| 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:
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:
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: 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) |
| 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. |
| In the Linux kernel, the following vulnerability has been resolved:
mm/rmap: fix incorrect pte restoration for lazyfree folios
We batch unmap anonymous lazyfree folios by folio_unmap_pte_batch. If the
batch has a mix of writable and non-writable bits, we may end up setting
the entire batch writable. Fix this by respecting writable bit during
batching.
Although on a successful unmap of a lazyfree folio, the soft-dirty bit is
lost, preserve it on pte restoration by respecting the bit during
batching, to make the fix consistent w.r.t both writable bit and
soft-dirty bit.
I was able to write the below reproducer and crash the kernel.
Explanation of reproducer (set 64K mTHP to always):
Fault in a 64K large folio. Split the VMA at mid-point with
MADV_DONTFORK. fork() - parent points to the folio with 8 writable ptes
and 8 non-writable ptes. Merge the VMAs with MADV_DOFORK so that
folio_unmap_pte_batch() can determine all the 16 ptes as a batch. Do
MADV_FREE on the range to mark the folio as lazyfree. Write to the memory
to dirty the pte, eventually rmap will dirty the folio. Then trigger
reclaim, we will hit the pte restoration path, and the kernel will crash
with the trace given below.
The BUG happens at:
BUG_ON(atomic_inc_return(&ptc->anon_map_count) > 1 && rw);
The code path is asking for anonymous page to be mapped writable into the
pagetable. The BUG_ON() firing implies that such a writable page has been
mapped into the pagetables of more than one process, which breaks
anonymous memory/CoW semantics.
[ 21.134473] kernel BUG at mm/page_table_check.c:118!
[ 21.134497] Internal error: Oops - BUG: 00000000f2000800 [#1] SMP
[ 21.135917] Modules linked in:
[ 21.136085] CPU: 1 UID: 0 PID: 1735 Comm: dup-lazyfree Not tainted 7.0.0-rc1-00116-g018018a17770 #1028 PREEMPT
[ 21.136858] Hardware name: linux,dummy-virt (DT)
[ 21.137019] pstate: 21400005 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
[ 21.137308] pc : page_table_check_set+0x28c/0x2a8
[ 21.137607] lr : page_table_check_set+0x134/0x2a8
[ 21.137885] sp : ffff80008a3b3340
[ 21.138124] x29: ffff80008a3b3340 x28: fffffdffc3d14400 x27: ffffd1a55e03d000
[ 21.138623] x26: 0040000000000040 x25: ffffd1a55f7dd000 x24: 0000000000000001
[ 21.139045] x23: 0000000000000001 x22: 0000000000000001 x21: ffffd1a55f217f30
[ 21.139629] x20: 0000000000134521 x19: 0000000000134519 x18: 005c43e000040000
[ 21.140027] x17: 0001400000000000 x16: 0001700000000000 x15: 000000000000ffff
[ 21.140578] x14: 000000000000000c x13: 005c006000000000 x12: 0000000000000020
[ 21.140828] x11: 0000000000000000 x10: 005c000000000000 x9 : ffffd1a55c079ee0
[ 21.141077] x8 : 0000000000000001 x7 : 005c03e000040000 x6 : 000000004000ffff
[ 21.141490] x5 : ffff00017fffce00 x4 : 0000000000000001 x3 : 0000000000000002
[ 21.141741] x2 : 0000000000134510 x1 : 0000000000000000 x0 : ffff0000c08228c0
[ 21.141991] Call trace:
[ 21.142093] page_table_check_set+0x28c/0x2a8 (P)
[ 21.142265] __page_table_check_ptes_set+0x144/0x1e8
[ 21.142441] __set_ptes_anysz.constprop.0+0x160/0x1a8
[ 21.142766] contpte_set_ptes+0xe8/0x140
[ 21.142907] try_to_unmap_one+0x10c4/0x10d0
[ 21.143177] rmap_walk_anon+0x100/0x250
[ 21.143315] try_to_unmap+0xa0/0xc8
[ 21.143441] shrink_folio_list+0x59c/0x18a8
[ 21.143759] shrink_lruvec+0x664/0xbf0
[ 21.144043] shrink_node+0x218/0x878
[ 21.144285] __node_reclaim.constprop.0+0x98/0x338
[ 21.144763] user_proactive_reclaim+0x2a4/0x340
[ 21.145056] reclaim_store+0x3c/0x60
[ 21.145216] dev_attr_store+0x20/0x40
[ 21.145585] sysfs_kf_write+0x84/0xa8
[ 21.145835] kernfs_fop_write_iter+0x130/0x1c8
[ 21.145994] vfs_write+0x2b8/0x368
[ 21.146119] ksys_write+0x70/0x110
[ 21.146240] __arm64_sys_write+0x24/0x38
[ 21.146380] invoke_syscall+0x50/0x120
[ 21.146513] el0_svc_common.constprop.0+0x48/0xf8
[ 21.146679] do_el0_svc+0x28/0x40
[ 21.146798] el0_svc+0x34/0x110
[ 21.146926] el0t
---truncated--- |
| In the Linux kernel, the following vulnerability has been resolved:
nvdimm/bus: Fix potential use after free in asynchronous initialization
Dingisoul with KASAN reports a use after free if device_add() fails in
nd_async_device_register().
Commit b6eae0f61db2 ("libnvdimm: Hold reference on parent while
scheduling async init") correctly added a reference on the parent device
to be held until asynchronous initialization was complete. However, if
device_add() results in an allocation failure the ref count of the
device drops to 0 prior to the parent pointer being accessed. Thus
resulting in use after free.
The bug bot AI correctly identified the fix. Save a reference to the
parent pointer to be used to drop the parent reference regardless of the
outcome of device_add(). |
| In the Linux kernel, the following vulnerability has been resolved:
sunrpc: fix cache_request leak in cache_release
When a reader's file descriptor is closed while in the middle of reading
a cache_request (rp->offset != 0), cache_release() decrements the
request's readers count but never checks whether it should free the
request.
In cache_read(), when readers drops to 0 and CACHE_PENDING is clear, the
cache_request is removed from the queue and freed along with its buffer
and cache_head reference. cache_release() lacks this cleanup.
The only other path that frees requests with readers == 0 is
cache_dequeue(), but it runs only when CACHE_PENDING transitions from
set to clear. If that transition already happened while readers was
still non-zero, cache_dequeue() will have skipped the request, and no
subsequent call will clean it up.
Add the same cleanup logic from cache_read() to cache_release(): after
decrementing readers, check if it reached 0 with CACHE_PENDING clear,
and if so, dequeue and free the cache_request. |
| In the Linux kernel, the following vulnerability has been resolved:
HID: bpf: prevent buffer overflow in hid_hw_request
right now the returned value is considered to be always valid. However,
when playing with HID-BPF, the return value can be arbitrary big,
because it's the return value of dispatch_hid_bpf_raw_requests(), which
calls the struct_ops and we have no guarantees that the value makes
sense. |
