Total
18785 CVE
| CVE | Vendors | Products | Updated | CVSS v2 | CVSS v3 |
|---|---|---|---|---|---|
| CVE-2026-23466 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.8 HIGH |
| 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) | |||||
| CVE-2026-23465 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| 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. | |||||
| CVE-2026-31406 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.8 HIGH |
| 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(). | |||||
| CVE-2026-31409 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 8.8 HIGH |
| 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. | |||||
| CVE-2026-23461 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 8.8 HIGH |
| 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. | |||||
| CVE-2026-31401 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.8 HIGH |
| 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. | |||||
| CVE-2026-23462 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 8.8 HIGH |
| 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--- | |||||
| CVE-2026-23460 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: net/rose: fix NULL pointer dereference in rose_transmit_link on reconnect syzkaller reported a bug [1], and the reproducer is available at [2]. ROSE sockets use four sk->sk_state values: TCP_CLOSE, TCP_LISTEN, TCP_SYN_SENT, and TCP_ESTABLISHED. rose_connect() already rejects calls for TCP_ESTABLISHED (-EISCONN) and TCP_CLOSE with SS_CONNECTING (-ECONNREFUSED), but lacks a check for TCP_SYN_SENT. When rose_connect() is called a second time while the first connection attempt is still in progress (TCP_SYN_SENT), it overwrites rose->neighbour via rose_get_neigh(). If that returns NULL, the socket is left with rose->state == ROSE_STATE_1 but rose->neighbour == NULL. When the socket is subsequently closed, rose_release() sees ROSE_STATE_1 and calls rose_write_internal() -> rose_transmit_link(skb, NULL), causing a NULL pointer dereference. Per connect(2), a second connect() while a connection is already in progress should return -EALREADY. Add this missing check for TCP_SYN_SENT to complete the state validation in rose_connect(). [1] https://syzkaller.appspot.com/bug?extid=d00f90e0af54102fb271 [2] https://gist.github.com/mrpre/9e6779e0d13e2c66779b1653fef80516 | |||||
| CVE-2026-23475 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| 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). | |||||
| CVE-2026-31394 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| 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] | |||||
| CVE-2026-31393 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 8.1 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Validate L2CAP_INFO_RSP payload length before access l2cap_information_rsp() checks that cmd_len covers the fixed l2cap_info_rsp header (type + result, 4 bytes) but then reads rsp->data without verifying that the payload is present: - L2CAP_IT_FEAT_MASK calls get_unaligned_le32(rsp->data), which reads 4 bytes past the header (needs cmd_len >= 8). - L2CAP_IT_FIXED_CHAN reads rsp->data[0], 1 byte past the header (needs cmd_len >= 5). A truncated L2CAP_INFO_RSP with result == L2CAP_IR_SUCCESS triggers an out-of-bounds read of adjacent skb data. Guard each data access with the required payload length check. If the payload is too short, skip the read and let the state machine complete with safe defaults (feat_mask and remote_fixed_chan remain zero from kzalloc), so the info timer cleanup and l2cap_conn_start() still run and the connection is not stalled. | |||||
| CVE-2026-23463 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 4.7 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: soc: fsl: qbman: fix race condition in qman_destroy_fq When QMAN_FQ_FLAG_DYNAMIC_FQID is set, there's a race condition between fq_table[fq->idx] state and freeing/allocating from the pool and WARN_ON(fq_table[fq->idx]) in qman_create_fq() gets triggered. Indeed, we can have: Thread A Thread B qman_destroy_fq() qman_create_fq() qman_release_fqid() qman_shutdown_fq() gen_pool_free() -- At this point, the fqid is available again -- qman_alloc_fqid() -- so, we can get the just-freed fqid in thread B -- fq->fqid = fqid; fq->idx = fqid * 2; WARN_ON(fq_table[fq->idx]); fq_table[fq->idx] = fq; fq_table[fq->idx] = NULL; And adding some logs between qman_release_fqid() and fq_table[fq->idx] = NULL makes the WARN_ON() trigger a lot more. To prevent that, ensure that fq_table[fq->idx] is set to NULL before gen_pool_free() is called by using smp_wmb(). | |||||
| CVE-2026-23467 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| 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) | |||||
| CVE-2026-31397 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.8 HIGH |
| 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. | |||||
| CVE-2026-31407 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.1 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: conntrack: add missing netlink policy validations Hyunwoo Kim reports out-of-bounds access in sctp and ctnetlink. These attributes are used by the kernel without any validation. Extend the netlink policies accordingly. Quoting the reporter: nlattr_to_sctp() assigns the user-supplied CTA_PROTOINFO_SCTP_STATE value directly to ct->proto.sctp.state without checking that it is within the valid range. [..] and: ... with exp->dir = 100, the access at ct->master->tuplehash[100] reads 5600 bytes past the start of a 320-byte nf_conn object, causing a slab-out-of-bounds read confirmed by UBSAN. | |||||
| CVE-2026-23459 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 8.2 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: ip_tunnel: adapt iptunnel_xmit_stats() to NETDEV_PCPU_STAT_DSTATS Blamed commits forgot that vxlan/geneve use udp_tunnel[6]_xmit_skb() which call iptunnel_xmit_stats(). iptunnel_xmit_stats() was assuming tunnels were only using NETDEV_PCPU_STAT_TSTATS. @syncp offset in pcpu_sw_netstats and pcpu_dstats is different. 32bit kernels would either have corruptions or freezes if the syncp sequence was overwritten. This patch also moves pcpu_stat_type closer to dev->{t,d}stats to avoid a potential cache line miss since iptunnel_xmit_stats() needs to read it. | |||||
| CVE-2026-31390 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: drm/xe: Fix memory leak in xe_vm_madvise_ioctl When check_bo_args_are_sane() validation fails, jump to the new free_vmas cleanup label to properly free the allocated resources. This ensures proper cleanup in this error path. (cherry picked from commit 29bd06faf727a4b76663e4be0f7d770e2d2a7965) | |||||
| CVE-2026-23456 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 8.2 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_h323: fix OOB read in decode_int() CONS case In decode_int(), the CONS case calls get_bits(bs, 2) to read a length value, then calls get_uint(bs, len) without checking that len bytes remain in the buffer. The existing boundary check only validates the 2 bits for get_bits(), not the subsequent 1-4 bytes that get_uint() reads. This allows a malformed H.323/RAS packet to cause a 1-4 byte slab-out-of-bounds read. Add a boundary check for len bytes after get_bits() and before get_uint(). | |||||
| CVE-2026-23455 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 9.1 CRITICAL |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_h323: check for zero length in DecodeQ931() In DecodeQ931(), the UserUserIE code path reads a 16-bit length from the packet, then decrements it by 1 to skip the protocol discriminator byte before passing it to DecodeH323_UserInformation(). If the encoded length is 0, the decrement wraps to -1, which is then passed as a large value to the decoder, leading to an out-of-bounds read. Add a check to ensure len is positive after the decrement. | |||||
| CVE-2026-23429 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.8 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: iommu/sva: Fix crash in iommu_sva_unbind_device() domain->mm->iommu_mm can be freed by iommu_domain_free(): iommu_domain_free() mmdrop() __mmdrop() mm_pasid_drop() After iommu_domain_free() returns, accessing domain->mm->iommu_mm may dereference a freed mm structure, leading to a crash. Fix this by moving the code that accesses domain->mm->iommu_mm to before the call to iommu_domain_free(). | |||||