| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| In the Linux kernel, the following vulnerability has been resolved:
xfs: avoid dereferencing log items after push callbacks
After xfsaild_push_item() calls iop_push(), the log item may have been
freed if the AIL lock was dropped during the push. Background inode
reclaim or the dquot shrinker can free the log item while the AIL lock
is not held, and the tracepoints in the switch statement dereference
the log item after iop_push() returns.
Fix this by capturing the log item type, flags, and LSN before calling
xfsaild_push_item(), and introducing a new xfs_ail_push_class trace
event class that takes these pre-captured values and the ailp pointer
instead of the log item pointer. |
| 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. |
| In the Linux kernel, the following vulnerability has been resolved:
ksmbd: fix use-after-free of share_conf in compound request
smb2_get_ksmbd_tcon() reuses work->tcon in compound requests without
validating tcon->t_state. ksmbd_tree_conn_lookup() checks t_state ==
TREE_CONNECTED on the initial lookup path, but the compound reuse path
bypasses this check entirely.
If a prior command in the compound (SMB2_TREE_DISCONNECT) sets t_state
to TREE_DISCONNECTED and frees share_conf via ksmbd_share_config_put(),
subsequent commands dereference the freed share_conf through
work->tcon->share_conf.
KASAN report:
[ 4.144653] ==================================================================
[ 4.145059] BUG: KASAN: slab-use-after-free in smb2_write+0xc74/0xe70
[ 4.145415] Read of size 4 at addr ffff88810430c194 by task kworker/1:1/44
[ 4.145772]
[ 4.145867] CPU: 1 UID: 0 PID: 44 Comm: kworker/1:1 Not tainted 7.0.0-rc3+ #60 PREEMPTLAZY
[ 4.145871] 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
[ 4.145875] Workqueue: ksmbd-io handle_ksmbd_work
[ 4.145888] Call Trace:
[ 4.145892] <TASK>
[ 4.145894] dump_stack_lvl+0x64/0x80
[ 4.145910] print_report+0xce/0x660
[ 4.145919] ? __pfx__raw_spin_lock_irqsave+0x10/0x10
[ 4.145928] ? smb2_write+0xc74/0xe70
[ 4.145931] kasan_report+0xce/0x100
[ 4.145934] ? smb2_write+0xc74/0xe70
[ 4.145937] smb2_write+0xc74/0xe70
[ 4.145939] ? __pfx_smb2_write+0x10/0x10
[ 4.145942] ? _raw_spin_unlock+0xe/0x30
[ 4.145945] ? ksmbd_smb2_check_message+0xeb2/0x24c0
[ 4.145948] ? smb2_tree_disconnect+0x31c/0x480
[ 4.145951] handle_ksmbd_work+0x40f/0x1080
[ 4.145953] process_one_work+0x5fa/0xef0
[ 4.145962] ? assign_work+0x122/0x3e0
[ 4.145964] worker_thread+0x54b/0xf70
[ 4.145967] ? __pfx_worker_thread+0x10/0x10
[ 4.145970] kthread+0x346/0x470
[ 4.145976] ? recalc_sigpending+0x19b/0x230
[ 4.145980] ? __pfx_kthread+0x10/0x10
[ 4.145984] ret_from_fork+0x4fb/0x6c0
[ 4.145992] ? __pfx_ret_from_fork+0x10/0x10
[ 4.145995] ? __switch_to+0x36c/0xbe0
[ 4.145999] ? __pfx_kthread+0x10/0x10
[ 4.146003] ret_from_fork_asm+0x1a/0x30
[ 4.146013] </TASK>
[ 4.146014]
[ 4.149858] Allocated by task 44:
[ 4.149953] kasan_save_stack+0x33/0x60
[ 4.150061] kasan_save_track+0x14/0x30
[ 4.150169] __kasan_kmalloc+0x8f/0xa0
[ 4.150274] ksmbd_share_config_get+0x1dd/0xdd0
[ 4.150401] ksmbd_tree_conn_connect+0x7e/0x600
[ 4.150529] smb2_tree_connect+0x2e6/0x1000
[ 4.150645] handle_ksmbd_work+0x40f/0x1080
[ 4.150761] process_one_work+0x5fa/0xef0
[ 4.150873] worker_thread+0x54b/0xf70
[ 4.150978] kthread+0x346/0x470
[ 4.151071] ret_from_fork+0x4fb/0x6c0
[ 4.151176] ret_from_fork_asm+0x1a/0x30
[ 4.151286]
[ 4.151332] Freed by task 44:
[ 4.151418] kasan_save_stack+0x33/0x60
[ 4.151526] kasan_save_track+0x14/0x30
[ 4.151634] kasan_save_free_info+0x3b/0x60
[ 4.151751] __kasan_slab_free+0x43/0x70
[ 4.151861] kfree+0x1ca/0x430
[ 4.151952] __ksmbd_tree_conn_disconnect+0xc8/0x190
[ 4.152088] smb2_tree_disconnect+0x1cd/0x480
[ 4.152211] handle_ksmbd_work+0x40f/0x1080
[ 4.152326] process_one_work+0x5fa/0xef0
[ 4.152438] worker_thread+0x54b/0xf70
[ 4.152545] kthread+0x346/0x470
[ 4.152638] ret_from_fork+0x4fb/0x6c0
[ 4.152743] ret_from_fork_asm+0x1a/0x30
[ 4.152853]
[ 4.152900] The buggy address belongs to the object at ffff88810430c180
[ 4.152900] which belongs to the cache kmalloc-96 of size 96
[ 4.153226] The buggy address is located 20 bytes inside of
[ 4.153226] freed 96-byte region [ffff88810430c180, ffff88810430c1e0)
[ 4.153549]
[ 4.153596] The buggy address belongs to the physical page:
[ 4.153750] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff88810430ce80 pfn:0x10430c
[ 4.154000] flags: 0x
---truncated--- |
| 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:
blktrace: fix __this_cpu_read/write in preemptible context
tracing_record_cmdline() internally uses __this_cpu_read() and
__this_cpu_write() on the per-CPU variable trace_cmdline_save, and
trace_save_cmdline() explicitly asserts preemption is disabled via
lockdep_assert_preemption_disabled(). These operations are only safe
when preemption is off, as they were designed to be called from the
scheduler context (probe_wakeup_sched_switch() / probe_wakeup()).
__blk_add_trace() was calling tracing_record_cmdline(current) early in
the blk_tracer path, before ring buffer reservation, from process
context where preemption is fully enabled. This triggers the following
using blktests/blktrace/002:
blktrace/002 (blktrace ftrace corruption with sysfs trace) [failed]
runtime 0.367s ... 0.437s
something found in dmesg:
[ 81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33
[ 81.239580] null_blk: disk nullb1 created
[ 81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516
[ 81.362842] caller is tracing_record_cmdline+0x10/0x40
[ 81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G N 7.0.0-rc1lblk+ #84 PREEMPT(full)
[ 81.362877] Tainted: [N]=TEST
[ 81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014
[ 81.362881] Call Trace:
[ 81.362884] <TASK>
[ 81.362886] dump_stack_lvl+0x8d/0xb0
...
(See '/mnt/sda/blktests/results/nodev/blktrace/002.dmesg' for the entire message)
[ 81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33
[ 81.239580] null_blk: disk nullb1 created
[ 81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516
[ 81.362842] caller is tracing_record_cmdline+0x10/0x40
[ 81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G N 7.0.0-rc1lblk+ #84 PREEMPT(full)
[ 81.362877] Tainted: [N]=TEST
[ 81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014
[ 81.362881] Call Trace:
[ 81.362884] <TASK>
[ 81.362886] dump_stack_lvl+0x8d/0xb0
[ 81.362895] check_preemption_disabled+0xce/0xe0
[ 81.362902] tracing_record_cmdline+0x10/0x40
[ 81.362923] __blk_add_trace+0x307/0x5d0
[ 81.362934] ? lock_acquire+0xe0/0x300
[ 81.362940] ? iov_iter_extract_pages+0x101/0xa30
[ 81.362959] blk_add_trace_bio+0x106/0x1e0
[ 81.362968] submit_bio_noacct_nocheck+0x24b/0x3a0
[ 81.362979] ? lockdep_init_map_type+0x58/0x260
[ 81.362988] submit_bio_wait+0x56/0x90
[ 81.363009] __blkdev_direct_IO_simple+0x16c/0x250
[ 81.363026] ? __pfx_submit_bio_wait_endio+0x10/0x10
[ 81.363038] ? rcu_read_lock_any_held+0x73/0xa0
[ 81.363051] blkdev_read_iter+0xc1/0x140
[ 81.363059] vfs_read+0x20b/0x330
[ 81.363083] ksys_read+0x67/0xe0
[ 81.363090] do_syscall_64+0xbf/0xf00
[ 81.363102] entry_SYSCALL_64_after_hwframe+0x76/0x7e
[ 81.363106] RIP: 0033:0x7f281906029d
[ 81.363111] Code: 31 c0 e9 c6 fe ff ff 50 48 8d 3d 66 63 0a 00 e8 59 ff 01 00 66 0f 1f 84 00 00 00 00 00 80 3d 41 33 0e 00 00 74 17 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 5b c3 66 2e 0f 1f 84 00 00 00 00 00 48 83 ec
[ 81.363113] RSP: 002b:00007ffca127dd48 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
[ 81.363120] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f281906029d
[ 81.363122] RDX: 0000000000001000 RSI: 0000559f8bfae000 RDI: 0000000000000000
[ 81.363123] RBP: 0000000000001000 R08: 0000002863a10a81 R09: 00007f281915f000
[ 81.363124] R10: 00007f2818f77b60 R11: 0000000000000246 R12: 0000559f8bfae000
[ 81.363126] R13: 0000000000000000 R14: 0000000000000000 R15: 000000000000000a
[ 81.363142] </TASK>
The same BUG fires from blk_add_trace_plug(), blk_add_trace_unplug(),
and blk_add_trace_rq() paths as well.
The purpose of tracin
---truncated--- |
| A flaw was found in p11-kit. A remote attacker could exploit this vulnerability by calling the C_DeriveKey function on a remote token with specific IBM kyber or IBM btc derive mechanism parameters set to NULL. This could lead to the RPC-client attempting to return an uninitialized value, potentially resulting in a NULL dereference or undefined behavior. This issue may cause an application level denial of service or other unpredictable system states. |
| Untrusted pointer dereference in Windows Virtualization-Based Security (VBS) Enclave allows an authorized attacker to bypass a security feature locally. |
| Untrusted pointer dereference in Windows Sensor Data Service allows an authorized attacker to elevate privileges locally. |
| In the Linux kernel, the following vulnerability has been resolved:
drm/amdgpu: Fix error handling in slot reset
If the device has not recovered after slot reset is called, it goes to
out label for error handling. There it could make decision based on
uninitialized hive pointer and could result in accessing an uninitialized
list.
Initialize the list and hive properly so that it handles the error
situation and also releases the reset domain lock which is acquired
during error_detected callback.
(cherry picked from commit bb71362182e59caa227e4192da5a612b09349696) |
| In the Linux kernel, the following vulnerability has been resolved:
net: bridge: fix nd_tbl NULL dereference when IPv6 is disabled
When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never
initialized because inet6_init() exits before ndisc_init() is called
which initializes it. Then, if neigh_suppress is enabled and an ICMPv6
Neighbor Discovery packet reaches the bridge, br_do_suppress_nd() will
dereference ipv6_stub->nd_tbl which is NULL, passing it to
neigh_lookup(). This causes a kernel NULL pointer dereference.
BUG: kernel NULL pointer dereference, address: 0000000000000268
Oops: 0000 [#1] PREEMPT SMP NOPTI
[...]
RIP: 0010:neigh_lookup+0x16/0xe0
[...]
Call Trace:
<IRQ>
? neigh_lookup+0x16/0xe0
br_do_suppress_nd+0x160/0x290 [bridge]
br_handle_frame_finish+0x500/0x620 [bridge]
br_handle_frame+0x353/0x440 [bridge]
__netif_receive_skb_core.constprop.0+0x298/0x1110
__netif_receive_skb_one_core+0x3d/0xa0
process_backlog+0xa0/0x140
__napi_poll+0x2c/0x170
net_rx_action+0x2c4/0x3a0
handle_softirqs+0xd0/0x270
do_softirq+0x3f/0x60
Fix this by replacing IS_ENABLED(IPV6) call with ipv6_mod_enabled() in
the callers. This is in essence disabling NS/NA suppression when IPv6 is
disabled. |
| In the Linux kernel, the following vulnerability has been resolved:
wifi: radiotap: reject radiotap with unknown bits
The radiotap parser is currently only used with the radiotap
namespace (not with vendor namespaces), but if the undefined
field 18 is used, the alignment/size is unknown as well. In
this case, iterator->_next_ns_data isn't initialized (it's
only set for skipping vendor namespaces), and syzbot points
out that we later compare against this uninitialized value.
Fix this by moving the rejection of unknown radiotap fields
down to after the in-namespace lookup, so it will really use
iterator->_next_ns_data only for vendor namespaces, even in
case undefined fields are present. |
| 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. |
| 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. |
