Linux

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

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()`.Show less

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

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

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.Show less

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.Show less

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.Show less

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/1ba5949c45529c511152e2f4c755b0f3Show less

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().Show less

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.Show less

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.Show less

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.Show less

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().Show less

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.Show less

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>Show less

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.Show less

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.Show less

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.Show less

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.Show less

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().Show less