Filtered by vendor Linux
Subscribe
Total
18838 CVE
| CVE | Vendors | Products | Updated | CVSS v2 | CVSS v3 |
|---|---|---|---|---|---|
| CVE-2026-31410 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: ksmbd: use volume UUID in FS_OBJECT_ID_INFORMATION Use sb->s_uuid for a proper volume identifier as the primary choice. For filesystems that do not provide a UUID, fall back to stfs.f_fsid obtained from vfs_statfs(). | |||||
| CVE-2026-23474 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: mtd: Avoid boot crash in RedBoot partition table parser Given CONFIG_FORTIFY_SOURCE=y and a recent compiler, commit 439a1bcac648 ("fortify: Use __builtin_dynamic_object_size() when available") produces the warning below and an oops. Searching for RedBoot partition table in 50000000.flash at offset 0x7e0000 ------------[ cut here ]------------ WARNING: lib/string_helpers.c:1035 at 0xc029e04c, CPU#0: swapper/0/1 memcmp: detected buffer overflow: 15 byte read of buffer size 14 Modules linked in: CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.19.0 #1 NONE As Kees said, "'names' is pointing to the final 'namelen' many bytes of the allocation ... 'namelen' could be basically any length at all. This fortify warning looks legit to me -- this code used to be reading beyond the end of the allocation." Since the size of the dynamic allocation is calculated with strlen() we can use strcmp() instead of memcmp() and remain within bounds. | |||||
| CVE-2026-31403 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.8 HIGH |
| 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. | |||||
| CVE-2026-23454 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.0 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: net: mana: fix use-after-free in mana_hwc_destroy_channel() by reordering teardown A potential race condition exists in mana_hwc_destroy_channel() where hwc->caller_ctx is freed before the HWC's Completion Queue (CQ) and Event Queue (EQ) are destroyed. This allows an in-flight CQ interrupt handler to dereference freed memory, leading to a use-after-free or NULL pointer dereference in mana_hwc_handle_resp(). mana_smc_teardown_hwc() signals the hardware to stop but does not synchronize against IRQ handlers already executing on other CPUs. The IRQ synchronization only happens in mana_hwc_destroy_cq() via mana_gd_destroy_eq() -> mana_gd_deregister_irq(). Since this runs after kfree(hwc->caller_ctx), a concurrent mana_hwc_rx_event_handler() can dereference freed caller_ctx (and rxq->msg_buf) in mana_hwc_handle_resp(). Fix this by reordering teardown to reverse-of-creation order: destroy the TX/RX work queues and CQ/EQ before freeing hwc->caller_ctx. This ensures all in-flight interrupt handlers complete before the memory they access is freed. | |||||
| CVE-2026-23458 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.8 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: fix use-after-free in ctnetlink_dump_exp_ct() ctnetlink_dump_exp_ct() stores a conntrack pointer in cb->data for the netlink dump callback ctnetlink_exp_ct_dump_table(), but drops the conntrack reference immediately after netlink_dump_start(). When the dump spans multiple rounds, the second recvmsg() triggers the dump callback which dereferences the now-freed conntrack via nfct_help(ct), leading to a use-after-free on ct->ext. The bug is that the netlink_dump_control has no .start or .done callbacks to manage the conntrack reference across dump rounds. Other dump functions in the same file (e.g. ctnetlink_get_conntrack) properly use .start/.done callbacks for this purpose. Fix this by adding .start and .done callbacks that hold and release the conntrack reference for the duration of the dump, and move the nfct_help() call after the cb->args[0] early-return check in the dump callback to avoid dereferencing ct->ext unnecessarily. BUG: KASAN: slab-use-after-free in ctnetlink_exp_ct_dump_table+0x4f/0x2e0 Read of size 8 at addr ffff88810597ebf0 by task ctnetlink_poc/133 CPU: 1 UID: 0 PID: 133 Comm: ctnetlink_poc Not tainted 7.0.0-rc2+ #3 PREEMPTLAZY Call Trace: <TASK> ctnetlink_exp_ct_dump_table+0x4f/0x2e0 netlink_dump+0x333/0x880 netlink_recvmsg+0x3e2/0x4b0 ? aa_sk_perm+0x184/0x450 sock_recvmsg+0xde/0xf0 Allocated by task 133: kmem_cache_alloc_noprof+0x134/0x440 __nf_conntrack_alloc+0xa8/0x2b0 ctnetlink_create_conntrack+0xa1/0x900 ctnetlink_new_conntrack+0x3cf/0x7d0 nfnetlink_rcv_msg+0x48e/0x510 netlink_rcv_skb+0xc9/0x1f0 nfnetlink_rcv+0xdb/0x220 netlink_unicast+0x3ec/0x590 netlink_sendmsg+0x397/0x690 __sys_sendmsg+0xf4/0x180 Freed by task 0: slab_free_after_rcu_debug+0xad/0x1e0 rcu_core+0x5c3/0x9c0 | |||||
| CVE-2026-23464 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: soc: microchip: mpfs: Fix memory leak in mpfs_sys_controller_probe() In mpfs_sys_controller_probe(), if of_get_mtd_device_by_node() fails, the function returns immediately without freeing the allocated memory for sys_controller, leading to a memory leak. Fix this by jumping to the out_free label to ensure the memory is properly freed. Also, consolidate the error handling for the mbox_request_channel() failure case to use the same label. | |||||
| CVE-2026-31404 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.8 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: NFSD: Defer sub-object cleanup in export put callbacks svc_export_put() calls path_put() and auth_domain_put() immediately when the last reference drops, before the RCU grace period. RCU readers in e_show() and c_show() access both ex_path (via seq_path/d_path) and ex_client->name (via seq_escape) without holding a reference. If cache_clean removes the entry and drops the last reference concurrently, the sub-objects are freed while still in use, producing a NULL pointer dereference in d_path. Commit 2530766492ec ("nfsd: fix UAF when access ex_uuid or ex_stats") moved kfree of ex_uuid and ex_stats into the call_rcu callback, but left path_put() and auth_domain_put() running before the grace period because both may sleep and call_rcu callbacks execute in softirq context. Replace call_rcu/kfree_rcu with queue_rcu_work(), which defers the callback until after the RCU grace period and executes it in process context where sleeping is permitted. This allows path_put() and auth_domain_put() to be moved into the deferred callback alongside the other resource releases. Apply the same fix to expkey_put(), which has the identical pattern with ek_path and ek_client. A dedicated workqueue scopes the shutdown drain to only NFSD export release work items; flushing the shared system_unbound_wq would stall on unrelated work from other subsystems. nfsd_export_shutdown() uses rcu_barrier() followed by flush_workqueue() to ensure all deferred release callbacks complete before the export caches are destroyed. Reviwed-by: Jeff Layton <jlayton@kernel.org> | |||||
| CVE-2026-31400 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: sunrpc: fix cache_request leak in cache_release When a reader's file descriptor is closed while in the middle of reading a cache_request (rp->offset != 0), cache_release() decrements the request's readers count but never checks whether it should free the request. In cache_read(), when readers drops to 0 and CACHE_PENDING is clear, the cache_request is removed from the queue and freed along with its buffer and cache_head reference. cache_release() lacks this cleanup. The only other path that frees requests with readers == 0 is cache_dequeue(), but it runs only when CACHE_PENDING transitions from set to clear. If that transition already happened while readers was still non-zero, cache_dequeue() will have skipped the request, and no subsequent call will clean it up. Add the same cleanup logic from cache_read() to cache_release(): after decrementing readers, check if it reached 0 with CACHE_PENDING clear, and if so, dequeue and free the cache_request. | |||||
| CVE-2026-31405 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 9.8 CRITICAL |
| In the Linux kernel, the following vulnerability has been resolved: media: dvb-net: fix OOB access in ULE extension header tables The ule_mandatory_ext_handlers[] and ule_optional_ext_handlers[] tables in handle_one_ule_extension() are declared with 255 elements (valid indices 0-254), but the index htype is derived from network-controlled data as (ule_sndu_type & 0x00FF), giving a range of 0-255. When htype equals 255, an out-of-bounds read occurs on the function pointer table, and the OOB value may be called as a function pointer. Add a bounds check on htype against the array size before either table is accessed. Out-of-range values now cause the SNDU to be discarded. | |||||
| CVE-2026-31391 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: crypto: atmel-sha204a - Fix OOM ->tfm_count leak If memory allocation fails, decrement ->tfm_count to avoid blocking future reads. | |||||
| CVE-2026-23468 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| 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) | |||||
| 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). | |||||