| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| In the Linux kernel, the following vulnerability has been resolved:
Revert "wireguard: device: enable threaded NAPI"
This reverts commit 933466fc50a8e4eb167acbd0d8ec96a078462e9c which is
commit db9ae3b6b43c79b1ba87eea849fd65efa05b4b2e upstream.
We have had three independent production user reports in combination
with Cilium utilizing WireGuard as encryption underneath that k8s Pod
E/W traffic to certain peer nodes fully stalled. The situation appears
as follows:
- Occurs very rarely but at random times under heavy networking load.
- Once the issue triggers the decryption side stops working completely
for that WireGuard peer, other peers keep working fine. The stall
happens also for newly initiated connections towards that particular
WireGuard peer.
- Only the decryption side is affected, never the encryption side.
- Once it triggers, it never recovers and remains in this state,
the CPU/mem on that node looks normal, no leak, busy loop or crash.
- bpftrace on the affected system shows that wg_prev_queue_enqueue
fails, thus the MAX_QUEUED_PACKETS (1024 skbs!) for the peer's
rx_queue is reached.
- Also, bpftrace shows that wg_packet_rx_poll for that peer is never
called again after reaching this state for that peer. For other
peers wg_packet_rx_poll does get called normally.
- Commit db9ae3b ("wireguard: device: enable threaded NAPI")
switched WireGuard to threaded NAPI by default. The default has
not been changed for triggering the issue, neither did CPU
hotplugging occur (i.e. 5bd8de2 ("wireguard: queueing: always
return valid online CPU in wg_cpumask_choose_online()")).
- The issue has been observed with stable kernels of v5.15 as well as
v6.1. It was reported to us that v5.10 stable is working fine, and
no report on v6.6 stable either (somewhat related discussion in [0]
though).
- In the WireGuard driver the only material difference between v5.10
stable and v5.15 stable is the switch to threaded NAPI by default.
[0] https://lore.kernel.org/netdev/CA+wXwBTT74RErDGAnj98PqS=wvdh8eM1pi4q6tTdExtjnokKqA@mail.gmail.com/
Breakdown of the problem:
1) skbs arriving for decryption are enqueued to the peer->rx_queue in
wg_packet_consume_data via wg_queue_enqueue_per_device_and_peer.
2) The latter only moves the skb into the MPSC peer queue if it does
not surpass MAX_QUEUED_PACKETS (1024) which is kept track in an
atomic counter via wg_prev_queue_enqueue.
3) In case enqueueing was successful, the skb is also queued up
in the device queue, round-robin picks a next online CPU, and
schedules the decryption worker.
4) The wg_packet_decrypt_worker, once scheduled, picks these up
from the queue, decrypts the packets and once done calls into
wg_queue_enqueue_per_peer_rx.
5) The latter updates the state to PACKET_STATE_CRYPTED on success
and calls napi_schedule on the per peer->napi instance.
6) NAPI then polls via wg_packet_rx_poll. wg_prev_queue_peek checks
on the peer->rx_queue. It will wg_prev_queue_dequeue if the
queue->peeked skb was not cached yet, or just return the latter
otherwise. (wg_prev_queue_drop_peeked later clears the cache.)
7) From an ordering perspective, the peer->rx_queue has skbs in order
while the device queue with the per-CPU worker threads from a
global ordering PoV can finish the decryption and signal the skb
PACKET_STATE_CRYPTED out of order.
8) A situation can be observed that the first packet coming in will
be stuck waiting for the decryption worker to be scheduled for
a longer time when the system is under pressure.
9) While this is the case, the other CPUs in the meantime finish
decryption and call into napi_schedule.
10) Now in wg_packet_rx_poll it picks up the first in-order skb
from the peer->rx_queue and sees that its state is still
PACKET_STATE_UNCRYPTED. The NAPI poll routine then exits e
---truncated--- |
| In the Linux kernel, the following vulnerability has been resolved:
xfrm: espintcp: do not reuse an in-progress partial send
espintcp keeps a single in-flight transmit in ctx->partial.
Before building a new sk_msg, espintcp_sendmsg() first tries to flush
that state through espintcp_push_msgs().
For blocking callers, espintcp_push_msgs() may return success even when
the previous partial send is still pending. espintcp_sendmsg() would
then reinitialize emsg->skmsg and reuse ctx->partial while the old
transfer still owns that state.
Do not rebuild the send message when ctx->partial is still in progress.
If espintcp_push_msgs() returns with emsg->len still set, fail the new
send instead of overwriting the live partial state.
This is a memory-safety fix: reusing the live partial-send state can
leave a stale offset attached to a new sk_msg and lead to an out-of-
bounds read in the send path.
tcp_sendmsg_locked() already handles waiting for send buffer memory, so
the fix here is just to preserve espintcp's one-message-at-a-time
transmit state. |
| In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: serialize accept_q access
bt_sock_poll() walks the accept queue without synchronization, while
child teardown can unlink the same socket and drop its last reference.
The unsynchronized accept queue walk has existed since the initial
Bluetooth import.
Protect accept_q with a dedicated lock for queue updates and polling.
Also rework bt_accept_dequeue() to take temporary child references under
the queue lock before dropping it and locking the child socket. |
| In the Linux kernel, the following vulnerability has been resolved:
dm: fix unlocked test for dm_suspended_md
The function dm_blk_report_zones tests if the device is suspended with
the "dm_suspended_md" call. However, this function is called without
holding any locks, so the device may be suspended just after it.
Move the call to dm_suspended_md after dm_get_live_table, so that the
device can't be suspended after the suspended state was tested. |
| In the Linux kernel, the following vulnerability has been resolved:
net/sched: act_ct: Only release RCU read lock after ct_ft
When looking up a flow table in act_ct in tcf_ct_flow_table_get(),
rhashtable_lookup_fast() internally opens and closes an RCU read critical
section before returning ct_ft.
The tcf_ct_flow_table_cleanup_work() can complete before refcount_inc_not_zero()
is invoked on the returned ct_ft resulting in a UAF on the already freed ct_ft
object. This vulnerability can lead to privilege escalation.
Analysis from zdi-disclosures@trendmicro.com:
When initializing act_ct, tcf_ct_init() is called, which internally triggers
tcf_ct_flow_table_get().
static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params)
{
struct zones_ht_key key = { .net = net, .zone = params->zone };
struct tcf_ct_flow_table *ct_ft;
int err = -ENOMEM;
mutex_lock(&zones_mutex);
ct_ft = rhashtable_lookup_fast(&zones_ht, &key, zones_params); // [1]
if (ct_ft && refcount_inc_not_zero(&ct_ft->ref)) // [2]
goto out_unlock;
...
}
static __always_inline void *rhashtable_lookup_fast(
struct rhashtable *ht, const void *key,
const struct rhashtable_params params)
{
void *obj;
rcu_read_lock();
obj = rhashtable_lookup(ht, key, params);
rcu_read_unlock();
return obj;
}
At [1], rhashtable_lookup_fast() looks up and returns the corresponding ct_ft
from zones_ht . The lookup is performed within an RCU read critical section
through rcu_read_lock() / rcu_read_unlock(), which prevents the object from
being freed. However, at the point of function return, rcu_read_unlock() has
already been called, and there is nothing preventing ct_ft from being freed
before reaching refcount_inc_not_zero(&ct_ft->ref) at [2]. This interval becomes
the race window, during which ct_ft can be freed.
Free Process:
tcf_ct_flow_table_put() is executed through the path tcf_ct_cleanup() call_rcu()
tcf_ct_params_free_rcu() tcf_ct_params_free() tcf_ct_flow_table_put().
static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft)
{
if (refcount_dec_and_test(&ct_ft->ref)) {
rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params);
INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work); // [3]
queue_rcu_work(act_ct_wq, &ct_ft->rwork);
}
}
At [3], tcf_ct_flow_table_cleanup_work() is scheduled as RCU work
static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
{
struct tcf_ct_flow_table *ct_ft;
struct flow_block *block;
ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table,
rwork);
nf_flow_table_free(&ct_ft->nf_ft);
block = &ct_ft->nf_ft.flow_block;
down_write(&ct_ft->nf_ft.flow_block_lock);
WARN_ON(!list_empty(&block->cb_list));
up_write(&ct_ft->nf_ft.flow_block_lock);
kfree(ct_ft); // [4]
module_put(THIS_MODULE);
}
tcf_ct_flow_table_cleanup_work() frees ct_ft at [4]. When this function executes
between [1] and [2], UAF occurs.
This race condition has a very short race window, making it generally
difficult to trigger. Therefore, to trigger the vulnerability an msleep(100) was
inserted after[1] |
| In the Linux kernel, the following vulnerability has been resolved:
KVM: arm64: vgic-its: Drop the translation cache reference only for the erased entry
vgic_its_invalidate_cache() walks the per-ITS translation cache with
xa_for_each() and drops the cache's reference on each entry with
vgic_put_irq(). It puts the iterated pointer, though, rather than the
value returned by xa_erase().
The function is called from contexts that do not exclude one another: the
ITS command handlers hold its_lock, the GITS_CTLR write path holds
cmd_lock, and the path that clears EnableLPIs in a redistributor's
GICR_CTLR holds neither. Two or more of them can drain the same cache
concurrently, and if each one observes the same entry, erases it and then
puts it, the single reference the cache holds on that entry is dropped
more than once. The entry can then be freed while an ITE still maps it.
xa_erase() is atomic and returns the previous entry, so put only the entry
that this context actually removed. The cache reference is then dropped
exactly once per entry even when the invalidations run concurrently, and
the behavior is unchanged when only one context runs. |
| In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu/userq: fix access to stale wptr mapping
Use drm_exec to take both locks i.e vm root bo and
wptr_obj bo to access the mapping data properly.
This fixes the security issue of unmap the wptr_obj while
a queue creation is in progress and passing other
bo at same address.
(cherry picked from commit 1fc6c8ab45dbee096469c08c13f6099d57a52d6c) |
| In the Linux kernel, the following vulnerability has been resolved:
sctp: revalidate list cursor after sctp_sendmsg_to_asoc() in SCTP_SENDALL
The SCTP_SENDALL path in sctp_sendmsg() iterates ep->asocs with
list_for_each_entry_safe(), which caches the next entry in @tmp before
the loop body runs. The body calls sctp_sendmsg_to_asoc(), which may
drop the socket lock inside sctp_wait_for_sndbuf().
While the lock is dropped, another thread can SCTP_SOCKOPT_PEELOFF the
association cached in @tmp, migrating it to a new endpoint via
sctp_sock_migrate() (list_del_init() + list_add_tail() to
newep->asocs), and optionally close the new socket which frees the
association via kfree_rcu(). The cached @tmp can also be freed by a
network ABORT for that association, processed in softirq while the
lock is dropped.
sctp_wait_for_sndbuf() revalidates @asoc (the current entry) on re-lock
via the "sk != asoc->base.sk" and "asoc->base.dead" checks, but nothing
revalidates @tmp. After a successful return, the iterator advances to
the stale @tmp, yielding either a use-after-free (if the peeled socket
was closed) or a list-walk onto the new endpoint's list head (type
confusion of &newep->asocs as a struct sctp_association *).
Both are reachable from CapEff=0; the type-confusion path gives
controlled indirect call via the outqueue.sched->init_sid pointer.
Fix by re-deriving @tmp from @asoc after sctp_sendmsg_to_asoc()
returns. @asoc is known to still be on ep->asocs at that point: the
only callers that list_del an association from ep->asocs are
sctp_association_free() (which sets asoc->base.dead) and
sctp_assoc_migrate() (which changes asoc->base.sk), and
sctp_wait_for_sndbuf() checks both under the lock before any
successful return; a tripped check propagates as err < 0 and the loop
bails before the re-derive.
The SCTP_ABORT path in sctp_sendmsg_check_sflags() returns 0 and the
loop hits 'continue' before sctp_sendmsg_to_asoc() is ever called, so
the @tmp cached by list_for_each_entry_safe() still covers the
lock-held free that ba59fb027307 ("sctp: walk the list of asoc
safely") was added for. |
| In the Linux kernel, the following vulnerability has been resolved:
wifi: mac80211: drop stray 'static' from fast-RX rx_result
ieee80211_invoke_fast_rx() is documented as safe for parallel RX, but
its per-invocation rx_result is declared static. Concurrent callers then
share one instance and can overwrite each other's result between
ieee80211_rx_mesh_data() and the switch on res.
That can make a packet that was queued or consumed by
ieee80211_rx_mesh_data() fall through into ieee80211_rx_8023(), or make
a packet that should continue return as queued.
Make res an automatic variable so each invocation keeps its own result. |
| In the Linux kernel, the following vulnerability has been resolved:
iommu/vt-d: Flush cache for PASID table before using it
When writing the address of a freshly allocated zero-initialized PASID
table to a PASID directory entry, do that after the CPU cache flush for
this PASID table, not before it, to avoid the time window when this
PASID table may be already used by non-coherent IOMMU hardware while
its contents in RAM is still some random old data, not zero-initialized. |
| In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu: Fix use-after-free race in VM acquire
Replace non-atomic vm->process_info assignment with cmpxchg()
to prevent race when parent/child processes sharing a drm_file
both try to acquire the same VM after fork().
(cherry picked from commit c7c573275ec20db05be769288a3e3bb2250ec618) |
| In the Linux kernel, the following vulnerability has been resolved:
io_uring/kbuf: check if target buffer list is still legacy on recycle
There's a gap between when the buffer was grabbed and when it
potentially gets recycled, where if the list is empty, someone could've
upgraded it to a ring provided type. This can happen if the request
is forced via io-wq. The legacy recycling is missing checking if the
buffer_list still exists, and if it's of the correct type. Add those
checks. |
| In the Linux kernel, the following vulnerability has been resolved:
KVM: x86: Add SRCU protection for reading PDPTRs in __get_sregs2()
Add SRCU read-side protection when reading PDPTR registers in
__get_sregs2().
Reading PDPTRs may trigger access to guest memory:
kvm_pdptr_read() -> svm_cache_reg() -> load_pdptrs() ->
kvm_vcpu_read_guest_page() -> kvm_vcpu_gfn_to_memslot()
kvm_vcpu_gfn_to_memslot() dereferences memslots via __kvm_memslots(),
which uses srcu_dereference_check() and requires either kvm->srcu or
kvm->slots_lock to be held. Currently only vcpu->mutex is held,
triggering lockdep warning:
=============================
WARNING: suspicious RCU usage in kvm_vcpu_gfn_to_memslot
6.12.59+ #3 Not tainted
include/linux/kvm_host.h:1062 suspicious rcu_dereference_check() usage!
other info that might help us debug this:
rcu_scheduler_active = 2, debug_locks = 1
1 lock held by syz.5.1717/15100:
#0: ff1100002f4b00b0 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x1d5/0x1590
Call Trace:
<TASK>
__dump_stack lib/dump_stack.c:94 [inline]
dump_stack_lvl+0xf0/0x120 lib/dump_stack.c:120
lockdep_rcu_suspicious+0x1e3/0x270 kernel/locking/lockdep.c:6824
__kvm_memslots include/linux/kvm_host.h:1062 [inline]
__kvm_memslots include/linux/kvm_host.h:1059 [inline]
kvm_vcpu_memslots include/linux/kvm_host.h:1076 [inline]
kvm_vcpu_gfn_to_memslot+0x518/0x5e0 virt/kvm/kvm_main.c:2617
kvm_vcpu_read_guest_page+0x27/0x50 virt/kvm/kvm_main.c:3302
load_pdptrs+0xff/0x4b0 arch/x86/kvm/x86.c:1065
svm_cache_reg+0x1c9/0x230 arch/x86/kvm/svm/svm.c:1688
kvm_pdptr_read arch/x86/kvm/kvm_cache_regs.h:141 [inline]
__get_sregs2 arch/x86/kvm/x86.c:11784 [inline]
kvm_arch_vcpu_ioctl+0x3e20/0x4aa0 arch/x86/kvm/x86.c:6279
kvm_vcpu_ioctl+0x856/0x1590 virt/kvm/kvm_main.c:4663
vfs_ioctl fs/ioctl.c:51 [inline]
__do_sys_ioctl fs/ioctl.c:907 [inline]
__se_sys_ioctl fs/ioctl.c:893 [inline]
__x64_sys_ioctl+0x18b/0x210 fs/ioctl.c:893
do_syscall_x64 arch/x86/entry/common.c:52 [inline]
do_syscall_64+0xbd/0x1d0 arch/x86/entry/common.c:83
entry_SYSCALL_64_after_hwframe+0x77/0x7f
Found by Linux Verification Center (linuxtesting.org) with Syzkaller. |
| In the Linux kernel, the following vulnerability has been resolved:
net: usb: kaweth: remove TX queue manipulation in kaweth_set_rx_mode
kaweth_set_rx_mode(), the ndo_set_rx_mode callback, calls
netif_stop_queue() and netif_wake_queue(). These are TX queue flow
control functions unrelated to RX multicast configuration.
The premature netif_wake_queue() can re-enable TX while tx_urb is still
in-flight, leading to a double usb_submit_urb() on the same URB:
kaweth_start_xmit() {
netif_stop_queue();
usb_submit_urb(kaweth->tx_urb);
}
kaweth_set_rx_mode() {
netif_stop_queue();
netif_wake_queue(); // wakes TX queue before URB is done
}
kaweth_start_xmit() {
netif_stop_queue();
usb_submit_urb(kaweth->tx_urb); // URB submitted while active
}
This triggers the WARN in usb_submit_urb():
"URB submitted while active"
This is a similar class of bug fixed in rtl8150 by
- commit 958baf5eaee3 ("net: usb: Remove disruptive netif_wake_queue in rtl8150_set_multicast").
Also kaweth_set_rx_mode() is already functionally broken, the
real set_rx_mode action is performed by kaweth_async_set_rx_mode(),
which in turn is not a no-op only at ndo_open() time. |
| In the Linux kernel, the following vulnerability has been resolved:
HID: roccat: fix use-after-free in roccat_report_event
roccat_report_event() iterates over the device->readers list without
holding the readers_lock. This allows a concurrent roccat_release() to
remove and free a reader while it's still being accessed, leading to a
use-after-free.
Protect the readers list traversal with the readers_lock mutex. |
| In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: hci_conn: fix potential UAF in set_cig_params_sync
hci_conn lookup and field access must be covered by hdev lock in
set_cig_params_sync, otherwise it's possible it is freed concurrently.
Take hdev lock to prevent hci_conn from being deleted or modified
concurrently. Just RCU lock is not suitable here, as we also want to
avoid "tearing" in the configuration. |
| In the Linux kernel, the following vulnerability has been resolved:
thermal: core: Address thermal zone removal races with resume
Since thermal_zone_pm_complete() and thermal_zone_device_resume()
re-initialize the poll_queue delayed work for the given thermal zone,
the cancel_delayed_work_sync() in thermal_zone_device_unregister()
may miss some already running work items and the thermal zone may
be freed prematurely [1].
There are two failing scenarios that both start with
running thermal_pm_notify_complete() right before invoking
thermal_zone_device_unregister() for one of the thermal zones.
In the first scenario, there is a work item already running for
the given thermal zone when thermal_pm_notify_complete() calls
thermal_zone_pm_complete() for that thermal zone and it continues to
run when thermal_zone_device_unregister() starts. Since the poll_queue
delayed work has been re-initialized by thermal_pm_notify_complete(), the
running work item will be missed by the cancel_delayed_work_sync() in
thermal_zone_device_unregister() and if it continues to run past the
freeing of the thermal zone object, a use-after-free will occur.
In the second scenario, thermal_zone_device_resume() queued up by
thermal_pm_notify_complete() runs right after the thermal_zone_exit()
called by thermal_zone_device_unregister() has returned. The poll_queue
delayed work is re-initialized by it before cancel_delayed_work_sync() is
called by thermal_zone_device_unregister(), so it may continue to run
after the freeing of the thermal zone object, which also leads to a
use-after-free.
Address the first failing scenario by ensuring that no thermal work
items will be running when thermal_pm_notify_complete() is called.
For this purpose, first move the cancel_delayed_work() call from
thermal_zone_pm_complete() to thermal_zone_pm_prepare() to prevent
new work from entering the workqueue going forward. Next, switch
over to using a dedicated workqueue for thermal events and update
the code in thermal_pm_notify() to flush that workqueue after
thermal_pm_notify_prepare() has returned which will take care of
all leftover thermal work already on the workqueue (that leftover
work would do nothing useful anyway because all of the thermal zones
have been flagged as suspended).
The second failing scenario is addressed by adding a tz->state check
to thermal_zone_device_resume() to prevent it from re-initializing
the poll_queue delayed work if the thermal zone is going away.
Note that the above changes will also facilitate relocating the suspend
and resume of thermal zones closer to the suspend and resume of devices,
respectively. |
| In the Linux kernel, the following vulnerability has been resolved:
rxrpc: only handle RESPONSE during service challenge
Only process RESPONSE packets while the service connection is still in
RXRPC_CONN_SERVICE_CHALLENGING. Check that state under state_lock before
running response verification and security initialization, then use a local
secured flag to decide whether to queue the secured-connection work after
the state transition. This keeps duplicate or late RESPONSE packets from
re-running the setup path and removes the unlocked post-transition state
test. |
| In the Linux kernel, the following vulnerability has been resolved:
af_unix: read UNIX_DIAG_VFS data under unix_state_lock
Exact UNIX diag lookups hold a reference to the socket, but not to
u->path. Meanwhile, unix_release_sock() clears u->path under
unix_state_lock() and drops the path reference after unlocking.
Read the inode and device numbers for UNIX_DIAG_VFS while holding
unix_state_lock(), then emit the netlink attribute after dropping the
lock.
This keeps the VFS data stable while the reply is being built. |
| 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) |
