| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| In the Linux kernel, the following vulnerability has been resolved:
ext4: reject mount if bigalloc with s_first_data_block != 0
bigalloc with s_first_data_block != 0 is not supported, reject mounting
it. |
| In the Linux kernel, the following vulnerability has been resolved:
ext4: fix use-after-free in update_super_work when racing with umount
Commit b98535d09179 ("ext4: fix bug_on in start_this_handle during umount
filesystem") moved ext4_unregister_sysfs() before flushing s_sb_upd_work
to prevent new error work from being queued via /proc/fs/ext4/xx/mb_groups
reads during unmount. However, this introduced a use-after-free because
update_super_work calls ext4_notify_error_sysfs() -> sysfs_notify() which
accesses the kobject's kernfs_node after it has been freed by kobject_del()
in ext4_unregister_sysfs():
update_super_work ext4_put_super
----------------- --------------
ext4_unregister_sysfs(sb)
kobject_del(&sbi->s_kobj)
__kobject_del()
sysfs_remove_dir()
kobj->sd = NULL
sysfs_put(sd)
kernfs_put() // RCU free
ext4_notify_error_sysfs(sbi)
sysfs_notify(&sbi->s_kobj)
kn = kobj->sd // stale pointer
kernfs_get(kn) // UAF on freed kernfs_node
ext4_journal_destroy()
flush_work(&sbi->s_sb_upd_work)
Instead of reordering the teardown sequence, fix this by making
ext4_notify_error_sysfs() detect that sysfs has already been torn down
by checking s_kobj.state_in_sysfs, and skipping the sysfs_notify() call
in that case. A dedicated mutex (s_error_notify_mutex) serializes
ext4_notify_error_sysfs() against kobject_del() in ext4_unregister_sysfs()
to prevent TOCTOU races where the kobject could be deleted between the
state_in_sysfs check and the sysfs_notify() call. |
| In the Linux kernel, the following vulnerability has been resolved:
dmaengine: idxd: Fix possible invalid memory access after FLR
In the case that the first Function Level Reset (FLR) concludes
correctly, but in the second FLR the scratch area for the saved
configuration cannot be allocated, it's possible for a invalid memory
access to happen.
Always set the deallocated scratch area to NULL after FLR completes. |
| In the Linux kernel, the following vulnerability has been resolved:
dmaengine: idxd: fix possible wrong descriptor completion in llist_abort_desc()
At the end of this function, d is the traversal cursor of flist, but the
code completes found instead. This can lead to issues such as NULL pointer
dereferences, double completion, or descriptor leaks.
Fix this by completing d instead of found in the final
list_for_each_entry_safe() loop. |
| In the Linux kernel, the following vulnerability has been resolved:
netfs: Fix read abandonment during retry
Under certain circumstances, all the remaining subrequests from a read
request will get abandoned during retry. The abandonment process expects
the 'subreq' variable to be set to the place to start abandonment from, but
it doesn't always have a useful value (it will be uninitialised on the
first pass through the loop and it may point to a deleted subrequest on
later passes).
Fix the first jump to "abandon:" to set subreq to the start of the first
subrequest expected to need retry (which, in this abandonment case, turned
out unexpectedly to no longer have NEED_RETRY set).
Also clear the subreq pointer after discarding superfluous retryable
subrequests to cause an oops if we do try to access it. |
| In the Linux kernel, the following vulnerability has been resolved:
ksmbd: fix potencial OOB in get_file_all_info() for compound requests
When a compound request consists of QUERY_DIRECTORY + QUERY_INFO
(FILE_ALL_INFORMATION) and the first command consumes nearly the entire
max_trans_size, get_file_all_info() would blindly call smbConvertToUTF16()
with PATH_MAX, causing out-of-bounds write beyond the response buffer.
In get_file_all_info(), there was a missing validation check for
the client-provided OutputBufferLength before copying the filename into
FileName field of the smb2_file_all_info structure.
If the filename length exceeds the available buffer space, it could lead to
potential buffer overflows or memory corruption during smbConvertToUTF16
conversion. This calculating the actual free buffer size using
smb2_calc_max_out_buf_len() and returning -EINVAL if the buffer is
insufficient and updating smbConvertToUTF16 to use the actual filename
length (clamped by PATH_MAX) to ensure a safe copy operation. |
| In the Linux kernel, the following vulnerability has been resolved:
ksmbd: fix OOB write in QUERY_INFO for compound requests
When a compound request such as READ + QUERY_INFO(Security) is received,
and the first command (READ) consumes most of the response buffer,
ksmbd could write beyond the allocated buffer while building a security
descriptor.
The root cause was that smb2_get_info_sec() checked buffer space using
ppntsd_size from xattr, while build_sec_desc() often synthesized a
significantly larger descriptor from POSIX ACLs.
This patch introduces smb_acl_sec_desc_scratch_len() to accurately
compute the final descriptor size beforehand, performs proper buffer
checking with smb2_calc_max_out_buf_len(), and uses exact-sized
allocation + iov pinning. |
| In the Linux kernel, the following vulnerability has been resolved:
crypto: algif_aead - Revert to operating out-of-place
This mostly reverts commit 72548b093ee3 except for the copying of
the associated data.
There is no benefit in operating in-place in algif_aead since the
source and destination come from different mappings. Get rid of
all the complexity added for in-place operation and just copy the
AD directly. |
| 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:
net: bonding: fix use-after-free in bond_xmit_broadcast()
bond_xmit_broadcast() reuses the original skb for the last slave
(determined by bond_is_last_slave()) and clones it for others.
Concurrent slave enslave/release can mutate the slave list during
RCU-protected iteration, changing which slave is "last" mid-loop.
This causes the original skb to be double-consumed (double-freed).
Replace the racy bond_is_last_slave() check with a simple index
comparison (i + 1 == slaves_count) against the pre-snapshot slave
count taken via READ_ONCE() before the loop. This preserves the
zero-copy optimization for the last slave while making the "last"
determination stable against concurrent list mutations.
The UAF can trigger the following crash:
==================================================================
BUG: KASAN: slab-use-after-free in skb_clone
Read of size 8 at addr ffff888100ef8d40 by task exploit/147
CPU: 1 UID: 0 PID: 147 Comm: exploit Not tainted 7.0.0-rc3+ #4 PREEMPTLAZY
Call Trace:
<TASK>
dump_stack_lvl (lib/dump_stack.c:123)
print_report (mm/kasan/report.c:379 mm/kasan/report.c:482)
kasan_report (mm/kasan/report.c:597)
skb_clone (include/linux/skbuff.h:1724 include/linux/skbuff.h:1792 include/linux/skbuff.h:3396 net/core/skbuff.c:2108)
bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5334)
bond_start_xmit (drivers/net/bonding/bond_main.c:5567 drivers/net/bonding/bond_main.c:5593)
dev_hard_start_xmit (include/linux/netdevice.h:5325 include/linux/netdevice.h:5334 net/core/dev.c:3871 net/core/dev.c:3887)
__dev_queue_xmit (include/linux/netdevice.h:3601 net/core/dev.c:4838)
ip6_finish_output2 (include/net/neighbour.h:540 include/net/neighbour.h:554 net/ipv6/ip6_output.c:136)
ip6_finish_output (net/ipv6/ip6_output.c:208 net/ipv6/ip6_output.c:219)
ip6_output (net/ipv6/ip6_output.c:250)
ip6_send_skb (net/ipv6/ip6_output.c:1985)
udp_v6_send_skb (net/ipv6/udp.c:1442)
udpv6_sendmsg (net/ipv6/udp.c:1733)
__sys_sendto (net/socket.c:730 net/socket.c:742 net/socket.c:2206)
__x64_sys_sendto (net/socket.c:2209)
do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
</TASK>
Allocated by task 147:
Freed by task 147:
The buggy address belongs to the object at ffff888100ef8c80
which belongs to the cache skbuff_head_cache of size 224
The buggy address is located 192 bytes inside of
freed 224-byte region [ffff888100ef8c80, ffff888100ef8d60)
Memory state around the buggy address:
ffff888100ef8c00: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc
ffff888100ef8c80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff888100ef8d00: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
^
ffff888100ef8d80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb
ffff888100ef8e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
================================================================== |
| In the Linux kernel, the following vulnerability has been resolved:
net/x25: Fix overflow when accumulating packets
Add a check to ensure that `x25_sock.fraglen` does not overflow.
The `fraglen` also needs to be resetted when purging `fragment_queue` in
`x25_clear_queues()`. |
| 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:
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:
ksmbd: unset conn->binding on failed binding request
When a multichannel SMB2_SESSION_SETUP request with
SMB2_SESSION_REQ_FLAG_BINDING fails ksmbd sets conn->binding = true
but never clears it on the error path. This leaves the connection in
a binding state where all subsequent ksmbd_session_lookup_all() calls
fall back to the global sessions table. This fix it by clearing
conn->binding = false in the error path. |
| 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:
netfilter: conntrack: add missing netlink policy validations
Hyunwoo Kim reports out-of-bounds access in sctp and ctnetlink.
These attributes are used by the kernel without any validation.
Extend the netlink policies accordingly.
Quoting the reporter:
nlattr_to_sctp() assigns the user-supplied CTA_PROTOINFO_SCTP_STATE
value directly to ct->proto.sctp.state without checking that it is
within the valid range. [..]
and: ... with exp->dir = 100, the access at
ct->master->tuplehash[100] reads 5600 bytes past the start of a
320-byte nf_conn object, causing a slab-out-of-bounds read confirmed by
UBSAN. |
| 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:
media: dvb-net: fix OOB access in ULE extension header tables
The ule_mandatory_ext_handlers[] and ule_optional_ext_handlers[] tables
in handle_one_ule_extension() are declared with 255 elements (valid
indices 0-254), but the index htype is derived from network-controlled
data as (ule_sndu_type & 0x00FF), giving a range of 0-255. When
htype equals 255, an out-of-bounds read occurs on the function pointer
table, and the OOB value may be called as a function pointer.
Add a bounds check on htype against the array size before either table
is accessed. Out-of-range values now cause the SNDU to be discarded. |
| In the Linux kernel, the following vulnerability has been resolved:
NFSD: Defer sub-object cleanup in export put callbacks
svc_export_put() calls path_put() and auth_domain_put() immediately
when the last reference drops, before the RCU grace period. RCU
readers in e_show() and c_show() access both ex_path (via
seq_path/d_path) and ex_client->name (via seq_escape) without
holding a reference. If cache_clean removes the entry and drops the
last reference concurrently, the sub-objects are freed while still
in use, producing a NULL pointer dereference in d_path.
Commit 2530766492ec ("nfsd: fix UAF when access ex_uuid or
ex_stats") moved kfree of ex_uuid and ex_stats into the
call_rcu callback, but left path_put() and auth_domain_put() running
before the grace period because both may sleep and call_rcu
callbacks execute in softirq context.
Replace call_rcu/kfree_rcu with queue_rcu_work(), which defers the
callback until after the RCU grace period and executes it in process
context where sleeping is permitted. This allows path_put() and
auth_domain_put() to be moved into the deferred callback alongside
the other resource releases. Apply the same fix to expkey_put(),
which has the identical pattern with ek_path and ek_client.
A dedicated workqueue scopes the shutdown drain to only NFSD
export release work items; flushing the shared
system_unbound_wq would stall on unrelated work from other
subsystems. nfsd_export_shutdown() uses rcu_barrier() followed
by flush_workqueue() to ensure all deferred release callbacks
complete before the export caches are destroyed.
Reviwed-by: Jeff Layton <jlayton@kernel.org> |
| 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. |
