| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| 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:
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 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:
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:
crypto: ccp - Fix use-after-free on error path
In the error path of sev_tsm_init_locked(), the code dereferences 't'
after it has been freed with kfree(). The pr_err() statement attempts
to access t->tio_en and t->tio_init_done after the memory has been
released.
Move the pr_err() call before kfree(t) to access the fields while the
memory is still valid.
This issue reported by Smatch static analyser |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: nft_set_pipapo: split gc into unlink and reclaim phase
Yiming Qian reports Use-after-free in the pipapo set type:
Under a large number of expired elements, commit-time GC can run for a very
long time in a non-preemptible context, triggering soft lockup warnings and
RCU stall reports (local denial of service).
We must split GC in an unlink and a reclaim phase.
We cannot queue elements for freeing until pointers have been swapped.
Expired elements are still exposed to both the packet path and userspace
dumpers via the live copy of the data structure.
call_rcu() does not protect us: dump operations or element lookups starting
after call_rcu has fired can still observe the free'd element, unless the
commit phase has made enough progress to swap the clone and live pointers
before any new reader has picked up the old version.
This a similar approach as done recently for the rbtree backend in commit
35f83a75529a ("netfilter: nft_set_rbtree: don't gc elements on insert"). |
| In the Linux kernel, the following vulnerability has been resolved:
mm: thp: deny THP for files on anonymous inodes
file_thp_enabled() incorrectly allows THP for files on anonymous inodes
(e.g. guest_memfd and secretmem). These files are created via
alloc_file_pseudo(), which does not call get_write_access() and leaves
inode->i_writecount at 0. Combined with S_ISREG(inode->i_mode) being
true, they appear as read-only regular files when
CONFIG_READ_ONLY_THP_FOR_FS is enabled, making them eligible for THP
collapse.
Anonymous inodes can never pass the inode_is_open_for_write() check
since their i_writecount is never incremented through the normal VFS
open path. The right thing to do is to exclude them from THP eligibility
altogether, since CONFIG_READ_ONLY_THP_FOR_FS was designed for real
filesystem files (e.g. shared libraries), not for pseudo-filesystem
inodes.
For guest_memfd, this allows khugepaged and MADV_COLLAPSE to create
large folios in the page cache via the collapse path, but the
guest_memfd fault handler does not support large folios. This triggers
WARN_ON_ONCE(folio_test_large(folio)) in kvm_gmem_fault_user_mapping().
For secretmem, collapse_file() tries to copy page contents through the
direct map, but secretmem pages are removed from the direct map. This
can result in a kernel crash:
BUG: unable to handle page fault for address: ffff88810284d000
RIP: 0010:memcpy_orig+0x16/0x130
Call Trace:
collapse_file
hpage_collapse_scan_file
madvise_collapse
Secretmem is not affected by the crash on upstream as the memory failure
recovery handles the failed copy gracefully, but it still triggers
confusing false memory failure reports:
Memory failure: 0x106d96f: recovery action for clean unevictable
LRU page: Recovered
Check IS_ANON_FILE(inode) in file_thp_enabled() to deny THP for all
anonymous inode files. |
| In the Linux kernel, the following vulnerability has been resolved:
apparmor: fix race between freeing data and fs accessing it
AppArmor was putting the reference to i_private data on its end after
removing the original entry from the file system. However the inode
can aand does live beyond that point and it is possible that some of
the fs call back functions will be invoked after the reference has
been put, which results in a race between freeing the data and
accessing it through the fs.
While the rawdata/loaddata is the most likely candidate to fail the
race, as it has the fewest references. If properly crafted it might be
possible to trigger a race for the other types stored in i_private.
Fix this by moving the put of i_private referenced data to the correct
place which is during inode eviction. |
| 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:
wifi: cfg80211: cancel rfkill_block work in wiphy_unregister()
There is a use-after-free error in cfg80211_shutdown_all_interfaces found
by syzkaller:
BUG: KASAN: use-after-free in cfg80211_shutdown_all_interfaces+0x213/0x220
Read of size 8 at addr ffff888112a78d98 by task kworker/0:5/5326
CPU: 0 UID: 0 PID: 5326 Comm: kworker/0:5 Not tainted 6.19.0-rc2 #2 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
Workqueue: events cfg80211_rfkill_block_work
Call Trace:
<TASK>
dump_stack_lvl+0x116/0x1f0
print_report+0xcd/0x630
kasan_report+0xe0/0x110
cfg80211_shutdown_all_interfaces+0x213/0x220
cfg80211_rfkill_block_work+0x1e/0x30
process_one_work+0x9cf/0x1b70
worker_thread+0x6c8/0xf10
kthread+0x3c5/0x780
ret_from_fork+0x56d/0x700
ret_from_fork_asm+0x1a/0x30
</TASK>
The problem arises due to the rfkill_block work is not cancelled when wiphy
is being unregistered. In order to fix the issue cancel the corresponding
work in wiphy_unregister().
Found by Linux Verification Center (linuxtesting.org) with Syzkaller. |
| In the Linux kernel, the following vulnerability has been resolved:
bpf: Fix a UAF issue in bpf_trampoline_link_cgroup_shim
The root cause of this bug is that when 'bpf_link_put' reduces the
refcount of 'shim_link->link.link' to zero, the resource is considered
released but may still be referenced via 'tr->progs_hlist' in
'cgroup_shim_find'. The actual cleanup of 'tr->progs_hlist' in
'bpf_shim_tramp_link_release' is deferred. During this window, another
process can cause a use-after-free via 'bpf_trampoline_link_cgroup_shim'.
Based on Martin KaFai Lau's suggestions, I have created a simple patch.
To fix this:
Add an atomic non-zero check in 'bpf_trampoline_link_cgroup_shim'.
Only increment the refcount if it is not already zero.
Testing:
I verified the fix by adding a delay in
'bpf_shim_tramp_link_release' to make the bug easier to trigger:
static void bpf_shim_tramp_link_release(struct bpf_link *link)
{
/* ... */
if (!shim_link->trampoline)
return;
+ msleep(100);
WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link,
shim_link->trampoline, NULL));
bpf_trampoline_put(shim_link->trampoline);
}
Before the patch, running a PoC easily reproduced the crash(almost 100%)
with a call trace similar to KaiyanM's report.
After the patch, the bug no longer occurs even after millions of
iterations. |
| libsixel is a SIXEL encoder/decoder implementation derived from kmiya's sixel. Versions 1.8.7 and prior contain a Use-After-Free vulnerability via the load_gif() function in fromgif.c, where a single sixel_frame_t object is reused across all frames of an animated GIF and gif_init_frame() unconditionally frees and reallocates frame->pixels between frames without consulting the object's reference count. Because the public API explicitly provides sixel_frame_ref() to retain a frame and sixel_frame_get_pixels() to access the raw pixel buffer, a callback following this documented usage pattern will hold a dangling pointer after the second frame is decoded, resulting in a heap use-after-free confirmed by ASAN. Any application using sixel_helper_load_image_file() with a multi-frame callback to process user-supplied animated GIFs is affected, with a reliable crash as the minimum impact and potential for code execution. This issue has been fixed in version 1.8.7-r1. |
| libsixel is a SIXEL encoder/decoder implementation derived from kmiya's sixel. In versions 1.8.7 and prior, when built with the --with-gdk-pixbuf2 option, a use-after-free vulnerability exists in load_with_gdkpixbuf() in loader.c. The cleanup path manually frees the sixel_frame_t object and its internal buffers without consulting the reference count, even though the object was created via the refcounted constructor sixel_frame_new() and exposed to the public callback. A callback that calls sixel_frame_ref(frame) to retain a logically valid reference will hold a dangling pointer after sixel_helper_load_image_file() returns, and any subsequent access to the frame or its fields triggers a use-after-free confirmed by AddressSanitizer. The root cause is a consistency failure between two cleanup strategies in the same codebase: sixel_frame_unref() is used in load_with_builtin() but raw free() is used in load_with_gdkpixbuf(). An attacker supplying a crafted image to any application built against libsixel with gdk-pixbuf2 support can trigger this reliably, potentially leading to information disclosure, memory corruption, or code execution. This issue has been fixed in version 1.8.7-r1. |
| libsixel is a SIXEL encoder/decoder implementation derived from kmiya's sixel. Versions 1.8.7 and prior contain a use-after-free vulnerability in sixel_encoder_encode_bytes() because sixel_frame_init() stores the caller-owned pixel buffer pointer directly in frame->pixels without making a defensive copy. When a resize operation is triggered, sixel_frame_convert_to_rgb888() unconditionally frees this caller-owned buffer and replaces it with a new internal allocation, leaving the caller with a dangling pointer. Any subsequent access to the original buffer by the caller constitutes a use-after-free, confirmed by AddressSanitizer. An attacker who controls incoming frames can trigger this bug repeatedly and predictably, resulting in a reliable crash with potential for code execution. This issue has been fixed in version 1.8.7-r1. |
| A use-after-free issue was addressed with improved memory management. This issue is fixed in Safari 26.2, iOS 18.7.3 and iPadOS 18.7.3, iOS 26.2 and iPadOS 26.2, macOS Tahoe 26.2, tvOS 26.2, visionOS 26.2, watchOS 26.2. Processing maliciously crafted web content may lead to arbitrary code execution. Apple is aware of a report that this issue may have been exploited in an extremely sophisticated attack against specific targeted individuals on versions of iOS before iOS 26. CVE-2025-14174 was also issued in response to this report. |
