| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| In the Linux kernel, the following vulnerability has been resolved:
net: rfkill: prevent unlimited numbers of rfkill events from being created
Userspace can create an unlimited number of rfkill events if the system
is so configured, while not consuming them from the rfkill file
descriptor, causing a potential out of memory situation. Prevent this
from bounding the number of pending rfkill events at a "large" number
(i.e. 1000) to prevent abuses like this. |
| In the Linux kernel, the following vulnerability has been resolved:
mptcp: fix slab-use-after-free in __inet_lookup_established
The ehash table lookups are lockless and rely on
SLAB_TYPESAFE_BY_RCU to guarantee socket memory stability
during RCU read-side critical sections. Both tcp_prot and
tcpv6_prot have their slab caches created with this flag
via proto_register().
However, MPTCP's mptcp_subflow_init() copies tcpv6_prot into
tcpv6_prot_override during inet_init() (fs_initcall, level 5),
before inet6_init() (module_init/device_initcall, level 6) has
called proto_register(&tcpv6_prot). At that point,
tcpv6_prot.slab is still NULL, so tcpv6_prot_override.slab
remains NULL permanently.
This causes MPTCP v6 subflow child sockets to be allocated via
kmalloc (falling into kmalloc-4k) instead of the TCPv6 slab
cache. The kmalloc-4k cache lacks SLAB_TYPESAFE_BY_RCU, so
when these sockets are freed without SOCK_RCU_FREE (which is
cleared for child sockets by design), the memory can be
immediately reused. Concurrent ehash lookups under
rcu_read_lock can then access freed memory, triggering a
slab-use-after-free in __inet_lookup_established.
Fix this by splitting the IPv6-specific initialization out of
mptcp_subflow_init() into a new mptcp_subflow_v6_init(), called
from mptcp_proto_v6_init() before protocol registration. This
ensures tcpv6_prot_override.slab correctly inherits the
SLAB_TYPESAFE_BY_RCU slab cache. |
| In the Linux kernel, the following vulnerability has been resolved:
seg6: separate dst_cache for input and output paths in seg6 lwtunnel
The seg6 lwtunnel uses a single dst_cache per encap route, shared
between seg6_input_core() and seg6_output_core(). These two paths
can perform the post-encap SID lookup in different routing contexts
(e.g., ip rules matching on the ingress interface, or VRF table
separation). Whichever path runs first populates the cache, and the
other reuses it blindly, bypassing its own lookup.
Fix this by splitting the cache into cache_input and cache_output,
so each path maintains its own cached dst independently. |
| In the Linux kernel, the following vulnerability has been resolved:
Input: uinput - fix circular locking dependency with ff-core
A lockdep circular locking dependency warning can be triggered
reproducibly when using a force-feedback gamepad with uinput (for
example, playing ELDEN RING under Wine with a Flydigi Vader 5
controller):
ff->mutex -> udev->mutex -> input_mutex -> dev->mutex -> ff->mutex
The cycle is caused by four lock acquisition paths:
1. ff upload: input_ff_upload() holds ff->mutex and calls
uinput_dev_upload_effect() -> uinput_request_submit() ->
uinput_request_send(), which acquires udev->mutex.
2. device create: uinput_ioctl_handler() holds udev->mutex and calls
uinput_create_device() -> input_register_device(), which acquires
input_mutex.
3. device register: input_register_device() holds input_mutex and
calls kbd_connect() -> input_register_handle(), which acquires
dev->mutex.
4. evdev release: evdev_release() calls input_flush_device() under
dev->mutex, which calls input_ff_flush() acquiring ff->mutex.
Fix this by introducing a new state_lock spinlock to protect
udev->state and udev->dev access in uinput_request_send() instead of
acquiring udev->mutex. The function only needs to atomically check
device state and queue an input event into the ring buffer via
uinput_dev_event() -- both operations are safe under a spinlock
(ktime_get_ts64() and wake_up_interruptible() do not sleep). This
breaks the ff->mutex -> udev->mutex link since a spinlock is a leaf in
the lock ordering and cannot form cycles with mutexes.
To keep state transitions visible to uinput_request_send(), protect
writes to udev->state in uinput_create_device() and
uinput_destroy_device() with the same state_lock spinlock.
Additionally, move init_completion(&request->done) from
uinput_request_send() to uinput_request_submit() before
uinput_request_reserve_slot(). Once the slot is allocated,
uinput_flush_requests() may call complete() on it at any time from
the destroy path, so the completion must be initialised before the
request becomes visible.
Lock ordering after the fix:
ff->mutex -> state_lock (spinlock, leaf)
udev->mutex -> state_lock (spinlock, leaf)
udev->mutex -> input_mutex -> dev->mutex -> ff->mutex (no back-edge) |
| In the Linux kernel, the following vulnerability has been resolved:
btrfs: fix incorrect return value after changing leaf in lookup_extent_data_ref()
After commit 1618aa3c2e01 ("btrfs: simplify return variables in
lookup_extent_data_ref()"), the err and ret variables were merged into
a single ret variable. However, when btrfs_next_leaf() returns 0
(success), ret is overwritten from -ENOENT to 0. If the first key in
the next leaf does not match (different objectid or type), the function
returns 0 instead of -ENOENT, making the caller believe the lookup
succeeded when it did not. This can lead to operations on the wrong
extent tree item, potentially causing extent tree corruption.
Fix this by returning -ENOENT directly when the key does not match,
instead of relying on the ret variable. |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: nft_ct: fix use-after-free in timeout object destroy
nft_ct_timeout_obj_destroy() frees the timeout object with kfree()
immediately after nf_ct_untimeout(), without waiting for an RCU grace
period. Concurrent packet processing on other CPUs may still hold
RCU-protected references to the timeout object obtained via
rcu_dereference() in nf_ct_timeout_data().
Add an rcu_head to struct nf_ct_timeout and use kfree_rcu() to defer
freeing until after an RCU grace period, matching the approach already
used in nfnetlink_cttimeout.c.
KASAN report:
BUG: KASAN: slab-use-after-free in nf_conntrack_tcp_packet+0x1381/0x29d0
Read of size 4 at addr ffff8881035fe19c by task exploit/80
Call Trace:
nf_conntrack_tcp_packet+0x1381/0x29d0
nf_conntrack_in+0x612/0x8b0
nf_hook_slow+0x70/0x100
__ip_local_out+0x1b2/0x210
tcp_sendmsg_locked+0x722/0x1580
__sys_sendto+0x2d8/0x320
Allocated by task 75:
nft_ct_timeout_obj_init+0xf6/0x290
nft_obj_init+0x107/0x1b0
nf_tables_newobj+0x680/0x9c0
nfnetlink_rcv_batch+0xc29/0xe00
Freed by task 26:
nft_obj_destroy+0x3f/0xa0
nf_tables_trans_destroy_work+0x51c/0x5c0
process_one_work+0x2c4/0x5a0 |
| In the Linux kernel, the following vulnerability has been resolved:
xfrm: clear trailing padding in build_polexpire()
build_expire() clears the trailing padding bytes of struct
xfrm_user_expire after setting the hard field via memset_after(),
but the analogous function build_polexpire() does not do this for
struct xfrm_user_polexpire.
The padding bytes after the __u8 hard field are left
uninitialized from the heap allocation, and are then sent to
userspace via netlink multicast to XFRMNLGRP_EXPIRE listeners,
leaking kernel heap memory contents.
Add the missing memset_after() call, matching build_expire(). |
| In the Linux kernel, the following vulnerability has been resolved:
xfrm: hold dev ref until after transport_finish NF_HOOK
After async crypto completes, xfrm_input_resume() calls dev_put()
immediately on re-entry before the skb reaches transport_finish.
The skb->dev pointer is then used inside NF_HOOK and its okfn,
which can race with device teardown.
Remove the dev_put from the async resumption entry and instead
drop the reference after the NF_HOOK call in transport_finish,
using a saved device pointer since NF_HOOK may consume the skb.
This covers NF_DROP, NF_QUEUE and NF_STOLEN paths that skip
the okfn.
For non-transport exits (decaps, gro, drop) and secondary
async return points, release the reference inline when
async is set. |
| In the Linux kernel, the following vulnerability has been resolved:
staging: rtl8723bs: initialize le_tmp64 in rtw_BIP_verify()
Initialize le_tmp64 to zero in rtw_BIP_verify() to prevent using
uninitialized data.
Smatch warns that only 6 bytes are copied to this 8-byte (u64)
variable, leaving the last two bytes uninitialized:
drivers/staging/rtl8723bs/core/rtw_security.c:1308 rtw_BIP_verify()
warn: not copying enough bytes for '&le_tmp64' (8 vs 6 bytes)
Initializing the variable at the start of the function fixes this
warning and ensures predictable behavior. |
| In the Linux kernel, the following vulnerability has been resolved:
NFC: digital: Bounds check NFC-A cascade depth in SDD response handler
The NFC-A anti-collision cascade in digital_in_recv_sdd_res() appends 3
or 4 bytes to target->nfcid1 on each round, but the number of cascade
rounds is controlled entirely by the peer device. The peer sets the
cascade tag in the SDD_RES (deciding 3 vs 4 bytes) and the
cascade-incomplete bit in the SEL_RES (deciding whether another round
follows).
ISO 14443-3 limits NFC-A to three cascade levels and target->nfcid1 is
sized accordingly (NFC_NFCID1_MAXSIZE = 10), but nothing in the driver
actually enforces this. This means a malicious peer can keep the
cascade running, writing past the heap-allocated nfc_target with each
round.
Fix this by rejecting the response when the accumulated UID would exceed
the buffer.
Commit e329e71013c9 ("NFC: nci: Bounds check struct nfc_target arrays")
fixed similar missing checks against the same field on the NCI path. |
| In the Linux kernel, the following vulnerability has been resolved:
smb: client: fix OOB reads parsing symlink error response
When a CREATE returns STATUS_STOPPED_ON_SYMLINK, smb2_check_message()
returns success without any length validation, leaving the symlink
parsers as the only defense against an untrusted server.
symlink_data() walks SMB 3.1.1 error contexts with the loop test "p <
end", but reads p->ErrorId at offset 4 and p->ErrorDataLength at offset
0. When the server-controlled ErrorDataLength advances p to within 1-7
bytes of end, the next iteration will read past it. When the matching
context is found, sym->SymLinkErrorTag is read at offset 4 from
p->ErrorContextData with no check that the symlink header itself fits.
smb2_parse_symlink_response() then bounds-checks the substitute name
using SMB2_SYMLINK_STRUCT_SIZE as the offset of PathBuffer from
iov_base. That value is computed as sizeof(smb2_err_rsp) +
sizeof(smb2_symlink_err_rsp), which is correct only when
ErrorContextCount == 0.
With at least one error context the symlink data sits 8 bytes deeper,
and each skipped non-matching context shifts it further by 8 +
ALIGN(ErrorDataLength, 8). The check is too short, allowing the
substitute name read to run past iov_len. The out-of-bound heap bytes
are UTF-16-decoded into the symlink target and returned to userspace via
readlink(2).
Fix this all up by making the loops test require the full context header
to fit, rejecting sym if its header runs past end, and bound the
substitute name against the actual position of sym->PathBuffer rather
than a fixed offset.
Because sub_offs and sub_len are 16bits, the pointer math will not
overflow here with the new greater-than. |
| 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. |
| 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. |
| 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 |
| 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()`. |
| 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. |
| 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. |
| 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. |
| 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. |
| 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(). |
