| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| In the Linux kernel, the following vulnerability has been resolved:
spi: fix statistics allocation
The controller per-cpu statistics is not allocated until after the
controller has been registered with driver core, which leaves a window
where accessing the sysfs attributes can trigger a NULL-pointer
dereference.
Fix this by moving the statistics allocation to controller allocation
while tying its lifetime to that of the controller (rather than using
implicit devres). |
| In the Linux kernel, the following vulnerability has been resolved:
drm/i915/dmc: Fix an unlikely NULL pointer deference at probe
intel_dmc_update_dc6_allowed_count() oopses when DMC hasn't been
initialized, and dmc is thus NULL.
That would be the case when the call path is
intel_power_domains_init_hw() -> {skl,bxt,icl}_display_core_init() ->
gen9_set_dc_state() -> intel_dmc_update_dc6_allowed_count(), as
intel_power_domains_init_hw() is called *before* intel_dmc_init().
However, gen9_set_dc_state() calls intel_dmc_update_dc6_allowed_count()
conditionally, depending on the current and target DC states. At probe,
the target is disabled, but if DC6 is enabled, the function is called,
and an oops follows. Apparently it's quite unlikely that DC6 is enabled
at probe, as we haven't seen this failure mode before.
It is also strange to have DC6 enabled at boot, since that would require
the DMC firmware (loaded by BIOS); the BIOS loading the DMC firmware and
the driver stopping / reprogramming the firmware is a poorly specified
sequence and as such unlikely an intentional BIOS behaviour. It's more
likely that BIOS is leaving an unintentionally enabled DC6 HW state
behind (without actually loading the required DMC firmware for this).
The tracking of the DC6 allowed counter only works if starting /
stopping the counter depends on the _SW_ DC6 state vs. the current _HW_
DC6 state (since stopping the counter requires the DC5 counter captured
when the counter was started). Thus, using the HW DC6 state is incorrect
and it also leads to the above oops. Fix both issues by using the SW DC6
state for the tracking.
This is v2 of the fix originally sent by Jani, updated based on the
first Link: discussion below.
(cherry picked from commit 2344b93af8eb5da5d496b4e0529d35f0f559eaf0) |
| 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/amdgpu: Limit BO list entry count to prevent resource exhaustion
Userspace can pass an arbitrary number of BO list entries via the
bo_number field. Although the previous multiplication overflow check
prevents out-of-bounds allocation, a large number of entries could still
cause excessive memory allocation (up to potentially gigabytes) and
unnecessarily long list processing times.
Introduce a hard limit of 128k entries per BO list, which is more than
sufficient for any realistic use case (e.g., a single list containing all
buffers in a large scene). This prevents memory exhaustion attacks and
ensures predictable performance.
Return -EINVAL if the requested entry count exceeds the limit
(cherry picked from commit 688b87d39e0aa8135105b40dc167d74b5ada5332) |
| In the Linux kernel, the following vulnerability has been resolved:
drm: Fix use-after-free on framebuffers and property blobs when calling drm_dev_unplug
When trying to do a rather aggressive test of igt's "xe_module_load
--r reload" with a full desktop environment and game running I noticed
a few OOPSes when dereferencing freed pointers, related to
framebuffers and property blobs after the compositor exits.
Solve this by guarding the freeing in drm_file with drm_dev_enter/exit,
and immediately put the references from struct drm_file objects during
drm_dev_unplug().
Related warnings for framebuffers on the subtest:
[ 739.713076] ------------[ cut here ]------------
WARN_ON(!list_empty(&dev->mode_config.fb_list))
[ 739.713079] WARNING: drivers/gpu/drm/drm_mode_config.c:584 at drm_mode_config_cleanup+0x30b/0x320 [drm], CPU#12: xe_module_load/13145
....
[ 739.713328] Call Trace:
[ 739.713330] <TASK>
[ 739.713335] ? intel_pmdemand_destroy_state+0x11/0x20 [xe]
[ 739.713574] ? intel_atomic_global_obj_cleanup+0xe4/0x1a0 [xe]
[ 739.713794] intel_display_driver_remove_noirq+0x51/0xb0 [xe]
[ 739.714041] xe_display_fini_early+0x33/0x50 [xe]
[ 739.714284] devm_action_release+0xf/0x20
[ 739.714294] devres_release_all+0xad/0xf0
[ 739.714301] device_unbind_cleanup+0x12/0xa0
[ 739.714305] device_release_driver_internal+0x1b7/0x210
[ 739.714311] device_driver_detach+0x14/0x20
[ 739.714315] unbind_store+0xa6/0xb0
[ 739.714319] drv_attr_store+0x21/0x30
[ 739.714322] sysfs_kf_write+0x48/0x60
[ 739.714328] kernfs_fop_write_iter+0x16b/0x240
[ 739.714333] vfs_write+0x266/0x520
[ 739.714341] ksys_write+0x72/0xe0
[ 739.714345] __x64_sys_write+0x19/0x20
[ 739.714347] x64_sys_call+0xa15/0xa30
[ 739.714355] do_syscall_64+0xd8/0xab0
[ 739.714361] entry_SYSCALL_64_after_hwframe+0x4b/0x53
and
[ 739.714459] ------------[ cut here ]------------
[ 739.714461] xe 0000:67:00.0: [drm] drm_WARN_ON(!list_empty(&fb->filp_head))
[ 739.714464] WARNING: drivers/gpu/drm/drm_framebuffer.c:833 at drm_framebuffer_free+0x6c/0x90 [drm], CPU#12: xe_module_load/13145
[ 739.714715] RIP: 0010:drm_framebuffer_free+0x7a/0x90 [drm]
...
[ 739.714869] Call Trace:
[ 739.714871] <TASK>
[ 739.714876] drm_mode_config_cleanup+0x26a/0x320 [drm]
[ 739.714998] ? __drm_printfn_seq_file+0x20/0x20 [drm]
[ 739.715115] ? drm_mode_config_cleanup+0x207/0x320 [drm]
[ 739.715235] intel_display_driver_remove_noirq+0x51/0xb0 [xe]
[ 739.715576] xe_display_fini_early+0x33/0x50 [xe]
[ 739.715821] devm_action_release+0xf/0x20
[ 739.715828] devres_release_all+0xad/0xf0
[ 739.715843] device_unbind_cleanup+0x12/0xa0
[ 739.715850] device_release_driver_internal+0x1b7/0x210
[ 739.715856] device_driver_detach+0x14/0x20
[ 739.715860] unbind_store+0xa6/0xb0
[ 739.715865] drv_attr_store+0x21/0x30
[ 739.715868] sysfs_kf_write+0x48/0x60
[ 739.715873] kernfs_fop_write_iter+0x16b/0x240
[ 739.715878] vfs_write+0x266/0x520
[ 739.715886] ksys_write+0x72/0xe0
[ 739.715890] __x64_sys_write+0x19/0x20
[ 739.715893] x64_sys_call+0xa15/0xa30
[ 739.715900] do_syscall_64+0xd8/0xab0
[ 739.715905] entry_SYSCALL_64_after_hwframe+0x4b/0x53
and then finally file close blows up:
[ 743.186530] Oops: general protection fault, probably for non-canonical address 0xdead000000000122: 0000 [#1] SMP
[ 743.186535] CPU: 3 UID: 1000 PID: 3453 Comm: kwin_wayland Tainted: G W 7.0.0-rc1-valkyria+ #110 PREEMPT_{RT,(lazy)}
[ 743.186537] Tainted: [W]=WARN
[ 743.186538] Hardware name: Gigabyte Technology Co., Ltd. X299 AORUS Gaming 3/X299 AORUS Gaming 3-CF, BIOS F8n 12/06/2021
[ 743.186539] RIP: 0010:drm_framebuffer_cleanup+0x55/0xc0 [drm]
[ 743.186588] Code: d8 72 73 0f b6 42 05 ff c3 39 c3 72 e8 49 8d bd 50 07 00 00 31 f6 e8 3a 80 d3 e1 49 8b 44 24 10 49 8d 7c 24 08 49 8b 54 24 08 <48> 3b 38 0f 85 95 7f 02 00 48 3b 7a 08 0f 85 8b 7f 02 00 48 89 42
[ 743.186589] RSP: 0018:ffffc900085e3cf8 EFLAGS: 00
---truncated--- |
| 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:
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. |
| 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: 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. |
| IBM Aspera Shares 1.9.9 through 1.11.0 uses weaker than expected cryptographic algorithms that could allow an attacker to decrypt highly sensitive information |
| In the Linux kernel, the following vulnerability has been resolved:
drm/xe/configfs: Free ctx_restore_mid_bb in release
ctx_restore_mid_bb memory is allocated in wa_bb_store(), but
xe_config_device_release() only frees ctx_restore_post_bb.
Free ctx_restore_mid_bb[0].cs as well to avoid leaking the allocation
when the configfs device is removed.
(cherry picked from commit a235e7d0098337c3f2d1e8f3610c719a589e115f) |
| In the Linux kernel, the following vulnerability has been resolved:
drm/logicvc: Fix device node reference leak in logicvc_drm_config_parse()
The logicvc_drm_config_parse() function calls of_get_child_by_name() to
find the "layers" node but fails to release the reference, leading to a
device node reference leak.
Fix this by using the __free(device_node) cleanup attribute to automatic
release the reference when the variable goes out of scope. |
| In the Linux kernel, the following vulnerability has been resolved:
macvlan: add forgotten nla_policy for IFLA_MACVLAN_BC_CUTOFF
The previous commit 954d1fa1ac93 ("macvlan: Add netlink attribute for
broadcast cutoff") added one additional attribute named
IFLA_MACVLAN_BC_CUTOFF to allow broadcast cutfoff.
However, it forgot to describe the nla_policy at macvlan_policy
(drivers/net/macvlan.c). Hence, this suppose NLA_S32 (4 bytes) integer
can be faked as empty (0 bytes) by a malicious user, which could leads
to OOB in heap just like CVE-2023-3773.
To fix it, this commit just completes the nla_policy description for
IFLA_MACVLAN_BC_CUTOFF. This enforces the length check and avoids the
potential OOB read. |
| In the Linux kernel, the following vulnerability has been resolved:
nbd: fix incomplete validation of ioctl arg
We tested and found an alarm caused by nbd_ioctl arg without verification.
The UBSAN warning calltrace like below:
UBSAN: Undefined behaviour in fs/buffer.c:1709:35
signed integer overflow:
-9223372036854775808 - 1 cannot be represented in type 'long long int'
CPU: 3 PID: 2523 Comm: syz-executor.0 Not tainted 4.19.90 #1
Hardware name: linux,dummy-virt (DT)
Call trace:
dump_backtrace+0x0/0x3f0 arch/arm64/kernel/time.c:78
show_stack+0x28/0x38 arch/arm64/kernel/traps.c:158
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x170/0x1dc lib/dump_stack.c:118
ubsan_epilogue+0x18/0xb4 lib/ubsan.c:161
handle_overflow+0x188/0x1dc lib/ubsan.c:192
__ubsan_handle_sub_overflow+0x34/0x44 lib/ubsan.c:206
__block_write_full_page+0x94c/0xa20 fs/buffer.c:1709
block_write_full_page+0x1f0/0x280 fs/buffer.c:2934
blkdev_writepage+0x34/0x40 fs/block_dev.c:607
__writepage+0x68/0xe8 mm/page-writeback.c:2305
write_cache_pages+0x44c/0xc70 mm/page-writeback.c:2240
generic_writepages+0xdc/0x148 mm/page-writeback.c:2329
blkdev_writepages+0x2c/0x38 fs/block_dev.c:2114
do_writepages+0xd4/0x250 mm/page-writeback.c:2344
The reason for triggering this warning is __block_write_full_page()
-> i_size_read(inode) - 1 overflow.
inode->i_size is assigned in __nbd_ioctl() -> nbd_set_size() -> bytesize.
We think it is necessary to limit the size of arg to prevent errors.
Moreover, __nbd_ioctl() -> nbd_add_socket(), arg will be cast to int.
Assuming the value of arg is 0x80000000000000001) (on a 64-bit machine),
it will become 1 after the coercion, which will return unexpected results.
Fix it by adding checks to prevent passing in too large numbers. |
| In the Linux kernel, the following vulnerability has been resolved:
io_uring: fix fget leak when fs don't support nowait buffered read
Heming reported a BUG when using io_uring doing link-cp on ocfs2. [1]
Do the following steps can reproduce this BUG:
mount -t ocfs2 /dev/vdc /mnt/ocfs2
cp testfile /mnt/ocfs2/
./link-cp /mnt/ocfs2/testfile /mnt/ocfs2/testfile.1
umount /mnt/ocfs2
Then umount will fail, and it outputs:
umount: /mnt/ocfs2: target is busy.
While tracing umount, it blames mnt_get_count() not return as expected.
Do a deep investigation for fget()/fput() on related code flow, I've
finally found that fget() leaks since ocfs2 doesn't support nowait
buffered read.
io_issue_sqe
|-io_assign_file // do fget() first
|-io_read
|-io_iter_do_read
|-ocfs2_file_read_iter // return -EOPNOTSUPP
|-kiocb_done
|-io_rw_done
|-__io_complete_rw_common // set REQ_F_REISSUE
|-io_resubmit_prep
|-io_req_prep_async // override req->file, leak happens
This was introduced by commit a196c78b5443 in v5.18. Fix it by don't
re-assign req->file if it has already been assigned.
[1] https://lore.kernel.org/ocfs2-devel/ab580a75-91c8-d68a-3455-40361be1bfa8@linux.alibaba.com/T/#t |
| In the Linux kernel, the following vulnerability has been resolved:
ext4: allow ext4_get_group_info() to fail
Previously, ext4_get_group_info() would treat an invalid group number
as BUG(), since in theory it should never happen. However, if a
malicious attaker (or fuzzer) modifies the superblock via the block
device while it is the file system is mounted, it is possible for
s_first_data_block to get set to a very large number. In that case,
when calculating the block group of some block number (such as the
starting block of a preallocation region), could result in an
underflow and very large block group number. Then the BUG_ON check in
ext4_get_group_info() would fire, resutling in a denial of service
attack that can be triggered by root or someone with write access to
the block device.
For a quality of implementation perspective, it's best that even if
the system administrator does something that they shouldn't, that it
will not trigger a BUG. So instead of BUG'ing, ext4_get_group_info()
will call ext4_error and return NULL. We also add fallback code in
all of the callers of ext4_get_group_info() that it might NULL.
Also, since ext4_get_group_info() was already borderline to be an
inline function, un-inline it. The results in a next reduction of the
compiled text size of ext4 by roughly 2k. |
| In the Linux kernel, the following vulnerability has been resolved:
net: phy: allow MDIO bus PM ops to start/stop state machine for phylink-controlled PHY
DSA has 2 kinds of drivers:
1. Those who call dsa_switch_suspend() and dsa_switch_resume() from
their device PM ops: qca8k-8xxx, bcm_sf2, microchip ksz
2. Those who don't: all others. The above methods should be optional.
For type 1, dsa_switch_suspend() calls dsa_user_suspend() -> phylink_stop(),
and dsa_switch_resume() calls dsa_user_resume() -> phylink_start().
These seem good candidates for setting mac_managed_pm = true because
that is essentially its definition [1], but that does not seem to be the
biggest problem for now, and is not what this change focuses on.
Talking strictly about the 2nd category of DSA drivers here (which
do not have MAC managed PM, meaning that for their attached PHYs,
mdio_bus_phy_suspend() and mdio_bus_phy_resume() should run in full),
I have noticed that the following warning from mdio_bus_phy_resume() is
triggered:
WARN_ON(phydev->state != PHY_HALTED && phydev->state != PHY_READY &&
phydev->state != PHY_UP);
because the PHY state machine is running.
It's running as a result of a previous dsa_user_open() -> ... ->
phylink_start() -> phy_start() having been initiated by the user.
The previous mdio_bus_phy_suspend() was supposed to have called
phy_stop_machine(), but it didn't. So this is why the PHY is in state
PHY_NOLINK by the time mdio_bus_phy_resume() runs.
mdio_bus_phy_suspend() did not call phy_stop_machine() because for
phylink, the phydev->adjust_link function pointer is NULL. This seems a
technicality introduced by commit fddd91016d16 ("phylib: fix PAL state
machine restart on resume"). That commit was written before phylink
existed, and was intended to avoid crashing with consumer drivers which
don't use the PHY state machine - phylink always does, when using a PHY.
But phylink itself has historically not been developed with
suspend/resume in mind, and apparently not tested too much in that
scenario, allowing this bug to exist unnoticed for so long. Plus, prior
to the WARN_ON(), it would have likely been invisible.
This issue is not in fact restricted to type 2 DSA drivers (according to
the above ad-hoc classification), but can be extrapolated to any MAC
driver with phylink and MDIO-bus-managed PHY PM ops. DSA is just where
the issue was reported. Assuming mac_managed_pm is set correctly, a
quick search indicates the following other drivers might be affected:
$ grep -Zlr PHYLINK_NETDEV drivers/ | xargs -0 grep -L mac_managed_pm
drivers/net/ethernet/atheros/ag71xx.c
drivers/net/ethernet/microchip/sparx5/sparx5_main.c
drivers/net/ethernet/microchip/lan966x/lan966x_main.c
drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c
drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
drivers/net/ethernet/freescale/ucc_geth.c
drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
drivers/net/ethernet/marvell/mvneta.c
drivers/net/ethernet/marvell/prestera/prestera_main.c
drivers/net/ethernet/mediatek/mtk_eth_soc.c
drivers/net/ethernet/altera/altera_tse_main.c
drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
drivers/net/ethernet/meta/fbnic/fbnic_phylink.c
drivers/net/ethernet/tehuti/tn40_phy.c
drivers/net/ethernet/mscc/ocelot_net.c
Make the existing conditions dependent on the PHY device having a
phydev->phy_link_change() implementation equal to the default
phy_link_change() provided by phylib. Otherwise, we implicitly know that
the phydev has the phylink-provided phylink_phy_change() callback, and
when phylink is used, the PHY state machine always needs to be stopped/
started on the suspend/resume path. The code is structured as such that
if phydev->phy_link_change() is absent, it is a matter of time until the
kernel will crash - no need to further complicate the test.
Thus, for the situation where the PM is not managed b
---truncated--- |
| In the Linux kernel, the following vulnerability has been resolved:
ksmbd: fix session use-after-free in multichannel connection
There is a race condition between session setup and
ksmbd_sessions_deregister. The session can be freed before the connection
is added to channel list of session.
This patch check reference count of session before freeing it. |
| In the Linux kernel, the following vulnerability has been resolved:
ksmbd: set ATTR_CTIME flags when setting mtime
David reported that the new warning from setattr_copy_mgtime is coming
like the following.
[ 113.215316] ------------[ cut here ]------------
[ 113.215974] WARNING: CPU: 1 PID: 31 at fs/attr.c:300 setattr_copy+0x1ee/0x200
[ 113.219192] CPU: 1 UID: 0 PID: 31 Comm: kworker/1:1 Not tainted 6.13.0-rc1+ #234
[ 113.220127] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-3-gd478f380-rebuilt.opensuse.org 04/01/2014
[ 113.221530] Workqueue: ksmbd-io handle_ksmbd_work [ksmbd]
[ 113.222220] RIP: 0010:setattr_copy+0x1ee/0x200
[ 113.222833] Code: 24 28 49 8b 44 24 30 48 89 53 58 89 43 6c 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc 48 89 df e8 77 d6 ff ff e9 cd fe ff ff <0f> 0b e9 be fe ff ff 66 0
[ 113.225110] RSP: 0018:ffffaf218010fb68 EFLAGS: 00010202
[ 113.225765] RAX: 0000000000000120 RBX: ffffa446815f8568 RCX: 0000000000000003
[ 113.226667] RDX: ffffaf218010fd38 RSI: ffffa446815f8568 RDI: ffffffff94eb03a0
[ 113.227531] RBP: ffffaf218010fb90 R08: 0000001a251e217d R09: 00000000675259fa
[ 113.228426] R10: 0000000002ba8a6d R11: ffffa4468196c7a8 R12: ffffaf218010fd38
[ 113.229304] R13: 0000000000000120 R14: ffffffff94eb03a0 R15: 0000000000000000
[ 113.230210] FS: 0000000000000000(0000) GS:ffffa44739d00000(0000) knlGS:0000000000000000
[ 113.231215] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 113.232055] CR2: 00007efe0053d27e CR3: 000000000331a000 CR4: 00000000000006b0
[ 113.232926] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 113.233812] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 113.234797] Call Trace:
[ 113.235116] <TASK>
[ 113.235393] ? __warn+0x73/0xd0
[ 113.235802] ? setattr_copy+0x1ee/0x200
[ 113.236299] ? report_bug+0xf3/0x1e0
[ 113.236757] ? handle_bug+0x4d/0x90
[ 113.237202] ? exc_invalid_op+0x13/0x60
[ 113.237689] ? asm_exc_invalid_op+0x16/0x20
[ 113.238185] ? setattr_copy+0x1ee/0x200
[ 113.238692] btrfs_setattr+0x80/0x820 [btrfs]
[ 113.239285] ? get_stack_info_noinstr+0x12/0xf0
[ 113.239857] ? __module_address+0x22/0xa0
[ 113.240368] ? handle_ksmbd_work+0x6e/0x460 [ksmbd]
[ 113.240993] ? __module_text_address+0x9/0x50
[ 113.241545] ? __module_address+0x22/0xa0
[ 113.242033] ? unwind_next_frame+0x10e/0x920
[ 113.242600] ? __pfx_stack_trace_consume_entry+0x10/0x10
[ 113.243268] notify_change+0x2c2/0x4e0
[ 113.243746] ? stack_depot_save_flags+0x27/0x730
[ 113.244339] ? set_file_basic_info+0x130/0x2b0 [ksmbd]
[ 113.244993] set_file_basic_info+0x130/0x2b0 [ksmbd]
[ 113.245613] ? process_scheduled_works+0xbe/0x310
[ 113.246181] ? worker_thread+0x100/0x240
[ 113.246696] ? kthread+0xc8/0x100
[ 113.247126] ? ret_from_fork+0x2b/0x40
[ 113.247606] ? ret_from_fork_asm+0x1a/0x30
[ 113.248132] smb2_set_info+0x63f/0xa70 [ksmbd]
ksmbd is trying to set the atime and mtime via notify_change without also
setting the ctime. so This patch add ATTR_CTIME flags when setting mtime
to avoid a warning. |
| In the Linux kernel, the following vulnerability has been resolved:
smb: client: Handle kstrdup failures for passwords
In smb3_reconfigure(), after duplicating ctx->password and
ctx->password2 with kstrdup(), we need to check for allocation
failures.
If ses->password allocation fails, return -ENOMEM.
If ses->password2 allocation fails, free ses->password, set it
to NULL, and return -ENOMEM. |
