| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| In the Linux kernel, the following vulnerability has been resolved:
fbdev: udlfb: add vm_ops to dlfb_ops_mmap to prevent use-after-free
dlfb_ops_mmap() uses remap_pfn_range() to map vmalloc framebuffer pages
to userspace but sets no vm_ops on the VMA. This means the kernel cannot
track active mmaps. When dlfb_realloc_framebuffer() replaces the backing
buffer via FBIOPUT_VSCREENINFO, existing mmap PTEs are not invalidated.
On USB disconnect, dlfb_ops_destroy() calls vfree() on the old pages
while userspace PTEs still reference them, resulting in a use-after-free:
the process retains read/write access to freed kernel pages.
Add vm_operations_struct with open/close callbacks that maintain an
atomic mmap_count on struct dlfb_data. In dlfb_realloc_framebuffer(),
check mmap_count and return -EBUSY if the buffer is currently mapped,
preventing buffer replacement while userspace holds stale PTEs.
Tested with PoC using dummy_hcd + raw_gadget USB device emulation. |
| In the Linux kernel, the following vulnerability has been resolved:
firmware: stratix10-rsu: Fix NULL pointer dereference when RSU is disabled
When the Remote System Update (RSU) isn't enabled in the First Stage
Boot Loader (FSBL), the driver encounters a NULL pointer dereference when
excute svc_normal_to_secure_thread() thread, resulting in a kernel panic:
Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008
Mem abort info:
...
Data abort info:
...
[0000000000000008] user address but active_mm is swapper
Internal error: Oops: 0000000096000004 [#1] SMP
Modules linked in:
CPU: 0 UID: 0 PID: 79 Comm: svc_smc_hvc_thr Not tainted 6.19.0-rc8-yocto-standard+ #59 PREEMPT
Hardware name: SoCFPGA Stratix 10 SoCDK (DT)
pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : svc_normal_to_secure_thread+0x38c/0x990
lr : svc_normal_to_secure_thread+0x144/0x990
...
Call trace:
svc_normal_to_secure_thread+0x38c/0x990 (P)
kthread+0x150/0x210
ret_from_fork+0x10/0x20
Code: 97cfc113 f9400260 aa1403e1 f9400400 (f9400402)
---[ end trace 0000000000000000 ]---
The issue occurs because rsu_send_async_msg() fails when RSU is not enabled
in firmware, causing the channel to be freed via stratix10_svc_free_channel().
However, the probe function continues execution and registers
svc_normal_to_secure_thread(), which subsequently attempts to access the
already-freed channel, triggering the NULL pointer dereference.
Fix this by properly cleaning up the async client and returning early on
failure, preventing the thread from being used with an invalid channel. |
| In the Linux kernel, the following vulnerability has been resolved:
kthread: consolidate kthread exit paths to prevent use-after-free
Guillaume reported crashes via corrupted RCU callback function pointers
during KUnit testing. The crash was traced back to the pidfs rhashtable
conversion which replaced the 24-byte rb_node with an 8-byte rhash_head
in struct pid, shrinking it from 160 to 144 bytes.
struct kthread (without CONFIG_BLK_CGROUP) is also 144 bytes. With
CONFIG_SLAB_MERGE_DEFAULT and SLAB_HWCACHE_ALIGN both round up to
192 bytes and share the same slab cache. struct pid.rcu.func and
struct kthread.affinity_node both sit at offset 0x78.
When a kthread exits via make_task_dead() it bypasses kthread_exit() and
misses the affinity_node cleanup. free_kthread_struct() frees the memory
while the node is still linked into the global kthread_affinity_list. A
subsequent list_del() by another kthread writes through dangling list
pointers into the freed and reused memory, corrupting the pid's
rcu.func pointer.
Instead of patching free_kthread_struct() to handle the missed cleanup,
consolidate all kthread exit paths. Turn kthread_exit() into a macro
that calls do_exit() and add kthread_do_exit() which is called from
do_exit() for any task with PF_KTHREAD set. This guarantees that
kthread-specific cleanup always happens regardless of the exit path -
make_task_dead(), direct do_exit(), or kthread_exit().
Replace __to_kthread() with a new tsk_is_kthread() accessor in the
public header. Export do_exit() since module code using the
kthread_exit() macro now needs it directly. |
| In the Linux kernel, the following vulnerability has been resolved:
ASoC: qcom: qdsp6: Fix q6apm remove ordering during ADSP stop and start
During ADSP stop and start, the kernel crashes due to the order in which
ASoC components are removed.
On ADSP stop, the q6apm-audio .remove callback unloads topology and removes
PCM runtimes during ASoC teardown. This deletes the RTDs that contain the
q6apm DAI components before their removal pass runs, leaving those
components still linked to the card and causing crashes on the next rebind.
Fix this by ensuring that all dependent (child) components are removed
first, and the q6apm component is removed last.
[ 48.105720] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000d0
[ 48.114763] Mem abort info:
[ 48.117650] ESR = 0x0000000096000004
[ 48.121526] EC = 0x25: DABT (current EL), IL = 32 bits
[ 48.127010] SET = 0, FnV = 0
[ 48.130172] EA = 0, S1PTW = 0
[ 48.133415] FSC = 0x04: level 0 translation fault
[ 48.138446] Data abort info:
[ 48.141422] ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
[ 48.147079] CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[ 48.152354] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[ 48.157859] user pgtable: 4k pages, 48-bit VAs, pgdp=00000001173cf000
[ 48.164517] [00000000000000d0] pgd=0000000000000000, p4d=0000000000000000
[ 48.171530] Internal error: Oops: 0000000096000004 [#1] SMP
[ 48.177348] Modules linked in: q6prm_clocks q6apm_lpass_dais q6apm_dai snd_q6dsp_common q6prm snd_q6apm 8021q garp mrp stp llc snd_soc_hdmi_codec apr pdr_interface phy_qcom_edp fastrpc qcom_pd_mapper rpmsg_ctrl qrtr_smd rpmsg_char qcom_pdr_msg qcom_iris v4l2_mem2mem videobuf2_dma_contig ath11k_pci msm ubwc_config at24 ath11k videobuf2_memops mac80211 ocmem videobuf2_v4l2 libarc4 drm_gpuvm mhi qrtr videodev drm_exec snd_soc_sc8280xp gpu_sched videobuf2_common nvmem_qcom_spmi_sdam snd_soc_qcom_sdw drm_dp_aux_bus qcom_q6v5_pas qcom_spmi_temp_alarm snd_soc_qcom_common rtc_pm8xxx qcom_pon drm_display_helper cec qcom_pil_info qcom_stats soundwire_bus drm_client_lib mc dispcc0_sa8775p videocc_sa8775p qcom_q6v5 camcc_sa8775p snd_soc_dmic phy_qcom_sgmii_eth snd_soc_max98357a i2c_qcom_geni snd_soc_core dwmac_qcom_ethqos llcc_qcom icc_bwmon qcom_sysmon snd_compress qcom_refgen_regulator coresight_stm stmmac_platform snd_pcm_dmaengine qcom_common coresight_tmc stmmac coresight_replicator qcom_glink_smem coresight_cti stm_core
[ 48.177444] coresight_funnel snd_pcm ufs_qcom phy_qcom_qmp_usb gpi phy_qcom_snps_femto_v2 coresight phy_qcom_qmp_ufs qcom_wdt gpucc_sa8775p pcs_xpcs mdt_loader qcom_ice icc_osm_l3 qmi_helpers snd_timer snd soundcore display_connector qcom_rng nvmem_reboot_mode drm_kms_helper phy_qcom_qmp_pcie sha256 cfg80211 rfkill socinfo fuse drm backlight ipv6
[ 48.301059] CPU: 2 UID: 0 PID: 293 Comm: kworker/u32:2 Not tainted 6.19.0-rc6-dirty #10 PREEMPT
[ 48.310081] Hardware name: Qualcomm Technologies, Inc. Lemans EVK (DT)
[ 48.316782] Workqueue: pdr_notifier_wq pdr_notifier_work [pdr_interface]
[ 48.323672] pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[ 48.330825] pc : mutex_lock+0xc/0x54
[ 48.334514] lr : soc_dapm_shutdown_dapm+0x44/0x174 [snd_soc_core]
[ 48.340794] sp : ffff800084ddb7b0
[ 48.344207] x29: ffff800084ddb7b0 x28: ffff00009cd9cf30 x27: ffff00009cd9cc00
[ 48.351544] x26: ffff000099610190 x25: ffffa31d2f19c810 x24: ffffa31d2f185098
[ 48.358869] x23: ffff800084ddb7f8 x22: 0000000000000000 x21: 00000000000000d0
[ 48.366198] x20: ffff00009ba6c338 x19: ffff00009ba6c338 x18: 00000000ffffffff
[ 48.373528] x17: 000000040044ffff x16: ffffa31d4ae6dca8 x15: 072007740775076f
[ 48.380853] x14: 0765076d07690774 x13: 00313a323a656369 x12: 767265733a637673
[ 48.388182] x11: 00000000000003f9 x10: ffffa31d4c7dea98 x9 : 0000000000000001
[ 48.395519] x8 : ffff00009a2aadc0 x7 : 0000000000000003 x6 : 0000000000000000
[ 48.402854] x5 : 0000000000000
---truncated--- |
| In the Linux kernel, the following vulnerability has been resolved:
ALSA: pcm: fix use-after-free on linked stream runtime in snd_pcm_drain()
In the drain loop, the local variable 'runtime' is reassigned to a
linked stream's runtime (runtime = s->runtime at line 2157). After
releasing the stream lock at line 2169, the code accesses
runtime->no_period_wakeup, runtime->rate, and runtime->buffer_size
(lines 2170-2178) — all referencing the linked stream's runtime without
any lock or refcount protecting its lifetime.
A concurrent close() on the linked stream's fd triggers
snd_pcm_release_substream() → snd_pcm_drop() → pcm_release_private()
→ snd_pcm_unlink() → snd_pcm_detach_substream() → kfree(runtime).
No synchronization prevents kfree(runtime) from completing while the
drain path dereferences the stale pointer.
Fix by caching the needed runtime fields (no_period_wakeup, rate,
buffer_size) into local variables while still holding the stream lock,
and using the cached values after the lock is released. |
| In the Linux kernel, the following vulnerability has been resolved:
net/mana: Null service_wq on setup error to prevent double destroy
In mana_gd_setup() error path, set gc->service_wq to NULL after
destroy_workqueue() to match the cleanup in mana_gd_cleanup().
This prevents a use-after-free if the workqueue pointer is checked
after a failed setup. |
| Use after free in Extensions in Google Chrome on Mac prior to 148.0.7778.168 allowed an attacker who convinced a user to install a malicious extension to execute arbitrary code via a crafted Chrome Extension. (Chromium security severity: Medium) |
| In the Linux kernel, the following vulnerability has been resolved:
iavf: fix PTP use-after-free during reset
Commit 7c01dbfc8a1c5f ("iavf: periodically cache PHC time") introduced a
worker to cache PHC time, but failed to stop it during reset or disable.
This creates a race condition where `iavf_reset_task()` or
`iavf_disable_vf()` free adapter resources (AQ) while the worker is still
running. If the worker triggers `iavf_queue_ptp_cmd()` during teardown, it
accesses freed memory/locks, leading to a crash.
Fix this by calling `iavf_ptp_release()` before tearing down the adapter.
This ensures `ptp_clock_unregister()` synchronously cancels the worker and
cleans up the chardev before the backing resources are destroyed. |
| In the Linux kernel, the following vulnerability has been resolved:
scsi: mpi3mr: Add NULL checks when resetting request and reply queues
The driver encountered a crash during resource cleanup when the reply and
request queues were NULL due to freed memory. This issue occurred when the
creation of reply or request queues failed, and the driver freed the memory
first, but attempted to mem set the content of the freed memory, leading to
a system crash.
Add NULL pointer checks for reply and request queues before accessing the
reply/request memory during cleanup |
| 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:
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 ] |
| 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. |
| 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:
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. |
| A flaw was found in the X.Org X server. This use-after-free vulnerability occurs in the XSYNC fence triggering logic, specifically within the miSyncTriggerFence() function. An attacker with access to the X11 server can exploit this without user interaction, leading to a server crash and potentially enabling memory corruption. This could result in a denial of service or further compromise of the system. |
