| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| NVIDIA Triton Inference Server contains a vulnerability where an attacker could cause a path traversal issue. A successful exploit of this vulnerability might lead to denial of service. |
| NVIDIA Triton Inference Server contains a vulnerability where an attacker could cause a path traversal issue. A successful exploit of this vulnerability might lead to denial of service. |
| NVIDIA Triton Inference Server contains a vulnerability where an attacker could cause an integer overflow. A successful exploit of this vulnerability might lead to denial of service. |
| 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:
ksmbd: use volume UUID in FS_OBJECT_ID_INFORMATION
Use sb->s_uuid for a proper volume identifier as the primary choice.
For filesystems that do not provide a UUID, fall back to stfs.f_fsid
obtained from vfs_statfs(). |
| 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:
net: atm: fix crash due to unvalidated vcc pointer in sigd_send()
Reproducer available at [1].
The ATM send path (sendmsg -> vcc_sendmsg -> sigd_send) reads the vcc
pointer from msg->vcc and uses it directly without any validation. This
pointer comes from userspace via sendmsg() and can be arbitrarily forged:
int fd = socket(AF_ATMSVC, SOCK_DGRAM, 0);
ioctl(fd, ATMSIGD_CTRL); // become ATM signaling daemon
struct msghdr msg = { .msg_iov = &iov, ... };
*(unsigned long *)(buf + 4) = 0xdeadbeef; // fake vcc pointer
sendmsg(fd, &msg, 0); // kernel dereferences 0xdeadbeef
In normal operation, the kernel sends the vcc pointer to the signaling
daemon via sigd_enq() when processing operations like connect(), bind(),
or listen(). The daemon is expected to return the same pointer when
responding. However, a malicious daemon can send arbitrary pointer values.
Fix this by introducing find_get_vcc() which validates the pointer by
searching through vcc_hash (similar to how sigd_close() iterates over
all VCCs), and acquires a reference via sock_hold() if found.
Since struct atm_vcc embeds struct sock as its first member, they share
the same lifetime. Therefore using sock_hold/sock_put is sufficient to
keep the vcc alive while it is being used.
Note that there may be a race with sigd_close() which could mark the vcc
with various flags (e.g., ATM_VF_RELEASED) after find_get_vcc() returns.
However, sock_hold() guarantees the memory remains valid, so this race
only affects the logical state, not memory safety.
[1]: https://gist.github.com/mrpre/1ba5949c45529c511152e2f4c755b0f3 |
| In the Linux kernel, the following vulnerability has been resolved:
usb: gadget: f_mass_storage: Fix potential integer overflow in check_command_size_in_blocks()
The `check_command_size_in_blocks()` function calculates the data size
in bytes by left shifting `common->data_size_from_cmnd` by the block
size (`common->curlun->blkbits`). However, it does not validate whether
this shift operation will cause an integer overflow.
Initially, the block size is set up in `fsg_lun_open()` , and the
`common->data_size_from_cmnd` is set up in `do_scsi_command()`. During
initialization, there is no integer overflow check for the interaction
between two variables.
So if a malicious USB host sends a SCSI READ or WRITE command
requesting a large amount of data (`common->data_size_from_cmnd`), the
left shift operation can wrap around. This results in a truncated data
size, which can bypass boundary checks and potentially lead to memory
corruption or out-of-bounds accesses.
Fix this by using the check_shl_overflow() macro to safely perform the
shift and catch any overflows. |
| 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:
ipv6: avoid overflows in ip6_datagram_send_ctl()
Yiming Qian reported :
<quote>
I believe I found a locally triggerable kernel bug in the IPv6 sendmsg
ancillary-data path that can panic the kernel via `skb_under_panic()`
(local DoS).
The core issue is a mismatch between:
- a 16-bit length accumulator (`struct ipv6_txoptions::opt_flen`, type
`__u16`) and
- a pointer to the *last* provided destination-options header (`opt->dst1opt`)
when multiple `IPV6_DSTOPTS` control messages (cmsgs) are provided.
- `include/net/ipv6.h`:
- `struct ipv6_txoptions::opt_flen` is `__u16` (wrap possible).
(lines 291-307, especially 298)
- `net/ipv6/datagram.c:ip6_datagram_send_ctl()`:
- Accepts repeated `IPV6_DSTOPTS` and accumulates into `opt_flen`
without rejecting duplicates. (lines 909-933)
- `net/ipv6/ip6_output.c:__ip6_append_data()`:
- Uses `opt->opt_flen + opt->opt_nflen` to compute header
sizes/headroom decisions. (lines 1448-1466, especially 1463-1465)
- `net/ipv6/ip6_output.c:__ip6_make_skb()`:
- Calls `ipv6_push_frag_opts()` if `opt->opt_flen` is non-zero.
(lines 1930-1934)
- `net/ipv6/exthdrs.c:ipv6_push_frag_opts()` / `ipv6_push_exthdr()`:
- Push size comes from `ipv6_optlen(opt->dst1opt)` (based on the
pointed-to header). (lines 1179-1185 and 1206-1211)
1. `opt_flen` is a 16-bit accumulator:
- `include/net/ipv6.h:298` defines `__u16 opt_flen; /* after fragment hdr */`.
2. `ip6_datagram_send_ctl()` accepts *repeated* `IPV6_DSTOPTS` cmsgs
and increments `opt_flen` each time:
- In `net/ipv6/datagram.c:909-933`, for `IPV6_DSTOPTS`:
- It computes `len = ((hdr->hdrlen + 1) << 3);`
- It checks `CAP_NET_RAW` using `ns_capable(net->user_ns,
CAP_NET_RAW)`. (line 922)
- Then it does:
- `opt->opt_flen += len;` (line 927)
- `opt->dst1opt = hdr;` (line 928)
There is no duplicate rejection here (unlike the legacy
`IPV6_2292DSTOPTS` path which rejects duplicates at
`net/ipv6/datagram.c:901-904`).
If enough large `IPV6_DSTOPTS` cmsgs are provided, `opt_flen` wraps
while `dst1opt` still points to a large (2048-byte)
destination-options header.
In the attached PoC (`poc.c`):
- 32 cmsgs with `hdrlen=255` => `len = (255+1)*8 = 2048`
- 1 cmsg with `hdrlen=0` => `len = 8`
- Total increment: `32*2048 + 8 = 65544`, so `(__u16)opt_flen == 8`
- The last cmsg is 2048 bytes, so `dst1opt` points to a 2048-byte header.
3. The transmit path sizes headers using the wrapped `opt_flen`:
- In `net/ipv6/ip6_output.c:1463-1465`:
- `headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen +
opt->opt_nflen : 0) + ...;`
With wrapped `opt_flen`, `headersize`/headroom decisions underestimate
what will be pushed later.
4. When building the final skb, the actual push length comes from
`dst1opt` and is not limited by wrapped `opt_flen`:
- In `net/ipv6/ip6_output.c:1930-1934`:
- `if (opt->opt_flen) proto = ipv6_push_frag_opts(skb, opt, proto);`
- In `net/ipv6/exthdrs.c:1206-1211`, `ipv6_push_frag_opts()` pushes
`dst1opt` via `ipv6_push_exthdr()`.
- In `net/ipv6/exthdrs.c:1179-1184`, `ipv6_push_exthdr()` does:
- `skb_push(skb, ipv6_optlen(opt));`
- `memcpy(h, opt, ipv6_optlen(opt));`
With insufficient headroom, `skb_push()` underflows and triggers
`skb_under_panic()` -> `BUG()`:
- `net/core/skbuff.c:2669-2675` (`skb_push()` calls `skb_under_panic()`)
- `net/core/skbuff.c:207-214` (`skb_panic()` ends in `BUG()`)
- The `IPV6_DSTOPTS` cmsg path requires `CAP_NET_RAW` in the target
netns user namespace (`ns_capable(net->user_ns, CAP_NET_RAW)`).
- Root (or any task with `CAP_NET_RAW`) can trigger this without user
namespaces.
- An unprivileged `uid=1000` user can trigger this if unprivileged
user namespaces are enabled and it can create a userns+netns to obtain
namespaced `CAP_NET_RAW` (the attached PoC does this).
- Local denial of service: kernel BUG/panic (system crash).
-
---truncated--- |
| 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:
soc: fsl: qbman: fix race condition in qman_destroy_fq
When QMAN_FQ_FLAG_DYNAMIC_FQID is set, there's a race condition between
fq_table[fq->idx] state and freeing/allocating from the pool and
WARN_ON(fq_table[fq->idx]) in qman_create_fq() gets triggered.
Indeed, we can have:
Thread A Thread B
qman_destroy_fq() qman_create_fq()
qman_release_fqid()
qman_shutdown_fq()
gen_pool_free()
-- At this point, the fqid is available again --
qman_alloc_fqid()
-- so, we can get the just-freed fqid in thread B --
fq->fqid = fqid;
fq->idx = fqid * 2;
WARN_ON(fq_table[fq->idx]);
fq_table[fq->idx] = fq;
fq_table[fq->idx] = NULL;
And adding some logs between qman_release_fqid() and
fq_table[fq->idx] = NULL makes the WARN_ON() trigger a lot more.
To prevent that, ensure that fq_table[fq->idx] is set to NULL before
gen_pool_free() is called by using smp_wmb(). |
| In the Linux kernel, the following vulnerability has been resolved:
soc: microchip: mpfs: Fix memory leak in mpfs_sys_controller_probe()
In mpfs_sys_controller_probe(), if of_get_mtd_device_by_node() fails,
the function returns immediately without freeing the allocated memory
for sys_controller, leading to a memory leak.
Fix this by jumping to the out_free label to ensure the memory is
properly freed.
Also, consolidate the error handling for the mbox_request_channel()
failure case to use the same label. |
| In the Linux kernel, the following vulnerability has been resolved:
btrfs: log new dentries when logging parent dir of a conflicting inode
If we log the parent directory of a conflicting inode, we are not logging
the new dentries of the directory, so when we finish we have the parent
directory's inode marked as logged but we did not log its new dentries.
As a consequence if the parent directory is explicitly fsynced later and
it does not have any new changes since we logged it, the fsync is a no-op
and after a power failure the new dentries are missing.
Example scenario:
$ mkdir foo
$ sync
$rmdir foo
$ mkdir dir1
$ mkdir dir2
# A file with the same name and parent as the directory we just deleted
# and was persisted in a past transaction. So the deleted directory's
# inode is a conflicting inode of this new file's inode.
$ touch foo
$ ln foo dir2/link
# The fsync on dir2 will log the parent directory (".") because the
# conflicting inode (deleted directory) does not exists anymore, but it
# it does not log its new dentries (dir1).
$ xfs_io -c "fsync" dir2
# This fsync on the parent directory is no-op, since the previous fsync
# logged it (but without logging its new dentries).
$ xfs_io -c "fsync" .
<power failure>
# After log replay dir1 is missing.
Fix this by ensuring we log new dir dentries whenever we log the parent
directory of a no longer existing conflicting inode.
A test case for fstests will follow soon. |
| In the Linux kernel, the following vulnerability has been resolved:
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) |
