| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| In the Linux kernel, the following vulnerability has been resolved:
bridge: mrp: reject zero test interval to avoid OOM panic
br_mrp_start_test() and br_mrp_start_in_test() accept the user-supplied
interval value from netlink without validation. When interval is 0,
usecs_to_jiffies(0) yields 0, causing the delayed work
(br_mrp_test_work_expired / br_mrp_in_test_work_expired) to reschedule
itself with zero delay. This creates a tight loop on system_percpu_wq
that allocates and transmits MRP test frames at maximum rate, exhausting
all system memory and causing a kernel panic via OOM deadlock.
The same zero-interval issue applies to br_mrp_start_in_test_parse()
for interconnect test frames.
Use NLA_POLICY_MIN(NLA_U32, 1) in the nla_policy tables for both
IFLA_BRIDGE_MRP_START_TEST_INTERVAL and
IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL, so zero is rejected at the
netlink attribute parsing layer before the value ever reaches the
workqueue scheduling code. This is consistent with how other bridge
subsystems (br_fdb, br_mst) enforce range constraints on netlink
attributes. |
| In the Linux kernel, the following vulnerability has been resolved:
net/sched: cls_fw: fix NULL pointer dereference on shared blocks
The old-method path in fw_classify() calls tcf_block_q() and
dereferences q->handle. Shared blocks leave block->q NULL, causing a
NULL deref when an empty cls_fw filter is attached to a shared block
and a packet with a nonzero major skb mark is classified.
Reject the configuration in fw_change() when the old method (no
TCA_OPTIONS) is used on a shared block, since fw_classify()'s
old-method path needs block->q which is NULL for shared blocks.
The fixed null-ptr-deref calling stack:
KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f]
RIP: 0010:fw_classify (net/sched/cls_fw.c:81)
Call Trace:
tcf_classify (./include/net/tc_wrapper.h:197 net/sched/cls_api.c:1764 net/sched/cls_api.c:1860)
tc_run (net/core/dev.c:4401)
__dev_queue_xmit (net/core/dev.c:4535 net/core/dev.c:4790) |
| In the Linux kernel, the following vulnerability has been resolved:
net/sched: cls_flow: fix NULL pointer dereference on shared blocks
flow_change() calls tcf_block_q() and dereferences q->handle to derive
a default baseclass. Shared blocks leave block->q NULL, causing a NULL
deref when a flow filter without a fully qualified baseclass is created
on a shared block.
Check tcf_block_shared() before accessing block->q and return -EINVAL
for shared blocks. This avoids the null-deref shown below:
=======================================================================
KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f]
RIP: 0010:flow_change (net/sched/cls_flow.c:508)
Call Trace:
tc_new_tfilter (net/sched/cls_api.c:2432)
rtnetlink_rcv_msg (net/core/rtnetlink.c:6980)
[...]
======================================================================= |
| In the Linux kernel, the following vulnerability has been resolved:
net/sched: sch_hfsc: fix divide-by-zero in rtsc_min()
m2sm() converts a u32 slope to a u64 scaled value. For large inputs
(e.g. m1=4000000000), the result can reach 2^32. rtsc_min() stores
the difference of two such u64 values in a u32 variable `dsm` and
uses it as a divisor. When the difference is exactly 2^32 the
truncation yields zero, causing a divide-by-zero oops in the
concave-curve intersection path:
Oops: divide error: 0000
RIP: 0010:rtsc_min (net/sched/sch_hfsc.c:601)
Call Trace:
init_ed (net/sched/sch_hfsc.c:629)
hfsc_enqueue (net/sched/sch_hfsc.c:1569)
[...]
Widen `dsm` to u64 and replace do_div() with div64_u64() so the full
difference is preserved. |
| In the Linux kernel, the following vulnerability has been resolved:
rds: ib: reject FRMR registration before IB connection is established
rds_ib_get_mr() extracts the rds_ib_connection from conn->c_transport_data
and passes it to rds_ib_reg_frmr() for FRWR memory registration. On a
fresh outgoing connection, ic is allocated in rds_ib_conn_alloc() with
i_cm_id = NULL because the connection worker has not yet called
rds_ib_conn_path_connect() to create the rdma_cm_id. When sendmsg() with
RDS_CMSG_RDMA_MAP is called on such a connection, the sendmsg path parses
the control message before any connection establishment, allowing
rds_ib_post_reg_frmr() to dereference ic->i_cm_id->qp and crash the
kernel.
The existing guard in rds_ib_reg_frmr() only checks for !ic (added in
commit 9e630bcb7701), which does not catch this case since ic is allocated
early and is always non-NULL once the connection object exists.
KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017]
RIP: 0010:rds_ib_post_reg_frmr+0x50e/0x920
Call Trace:
rds_ib_post_reg_frmr (net/rds/ib_frmr.c:167)
rds_ib_map_frmr (net/rds/ib_frmr.c:252)
rds_ib_reg_frmr (net/rds/ib_frmr.c:430)
rds_ib_get_mr (net/rds/ib_rdma.c:615)
__rds_rdma_map (net/rds/rdma.c:295)
rds_cmsg_rdma_map (net/rds/rdma.c:860)
rds_sendmsg (net/rds/send.c:1363)
____sys_sendmsg
do_syscall_64
Add a check in rds_ib_get_mr() that verifies ic, i_cm_id, and qp are all
non-NULL before proceeding with FRMR registration, mirroring the guard
already present in rds_ib_post_inv(). Return -ENODEV when the connection
is not ready, which the existing error handling in rds_cmsg_send() converts
to -EAGAIN for userspace retry and triggers rds_conn_connect_if_down() to
start the connection worker. |
| 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:
netfilter: nf_conntrack_sip: fix use of uninitialized rtp_addr in process_sdp
process_sdp() declares union nf_inet_addr rtp_addr on the stack and
passes it to the nf_nat_sip sdp_session hook after walking the SDP
media descriptions. However rtp_addr is only initialized inside the
media loop when a recognized media type with a non-zero port is found.
If the SDP body contains no m= lines, only inactive media sections
(m=audio 0 ...) or only unrecognized media types, rtp_addr is never
assigned. Despite that, the function still calls hooks->sdp_session()
with &rtp_addr, causing nf_nat_sdp_session() to format the stale stack
value as an IP address and rewrite the SDP session owner and connection
lines with it.
With CONFIG_INIT_STACK_ALL_ZERO (default on most distributions) this
results in the session-level o= and c= addresses being rewritten to
0.0.0.0 for inactive SDP sessions. Without stack auto-init the
rewritten address is whatever happened to be on the stack.
Fix this by pre-initializing rtp_addr from the session-level connection
address (caddr) when available, and tracking via a have_rtp_addr flag
whether any valid address was established. Skip the sdp_session hook
entirely when no valid address exists. |
| 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. |
| 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. |
| In the Linux kernel, the following vulnerability has been resolved:
net: bonding: fix use-after-free in bond_xmit_broadcast()
bond_xmit_broadcast() reuses the original skb for the last slave
(determined by bond_is_last_slave()) and clones it for others.
Concurrent slave enslave/release can mutate the slave list during
RCU-protected iteration, changing which slave is "last" mid-loop.
This causes the original skb to be double-consumed (double-freed).
Replace the racy bond_is_last_slave() check with a simple index
comparison (i + 1 == slaves_count) against the pre-snapshot slave
count taken via READ_ONCE() before the loop. This preserves the
zero-copy optimization for the last slave while making the "last"
determination stable against concurrent list mutations.
The UAF can trigger the following crash:
==================================================================
BUG: KASAN: slab-use-after-free in skb_clone
Read of size 8 at addr ffff888100ef8d40 by task exploit/147
CPU: 1 UID: 0 PID: 147 Comm: exploit Not tainted 7.0.0-rc3+ #4 PREEMPTLAZY
Call Trace:
<TASK>
dump_stack_lvl (lib/dump_stack.c:123)
print_report (mm/kasan/report.c:379 mm/kasan/report.c:482)
kasan_report (mm/kasan/report.c:597)
skb_clone (include/linux/skbuff.h:1724 include/linux/skbuff.h:1792 include/linux/skbuff.h:3396 net/core/skbuff.c:2108)
bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5334)
bond_start_xmit (drivers/net/bonding/bond_main.c:5567 drivers/net/bonding/bond_main.c:5593)
dev_hard_start_xmit (include/linux/netdevice.h:5325 include/linux/netdevice.h:5334 net/core/dev.c:3871 net/core/dev.c:3887)
__dev_queue_xmit (include/linux/netdevice.h:3601 net/core/dev.c:4838)
ip6_finish_output2 (include/net/neighbour.h:540 include/net/neighbour.h:554 net/ipv6/ip6_output.c:136)
ip6_finish_output (net/ipv6/ip6_output.c:208 net/ipv6/ip6_output.c:219)
ip6_output (net/ipv6/ip6_output.c:250)
ip6_send_skb (net/ipv6/ip6_output.c:1985)
udp_v6_send_skb (net/ipv6/udp.c:1442)
udpv6_sendmsg (net/ipv6/udp.c:1733)
__sys_sendto (net/socket.c:730 net/socket.c:742 net/socket.c:2206)
__x64_sys_sendto (net/socket.c:2209)
do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
</TASK>
Allocated by task 147:
Freed by task 147:
The buggy address belongs to the object at ffff888100ef8c80
which belongs to the cache skbuff_head_cache of size 224
The buggy address is located 192 bytes inside of
freed 224-byte region [ffff888100ef8c80, ffff888100ef8d60)
Memory state around the buggy address:
ffff888100ef8c00: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc
ffff888100ef8c80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff888100ef8d00: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
^
ffff888100ef8d80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb
ffff888100ef8e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
================================================================== |
| This CVE ID has been rejected or withdrawn by its CVE Numbering Authority. |
| This CVE ID has been rejected or withdrawn by its CVE Numbering Authority. |
| In the Linux kernel, the following vulnerability has been resolved:
xen/privcmd: restrict usage in unprivileged domU
The Xen privcmd driver allows to issue arbitrary hypercalls from
user space processes. This is normally no problem, as access is
usually limited to root and the hypervisor will deny any hypercalls
affecting other domains.
In case the guest is booted using secure boot, however, the privcmd
driver would be enabling a root user process to modify e.g. kernel
memory contents, thus breaking the secure boot feature.
The only known case where an unprivileged domU is really needing to
use the privcmd driver is the case when it is acting as the device
model for another guest. In this case all hypercalls issued via the
privcmd driver will target that other guest.
Fortunately the privcmd driver can already be locked down to allow
only hypercalls targeting a specific domain, but this mode can be
activated from user land only today.
The target domain can be obtained from Xenstore, so when not running
in dom0 restrict the privcmd driver to that target domain from the
beginning, resolving the potential problem of breaking secure boot.
This is XSA-482
---
V2:
- defer reading from Xenstore if Xenstore isn't ready yet (Jan Beulich)
- wait in open() if target domain isn't known yet
- issue message in case no target domain found (Jan Beulich) |
| 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 |
| 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(). |
| 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(). |
| 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. |
