| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| A use-after-return vulnerability exists in the `named` server when handling DNS queries signed with SIG(0). Using a specially-crafted DNS request, an attacker may be able to cause an ACL to improperly (mis)match an IP address. In a default-allow ACL (denying only specific IP addresses), this may lead to unauthorized access. Default-deny ACLs should fail-secure.
This issue affects BIND 9 versions 9.20.0 through 9.20.20, 9.21.0 through 9.21.19, and 9.20.9-S1 through 9.20.20-S1.
BIND 9 versions 9.18.0 through 9.18.46 and 9.18.11-S1 through 9.18.46-S1 are NOT affected. |
| A use-after-free vulnerability exists within the DNS-over-HTTPS implementation.
This issue affects BIND 9 versions 9.20.0 through 9.20.22, 9.21.0 through 9.21.21, and 9.20.9-S1 through 9.20.22-S1.
BIND 9 versions 9.18.0 through 9.18.48 and 9.18.11-S1 through 9.18.48-S1 are NOT affected. |
| In the Linux kernel, the following vulnerability has been resolved:
scsi: storvsc: Fix scheduling while atomic on PREEMPT_RT
This resolves the follow splat and lock-up when running with PREEMPT_RT
enabled on Hyper-V:
[ 415.140818] BUG: scheduling while atomic: stress-ng-iomix/1048/0x00000002
[ 415.140822] INFO: lockdep is turned off.
[ 415.140823] Modules linked in: intel_rapl_msr intel_rapl_common intel_uncore_frequency_common intel_pmc_core pmt_telemetry pmt_discovery pmt_class intel_pmc_ssram_telemetry intel_vsec ghash_clmulni_intel aesni_intel rapl binfmt_misc nls_ascii nls_cp437 vfat fat snd_pcm hyperv_drm snd_timer drm_client_lib drm_shmem_helper snd sg soundcore drm_kms_helper pcspkr hv_balloon hv_utils evdev joydev drm configfs efi_pstore nfnetlink vsock_loopback vmw_vsock_virtio_transport_common hv_sock vmw_vsock_vmci_transport vsock vmw_vmci efivarfs autofs4 ext4 crc16 mbcache jbd2 sr_mod sd_mod cdrom hv_storvsc serio_raw hid_generic scsi_transport_fc hid_hyperv scsi_mod hid hv_netvsc hyperv_keyboard scsi_common
[ 415.140846] Preemption disabled at:
[ 415.140847] [<ffffffffc0656171>] storvsc_queuecommand+0x2e1/0xbe0 [hv_storvsc]
[ 415.140854] CPU: 8 UID: 0 PID: 1048 Comm: stress-ng-iomix Not tainted 6.19.0-rc7 #30 PREEMPT_{RT,(full)}
[ 415.140856] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 09/04/2024
[ 415.140857] Call Trace:
[ 415.140861] <TASK>
[ 415.140861] ? storvsc_queuecommand+0x2e1/0xbe0 [hv_storvsc]
[ 415.140863] dump_stack_lvl+0x91/0xb0
[ 415.140870] __schedule_bug+0x9c/0xc0
[ 415.140875] __schedule+0xdf6/0x1300
[ 415.140877] ? rtlock_slowlock_locked+0x56c/0x1980
[ 415.140879] ? rcu_is_watching+0x12/0x60
[ 415.140883] schedule_rtlock+0x21/0x40
[ 415.140885] rtlock_slowlock_locked+0x502/0x1980
[ 415.140891] rt_spin_lock+0x89/0x1e0
[ 415.140893] hv_ringbuffer_write+0x87/0x2a0
[ 415.140899] vmbus_sendpacket_mpb_desc+0xb6/0xe0
[ 415.140900] ? rcu_is_watching+0x12/0x60
[ 415.140902] storvsc_queuecommand+0x669/0xbe0 [hv_storvsc]
[ 415.140904] ? HARDIRQ_verbose+0x10/0x10
[ 415.140908] ? __rq_qos_issue+0x28/0x40
[ 415.140911] scsi_queue_rq+0x760/0xd80 [scsi_mod]
[ 415.140926] __blk_mq_issue_directly+0x4a/0xc0
[ 415.140928] blk_mq_issue_direct+0x87/0x2b0
[ 415.140931] blk_mq_dispatch_queue_requests+0x120/0x440
[ 415.140933] blk_mq_flush_plug_list+0x7a/0x1a0
[ 415.140935] __blk_flush_plug+0xf4/0x150
[ 415.140940] __submit_bio+0x2b2/0x5c0
[ 415.140944] ? submit_bio_noacct_nocheck+0x272/0x360
[ 415.140946] submit_bio_noacct_nocheck+0x272/0x360
[ 415.140951] ext4_read_bh_lock+0x3e/0x60 [ext4]
[ 415.140995] ext4_block_write_begin+0x396/0x650 [ext4]
[ 415.141018] ? __pfx_ext4_da_get_block_prep+0x10/0x10 [ext4]
[ 415.141038] ext4_da_write_begin+0x1c4/0x350 [ext4]
[ 415.141060] generic_perform_write+0x14e/0x2c0
[ 415.141065] ext4_buffered_write_iter+0x6b/0x120 [ext4]
[ 415.141083] vfs_write+0x2ca/0x570
[ 415.141087] ksys_write+0x76/0xf0
[ 415.141089] do_syscall_64+0x99/0x1490
[ 415.141093] ? rcu_is_watching+0x12/0x60
[ 415.141095] ? finish_task_switch.isra.0+0xdf/0x3d0
[ 415.141097] ? rcu_is_watching+0x12/0x60
[ 415.141098] ? lock_release+0x1f0/0x2a0
[ 415.141100] ? rcu_is_watching+0x12/0x60
[ 415.141101] ? finish_task_switch.isra.0+0xe4/0x3d0
[ 415.141103] ? rcu_is_watching+0x12/0x60
[ 415.141104] ? __schedule+0xb34/0x1300
[ 415.141106] ? hrtimer_try_to_cancel+0x1d/0x170
[ 415.141109] ? do_nanosleep+0x8b/0x160
[ 415.141111] ? hrtimer_nanosleep+0x89/0x100
[ 415.141114] ? __pfx_hrtimer_wakeup+0x10/0x10
[ 415.141116] ? xfd_validate_state+0x26/0x90
[ 415.141118] ? rcu_is_watching+0x12/0x60
[ 415.141120] ? do_syscall_64+0x1e0/0x1490
[ 415.141121] ? do_syscall_64+0x1e0/0x1490
[ 415.141123] ? rcu_is_watching+0x12/0x60
[ 415.141124] ? do_syscall_64+0x1e0/0x1490
[ 415.141125] ? do_syscall_64+0x1e0/0x1490
[ 415.141127] ? irqentry_exit+0x140/0
---truncated--- |
| In the Linux kernel, the following vulnerability has been resolved:
rtmutex: Use waiter::task instead of current in remove_waiter()
remove_waiter() is used by the slowlock paths, but it is also used for
proxy-lock rollback in rt_mutex_start_proxy_lock() when invoked from
futex_requeue().
In the latter case waiter::task is not current, but remove_waiter()
operates on current for the dequeue operation. That results in several
problems:
1) the rbtree dequeue happens without waiter::task::pi_lock being held
2) the waiter task's pi_blocked_on state is not cleared, which leaves a
dangling pointer primed for UAF around.
3) rt_mutex_adjust_prio_chain() operates on the wrong top priority waiter
task
Use waiter::task instead of current in all related operations in
remove_waiter() to cure those problems.
[ tglx: Fixup rt_mutex_adjust_prio_chain(), add a comment and amend the
changelog ] |
| Untrusted pointer dereference in Windows Kernel allows an authorized attacker to elevate privileges locally. |
| Untrusted pointer dereference in Microsoft Office Word allows an unauthorized attacker to execute code locally. |
| In the Linux kernel, the following vulnerability has been resolved:
eventpoll: defer struct eventpoll free to RCU grace period
In certain situations, ep_free() in eventpoll.c will kfree the epi->ep
eventpoll struct while it still being used by another concurrent thread.
Defer the kfree() to an RCU callback to prevent UAF. |
| NLnet Labs Unbound up to and including version 1.25.0 has a denial of service vulnerability in the DNSSEC validator that can lead to a crash given malicious upstream replies. When Unbound constructs chase-reply messages for validation, the code uses the wrong counter to calculate write offsets for ADDITIONAL section rrsets. DNAME duplication could increase the ANSWER section count and authority filtering could decrease the AUTHORITY section count and create an uninitialized array slot. Combining these two, the validator later dereferences this uninitialized pointer, causing an immediate process crash. An adversary controlling a DNSSEC-signed domain can trigger this bug with a single query by configuring a DNAME chain with unsigned CNAMEs and a response containing unsigned AUTHORITY records alongside signed ADDITIONAL glue records. Unbound 1.25.1 contains a patch with a fix to use the proper counters to calculate the write offsets. |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_conntrack_sip: fix use of uninitialized rtp_addr in process_sdp
process_sdp() declares union nf_inet_addr rtp_addr on the stack and
passes it to the nf_nat_sip sdp_session hook after walking the SDP
media descriptions. However rtp_addr is only initialized inside the
media loop when a recognized media type with a non-zero port is found.
If the SDP body contains no m= lines, only inactive media sections
(m=audio 0 ...) or only unrecognized media types, rtp_addr is never
assigned. Despite that, the function still calls hooks->sdp_session()
with &rtp_addr, causing nf_nat_sdp_session() to format the stale stack
value as an IP address and rewrite the SDP session owner and connection
lines with it.
With CONFIG_INIT_STACK_ALL_ZERO (default on most distributions) this
results in the session-level o= and c= addresses being rewritten to
0.0.0.0 for inactive SDP sessions. Without stack auto-init the
rewritten address is whatever happened to be on the stack.
Fix this by pre-initializing rtp_addr from the session-level connection
address (caddr) when available, and tracking via a have_rtp_addr flag
whether any valid address was established. Skip the sdp_session hook
entirely when no valid address exists. |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: nfnetlink_log: fix uninitialized padding leak in NFULA_PAYLOAD
__build_packet_message() manually constructs the NFULA_PAYLOAD netlink
attribute using skb_put() and skb_copy_bits(), bypassing the standard
nla_reserve()/nla_put() helpers. While nla_total_size(data_len) bytes
are allocated (including NLA alignment padding), only data_len bytes
of actual packet data are copied. The trailing nla_padlen(data_len)
bytes (1-3 when data_len is not 4-byte aligned) are never initialized,
leaking stale heap contents to userspace via the NFLOG netlink socket.
Replace the manual attribute construction with nla_reserve(), which
handles the tailroom check, header setup, and padding zeroing via
__nla_reserve(). The subsequent skb_copy_bits() fills in the payload
data on top of the properly initialized attribute. |
| In the Linux kernel, the following vulnerability has been resolved:
ACPI: EC: clean up handlers on probe failure in acpi_ec_setup()
When ec_install_handlers() returns -EPROBE_DEFER on reduced-hardware
platforms, it has already started the EC and installed the address
space handler with the struct acpi_ec pointer as handler context.
However, acpi_ec_setup() propagates the error without any cleanup.
The caller acpi_ec_add() then frees the struct acpi_ec for non-boot
instances, leaving a dangling handler context in ACPICA.
Any subsequent AML evaluation that accesses an EC OpRegion field
dispatches into acpi_ec_space_handler() with the freed pointer,
causing a use-after-free:
BUG: KASAN: slab-use-after-free in mutex_lock (kernel/locking/mutex.c:289)
Write of size 8 at addr ffff88800721de38 by task init/1
Call Trace:
<TASK>
mutex_lock (kernel/locking/mutex.c:289)
acpi_ec_space_handler (drivers/acpi/ec.c:1362)
acpi_ev_address_space_dispatch (drivers/acpi/acpica/evregion.c:293)
acpi_ex_access_region (drivers/acpi/acpica/exfldio.c:246)
acpi_ex_field_datum_io (drivers/acpi/acpica/exfldio.c:509)
acpi_ex_extract_from_field (drivers/acpi/acpica/exfldio.c:700)
acpi_ex_read_data_from_field (drivers/acpi/acpica/exfield.c:327)
acpi_ex_resolve_node_to_value (drivers/acpi/acpica/exresolv.c:392)
</TASK>
Allocated by task 1:
acpi_ec_alloc (drivers/acpi/ec.c:1424)
acpi_ec_add (drivers/acpi/ec.c:1692)
Freed by task 1:
kfree (mm/slub.c:6876)
acpi_ec_add (drivers/acpi/ec.c:1751)
The bug triggers on reduced-hardware EC platforms (ec->gpe < 0)
when the GPIO IRQ provider defers probing. Once the stale handler
exists, any unprivileged sysfs read that causes AML to touch an
EC OpRegion (battery, thermal, backlight) exercises the dangling
pointer.
Fix this by calling ec_remove_handlers() in the error path of
acpi_ec_setup() before clearing first_ec. ec_remove_handlers()
checks each EC_FLAGS_* bit before acting, so it is safe to call
regardless of how far ec_install_handlers() progressed:
-ENODEV (handler not installed): only calls acpi_ec_stop()
-EPROBE_DEFER (handler installed): removes handler, stops EC |
| 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:
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 |
| OpenStack Ironic before 35.0.1 allows ipmitool execution in a non-default configuration that has a console interface. |
| 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:
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:
spi: fix use-after-free on controller registration failure
Make sure to deregister from driver core also in the unlikely event that
per-cpu statistics allocation fails during controller registration to
avoid use-after-free (of driver resources) and unclocked register
accesses. |
| In the Linux kernel, the following vulnerability has been resolved:
net: macb: fix use-after-free access to PTP clock
PTP clock is registered on every opening of the interface and destroyed on
every closing. However it may be accessed via get_ts_info ethtool call
which is possible while the interface is just present in the kernel.
BUG: KASAN: use-after-free in ptp_clock_index+0x47/0x50 drivers/ptp/ptp_clock.c:426
Read of size 4 at addr ffff8880194345cc by task syz.0.6/948
CPU: 1 PID: 948 Comm: syz.0.6 Not tainted 6.1.164+ #109
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.1-0-g3208b098f51a-prebuilt.qemu.org 04/01/2014
Call Trace:
<TASK>
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0x8d/0xba lib/dump_stack.c:106
print_address_description mm/kasan/report.c:316 [inline]
print_report+0x17f/0x496 mm/kasan/report.c:420
kasan_report+0xd9/0x180 mm/kasan/report.c:524
ptp_clock_index+0x47/0x50 drivers/ptp/ptp_clock.c:426
gem_get_ts_info+0x138/0x1e0 drivers/net/ethernet/cadence/macb_main.c:3349
macb_get_ts_info+0x68/0xb0 drivers/net/ethernet/cadence/macb_main.c:3371
__ethtool_get_ts_info+0x17c/0x260 net/ethtool/common.c:558
ethtool_get_ts_info net/ethtool/ioctl.c:2367 [inline]
__dev_ethtool net/ethtool/ioctl.c:3017 [inline]
dev_ethtool+0x2b05/0x6290 net/ethtool/ioctl.c:3095
dev_ioctl+0x637/0x1070 net/core/dev_ioctl.c:510
sock_do_ioctl+0x20d/0x2c0 net/socket.c:1215
sock_ioctl+0x577/0x6d0 net/socket.c:1320
vfs_ioctl fs/ioctl.c:51 [inline]
__do_sys_ioctl fs/ioctl.c:870 [inline]
__se_sys_ioctl fs/ioctl.c:856 [inline]
__x64_sys_ioctl+0x18c/0x210 fs/ioctl.c:856
do_syscall_x64 arch/x86/entry/common.c:46 [inline]
do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76
entry_SYSCALL_64_after_hwframe+0x6e/0xd8
</TASK>
Allocated by task 457:
kmalloc include/linux/slab.h:563 [inline]
kzalloc include/linux/slab.h:699 [inline]
ptp_clock_register+0x144/0x10e0 drivers/ptp/ptp_clock.c:235
gem_ptp_init+0x46f/0x930 drivers/net/ethernet/cadence/macb_ptp.c:375
macb_open+0x901/0xd10 drivers/net/ethernet/cadence/macb_main.c:2920
__dev_open+0x2ce/0x500 net/core/dev.c:1501
__dev_change_flags+0x56a/0x740 net/core/dev.c:8651
dev_change_flags+0x92/0x170 net/core/dev.c:8722
do_setlink+0xaf8/0x3a80 net/core/rtnetlink.c:2833
__rtnl_newlink+0xbf4/0x1940 net/core/rtnetlink.c:3608
rtnl_newlink+0x63/0xa0 net/core/rtnetlink.c:3655
rtnetlink_rcv_msg+0x3c6/0xed0 net/core/rtnetlink.c:6150
netlink_rcv_skb+0x15d/0x430 net/netlink/af_netlink.c:2511
netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline]
netlink_unicast+0x6d7/0xa30 net/netlink/af_netlink.c:1344
netlink_sendmsg+0x97e/0xeb0 net/netlink/af_netlink.c:1872
sock_sendmsg_nosec net/socket.c:718 [inline]
__sock_sendmsg+0x14b/0x180 net/socket.c:730
__sys_sendto+0x320/0x3b0 net/socket.c:2152
__do_sys_sendto net/socket.c:2164 [inline]
__se_sys_sendto net/socket.c:2160 [inline]
__x64_sys_sendto+0xdc/0x1b0 net/socket.c:2160
do_syscall_x64 arch/x86/entry/common.c:46 [inline]
do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76
entry_SYSCALL_64_after_hwframe+0x6e/0xd8
Freed by task 938:
kasan_slab_free include/linux/kasan.h:177 [inline]
slab_free_hook mm/slub.c:1729 [inline]
slab_free_freelist_hook mm/slub.c:1755 [inline]
slab_free mm/slub.c:3687 [inline]
__kmem_cache_free+0xbc/0x320 mm/slub.c:3700
device_release+0xa0/0x240 drivers/base/core.c:2507
kobject_cleanup lib/kobject.c:681 [inline]
kobject_release lib/kobject.c:712 [inline]
kref_put include/linux/kref.h:65 [inline]
kobject_put+0x1cd/0x350 lib/kobject.c:729
put_device+0x1b/0x30 drivers/base/core.c:3805
ptp_clock_unregister+0x171/0x270 drivers/ptp/ptp_clock.c:391
gem_ptp_remove+0x4e/0x1f0 drivers/net/ethernet/cadence/macb_ptp.c:404
macb_close+0x1c8/0x270 drivers/net/ethernet/cadence/macb_main.c:2966
__dev_close_many+0x1b9/0x310 net/core/dev.c:1585
__dev_close net/core/dev.c:1597 [inline]
__dev_change_flags+0x2bb/0x740 net/core/dev.c:8649
dev_change_fl
---truncated--- |
| In the Linux kernel, the following vulnerability has been resolved:
NFSD: Hold net reference for the lifetime of /proc/fs/nfs/exports fd
The /proc/fs/nfs/exports proc entry is created at module init
and persists for the module's lifetime. exports_proc_open()
captures the caller's current network namespace and stores
its svc_export_cache in seq->private, but takes no reference
on the namespace. If the namespace is subsequently torn down
(e.g. container destruction after the opener does setns() to a
different namespace), nfsd_net_exit() calls nfsd_export_shutdown()
which frees the cache. Subsequent reads on the still-open fd
dereference the freed cache_detail, walking a freed hash table.
Hold a reference on the struct net for the lifetime of the open
file descriptor. This prevents nfsd_net_exit() from running --
and thus prevents nfsd_export_shutdown() from freeing the cache
-- while any exports fd is open. cache_detail already stores
its net pointer (cd->net, set by cache_create_net()), so
exports_release() can retrieve it without additional per-file
storage. |
