| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| In the Linux kernel, the following vulnerability has been resolved:
hwmon: (powerz) Fix use-after-free on USB disconnect
After powerz_disconnect() frees the URB and releases the mutex, a
subsequent powerz_read() call can acquire the mutex and call
powerz_read_data(), which dereferences the freed URB pointer.
Fix by:
- Setting priv->urb to NULL in powerz_disconnect() so that
powerz_read_data() can detect the disconnected state.
- Adding a !priv->urb check at the start of powerz_read_data()
to return -ENODEV on a disconnected device.
- Moving usb_set_intfdata() before hwmon registration so the
disconnect handler can always find the priv pointer. |
| In the Linux kernel, the following vulnerability has been resolved:
media: mediatek: vcodec: fix use-after-free in encoder release path
The fops_vcodec_release() function frees the context structure (ctx)
without first cancelling any pending or running work in ctx->encode_work.
This creates a race window where the workqueue handler (mtk_venc_worker)
may still be accessing the context memory after it has been freed.
Race condition:
CPU 0 (release path) CPU 1 (workqueue)
--------------------- ------------------
fops_vcodec_release()
v4l2_m2m_ctx_release()
v4l2_m2m_cancel_job()
// waits for m2m job "done"
mtk_venc_worker()
v4l2_m2m_job_finish()
// m2m job "done"
// BUT worker still running!
// post-job_finish access:
other ctx dereferences
// UAF if ctx already freed
// returns (job "done")
kfree(ctx) // ctx freed
Root cause: The v4l2_m2m_ctx_release() only waits for the m2m job
lifecycle (via TRANS_RUNNING flag), not the workqueue lifecycle.
After v4l2_m2m_job_finish() is called, the m2m framework considers
the job complete and v4l2_m2m_ctx_release() returns, but the worker
function continues executing and may still access ctx.
The work is queued during encode operations via:
queue_work(ctx->dev->encode_workqueue, &ctx->encode_work)
The worker function accesses ctx->m2m_ctx, ctx->dev, and other ctx
fields even after calling v4l2_m2m_job_finish().
This vulnerability was confirmed with KASAN by running an instrumented
test module that widens the post-job_finish race window. KASAN detected:
BUG: KASAN: slab-use-after-free in mtk_venc_worker+0x159/0x180
Read of size 4 at addr ffff88800326e000 by task kworker/u8:0/12
Workqueue: mtk_vcodec_enc_wq mtk_venc_worker
Allocated by task 47:
__kasan_kmalloc+0x7f/0x90
fops_vcodec_open+0x85/0x1a0
Freed by task 47:
__kasan_slab_free+0x43/0x70
kfree+0xee/0x3a0
fops_vcodec_release+0xb7/0x190
Fix this by calling cancel_work_sync(&ctx->encode_work) before kfree(ctx).
This ensures the workqueue handler is both cancelled (if pending) and
synchronized (waits for any running handler to complete) before the
context is freed.
Placement rationale: The fix is placed after v4l2_ctrl_handler_free()
and before list_del_init(&ctx->list). At this point, all m2m operations
are done (v4l2_m2m_ctx_release() has returned), and we need to ensure
the workqueue is synchronized before removing ctx from the list and
freeing it.
Note: The open error path does NOT need cancel_work_sync() because
INIT_WORK() only initializes the work structure - it does not schedule
it. Work is only scheduled later during device_run() operations. |
| In the Linux kernel, the following vulnerability has been resolved:
rxrpc: Fix call removal to use RCU safe deletion
Fix rxrpc call removal from the rxnet->calls list to use list_del_rcu()
rather than list_del_init() to prevent stuffing up reading
/proc/net/rxrpc/calls from potentially getting into an infinite loop.
This, however, means that list_empty() no longer works on an entry that's
been deleted from the list, making it harder to detect prior deletion. Fix
this by:
Firstly, make rxrpc_destroy_all_calls() only dump the first ten calls that
are unexpectedly still on the list. Limiting the number of steps means
there's no need to call cond_resched() or to remove calls from the list
here, thereby eliminating the need for rxrpc_put_call() to check for that.
rxrpc_put_call() can then be fixed to unconditionally delete the call from
the list as it is the only place that the deletion occurs. |
| In the Linux kernel, the following vulnerability has been resolved:
net: lan966x: fix use-after-free and leak in lan966x_fdma_reload()
When lan966x_fdma_reload() fails to allocate new RX buffers, the restore
path restarts DMA using old descriptors whose pages were already freed
via lan966x_fdma_rx_free_pages(). Since page_pool_put_full_page() can
release pages back to the buddy allocator, the hardware may DMA into
memory now owned by other kernel subsystems.
Additionally, on the restore path, the newly created page pool (if
allocation partially succeeded) is overwritten without being destroyed,
leaking it.
Fix both issues by deferring the release of old pages until after the
new allocation succeeds. Save the old page array before the allocation
so old pages can be freed on the success path. On the failure path, the
old descriptors, pages and page pool are all still valid, making the
restore safe. Also ensure the restore path re-enables NAPI and wakes
the netdev, matching the success path. |
| In the Linux kernel, the following vulnerability has been resolved:
batman-adv: hold claim backbone gateways by reference
batadv_bla_add_claim() can replace claim->backbone_gw and drop the old
gateway's last reference while readers still follow the pointer.
The netlink claim dump path dereferences claim->backbone_gw->orig and
takes claim->backbone_gw->crc_lock without pinning the underlying
backbone gateway. batadv_bla_check_claim() still has the same naked
pointer access pattern.
Reuse batadv_bla_claim_get_backbone_gw() in both readers so they operate
on a stable gateway reference until the read-side work is complete.
This keeps the dump and claim-check paths aligned with the lifetime
rules introduced for the other BLA claim readers. |
| In the Linux kernel, the following vulnerability has been resolved:
pmdomain: bcm: bcm2835-power: Increase ASB control timeout
The bcm2835_asb_control() function uses a tight polling loop to wait
for the ASB bridge to acknowledge a request. During intensive workloads,
this handshake intermittently fails for V3D's master ASB on BCM2711,
resulting in "Failed to disable ASB master for v3d" errors during
runtime PM suspend. As a consequence, the failed power-off leaves V3D in
a broken state, leading to bus faults or system hangs on later accesses.
As the timeout is insufficient in some scenarios, increase the polling
timeout from 1us to 5us, which is still negligible in the context of a
power domain transition. Also, replace the open-coded ktime_get_ns()/
cpu_relax() polling loop with readl_poll_timeout_atomic(). |
| In the Linux kernel, the following vulnerability has been resolved:
futex: Require sys_futex_requeue() to have identical flags
Nicholas reported that his LLM found it was possible to create a UaF
when sys_futex_requeue() is used with different flags. The initial
motivation for allowing different flags was the variable sized futex,
but since that hasn't been merged (yet), simply mandate the flags are
identical, as is the case for the old style sys_futex() requeue
operations. |
| In the Linux kernel, the following vulnerability has been resolved:
futex: Clear stale exiting pointer in futex_lock_pi() retry path
Fuzzying/stressing futexes triggered:
WARNING: kernel/futex/core.c:825 at wait_for_owner_exiting+0x7a/0x80, CPU#11: futex_lock_pi_s/524
When futex_lock_pi_atomic() sees the owner is exiting, it returns -EBUSY
and stores a refcounted task pointer in 'exiting'.
After wait_for_owner_exiting() consumes that reference, the local pointer
is never reset to nil. Upon a retry, if futex_lock_pi_atomic() returns a
different error, the bogus pointer is passed to wait_for_owner_exiting().
CPU0 CPU1 CPU2
futex_lock_pi(uaddr)
// acquires the PI futex
exit()
futex_cleanup_begin()
futex_state = EXITING;
futex_lock_pi(uaddr)
futex_lock_pi_atomic()
attach_to_pi_owner()
// observes EXITING
*exiting = owner; // takes ref
return -EBUSY
wait_for_owner_exiting(-EBUSY, owner)
put_task_struct(); // drops ref
// exiting still points to owner
goto retry;
futex_lock_pi_atomic()
lock_pi_update_atomic()
cmpxchg(uaddr)
*uaddr ^= WAITERS // whatever
// value changed
return -EAGAIN;
wait_for_owner_exiting(-EAGAIN, exiting) // stale
WARN_ON_ONCE(exiting)
Fix this by resetting upon retry, essentially aligning it with requeue_pi. |
| 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. |
| A use-after-free vulnerability was found in libxslt while parsing xsl nodes that may lead to the dereference of expired pointers and application crash. |
| 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: 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:
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:
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:
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. |
| 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/ethernet/cadence/macb_main.c:3349
macb_get_ts_info+0x68/0xb0 drivers/net/ethernet/cadence/macb_main.c:3371
__ethtool_get_ts_info+0x17c/0x260 net/ethtool/common.c:558
ethtool_get_ts_info net/ethtool/ioctl.c:2367 [inline]
__dev_ethtool net/ethtool/ioctl.c:3017 [inline]
dev_ethtool+0x2b05/0x6290 net/ethtool/ioctl.c:3095
dev_ioctl+0x637/0x1070 net/core/dev_ioctl.c:510
sock_do_ioctl+0x20d/0x2c0 net/socket.c:1215
sock_ioctl+0x577/0x6d0 net/socket.c:1320
vfs_ioctl fs/ioctl.c:51 [inline]
__do_sys_ioctl fs/ioctl.c:870 [inline]
__se_sys_ioctl fs/ioctl.c:856 [inline]
__x64_sys_ioctl+0x18c/0x210 fs/ioctl.c:856
do_syscall_x64 arch/x86/entry/common.c:46 [inline]
do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76
entry_SYSCALL_64_after_hwframe+0x6e/0xd8
</TASK>
Allocated by task 457:
kmalloc include/linux/slab.h:563 [inline]
kzalloc include/linux/slab.h:699 [inline]
ptp_clock_register+0x144/0x10e0 drivers/ptp/ptp_clock.c:235
gem_ptp_init+0x46f/0x930 drivers/net/ethernet/cadence/macb_ptp.c:375
macb_open+0x901/0xd10 drivers/net/ethernet/cadence/macb_main.c:2920
__dev_open+0x2ce/0x500 net/core/dev.c:1501
__dev_change_flags+0x56a/0x740 net/core/dev.c:8651
dev_change_flags+0x92/0x170 net/core/dev.c:8722
do_setlink+0xaf8/0x3a80 net/core/rtnetlink.c:2833
__rtnl_newlink+0xbf4/0x1940 net/core/rtnetlink.c:3608
rtnl_newlink+0x63/0xa0 net/core/rtnetlink.c:3655
rtnetlink_rcv_msg+0x3c6/0xed0 net/core/rtnetlink.c:6150
netlink_rcv_skb+0x15d/0x430 net/netlink/af_netlink.c:2511
netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline]
netlink_unicast+0x6d7/0xa30 net/netlink/af_netlink.c:1344
netlink_sendmsg+0x97e/0xeb0 net/netlink/af_netlink.c:1872
sock_sendmsg_nosec net/socket.c:718 [inline]
__sock_sendmsg+0x14b/0x180 net/socket.c:730
__sys_sendto+0x320/0x3b0 net/socket.c:2152
__do_sys_sendto net/socket.c:2164 [inline]
__se_sys_sendto net/socket.c:2160 [inline]
__x64_sys_sendto+0xdc/0x1b0 net/socket.c:2160
do_syscall_x64 arch/x86/entry/common.c:46 [inline]
do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76
entry_SYSCALL_64_after_hwframe+0x6e/0xd8
Freed by task 938:
kasan_slab_free include/linux/kasan.h:177 [inline]
slab_free_hook mm/slub.c:1729 [inline]
slab_free_freelist_hook mm/slub.c:1755 [inline]
slab_free mm/slub.c:3687 [inline]
__kmem_cache_free+0xbc/0x320 mm/slub.c:3700
device_release+0xa0/0x240 drivers/base/core.c:2507
kobject_cleanup lib/kobject.c:681 [inline]
kobject_release lib/kobject.c:712 [inline]
kref_put include/linux/kref.h:65 [inline]
kobject_put+0x1cd/0x350 lib/kobject.c:729
put_device+0x1b/0x30 drivers/base/core.c:3805
ptp_clock_unregister+0x171/0x270 drivers/ptp/ptp_clock.c:391
gem_ptp_remove+0x4e/0x1f0 drivers/net/ethernet/cadence/macb_ptp.c:404
macb_close+0x1c8/0x270 drivers/net/ethernet/cadence/macb_main.c:2966
__dev_close_many+0x1b9/0x310 net/core/dev.c:1585
__dev_close net/core/dev.c:1597 [inline]
__dev_change_flags+0x2bb/0x740 net/core/dev.c:8649
dev_change_fl
---truncated--- |
| 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. |
| In the Linux kernel, the following vulnerability has been resolved:
ip_tunnel: adapt iptunnel_xmit_stats() to NETDEV_PCPU_STAT_DSTATS
Blamed commits forgot that vxlan/geneve use udp_tunnel[6]_xmit_skb() which
call iptunnel_xmit_stats().
iptunnel_xmit_stats() was assuming tunnels were only using
NETDEV_PCPU_STAT_TSTATS.
@syncp offset in pcpu_sw_netstats and pcpu_dstats is different.
32bit kernels would either have corruptions or freezes if the syncp
sequence was overwritten.
This patch also moves pcpu_stat_type closer to dev->{t,d}stats to avoid
a potential cache line miss since iptunnel_xmit_stats() needs to read it. |
| In the Linux kernel, the following vulnerability has been resolved:
net: shaper: protect late read accesses to the hierarchy
We look up a netdev during prep of Netlink ops (pre- callbacks)
and take a ref to it. Then later in the body of the callback
we take its lock or RCU which are the actual protections.
This is not proper, a conversion from a ref to a locked netdev
must include a liveness check (a check if the netdev hasn't been
unregistered already). Fix the read cases (those under RCU).
Writes needs a separate change to protect from creating the
hierarchy after flush has already run. |
| In the Linux kernel, the following vulnerability has been resolved:
mtd: rawnand: serialize lock/unlock against other NAND operations
nand_lock() and nand_unlock() call into chip->ops.lock_area/unlock_area
without holding the NAND device lock. On controllers that implement
SET_FEATURES via multiple low-level PIO commands, these can race with
concurrent UBI/UBIFS background erase/write operations that hold the
device lock, resulting in cmd_pending conflicts on the NAND controller.
Add nand_get_device()/nand_release_device() around the lock/unlock
operations to serialize them against all other NAND controller access. |
