| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| Memory safety bugs present in Firefox 144 and Thunderbird 144. Some of these bugs showed evidence of memory corruption and we presume that with enough effort some of these could have been exploited to run arbitrary code. This vulnerability was fixed in Firefox 145 and Thunderbird 145. |
| Use-after-free in the WebRTC: Audio/Video component. This vulnerability was fixed in Firefox 145, Firefox ESR 140.5, Thunderbird 145, and Thunderbird 140.5. |
| Use-after-free in the Audio/Video component. This vulnerability was fixed in Firefox 145, Firefox ESR 140.5, Firefox ESR 115.30, Thunderbird 145, and Thunderbird 140.5. |
| Sandbox escape due to undefined behavior, invalid pointer in the Graphics: Canvas2D component. This vulnerability was fixed in Firefox 143, Firefox ESR 140.3, Thunderbird 143, and Thunderbird 140.3. |
| LIBPNG is a reference library for use in applications that read, create, and manipulate PNG (Portable Network Graphics) raster image files. From 1.0.9 to before 1.6.57, passing a pointer obtained from png_get_PLTE, png_get_tRNS, or png_get_hIST back into the corresponding setter on the same png_struct/png_info pair causes the setter to read from freed memory and copy its contents into the replacement buffer. The setter frees the internal buffer before copying from the caller-supplied pointer, which now dangles. The freed region may contain stale data (producing silently corrupted chunk metadata) or data from subsequent heap allocations (leaking unrelated heap contents into the chunk struct). This vulnerability is fixed in 1.6.57. |
| Wasmtime is a runtime for WebAssembly. Prior to 24.0.7, 36.0.7, 42.0.2, and 43.0.1, Wasmtime's implementation of transcoding strings into the Component Model's utf16 or latin1+utf16 encodings improperly verified the alignment of reallocated strings. This meant that unaligned pointers could be passed to the host for transcoding which would trigger a host panic. This panic is possible to trigger from malicious guests which transfer very specific strings across components with specific addresses. Host panics are considered a DoS vector in Wasmtime as the panic conditions are controlled by the guest in this situation. This vulnerability is fixed in 24.0.7, 36.0.7, 42.0.2, and 43.0.1. |
| This CVE ID has been rejected or withdrawn by its CVE Numbering Authority. |
| 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:
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:
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:
spi: fix statistics allocation
The controller per-cpu statistics is not allocated until after the
controller has been registered with driver core, which leaves a window
where accessing the sysfs attributes can trigger a NULL-pointer
dereference.
Fix this by moving the statistics allocation to controller allocation
while tying its lifetime to that of the controller (rather than using
implicit devres). |
| In the Linux kernel, the following vulnerability has been resolved:
btrfs: log new dentries when logging parent dir of a conflicting inode
If we log the parent directory of a conflicting inode, we are not logging
the new dentries of the directory, so when we finish we have the parent
directory's inode marked as logged but we did not log its new dentries.
As a consequence if the parent directory is explicitly fsynced later and
it does not have any new changes since we logged it, the fsync is a no-op
and after a power failure the new dentries are missing.
Example scenario:
$ mkdir foo
$ sync
$rmdir foo
$ mkdir dir1
$ mkdir dir2
# A file with the same name and parent as the directory we just deleted
# and was persisted in a past transaction. So the deleted directory's
# inode is a conflicting inode of this new file's inode.
$ touch foo
$ ln foo dir2/link
# The fsync on dir2 will log the parent directory (".") because the
# conflicting inode (deleted directory) does not exists anymore, but it
# it does not log its new dentries (dir1).
$ xfs_io -c "fsync" dir2
# This fsync on the parent directory is no-op, since the previous fsync
# logged it (but without logging its new dentries).
$ xfs_io -c "fsync" .
<power failure>
# After log replay dir1 is missing.
Fix this by ensuring we log new dir dentries whenever we log the parent
directory of a no longer existing conflicting inode.
A test case for fstests will follow soon. |
| 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/mlx5e: Prevent concurrent access to IPSec ASO context
The query or updating IPSec offload object is through Access ASO WQE.
The driver uses a single mlx5e_ipsec_aso struct for each PF, which
contains a shared DMA-mapped context for all ASO operations.
A race condition exists because the ASO spinlock is released before
the hardware has finished processing WQE. If a second operation is
initiated immediately after, it overwrites the shared context in the
DMA area.
When the first operation's completion is processed later, it reads
this corrupted context, leading to unexpected behavior and incorrect
results.
This commit fixes the race by introducing a private context within
each IPSec offload object. The shared ASO context is now copied to
this private context while the ASO spinlock is held. Subsequent
processing uses this saved, per-object context, ensuring its integrity
is maintained. |
| 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:
ksmbd: fix use-after-free in durable v2 replay of active file handles
parse_durable_handle_context() unconditionally assigns dh_info->fp->conn
to the current connection when handling a DURABLE_REQ_V2 context with
SMB2_FLAGS_REPLAY_OPERATION. ksmbd_lookup_fd_cguid() does not filter by
fp->conn, so it returns file handles that are already actively connected.
The unconditional overwrite replaces fp->conn, and when the overwriting
connection is subsequently freed, __ksmbd_close_fd() dereferences the
stale fp->conn via spin_lock(&fp->conn->llist_lock), causing a
use-after-free.
KASAN report:
[ 7.349357] ==================================================================
[ 7.349607] BUG: KASAN: slab-use-after-free in _raw_spin_lock+0x75/0xe0
[ 7.349811] Write of size 4 at addr ffff8881056ac18c by task kworker/1:2/108
[ 7.350010]
[ 7.350064] CPU: 1 UID: 0 PID: 108 Comm: kworker/1:2 Not tainted 7.0.0-rc3+ #58 PREEMPTLAZY
[ 7.350068] Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[ 7.350070] Workqueue: ksmbd-io handle_ksmbd_work
[ 7.350083] Call Trace:
[ 7.350087] <TASK>
[ 7.350087] dump_stack_lvl+0x64/0x80
[ 7.350094] print_report+0xce/0x660
[ 7.350100] ? __pfx__raw_spin_lock_irqsave+0x10/0x10
[ 7.350101] ? __pfx___mod_timer+0x10/0x10
[ 7.350106] ? _raw_spin_lock+0x75/0xe0
[ 7.350108] kasan_report+0xce/0x100
[ 7.350109] ? _raw_spin_lock+0x75/0xe0
[ 7.350114] kasan_check_range+0x105/0x1b0
[ 7.350116] _raw_spin_lock+0x75/0xe0
[ 7.350118] ? __pfx__raw_spin_lock+0x10/0x10
[ 7.350119] ? __call_rcu_common.constprop.0+0x25e/0x780
[ 7.350125] ? close_id_del_oplock+0x2cc/0x4e0
[ 7.350128] __ksmbd_close_fd+0x27f/0xaf0
[ 7.350131] ksmbd_close_fd+0x135/0x1b0
[ 7.350133] smb2_close+0xb19/0x15b0
[ 7.350142] ? __pfx_smb2_close+0x10/0x10
[ 7.350143] ? xas_load+0x18/0x270
[ 7.350146] ? _raw_spin_lock+0x84/0xe0
[ 7.350148] ? __pfx__raw_spin_lock+0x10/0x10
[ 7.350150] ? _raw_spin_unlock+0xe/0x30
[ 7.350151] ? ksmbd_smb2_check_message+0xeb2/0x24c0
[ 7.350153] ? ksmbd_tree_conn_lookup+0xcd/0xf0
[ 7.350154] handle_ksmbd_work+0x40f/0x1080
[ 7.350156] process_one_work+0x5fa/0xef0
[ 7.350162] ? assign_work+0x122/0x3e0
[ 7.350163] worker_thread+0x54b/0xf70
[ 7.350165] ? __pfx_worker_thread+0x10/0x10
[ 7.350166] kthread+0x346/0x470
[ 7.350170] ? recalc_sigpending+0x19b/0x230
[ 7.350176] ? __pfx_kthread+0x10/0x10
[ 7.350178] ret_from_fork+0x4fb/0x6c0
[ 7.350183] ? __pfx_ret_from_fork+0x10/0x10
[ 7.350185] ? __switch_to+0x36c/0xbe0
[ 7.350188] ? __pfx_kthread+0x10/0x10
[ 7.350190] ret_from_fork_asm+0x1a/0x30
[ 7.350197] </TASK>
[ 7.350197]
[ 7.355160] Allocated by task 123:
[ 7.355261] kasan_save_stack+0x33/0x60
[ 7.355373] kasan_save_track+0x14/0x30
[ 7.355484] __kasan_kmalloc+0x8f/0xa0
[ 7.355593] ksmbd_conn_alloc+0x44/0x6d0
[ 7.355711] ksmbd_kthread_fn+0x243/0xd70
[ 7.355839] kthread+0x346/0x470
[ 7.355942] ret_from_fork+0x4fb/0x6c0
[ 7.356051] ret_from_fork_asm+0x1a/0x30
[ 7.356164]
[ 7.356214] Freed by task 134:
[ 7.356305] kasan_save_stack+0x33/0x60
[ 7.356416] kasan_save_track+0x14/0x30
[ 7.356527] kasan_save_free_info+0x3b/0x60
[ 7.356646] __kasan_slab_free+0x43/0x70
[ 7.356761] kfree+0x1ca/0x430
[ 7.356862] ksmbd_tcp_disconnect+0x59/0xe0
[ 7.356993] ksmbd_conn_handler_loop+0x77e/0xd40
[ 7.357138] kthread+0x346/0x470
[ 7.357240] ret_from_fork+0x4fb/0x6c0
[ 7.357350] ret_from_fork_asm+0x1a/0x30
[ 7.357463]
[ 7.357513] The buggy address belongs to the object at ffff8881056ac000
[ 7.357513] which belongs to the cache kmalloc-1k of size 1024
[ 7.357857] The buggy address is located 396 bytes inside of
[ 7.357857] freed 1024-byte region
---truncated--- |
| In the Linux kernel, the following vulnerability has been resolved:
mm/mseal: update VMA end correctly on merge
Previously we stored the end of the current VMA in curr_end, and then upon
iterating to the next VMA updated curr_start to curr_end to advance to the
next VMA.
However, this doesn't take into account the fact that a VMA might be
updated due to a merge by vma_modify_flags(), which can result in curr_end
being stale and thus, upon setting curr_start to curr_end, ending up with
an incorrect curr_start on the next iteration.
Resolve the issue by setting curr_end to vma->vm_end unconditionally to
ensure this value remains updated should this occur.
While we're here, eliminate this entire class of bug by simply setting
const curr_[start/end] to be clamped to the input range and VMAs, which
also happens to simplify the logic. |
| In the Linux kernel, the following vulnerability has been resolved:
bridge: cfm: Fix race condition in peer_mep deletion
When a peer MEP is being deleted, cancel_delayed_work_sync() is called
on ccm_rx_dwork before freeing. However, br_cfm_frame_rx() runs in
softirq context under rcu_read_lock (without RTNL) and can re-schedule
ccm_rx_dwork via ccm_rx_timer_start() between cancel_delayed_work_sync()
returning and kfree_rcu() being called.
The following is a simple race scenario:
cpu0 cpu1
mep_delete_implementation()
cancel_delayed_work_sync(ccm_rx_dwork);
br_cfm_frame_rx()
// peer_mep still in hlist
if (peer_mep->ccm_defect)
ccm_rx_timer_start()
queue_delayed_work(ccm_rx_dwork)
hlist_del_rcu(&peer_mep->head);
kfree_rcu(peer_mep, rcu);
ccm_rx_work_expired()
// on freed peer_mep
To prevent this, cancel_delayed_work_sync() is replaced with
disable_delayed_work_sync() in both peer MEP deletion paths, so
that subsequent queue_delayed_work() calls from br_cfm_frame_rx()
are silently rejected.
The cc_peer_disable() helper retains cancel_delayed_work_sync()
because it is also used for the CC enable/disable toggle path where
the work must remain re-schedulable. |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_tables: release flowtable after rcu grace period on error
Call synchronize_rcu() after unregistering the hooks from error path,
since a hook that already refers to this flowtable can be already
registered, exposing this flowtable to packet path and nfnetlink_hook
control plane.
This error path is rare, it should only happen by reaching the maximum
number hooks or by failing to set up to hardware offload, just call
synchronize_rcu().
There is a check for already used device hooks by different flowtable
that could result in EEXIST at this late stage. The hook parser can be
updated to perform this check earlier to this error path really becomes
rarely exercised.
Uncovered by KASAN reported as use-after-free from nfnetlink_hook path
when dumping hooks. |
| In the Linux kernel, the following vulnerability has been resolved:
drm/client: Do not destroy NULL modes
'modes' in drm_client_modeset_probe may fail to kcalloc. If this
occurs, we jump to 'out', calling modes_destroy on it, which
dereferences it. This may result in a NULL pointer dereference in the
error case. Prevent that. |
