CVE | Vendors | Products | Updated | CVSS v2 | CVSS v3 |
|---|---|---|---|---|---|
| CVE-2026-52950 | 1 Linux | 1 Linux Kernel | 2026-07-27 | N/A | 7.8 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: drm/xe/dma-buf: fix UAF with retry loop Retry doesn't work here, since bo will be freed on error, leading to UAF. However, now that we do the alloc & init before the attach, we can now combine this as one unit and have the init do the alloc for us. This should make the retry safe. Reported by Sashiko. v2: Fix up the error unwind (CI) (cherry picked from commit 479669418253e0f27f8cf5db01a731352ea592e7) | |||||
| CVE-2026-46287 | 1 Linux | 1 Linux Kernel | 2026-07-25 | N/A | 5.5 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: net: txgbe: fix RTNL assertion warning when remove module For the copper NIC with external PHY, the driver called phylink_connect_phy() during probe and phylink_disconnect_phy() during remove. It caused an RTNL assertion warning in phylink_disconnect_phy() upon module remove. To fix this, add rtnl_lock() and rtnl_unlock() around the phylink_disconnect_phy() in remove function. ------------[ cut here ]------------ RTNL: assertion failed at drivers/net/phy/phylink.c (2351) WARNING: drivers/net/phy/phylink.c:2351 at phylink_disconnect_phy+0xd8/0xf0 [phylink], CPU#0: rmmod/4464 Modules linked in: ... CPU: 0 UID: 0 PID: 4464 Comm: rmmod Kdump: loaded Not tainted 7.0.0-rc4+ Hardware name: Micro-Star International Co., Ltd. MS-7E16/X670E GAMING PLUS WIFI (MS-7E16), BIOS 1.90 12/31/2024 RIP: 0010:phylink_disconnect_phy+0xe4/0xf0 [phylink] Code: 5b 41 5c 41 5d 41 5e 41 5f 5d 31 c0 31 d2 31 f6 31 ff e9 3a 38 8f e7 48 8d 3d 48 87 e2 ff ba 2f 09 00 00 48 c7 c6 c1 22 24 c0 <67> 48 0f b9 3a e9 34 ff ff ff 66 90 90 90 90 90 90 90 90 90 90 90 RSP: 0018:ffffce7288363ac0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff89654b2a1a00 RCX: 0000000000000000 RDX: 000000000000092f RSI: ffffffffc02422c1 RDI: ffffffffc0239020 RBP: ffffce7288363ae8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8964c4022000 R13: ffff89654fce3028 R14: ffff89654ebb4000 R15: ffffffffc0226348 FS: 0000795e80d93780(0000) GS:ffff896c52857000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005b528b592000 CR3: 0000000170d0f000 CR4: 0000000000f50ef0 PKRU: 55555554 Call Trace: <TASK> txgbe_remove_phy+0xbb/0xd0 [txgbe] txgbe_remove+0x4c/0xb0 [txgbe] pci_device_remove+0x41/0xb0 device_remove+0x43/0x80 device_release_driver_internal+0x206/0x270 driver_detach+0x4a/0xa0 bus_remove_driver+0x83/0x120 driver_unregister+0x2f/0x60 pci_unregister_driver+0x40/0x90 txgbe_driver_exit+0x10/0x850 [txgbe] __do_sys_delete_module.isra.0+0x1c3/0x2f0 __x64_sys_delete_module+0x12/0x20 x64_sys_call+0x20c3/0x2390 do_syscall_64+0x11c/0x1500 ? srso_alias_return_thunk+0x5/0xfbef5 ? do_syscall_64+0x15a/0x1500 ? srso_alias_return_thunk+0x5/0xfbef5 ? do_fault+0x312/0x580 ? srso_alias_return_thunk+0x5/0xfbef5 ? __handle_mm_fault+0x9d5/0x1040 ? srso_alias_return_thunk+0x5/0xfbef5 ? count_memcg_events+0x101/0x1d0 ? srso_alias_return_thunk+0x5/0xfbef5 ? handle_mm_fault+0x1e8/0x2f0 ? srso_alias_return_thunk+0x5/0xfbef5 ? do_user_addr_fault+0x2f8/0x820 ? srso_alias_return_thunk+0x5/0xfbef5 ? irqentry_exit+0xb2/0x600 ? srso_alias_return_thunk+0x5/0xfbef5 ? exc_page_fault+0x92/0x1c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e | |||||
| CVE-2026-33116 | 3 Apple, Linux, Microsoft | 18 Macos, Linux Kernel, .net and 15 more | 2026-07-25 | N/A | 7.5 HIGH |
| Loop with unreachable exit condition ('infinite loop') in .NET, .NET Framework, Visual Studio allows an unauthorized attacker to deny service over a network. | |||||
| CVE-2026-31411 | 1 Linux | 1 Linux Kernel | 2026-07-25 | N/A | 5.5 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: net: atm: fix crash due to unvalidated vcc pointer in sigd_send() Reproducer available at [1]. The ATM send path (sendmsg -> vcc_sendmsg -> sigd_send) reads the vcc pointer from msg->vcc and uses it directly without any validation. This pointer comes from userspace via sendmsg() and can be arbitrarily forged: int fd = socket(AF_ATMSVC, SOCK_DGRAM, 0); ioctl(fd, ATMSIGD_CTRL); // become ATM signaling daemon struct msghdr msg = { .msg_iov = &iov, ... }; *(unsigned long *)(buf + 4) = 0xdeadbeef; // fake vcc pointer sendmsg(fd, &msg, 0); // kernel dereferences 0xdeadbeef In normal operation, the kernel sends the vcc pointer to the signaling daemon via sigd_enq() when processing operations like connect(), bind(), or listen(). The daemon is expected to return the same pointer when responding. However, a malicious daemon can send arbitrary pointer values. Fix this by introducing find_get_vcc() which validates the pointer by searching through vcc_hash (similar to how sigd_close() iterates over all VCCs), and acquires a reference via sock_hold() if found. Since struct atm_vcc embeds struct sock as its first member, they share the same lifetime. Therefore using sock_hold/sock_put is sufficient to keep the vcc alive while it is being used. Note that there may be a race with sigd_close() which could mark the vcc with various flags (e.g., ATM_VF_RELEASED) after find_get_vcc() returns. However, sock_hold() guarantees the memory remains valid, so this race only affects the logical state, not memory safety. [1]: https://gist.github.com/mrpre/1ba5949c45529c511152e2f4c755b0f3 | |||||
| CVE-2026-31389 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 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-2026-31394 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| 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] | |||||
| CVE-2026-23460 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: net/rose: fix NULL pointer dereference in rose_transmit_link on reconnect syzkaller reported a bug [1], and the reproducer is available at [2]. ROSE sockets use four sk->sk_state values: TCP_CLOSE, TCP_LISTEN, TCP_SYN_SENT, and TCP_ESTABLISHED. rose_connect() already rejects calls for TCP_ESTABLISHED (-EISCONN) and TCP_CLOSE with SS_CONNECTING (-ECONNREFUSED), but lacks a check for TCP_SYN_SENT. When rose_connect() is called a second time while the first connection attempt is still in progress (TCP_SYN_SENT), it overwrites rose->neighbour via rose_get_neigh(). If that returns NULL, the socket is left with rose->state == ROSE_STATE_1 but rose->neighbour == NULL. When the socket is subsequently closed, rose_release() sees ROSE_STATE_1 and calls rose_write_internal() -> rose_transmit_link(skb, NULL), causing a NULL pointer dereference. Per connect(2), a second connect() while a connection is already in progress should return -EALREADY. Add this missing check for TCP_SYN_SENT to complete the state validation in rose_connect(). [1] https://syzkaller.appspot.com/bug?extid=d00f90e0af54102fb271 [2] https://gist.github.com/mrpre/9e6779e0d13e2c66779b1653fef80516 | |||||
| CVE-2026-31399 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.8 HIGH |
| 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(). | |||||
| CVE-2026-31409 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 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-2026-23457 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 8.6 HIGH |
| 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. | |||||
| CVE-2026-31390 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| 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) | |||||
| CVE-2026-31410 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| 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(). | |||||
| CVE-2026-31407 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 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 | 2026-07-24 | N/A | 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-2026-31400 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| 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. | |||||
| CVE-2026-23475 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| 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). | |||||
| CVE-2026-23462 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 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-2026-31401 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 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-2026-23456 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 8.2 HIGH |
| 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(). | |||||
| CVE-2026-23458 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.8 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: fix use-after-free in ctnetlink_dump_exp_ct() ctnetlink_dump_exp_ct() stores a conntrack pointer in cb->data for the netlink dump callback ctnetlink_exp_ct_dump_table(), but drops the conntrack reference immediately after netlink_dump_start(). When the dump spans multiple rounds, the second recvmsg() triggers the dump callback which dereferences the now-freed conntrack via nfct_help(ct), leading to a use-after-free on ct->ext. The bug is that the netlink_dump_control has no .start or .done callbacks to manage the conntrack reference across dump rounds. Other dump functions in the same file (e.g. ctnetlink_get_conntrack) properly use .start/.done callbacks for this purpose. Fix this by adding .start and .done callbacks that hold and release the conntrack reference for the duration of the dump, and move the nfct_help() call after the cb->args[0] early-return check in the dump callback to avoid dereferencing ct->ext unnecessarily. BUG: KASAN: slab-use-after-free in ctnetlink_exp_ct_dump_table+0x4f/0x2e0 Read of size 8 at addr ffff88810597ebf0 by task ctnetlink_poc/133 CPU: 1 UID: 0 PID: 133 Comm: ctnetlink_poc Not tainted 7.0.0-rc2+ #3 PREEMPTLAZY Call Trace: <TASK> ctnetlink_exp_ct_dump_table+0x4f/0x2e0 netlink_dump+0x333/0x880 netlink_recvmsg+0x3e2/0x4b0 ? aa_sk_perm+0x184/0x450 sock_recvmsg+0xde/0xf0 Allocated by task 133: kmem_cache_alloc_noprof+0x134/0x440 __nf_conntrack_alloc+0xa8/0x2b0 ctnetlink_create_conntrack+0xa1/0x900 ctnetlink_new_conntrack+0x3cf/0x7d0 nfnetlink_rcv_msg+0x48e/0x510 netlink_rcv_skb+0xc9/0x1f0 nfnetlink_rcv+0xdb/0x220 netlink_unicast+0x3ec/0x590 netlink_sendmsg+0x397/0x690 __sys_sendmsg+0xf4/0x180 Freed by task 0: slab_free_after_rcu_debug+0xad/0x1e0 rcu_core+0x5c3/0x9c0 | |||||