| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| In the Linux kernel, the following vulnerability has been resolved:
usb: xhci: Fix memory leak in xhci_disable_slot()
xhci_alloc_command() allocates a command structure and, when the
second argument is true, also allocates a completion structure.
Currently, the error handling path in xhci_disable_slot() only frees
the command structure using kfree(), causing the completion structure
to leak.
Use xhci_free_command() instead of kfree(). xhci_free_command() correctly
frees both the command structure and the associated completion structure.
Since the command structure is allocated with zero-initialization,
command->in_ctx is NULL and will not be erroneously freed by
xhci_free_command().
This bug was found using an experimental static analysis tool we are
developing. The tool is based on the LLVM framework and is specifically
designed to detect memory management issues. It is currently under
active development and not yet publicly available, but we plan to
open-source it after our research is published.
The bug was originally detected on v6.13-rc1 using our static analysis
tool, and we have verified that the issue persists in the latest mainline
kernel.
We performed build testing on x86_64 with allyesconfig using GCC=11.4.0.
Since triggering these error paths in xhci_disable_slot() requires specific
hardware conditions or abnormal state, we were unable to construct a test
case to reliably trigger these specific error paths at runtime. |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_tables: Fix for duplicate device in netdev hooks
When handling NETDEV_REGISTER notification, duplicate device
registration must be avoided since the device may have been added by
nft_netdev_hook_alloc() already when creating the hook. |
| In the Linux kernel, the following vulnerability has been resolved:
mctp: route: hold key->lock in mctp_flow_prepare_output()
mctp_flow_prepare_output() checks key->dev and may call
mctp_dev_set_key(), but it does not hold key->lock while doing so.
mctp_dev_set_key() and mctp_dev_release_key() are annotated with
__must_hold(&key->lock), so key->dev access is intended to be
serialized by key->lock. The mctp_sendmsg() transmit path reaches
mctp_flow_prepare_output() via mctp_local_output() -> mctp_dst_output()
without holding key->lock, so the check-and-set sequence is racy.
Example interleaving:
CPU0 CPU1
---- ----
mctp_flow_prepare_output(key, devA)
if (!key->dev) // sees NULL
mctp_flow_prepare_output(
key, devB)
if (!key->dev) // still NULL
mctp_dev_set_key(devB, key)
mctp_dev_hold(devB)
key->dev = devB
mctp_dev_set_key(devA, key)
mctp_dev_hold(devA)
key->dev = devA // overwrites devB
Now both devA and devB references were acquired, but only the final
key->dev value is tracked for release. One reference can be lost,
causing a resource leak as mctp_dev_release_key() would only decrease
the reference on one dev.
Fix by taking key->lock around the key->dev check and
mctp_dev_set_key() call. |
| In the Linux kernel, the following vulnerability has been resolved:
rds: ib: reject FRMR registration before IB connection is established
rds_ib_get_mr() extracts the rds_ib_connection from conn->c_transport_data
and passes it to rds_ib_reg_frmr() for FRWR memory registration. On a
fresh outgoing connection, ic is allocated in rds_ib_conn_alloc() with
i_cm_id = NULL because the connection worker has not yet called
rds_ib_conn_path_connect() to create the rdma_cm_id. When sendmsg() with
RDS_CMSG_RDMA_MAP is called on such a connection, the sendmsg path parses
the control message before any connection establishment, allowing
rds_ib_post_reg_frmr() to dereference ic->i_cm_id->qp and crash the
kernel.
The existing guard in rds_ib_reg_frmr() only checks for !ic (added in
commit 9e630bcb7701), which does not catch this case since ic is allocated
early and is always non-NULL once the connection object exists.
KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017]
RIP: 0010:rds_ib_post_reg_frmr+0x50e/0x920
Call Trace:
rds_ib_post_reg_frmr (net/rds/ib_frmr.c:167)
rds_ib_map_frmr (net/rds/ib_frmr.c:252)
rds_ib_reg_frmr (net/rds/ib_frmr.c:430)
rds_ib_get_mr (net/rds/ib_rdma.c:615)
__rds_rdma_map (net/rds/rdma.c:295)
rds_cmsg_rdma_map (net/rds/rdma.c:860)
rds_sendmsg (net/rds/send.c:1363)
____sys_sendmsg
do_syscall_64
Add a check in rds_ib_get_mr() that verifies ic, i_cm_id, and qp are all
non-NULL before proceeding with FRMR registration, mirroring the guard
already present in rds_ib_post_inv(). Return -ENODEV when the connection
is not ready, which the existing error handling in rds_cmsg_send() converts
to -EAGAIN for userspace retry and triggers rds_conn_connect_if_down() to
start the connection worker. |
| NVIDIA Triton Inference Server contains a vulnerability where an attacker could cause an authentication bypass. A successful exploit of this vulnerability might lead to escalation of privileges, denial of service, or information disclosure. |
| 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:
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:
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:
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:
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:
btrfs: fix leak of kobject name for sub-group space_info
When create_space_info_sub_group() allocates elements of
space_info->sub_group[], kobject_init_and_add() is called for each
element via btrfs_sysfs_add_space_info_type(). However, when
check_removing_space_info() frees these elements, it does not call
btrfs_sysfs_remove_space_info() on them. As a result, kobject_put() is
not called and the associated kobj->name objects are leaked.
This memory leak is reproduced by running the blktests test case
zbd/009 on kernels built with CONFIG_DEBUG_KMEMLEAK. The kmemleak
feature reports the following error:
unreferenced object 0xffff888112877d40 (size 16):
comm "mount", pid 1244, jiffies 4294996972
hex dump (first 16 bytes):
64 61 74 61 2d 72 65 6c 6f 63 00 c4 c6 a7 cb 7f data-reloc......
backtrace (crc 53ffde4d):
__kmalloc_node_track_caller_noprof+0x619/0x870
kstrdup+0x42/0xc0
kobject_set_name_vargs+0x44/0x110
kobject_init_and_add+0xcf/0x150
btrfs_sysfs_add_space_info_type+0xfc/0x210 [btrfs]
create_space_info_sub_group.constprop.0+0xfb/0x1b0 [btrfs]
create_space_info+0x211/0x320 [btrfs]
btrfs_init_space_info+0x15a/0x1b0 [btrfs]
open_ctree+0x33c7/0x4a50 [btrfs]
btrfs_get_tree.cold+0x9f/0x1ee [btrfs]
vfs_get_tree+0x87/0x2f0
vfs_cmd_create+0xbd/0x280
__do_sys_fsconfig+0x3df/0x990
do_syscall_64+0x136/0x1540
entry_SYSCALL_64_after_hwframe+0x76/0x7e
To avoid the leak, call btrfs_sysfs_remove_space_info() instead of
kfree() for the elements. |
| In the Linux kernel, the following vulnerability has been resolved:
mac80211: fix crash in ieee80211_chan_bw_change for AP_VLAN stations
ieee80211_chan_bw_change() iterates all stations and accesses
link->reserved.oper via sta->sdata->link[link_id]. For stations on
AP_VLAN interfaces (e.g. 4addr WDS clients), sta->sdata points to
the VLAN sdata, whose link never participates in chanctx reservations.
This leaves link->reserved.oper zero-initialized with chan == NULL,
causing a NULL pointer dereference in __ieee80211_sta_cap_rx_bw()
when accessing chandef->chan->band during CSA.
Resolve the VLAN sdata to its parent AP sdata using get_bss_sdata()
before accessing link data.
[also change sta->sdata in ARRAY_SIZE even if it doesn't matter] |
| In the Linux kernel, the following vulnerability has been resolved:
bnxt_en: fix OOB access in DBG_BUF_PRODUCER async event handler
The ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER handler in
bnxt_async_event_process() uses a firmware-supplied 'type' field
directly as an index into bp->bs_trace[] without bounds validation.
The 'type' field is a 16-bit value extracted from DMA-mapped completion
ring memory that the NIC writes directly to host RAM. A malicious or
compromised NIC can supply any value from 0 to 65535, causing an
out-of-bounds access into kernel heap memory.
The bnxt_bs_trace_check_wrap() call then dereferences bs_trace->magic_byte
and writes to bs_trace->last_offset and bs_trace->wrapped, leading to
kernel memory corruption or a crash.
Fix by adding a bounds check and defining BNXT_TRACE_MAX as
DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ERR_QPC_TRACE + 1 to cover all currently
defined firmware trace types (0x0 through 0xc). |
| In the Linux kernel, the following vulnerability has been resolved:
mm/huge_memory: fix use of NULL folio in move_pages_huge_pmd()
move_pages_huge_pmd() handles UFFDIO_MOVE for both normal THPs and huge
zero pages. For the huge zero page path, src_folio is explicitly set to
NULL, and is used as a sentinel to skip folio operations like lock and
rmap.
In the huge zero page branch, src_folio is NULL, so folio_mk_pmd(NULL,
pgprot) passes NULL through folio_pfn() and page_to_pfn(). With
SPARSEMEM_VMEMMAP this silently produces a bogus PFN, installing a PMD
pointing to non-existent physical memory. On other memory models it is a
NULL dereference.
Use page_folio(src_page) to obtain the valid huge zero folio from the
page, which was obtained from pmd_page() and remains valid throughout.
After commit d82d09e48219 ("mm/huge_memory: mark PMD mappings of the huge
zero folio special"), moved huge zero PMDs must remain special so
vm_normal_page_pmd() continues to treat them as special mappings.
move_pages_huge_pmd() currently reconstructs the destination PMD in the
huge zero page branch, which drops PMD state such as pmd_special() on
architectures with CONFIG_ARCH_HAS_PTE_SPECIAL. As a result,
vm_normal_page_pmd() can treat the moved huge zero PMD as a normal page
and corrupt its refcount.
Instead of reconstructing the PMD from the folio, derive the destination
entry from src_pmdval after pmdp_huge_clear_flush(), then handle the PMD
metadata the same way move_huge_pmd() does for moved entries by marking it
soft-dirty and clearing uffd-wp. |
