| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| In the Linux kernel, the following vulnerability has been resolved:
iio: chemical: sps30_i2c: fix buffer size in sps30_i2c_read_meas()
sizeof(num) evaluates to sizeof(size_t) (8 bytes on 64-bit) instead
of the intended __be32 element size (4 bytes). Use sizeof(*meas) to
correctly match the buffer element type. |
| Improper link resolution before file access ('link following') in Microsoft Defender allows an authorized attacker to elevate privileges locally. |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_tables: Fix for duplicate device in netdev hooks
When handling NETDEV_REGISTER notification, duplicate device
registration must be avoided since the device may have been added by
nft_netdev_hook_alloc() already when creating the hook. |
| 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_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:
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:
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:
net-shapers: don't free reply skb after genlmsg_reply()
genlmsg_reply() hands the reply skb to netlink, and
netlink_unicast() consumes it on all return paths, whether the
skb is queued successfully or freed on an error path.
net_shaper_nl_get_doit() and net_shaper_nl_cap_get_doit()
currently jump to free_msg after genlmsg_reply() fails and call
nlmsg_free(msg), which can hit the same skb twice.
Return the genlmsg_reply() error directly and keep free_msg
only for pre-reply failures. |
| In the Linux kernel, the following vulnerability has been resolved:
hwmon: (pmbus/q54sj108a2) fix stack overflow in debugfs read
The q54sj108a2_debugfs_read function suffers from a stack buffer overflow
due to incorrect arguments passed to bin2hex(). The function currently
passes 'data' as the destination and 'data_char' as the source.
Because bin2hex() converts each input byte into two hex characters, a
32-byte block read results in 64 bytes of output. Since 'data' is only
34 bytes (I2C_SMBUS_BLOCK_MAX + 2), this writes 30 bytes past the end
of the buffer onto the stack.
Additionally, the arguments were swapped: it was reading from the
zero-initialized 'data_char' and writing to 'data', resulting in
all-zero output regardless of the actual I2C read.
Fix this by:
1. Expanding 'data_char' to 66 bytes to safely hold the hex output.
2. Correcting the bin2hex() argument order and using the actual read count.
3. Using a pointer to select the correct output buffer for the final
simple_read_from_buffer call. |
| In the Linux kernel, the following vulnerability has been resolved:
smb: server: fix use-after-free in smb2_open()
The opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is
dereferenced after rcu_read_unlock(), creating a use-after-free
window. |
| 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:
Bluetooth: L2CAP: Fix use-after-free in l2cap_unregister_user
After commit ab4eedb790ca ("Bluetooth: L2CAP: Fix corrupted list in
hci_chan_del"), l2cap_conn_del() uses conn->lock to protect access to
conn->users. However, l2cap_register_user() and l2cap_unregister_user()
don't use conn->lock, creating a race condition where these functions can
access conn->users and conn->hchan concurrently with l2cap_conn_del().
This can lead to use-after-free and list corruption bugs, as reported
by syzbot.
Fix this by changing l2cap_register_user() and l2cap_unregister_user()
to use conn->lock instead of hci_dev_lock(), ensuring consistent locking
for the l2cap_conn structure. |
| In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: HIDP: Fix possible UAF
This fixes the following trace caused by not dropping l2cap_conn
reference when user->remove callback is called:
[ 97.809249] l2cap_conn_free: freeing conn ffff88810a171c00
[ 97.809907] CPU: 1 UID: 0 PID: 1419 Comm: repro_standalon Not tainted 7.0.0-rc1-dirty #14 PREEMPT(lazy)
[ 97.809935] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
[ 97.809947] Call Trace:
[ 97.809954] <TASK>
[ 97.809961] dump_stack_lvl (lib/dump_stack.c:122)
[ 97.809990] l2cap_conn_free (net/bluetooth/l2cap_core.c:1808)
[ 97.810017] l2cap_conn_del (./include/linux/kref.h:66 net/bluetooth/l2cap_core.c:1821 net/bluetooth/l2cap_core.c:1798)
[ 97.810055] l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7347 (discriminator 1) net/bluetooth/l2cap_core.c:7340 (discriminator 1))
[ 97.810086] ? __pfx_l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7341)
[ 97.810117] hci_conn_hash_flush (./include/net/bluetooth/hci_core.h:2152 (discriminator 2) net/bluetooth/hci_conn.c:2644 (discriminator 2))
[ 97.810148] hci_dev_close_sync (net/bluetooth/hci_sync.c:5360)
[ 97.810180] ? __pfx_hci_dev_close_sync (net/bluetooth/hci_sync.c:5285)
[ 97.810212] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[ 97.810242] ? up_write (./arch/x86/include/asm/atomic64_64.h:87 (discriminator 5) ./include/linux/atomic/atomic-arch-fallback.h:2852 (discriminator 5) ./include/linux/atomic/atomic-long.h:268 (discriminator 5) ./include/linux/atomic/atomic-instrumented.h:3391 (discriminator 5) kernel/locking/rwsem.c:1385 (discriminator 5) kernel/locking/rwsem.c:1643 (discriminator 5))
[ 97.810267] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[ 97.810290] ? rcu_is_watching (./arch/x86/include/asm/atomic.h:23 ./include/linux/atomic/atomic-arch-fallback.h:457 ./include/linux/context_tracking.h:128 kernel/rcu/tree.c:752)
[ 97.810320] hci_unregister_dev (net/bluetooth/hci_core.c:504 net/bluetooth/hci_core.c:2716)
[ 97.810346] vhci_release (drivers/bluetooth/hci_vhci.c:691)
[ 97.810375] ? __pfx_vhci_release (drivers/bluetooth/hci_vhci.c:678)
[ 97.810404] __fput (fs/file_table.c:470)
[ 97.810430] task_work_run (kernel/task_work.c:235)
[ 97.810451] ? __pfx_task_work_run (kernel/task_work.c:201)
[ 97.810472] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[ 97.810495] ? do_raw_spin_unlock (./include/asm-generic/qspinlock.h:128 (discriminator 5) kernel/locking/spinlock_debug.c:142 (discriminator 5))
[ 97.810527] do_exit (kernel/exit.c:972)
[ 97.810547] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[ 97.810574] ? __pfx_do_exit (kernel/exit.c:897)
[ 97.810594] ? lock_acquire (kernel/locking/lockdep.c:470 (discriminator 6) kernel/locking/lockdep.c:5870 (discriminator 6) kernel/locking/lockdep.c:5825 (discriminator 6))
[ 97.810616] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[ 97.810639] ? do_raw_spin_lock (kernel/locking/spinlock_debug.c:95 (discriminator 4) kernel/locking/spinlock_debug.c:118 (discriminator 4))
[ 97.810664] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[ 97.810688] ? find_held_lock (kernel/locking/lockdep.c:5350 (discriminator 1))
[ 97.810721] do_group_exit (kernel/exit.c:1093)
[ 97.810745] get_signal (kernel/signal.c:3007 (discriminator 1))
[ 97.810772] ? security_file_permission (./arch/x86/include/asm/jump_label.h:37 security/security.c:2366)
[ 97.810803] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[ 97.810826] ? vfs_read (fs/read_write.c:555)
[ 97.810854] ? __pfx_get_signal (kernel/signal.c:2800)
[ 97.810880] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[ 97.810905] ? __pfx_vfs_read (fs/read_write.c:555)
[ 97.810932] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[ 97.810960] arch_do_signal_or_restart (arch/
---truncated--- |
| In the Linux kernel, the following vulnerability has been resolved:
drm/xe: Open-code GGTT MMIO access protection
GGTT MMIO access is currently protected by hotplug (drm_dev_enter),
which works correctly when the driver loads successfully and is later
unbound or unloaded. However, if driver load fails, this protection is
insufficient because drm_dev_unplug() is never called.
Additionally, devm release functions cannot guarantee that all BOs with
GGTT mappings are destroyed before the GGTT MMIO region is removed, as
some BOs may be freed asynchronously by worker threads.
To address this, introduce an open-coded flag, protected by the GGTT
lock, that guards GGTT MMIO access. The flag is cleared during the
dev_fini_ggtt devm release function to ensure MMIO access is disabled
once teardown begins.
(cherry picked from commit 4f3a998a173b4325c2efd90bdadc6ccd3ad9a431) |
| 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. |
| Template::Plugin::HTML versions through 3.102 for Perl allows HTML and JavaScript to be injected.
The html_filter function did not escape single quotes. HTML attributes inside of single quotes could be have code injected. For example, the variable "var" in
<a id='ref' title='[% var | html %]'>
would not be properly escaped. An attacker could insert some limited HTML and JavaScript, for example,
var = " ' onclick='while (true) { alert(1) }'"
Note that arbitrary HTML and JavaScript would be difficult to inject, because angle brackets, ampersands and double-quotes would still be escaped. |
| A flaw was found in nano. A local user could exploit a format string vulnerability in the `statusline()` function. By creating a directory with a name containing `printf` specifiers, the application attempts to display this name, leading to a segmentation fault (SEGV). This results in a Denial of Service (DoS) for the `nano` application. |
| A flaw was found in ansible-collection-community-general. This vulnerability allows for information exposure (IE) of sensitive credentials, specifically plaintext passwords, via verbose output when running Ansible with debug modes. Attackers with access to logs could retrieve these secrets and potentially compromise Keycloak accounts or administrative access. |
| 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:
mm/huge_memory: fix use of NULL folio in move_pages_huge_pmd()
move_pages_huge_pmd() handles UFFDIO_MOVE for both normal THPs and huge
zero pages. For the huge zero page path, src_folio is explicitly set to
NULL, and is used as a sentinel to skip folio operations like lock and
rmap.
In the huge zero page branch, src_folio is NULL, so folio_mk_pmd(NULL,
pgprot) passes NULL through folio_pfn() and page_to_pfn(). With
SPARSEMEM_VMEMMAP this silently produces a bogus PFN, installing a PMD
pointing to non-existent physical memory. On other memory models it is a
NULL dereference.
Use page_folio(src_page) to obtain the valid huge zero folio from the
page, which was obtained from pmd_page() and remains valid throughout.
After commit d82d09e48219 ("mm/huge_memory: mark PMD mappings of the huge
zero folio special"), moved huge zero PMDs must remain special so
vm_normal_page_pmd() continues to treat them as special mappings.
move_pages_huge_pmd() currently reconstructs the destination PMD in the
huge zero page branch, which drops PMD state such as pmd_special() on
architectures with CONFIG_ARCH_HAS_PTE_SPECIAL. As a result,
vm_normal_page_pmd() can treat the moved huge zero PMD as a normal page
and corrupt its refcount.
Instead of reconstructing the PMD from the folio, derive the destination
entry from src_pmdval after pmdp_huge_clear_flush(), then handle the PMD
metadata the same way move_huge_pmd() does for moved entries by marking it
soft-dirty and clearing uffd-wp. |
