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 thi...

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.

Rejected reason: This CVE ID has been rejected or withdrawn by its CVE Numbering Authority.

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(...

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 ...

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.

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, deq...

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().

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 ...

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...

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...

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

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]

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

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

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

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)

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.

The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec() function without any sanitization, sandboxing, or security restrictions. An attacker can exploit this by crafting a malicious llm command with arbitrary Python code in the --functions argument and using social engineering to trick a victim into running it. This leads to arbitrary code execution on the victim's system, potentially granting the attacker full control.

PyTorch-Lightning versions 2.6.0 and earlier contain an insecure deserialization vulnerability (CWE-502) in the checkpoint loading mechanism. The LightningModule.load_from_checkpoint() method, which is commonly used to load saved model states, internally calls torch.load() without setting the security-restrictive weights_only=True parameter. This default behavior allows the deserialization of arbitrary Python objects via the Pickle module. A remote attacker can exploit this by providing a maliciously crafted checkpoint file, leading to arbitrary code execution on the victim's system when the file is loaded.