| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| 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:
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:
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(). |
| 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:
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. |
| In the Linux kernel, the following vulnerability has been resolved:
clk: mediatek: fix of_iomap memory leak
Smatch reports:
drivers/clk/mediatek/clk-mtk.c:583 mtk_clk_simple_probe() warn:
'base' from of_iomap() not released on lines: 496.
This problem was also found in linux-next. In mtk_clk_simple_probe(),
base is not released when handling errors
if clk_data is not existed, which may cause a leak.
So free_base should be added here to release base. |
| In the Linux kernel, the following vulnerability has been resolved:
blk-cgroup: Reinit blkg_iostat_set after clearing in blkcg_reset_stats()
When blkg_alloc() is called to allocate a blkcg_gq structure
with the associated blkg_iostat_set's, there are 2 fields within
blkg_iostat_set that requires proper initialization - blkg & sync.
The former field was introduced by commit 3b8cc6298724 ("blk-cgroup:
Optimize blkcg_rstat_flush()") while the later one was introduced by
commit f73316482977 ("blk-cgroup: reimplement basic IO stats using
cgroup rstat").
Unfortunately those fields in the blkg_iostat_set's are not properly
re-initialized when they are cleared in v1's blkcg_reset_stats(). This
can lead to a kernel panic due to NULL pointer access of the blkg
pointer. The missing initialization of sync is less problematic and
can be a problem in a debug kernel due to missing lockdep initialization.
Fix these problems by re-initializing them after memory clearing. |
| In the Linux kernel, the following vulnerability has been resolved:
scsi: ufs: core: Fix handling of lrbp->cmd
ufshcd_queuecommand() may be called two times in a row for a SCSI command
before it is completed. Hence make the following changes:
- In the functions that submit a command, do not check the old value of
lrbp->cmd nor clear lrbp->cmd in error paths.
- In ufshcd_release_scsi_cmd(), do not clear lrbp->cmd.
See also scsi_send_eh_cmnd().
This commit prevents that the following appears if a command times out:
WARNING: at drivers/ufs/core/ufshcd.c:2965 ufshcd_queuecommand+0x6f8/0x9a8
Call trace:
ufshcd_queuecommand+0x6f8/0x9a8
scsi_send_eh_cmnd+0x2c0/0x960
scsi_eh_test_devices+0x100/0x314
scsi_eh_ready_devs+0xd90/0x114c
scsi_error_handler+0x2b4/0xb70
kthread+0x16c/0x1e0 |
| In the Linux kernel, the following vulnerability has been resolved:
vhost-scsi: Fix handling of multiple calls to vhost_scsi_set_endpoint
If vhost_scsi_set_endpoint is called multiple times without a
vhost_scsi_clear_endpoint between them, we can hit multiple bugs
found by Haoran Zhang:
1. Use-after-free when no tpgs are found:
This fixes a use after free that occurs when vhost_scsi_set_endpoint is
called more than once and calls after the first call do not find any
tpgs to add to the vs_tpg. When vhost_scsi_set_endpoint first finds
tpgs to add to the vs_tpg array match=true, so we will do:
vhost_vq_set_backend(vq, vs_tpg);
...
kfree(vs->vs_tpg);
vs->vs_tpg = vs_tpg;
If vhost_scsi_set_endpoint is called again and no tpgs are found
match=false so we skip the vhost_vq_set_backend call leaving the
pointer to the vs_tpg we then free via:
kfree(vs->vs_tpg);
vs->vs_tpg = vs_tpg;
If a scsi request is then sent we do:
vhost_scsi_handle_vq -> vhost_scsi_get_req -> vhost_vq_get_backend
which sees the vs_tpg we just did a kfree on.
2. Tpg dir removal hang:
This patch fixes an issue where we cannot remove a LIO/target layer
tpg (and structs above it like the target) dir due to the refcount
dropping to -1.
The problem is that if vhost_scsi_set_endpoint detects a tpg is already
in the vs->vs_tpg array or if the tpg has been removed so
target_depend_item fails, the undepend goto handler will do
target_undepend_item on all tpgs in the vs_tpg array dropping their
refcount to 0. At this time vs_tpg contains both the tpgs we have added
in the current vhost_scsi_set_endpoint call as well as tpgs we added in
previous calls which are also in vs->vs_tpg.
Later, when vhost_scsi_clear_endpoint runs it will do
target_undepend_item on all the tpgs in the vs->vs_tpg which will drop
their refcount to -1. Userspace will then not be able to remove the tpg
and will hang when it tries to do rmdir on the tpg dir.
3. Tpg leak:
This fixes a bug where we can leak tpgs and cause them to be
un-removable because the target name is overwritten when
vhost_scsi_set_endpoint is called multiple times but with different
target names.
The bug occurs if a user has called VHOST_SCSI_SET_ENDPOINT and setup
a vhost-scsi device to target/tpg mapping, then calls
VHOST_SCSI_SET_ENDPOINT again with a new target name that has tpgs we
haven't seen before (target1 has tpg1 but target2 has tpg2). When this
happens we don't teardown the old target tpg mapping and just overwrite
the target name and the vs->vs_tpg array. Later when we do
vhost_scsi_clear_endpoint, we are passed in either target1 or target2's
name and we will only match that target's tpgs when we loop over the
vs->vs_tpg. We will then return from the function without doing
target_undepend_item on the tpgs.
Because of all these bugs, it looks like being able to call
vhost_scsi_set_endpoint multiple times was never supported. The major
user, QEMU, already has checks to prevent this use case. So to fix the
issues, this patch prevents vhost_scsi_set_endpoint from being called
if it's already successfully added tpgs. To add, remove or change the
tpg config or target name, you must do a vhost_scsi_clear_endpoint
first. |
| In the Linux kernel, the following vulnerability has been resolved:
ksmbd: add bounds check for create lease context
Add missing bounds check for create lease context. |
| In the Linux kernel, the following vulnerability has been resolved:
riscv: fgraph: Fix stack layout to match __arch_ftrace_regs argument of ftrace_return_to_handler
Naresh Kamboju reported a "Bad frame pointer" kernel warning while
running LTP trace ftrace_stress_test.sh in riscv. We can reproduce the
same issue with the following command:
```
$ cd /sys/kernel/debug/tracing
$ echo 'f:myprobe do_nanosleep%return args1=$retval' > dynamic_events
$ echo 1 > events/fprobes/enable
$ echo 1 > tracing_on
$ sleep 1
```
And we can get the following kernel warning:
[ 127.692888] ------------[ cut here ]------------
[ 127.693755] Bad frame pointer: expected ff2000000065be50, received ba34c141e9594000
[ 127.693755] from func do_nanosleep return to ffffffff800ccb16
[ 127.698699] WARNING: CPU: 1 PID: 129 at kernel/trace/fgraph.c:755 ftrace_return_to_handler+0x1b2/0x1be
[ 127.699894] Modules linked in:
[ 127.700908] CPU: 1 UID: 0 PID: 129 Comm: sleep Not tainted 6.14.0-rc3-g0ab191c74642 #32
[ 127.701453] Hardware name: riscv-virtio,qemu (DT)
[ 127.701859] epc : ftrace_return_to_handler+0x1b2/0x1be
[ 127.702032] ra : ftrace_return_to_handler+0x1b2/0x1be
[ 127.702151] epc : ffffffff8013b5e0 ra : ffffffff8013b5e0 sp : ff2000000065bd10
[ 127.702221] gp : ffffffff819c12f8 tp : ff60000080853100 t0 : 6e00000000000000
[ 127.702284] t1 : 0000000000000020 t2 : 6e7566206d6f7266 s0 : ff2000000065bd80
[ 127.702346] s1 : ff60000081262000 a0 : 000000000000007b a1 : ffffffff81894f20
[ 127.702408] a2 : 0000000000000010 a3 : fffffffffffffffe a4 : 0000000000000000
[ 127.702470] a5 : 0000000000000000 a6 : 0000000000000008 a7 : 0000000000000038
[ 127.702530] s2 : ba34c141e9594000 s3 : 0000000000000000 s4 : ff2000000065bdd0
[ 127.702591] s5 : 00007fff8adcf400 s6 : 000055556dc1d8c0 s7 : 0000000000000068
[ 127.702651] s8 : 00007fff8adf5d10 s9 : 000000000000006d s10: 0000000000000001
[ 127.702710] s11: 00005555737377c8 t3 : ffffffff819d899e t4 : ffffffff819d899e
[ 127.702769] t5 : ffffffff819d89a0 t6 : ff2000000065bb18
[ 127.702826] status: 0000000200000120 badaddr: 0000000000000000 cause: 0000000000000003
[ 127.703292] [<ffffffff8013b5e0>] ftrace_return_to_handler+0x1b2/0x1be
[ 127.703760] [<ffffffff80017bce>] return_to_handler+0x16/0x26
[ 127.704009] [<ffffffff80017bb8>] return_to_handler+0x0/0x26
[ 127.704057] [<ffffffff800d3352>] common_nsleep+0x42/0x54
[ 127.704117] [<ffffffff800d44a2>] __riscv_sys_clock_nanosleep+0xba/0x10a
[ 127.704176] [<ffffffff80901c56>] do_trap_ecall_u+0x188/0x218
[ 127.704295] [<ffffffff8090cc3e>] handle_exception+0x14a/0x156
[ 127.705436] ---[ end trace 0000000000000000 ]---
The reason is that the stack layout for constructing argument for the
ftrace_return_to_handler in the return_to_handler does not match the
__arch_ftrace_regs structure of riscv, leading to unexpected results. |
| In the Linux kernel, the following vulnerability has been resolved:
wifi: ath11k: fix RCU stall while reaping monitor destination ring
While processing the monitor destination ring, MSDUs are reaped from the
link descriptor based on the corresponding buf_id.
However, sometimes the driver cannot obtain a valid buffer corresponding
to the buf_id received from the hardware. This causes an infinite loop
in the destination processing, resulting in a kernel crash.
kernel log:
ath11k_pci 0000:58:00.0: data msdu_pop: invalid buf_id 309
ath11k_pci 0000:58:00.0: data dp_rx_monitor_link_desc_return failed
ath11k_pci 0000:58:00.0: data msdu_pop: invalid buf_id 309
ath11k_pci 0000:58:00.0: data dp_rx_monitor_link_desc_return failed
Fix this by skipping the problematic buf_id and reaping the next entry,
replacing the break with the next MSDU processing.
Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30
Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1 |
