In the Linux kernel, the following vulnerability has been resolved: xfs: save ailp before dropping the AIL lock in push callbacks In xfs_inode_item_push() and xfs_qm_dquot_logitem_push(), the AIL lock is dropped to perform buffer IO. Once the cluster buffer no longer protects the log item from reclaim, the log item may be freed by background reclaim or the dquot shrinker. The subsequent spin_lock() call dereferences lip->li_ailp, which is a use-after-free. Fix this by saving the ailp pointer in a local variable while the AIL lock is held and the log item is guaranteed to be valid.

In the Linux kernel, the following vulnerability has been resolved: virtio_net: Fix UAF on dst_ops when IFF_XMIT_DST_RELEASE is cleared and napi_tx is false A UAF issue occurs when the virtio_net driver is configured with napi_tx=N and the device's IFF_XMIT_DST_RELEASE flag is cleared (e.g., during the configuration of tc route filter rules). When IFF_XMIT_DST_RELEASE is removed from the net_device, the network stack expects the driver to hold the reference to skb->dst until the packet is fully transmitted and freed. In virtio_net with napi_tx=N, skbs may remain in the virtio transmit ring for an extended period. If the network namespace is destroyed while these skbs are still pending, the corresponding dst_ops structure has freed. When a subsequent packet is transmitted, free_old_xmit() is triggered to clean up old skbs. It then calls dst_release() on the skb associated with the stale dst_entry. Since the dst_ops (referenced by the dst_entry) has already been freed, a UAF kernel paging request occurs. fix it by adds skb_dst_drop(skb) in start_xmit to explicitly release the dst reference before the skb is queued in virtio_net. Call Trace: Unable to handle kernel paging request at virtual address ffff80007e150000 CPU: 2 UID: 0 PID: 6236 Comm: ping Kdump: loaded Not tainted 7.0.0-rc1+ #6 PREEMPT ... percpu_counter_add_batch+0x3c/0x158 lib/percpu_counter.c:98 (P) dst_release+0xe0/0x110 net/core/dst.c:177 skb_release_head_state+0xe8/0x108 net/core/skbuff.c:1177 sk_skb_reason_drop+0x54/0x2d8 net/core/skbuff.c:1255 dev_kfree_skb_any_reason+0x64/0x78 net/core/dev.c:3469 napi_consume_skb+0x1c4/0x3a0 net/core/skbuff.c:1527 __free_old_xmit+0x164/0x230 drivers/net/virtio_net.c:611 [virtio_net] free_old_xmit drivers/net/virtio_net.c:1081 [virtio_net] start_xmit+0x7c/0x530 drivers/net/virtio_net.c:3329 [virtio_net] ... Reproduction Steps: NETDEV="enp3s0" config_qdisc_route_filter() { tc qdisc del dev $NETDEV root tc qdisc add dev $NETDEV root handle 1: prio tc filter add dev $NETDEV parent 1:0 \ protocol ip prio 100 route to 100 flowid 1:1 ip route add 192.168.1.100/32 dev $NETDEV realm 100 } test_ns() { ip netns add testns ip link set $NETDEV netns testns ip netns exec testns ifconfig $NETDEV 10.0.32.46/24 ip netns exec testns ping -c 1 10.0.32.1 ip netns del testns } config_qdisc_route_filter test_ns sleep 2 test_ns

In the Linux kernel, the following vulnerability has been resolved: net: bcmasp: fix double free of WoL irq We do not need to free wol_irq since it was instantiated with devm_request_irq(). So devres will free for us.

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix unsound scalar forking in maybe_fork_scalars() for BPF_OR maybe_fork_scalars() is called for both BPF_AND and BPF_OR when the source operand is a constant. When dst has signed range [-1, 0], it forks the verifier state: the pushed path gets dst = 0, the current path gets dst = -1. For BPF_AND this is correct: 0 & K == 0. For BPF_OR this is wrong: 0 | K == K, not 0. The pushed path therefore tracks dst as 0 when the runtime value is K, producing an exploitable verifier/runtime divergence that allows out-of-bounds map access. Fix this by passing env->insn_idx (instead of env->insn_idx + 1) to push_stack(), so the pushed path re-executes the ALU instruction with dst = 0 and naturally computes the correct result for any opcode.

In the Linux kernel, the following vulnerability has been resolved: mm/rmap: fix incorrect pte restoration for lazyfree folios We batch unmap anonymous lazyfree folios by folio_unmap_pte_batch. If the batch has a mix of writable and non-writable bits, we may end up setting the entire batch writable. Fix this by respecting writable bit during batching. Although on a successful unmap of a lazyfree folio, the soft-dirty bit is lost, preserve it on pte restoration by respecting the bit during batching, to make the fix consistent w.r.t both writable bit and soft-dirty bit. I was able to write the below reproducer and crash the kernel. Explanation of reproducer (set 64K mTHP to always): Fault in a 64K large folio. Split the VMA at mid-point with MADV_DONTFORK. fork() - parent points to the folio with 8 writable ptes and 8 non-writable ptes. Merge the VMAs with MADV_DOFORK so that folio_unmap_pte_batch() can determine all the 16 ptes as a batch. Do MADV_FREE on the range to mark the folio as lazyfree. Write to the memory to dirty the pte, eventually rmap will dirty the folio. Then trigger reclaim, we will hit the pte restoration path, and the kernel will crash with the trace given below. The BUG happens at: BUG_ON(atomic_inc_return(&ptc->anon_map_count) > 1 && rw); The code path is asking for anonymous page to be mapped writable into the pagetable. The BUG_ON() firing implies that such a writable page has been mapped into the pagetables of more than one process, which breaks anonymous memory/CoW semantics. [ 21.134473] kernel BUG at mm/page_table_check.c:118! [ 21.134497] Internal error: Oops - BUG: 00000000f2000800 [#1] SMP [ 21.135917] Modules linked in: [ 21.136085] CPU: 1 UID: 0 PID: 1735 Comm: dup-lazyfree Not tainted 7.0.0-rc1-00116-g018018a17770 #1028 PREEMPT [ 21.136858] Hardware name: linux,dummy-virt (DT) [ 21.137019] pstate: 21400005 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) [ 21.137308] pc : page_table_check_set+0x28c/0x2a8 [ 21.137607] lr : page_table_check_set+0x134/0x2a8 [ 21.137885] sp : ffff80008a3b3340 [ 21.138124] x29: ffff80008a3b3340 x28: fffffdffc3d14400 x27: ffffd1a55e03d000 [ 21.138623] x26: 0040000000000040 x25: ffffd1a55f7dd000 x24: 0000000000000001 [ 21.139045] x23: 0000000000000001 x22: 0000000000000001 x21: ffffd1a55f217f30 [ 21.139629] x20: 0000000000134521 x19: 0000000000134519 x18: 005c43e000040000 [ 21.140027] x17: 0001400000000000 x16: 0001700000000000 x15: 000000000000ffff [ 21.140578] x14: 000000000000000c x13: 005c006000000000 x12: 0000000000000020 [ 21.140828] x11: 0000000000000000 x10: 005c000000000000 x9 : ffffd1a55c079ee0 [ 21.141077] x8 : 0000000000000001 x7 : 005c03e000040000 x6 : 000000004000ffff [ 21.141490] x5 : ffff00017fffce00 x4 : 0000000000000001 x3 : 0000000000000002 [ 21.141741] x2 : 0000000000134510 x1 : 0000000000000000 x0 : ffff0000c08228c0 [ 21.141991] Call trace: [ 21.142093] page_table_check_set+0x28c/0x2a8 (P) [ 21.142265] __page_table_check_ptes_set+0x144/0x1e8 [ 21.142441] __set_ptes_anysz.constprop.0+0x160/0x1a8 [ 21.142766] contpte_set_ptes+0xe8/0x140 [ 21.142907] try_to_unmap_one+0x10c4/0x10d0 [ 21.143177] rmap_walk_anon+0x100/0x250 [ 21.143315] try_to_unmap+0xa0/0xc8 [ 21.143441] shrink_folio_list+0x59c/0x18a8 [ 21.143759] shrink_lruvec+0x664/0xbf0 [ 21.144043] shrink_node+0x218/0x878 [ 21.144285] __node_reclaim.constprop.0+0x98/0x338 [ 21.144763] user_proactive_reclaim+0x2a4/0x340 [ 21.145056] reclaim_store+0x3c/0x60 [ 21.145216] dev_attr_store+0x20/0x40 [ 21.145585] sysfs_kf_write+0x84/0xa8 [ 21.145835] kernfs_fop_write_iter+0x130/0x1c8 [ 21.145994] vfs_write+0x2b8/0x368 [ 21.146119] ksys_write+0x70/0x110 [ 21.146240] __arm64_sys_write+0x24/0x38 [ 21.146380] invoke_syscall+0x50/0x120 [ 21.146513] el0_svc_common.constprop.0+0x48/0xf8 [ 21.146679] do_el0_svc+0x28/0x40 [ 21.146798] el0_svc+0x34/0x110 [ 21.146926] el0t ---truncated---

In the Linux kernel, the following vulnerability has been resolved: drm/xe/pf: Fix use-after-free in migration restore When an error is returned from xe_sriov_pf_migration_restore_produce(), the data pointer is not set to NULL, which can trigger use-after-free in subsequent .write() calls. Set the pointer to NULL upon error to fix the problem. (cherry picked from commit 4f53d8c6d23527d734fe3531d08e15cb170a0819)

The futex_requeue function in kernel/futex.c in the Linux kernel through 3.14.5 does not ensure that calls have two different futex addresses, which allows local users to gain privileges via a crafted FUTEX_REQUEUE command that facilitates unsafe waiter modification.

In the Linux kernel, the following vulnerability has been resolved: spi: meson-spicc: Fix double-put in remove path meson_spicc_probe() registers the controller with devm_spi_register_controller(), so teardown already drops the controller reference via devm cleanup. Calling spi_controller_put() again in meson_spicc_remove() causes a double-put.

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.

In the Linux kernel, the following vulnerability has been resolved: Bluetooth: MGMT: Fix dangling pointer on mgmt_add_adv_patterns_monitor_complete This fixes the condition checking so mgmt_pending_valid is executed whenever status != -ECANCELED otherwise calling mgmt_pending_free(cmd) would kfree(cmd) without unlinking it from the list first, leaving a dangling pointer. Any subsequent list traversal (e.g., mgmt_pending_foreach during __mgmt_power_off, or another mgmt_pending_valid call) would dereference freed memory.

In the Linux kernel, the following vulnerability has been resolved: xfs: avoid dereferencing log items after push callbacks After xfsaild_push_item() calls iop_push(), the log item may have been freed if the AIL lock was dropped during the push. Background inode reclaim or the dquot shrinker can free the log item while the AIL lock is not held, and the tracepoints in the switch statement dereference the log item after iop_push() returns. Fix this by capturing the log item type, flags, and LSN before calling xfsaild_push_item(), and introducing a new xfs_ail_push_class trace event class that takes these pre-captured values and the ailp pointer instead of the log item pointer.

In the Linux kernel, the following vulnerability has been resolved: isdn: cpai: check ctr->cnr to avoid array index out of bound The cmtp_add_connection() would add a cmtp session to a controller and run a kernel thread to process cmtp. __module_get(THIS_MODULE); session->task = kthread_run(cmtp_session, session, "kcmtpd_ctr_%d", session->num); During this process, the kernel thread would call detach_capi_ctr() to detach a register controller. if the controller was not attached yet, detach_capi_ctr() would trigger an array-index-out-bounds bug. [ 46.866069][ T6479] UBSAN: array-index-out-of-bounds in drivers/isdn/capi/kcapi.c:483:21 [ 46.867196][ T6479] index -1 is out of range for type 'capi_ctr *[32]' [ 46.867982][ T6479] CPU: 1 PID: 6479 Comm: kcmtpd_ctr_0 Not tainted 5.15.0-rc2+ #8 [ 46.869002][ T6479] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 [ 46.870107][ T6479] Call Trace: [ 46.870473][ T6479] dump_stack_lvl+0x57/0x7d [ 46.870974][ T6479] ubsan_epilogue+0x5/0x40 [ 46.871458][ T6479] __ubsan_handle_out_of_bounds.cold+0x43/0x48 [ 46.872135][ T6479] detach_capi_ctr+0x64/0xc0 [ 46.872639][ T6479] cmtp_session+0x5c8/0x5d0 [ 46.873131][ T6479] ? __init_waitqueue_head+0x60/0x60 [ 46.873712][ T6479] ? cmtp_add_msgpart+0x120/0x120 [ 46.874256][ T6479] kthread+0x147/0x170 [ 46.874709][ T6479] ? set_kthread_struct+0x40/0x40 [ 46.875248][ T6479] ret_from_fork+0x1f/0x30 [ 46.875773][ T6479]

A use after free in the Linux kernel File System notify functionality was found in the way user triggers copy_info_records_to_user() call to fail in copy_event_to_user(). A local user could use this flaw to crash the system or potentially escalate their privileges on the system.

A use-after-free flaw was found in the Linux kernel’s FUSE filesystem in the way a user triggers write(). This flaw allows a local user to gain unauthorized access to data from the FUSE filesystem, resulting in privilege escalation.

A use-after-free vulnerability in the Linux kernel's netfilter: nf_tables component can be exploited to achieve local privilege escalation. The function nft_pipapo_walk did not skip inactive elements during set walk which could lead double deactivations of PIPAPO (Pile Packet Policies) elements, leading to use-after-free. We recommend upgrading past commit 317eb9685095678f2c9f5a8189de698c5354316a.

A use-after-free flaw was found in the Linux kernel’s io_uring subsystem in the way a user sets up a ring with IORING_SETUP_IOPOLL with more than one task completing submissions on this ring. This flaw allows a local user to crash or escalate their privileges on the system.

Integer Overflow or Wraparound vulnerability in io_uring of Linux Kernel allows local attacker to cause memory corruption and escalate privileges to root. This issue affects: Linux Kernel versions prior to 5.4.189; version 5.4.24 and later versions.

A use-after-free flaw was found in the Linux kernel’s pipes functionality in how a user performs manipulations with the pipe post_one_notification() after free_pipe_info() that is already called. This flaw allows a local user to crash or potentially escalate their privileges on the system.

An integer overflow flaw was found in the Linux kernel’s virtio device driver code in the way a user triggers the vhost_vdpa_config_validate function. This flaw allows a local user to crash or potentially escalate their privileges on the system.

In the Linux kernel, the following vulnerability has been resolved: binder: fix use-after-free in shinker's callback The mmap read lock is used during the shrinker's callback, which means that using alloc->vma pointer isn't safe as it can race with munmap(). As of commit dd2283f2605e ("mm: mmap: zap pages with read mmap_sem in munmap") the mmap lock is downgraded after the vma has been isolated. I was able to reproduce this issue by manually adding some delays and triggering page reclaiming through the shrinker's debug sysfs. The following KASAN report confirms the UAF: ================================================================== BUG: KASAN: slab-use-after-free in zap_page_range_single+0x470/0x4b8 Read of size 8 at addr ffff356ed50e50f0 by task bash/478 CPU: 1 PID: 478 Comm: bash Not tainted 6.6.0-rc5-00055-g1c8b86a3799f-dirty #70 Hardware name: linux,dummy-virt (DT) Call trace: zap_page_range_single+0x470/0x4b8 binder_alloc_free_page+0x608/0xadc __list_lru_walk_one+0x130/0x3b0 list_lru_walk_node+0xc4/0x22c binder_shrink_scan+0x108/0x1dc shrinker_debugfs_scan_write+0x2b4/0x500 full_proxy_write+0xd4/0x140 vfs_write+0x1ac/0x758 ksys_write+0xf0/0x1dc __arm64_sys_write+0x6c/0x9c Allocated by task 492: kmem_cache_alloc+0x130/0x368 vm_area_alloc+0x2c/0x190 mmap_region+0x258/0x18bc do_mmap+0x694/0xa60 vm_mmap_pgoff+0x170/0x29c ksys_mmap_pgoff+0x290/0x3a0 __arm64_sys_mmap+0xcc/0x144 Freed by task 491: kmem_cache_free+0x17c/0x3c8 vm_area_free_rcu_cb+0x74/0x98 rcu_core+0xa38/0x26d4 rcu_core_si+0x10/0x1c __do_softirq+0x2fc/0xd24 Last potentially related work creation: __call_rcu_common.constprop.0+0x6c/0xba0 call_rcu+0x10/0x1c vm_area_free+0x18/0x24 remove_vma+0xe4/0x118 do_vmi_align_munmap.isra.0+0x718/0xb5c do_vmi_munmap+0xdc/0x1fc __vm_munmap+0x10c/0x278 __arm64_sys_munmap+0x58/0x7c Fix this issue by performing instead a vma_lookup() which will fail to find the vma that was isolated before the mmap lock downgrade. Note that this option has better performance than upgrading to a mmap write lock which would increase contention. Plus, mmap_write_trylock() has been recently removed anyway.

In the Linux kernel, the following vulnerability has been resolved: ext4: convert inline data to extents when truncate exceeds inline size Add a check in ext4_setattr() to convert files from inline data storage to extent-based storage when truncate() grows the file size beyond the inline capacity. This prevents the filesystem from entering an inconsistent state where the inline data flag is set but the file size exceeds what can be stored inline. Without this fix, the following sequence causes a kernel BUG_ON(): 1. Mount filesystem with inode that has inline flag set and small size 2. truncate(file, 50MB) - grows size but inline flag remains set 3. sendfile() attempts to write data 4. ext4_write_inline_data() hits BUG_ON(write_size > inline_capacity) The crash occurs because ext4_write_inline_data() expects inline storage to accommodate the write, but the actual inline capacity (~60 bytes for i_block + ~96 bytes for xattrs) is far smaller than the file size and write request. The fix checks if the new size from setattr exceeds the inode's actual inline capacity (EXT4_I(inode)->i_inline_size) and converts the file to extent-based storage before proceeding with the size change. This addresses the root cause by ensuring the inline data flag and file size remain consistent during truncate operations.

The root cause of this vulnerability is that the ioctl$DRM_IOCTL_MODE_DESTROY_DUMB can decrease refcount of *drm_vgem_gem_object *(created in *vgem_gem_dumb_create*) concurrently, and *vgem_gem_dumb_create *will access the freed drm_vgem_gem_object.

A use-after-free vulnerability in the Linux kernel's netfilter: nf_tables component can be exploited to achieve local privilege escalation. The function nft_trans_gc_catchall did not remove the catchall set element from the catchall_list when the argument sync is true, making it possible to free a catchall set element many times. We recommend upgrading past commit 93995bf4af2c5a99e2a87f0cd5ce547d31eb7630.

In the Linux kernel, the following vulnerability has been resolved: media: mc, v4l2: serialize REINIT and REQBUFS with req_queue_mutex MEDIA_REQUEST_IOC_REINIT can run concurrently with VIDIOC_REQBUFS(0) queue teardown paths. This can race request object cleanup against vb2 queue cancellation and lead to use-after-free reports. We already serialize request queueing against STREAMON/OFF with req_queue_mutex. Extend that serialization to REQBUFS, and also take the same mutex in media_request_ioctl_reinit() so REINIT is in the same exclusion domain. This keeps request cleanup and queue cancellation from running in parallel for request-capable devices.

In the Linux kernel, the following vulnerability has been resolved: ASoC: sma1307: fix double free of devm_kzalloc() memory A previous change added NULL checks and cleanup for allocation failures in sma1307_setting_loaded(). However, the cleanup for mode_set entries is wrong. Those entries are allocated with devm_kzalloc(), so they are device-managed resources and must not be freed with kfree(). Manually freeing them in the error path can lead to a double free when devres later releases the same memory. Drop the manual kfree() loop and let devres handle the cleanup.

A flaw out of bounds memory write in the Linux kernel UDF file system functionality was found in the way user triggers some file operation which triggers udf_write_fi(). A local user could use this flaw to crash the system or potentially

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>

In the Linux kernel, the following vulnerability has been resolved: vfio/pci: Fix double free in dma-buf feature The error path through vfio_pci_core_feature_dma_buf() ignores its own advice to only use dma_buf_put() after dma_buf_export(), instead falling through the entire unwind chain. In the unlikely event that we encounter file descriptor exhaustion, this can result in an unbalanced refcount on the vfio device and double free of allocated objects. Avoid this by moving the "put" directly into the error path and return the errno rather than entering the unwind chain.

An out-of-bounds (OOB) memory write flaw was found in the Linux kernel’s watch_queue event notification subsystem. This flaw can overwrite parts of the kernel state, potentially allowing a local user to gain privileged access or cause a denial of service on the system.

In the Linux kernel, the following vulnerability has been resolved: crypto: algif_aead - Revert to operating out-of-place This mostly reverts commit 72548b093ee3 except for the copying of the associated data. There is no benefit in operating in-place in algif_aead since the source and destination come from different mappings. Get rid of all the complexity added for in-place operation and just copy the AD directly.

In the Linux kernel, the following vulnerability has been resolved: team: fix header_ops type confusion with non-Ethernet ports Similar to commit 950803f72547 ("bonding: fix type confusion in bond_setup_by_slave()") team has the same class of header_ops type confusion. For non-Ethernet ports, team_setup_by_port() copies port_dev->header_ops directly. When the team device later calls dev_hard_header() or dev_parse_header(), these callbacks can run with the team net_device instead of the real lower device, so netdev_priv(dev) is interpreted as the wrong private type and can crash. The syzbot report shows a crash in bond_header_create(), but the root cause is in team: the topology is gre -> bond -> team, and team calls the inherited header_ops with its own net_device instead of the lower device, so bond_header_create() receives a team device and interprets netdev_priv() as bonding private data, causing a type confusion crash. Fix this by introducing team header_ops wrappers for create/parse, selecting a team port under RCU, and calling the lower device callbacks with port->dev, so each callback always sees the correct net_device context. Also pass the selected lower device to the lower parse callback, so recursion is bounded in stacked non-Ethernet topologies and parse callbacks always run with the correct device context.

In the Linux kernel, the following vulnerability has been resolved: tracing: Fix use-after-free in print_graph_function_flags during tracer switching Kairui reported a UAF issue in print_graph_function_flags() during ftrace stress testing [1]. This issue can be reproduced if puting a 'mdelay(10)' after 'mutex_unlock(&trace_types_lock)' in s_start(), and executing the following script: $ echo function_graph > current_tracer $ cat trace > /dev/null & $ sleep 5 # Ensure the 'cat' reaches the 'mdelay(10)' point $ echo timerlat > current_tracer The root cause lies in the two calls to print_graph_function_flags within print_trace_line during each s_show(): * One through 'iter->trace->print_line()'; * Another through 'event->funcs->trace()', which is hidden in print_trace_fmt() before print_trace_line returns. Tracer switching only updates the former, while the latter continues to use the print_line function of the old tracer, which in the script above is print_graph_function_flags. Moreover, when switching from the 'function_graph' tracer to the 'timerlat' tracer, s_start only calls graph_trace_close of the 'function_graph' tracer to free 'iter->private', but does not set it to NULL. This provides an opportunity for 'event->funcs->trace()' to use an invalid 'iter->private'. To fix this issue, set 'iter->private' to NULL immediately after freeing it in graph_trace_close(), ensuring that an invalid pointer is not passed to other tracers. Additionally, clean up the unnecessary 'iter->private = NULL' during each 'cat trace' when using wakeup and irqsoff tracers. [1] https://lore.kernel.org/all/20231112150030.84609-1-ryncsn@gmail.com/

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: 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: drm/xe: always keep track of remap prev/next During 3D workload, user is reporting hitting: [ 413.361679] WARNING: drivers/gpu/drm/xe/xe_vm.c:1217 at vm_bind_ioctl_ops_unwind+0x1e2/0x2e0 [xe], CPU#7: vkd3d_queue/9925 [ 413.361944] CPU: 7 UID: 1000 PID: 9925 Comm: vkd3d_queue Kdump: loaded Not tainted 7.0.0-070000rc3-generic #202603090038 PREEMPT(lazy) [ 413.361949] RIP: 0010:vm_bind_ioctl_ops_unwind+0x1e2/0x2e0 [xe] [ 413.362074] RSP: 0018:ffffd4c25c3df930 EFLAGS: 00010282 [ 413.362077] RAX: 0000000000000000 RBX: ffff8f3ee817ed10 RCX: 0000000000000000 [ 413.362078] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 [ 413.362079] RBP: ffffd4c25c3df980 R08: 0000000000000000 R09: 0000000000000000 [ 413.362081] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8f41fbf99380 [ 413.362082] R13: ffff8f3ee817e968 R14: 00000000ffffffef R15: ffff8f43d00bd380 [ 413.362083] FS: 00000001040ff6c0(0000) GS:ffff8f4696d89000(0000) knlGS:00000000330b0000 [ 413.362085] CS: 0010 DS: 002b ES: 002b CR0: 0000000080050033 [ 413.362086] CR2: 00007ddfc4747000 CR3: 00000002e6262005 CR4: 0000000000f72ef0 [ 413.362088] PKRU: 55555554 [ 413.362089] Call Trace: [ 413.362092] <TASK> [ 413.362096] xe_vm_bind_ioctl+0xa9a/0xc60 [xe] Which seems to hint that the vma we are re-inserting for the ops unwind is either invalid or overlapping with something already inserted in the vm. It shouldn't be invalid since this is a re-insertion, so must have worked before. Leaving the likely culprit as something already placed where we want to insert the vma. Following from that, for the case where we do something like a rebind in the middle of a vma, and one or both mapped ends are already compatible, we skip doing the rebind of those vma and set next/prev to NULL. As well as then adjust the original unmap va range, to avoid unmapping the ends. However, if we trigger the unwind path, we end up with three va, with the two ends never being removed and the original va range in the middle still being the shrunken size. If this occurs, one failure mode is when another unwind op needs to interact with that range, which can happen with a vector of binds. For example, if we need to re-insert something in place of the original va. In this case the va is still the shrunken version, so when removing it and then doing a re-insert it can overlap with the ends, which were never removed, triggering a warning like above, plus leaving the vm in a bad state. With that, we need two things here: 1) Stop nuking the prev/next tracking for the skip cases. Instead relying on checking for skip prev/next, where needed. That way on the unwind path, we now correctly remove both ends. 2) Undo the unmap va shrinkage, on the unwind path. With the two ends now removed the unmap va should expand back to the original size again, before re-insertion. v2: - Update the explanation in the commit message, based on an actual IGT of triggering this issue, rather than conjecture. - Also undo the unmap shrinkage, for the skip case. With the two ends now removed, the original unmap va range should expand back to the original range. v3: - Track the old start/range separately. vma_size/start() uses the va info directly. (cherry picked from commit aec6969f75afbf4e01fd5fb5850ed3e9c27043ac)

Linux Kernel could allow a local attacker to execute arbitrary code on the system, caused by a concurrency use-after-free flaw in the bad_flp_intr function. By executing a specially-crafted program, an attacker could exploit this vulnerability to execute arbitrary code or cause a denial of service condition on the system.

A flaw was found in the Linux kernel’s implementation of IO-URING. This flaw allows an attacker with local executable permission to create a string of requests that can cause a use-after-free flaw within the kernel. This issue leads to memory corruption and possible privilege escalation.

A heap out-of-bounds write vulnerability in the Linux kernel's Linux Kernel Performance Events (perf) component can be exploited to achieve local privilege escalation. If perf_read_group() is called while an event's sibling_list is smaller than its child's sibling_list, it can increment or write to memory locations outside of the allocated buffer. We recommend upgrading past commit 32671e3799ca2e4590773fd0e63aaa4229e50c06.

In the Linux kernel, the following vulnerability has been resolved: RDMA/efa: Fix use of completion ctx after free On admin queue completion handling, if the admin command completed with error we print data from the completion context. The issue is that we already freed the completion context in polling/interrupts handler which means we print data from context in an unknown state (it might be already used again). Change the admin submission flow so alloc/dealloc of the context will be symmetric and dealloc will be called after any potential use of the context.

In the Linux kernel, the following vulnerability has been resolved: spi: spi-fsl-lpspi: fix teardown order issue (UAF) There is a teardown order issue in the driver. The SPI controller is registered using devm_spi_register_controller(), which delays unregistration of the SPI controller until after the fsl_lpspi_remove() function returns. As the fsl_lpspi_remove() function synchronously tears down the DMA channels, a running SPI transfer triggers the following NULL pointer dereference due to use after free: | fsl_lpspi 42550000.spi: I/O Error in DMA RX | Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [...] | Call trace: | fsl_lpspi_dma_transfer+0x260/0x340 [spi_fsl_lpspi] | fsl_lpspi_transfer_one+0x198/0x448 [spi_fsl_lpspi] | spi_transfer_one_message+0x49c/0x7c8 | __spi_pump_transfer_message+0x120/0x420 | __spi_sync+0x2c4/0x520 | spi_sync+0x34/0x60 | spidev_message+0x20c/0x378 [spidev] | spidev_ioctl+0x398/0x750 [spidev] [...] Switch from devm_spi_register_controller() to spi_register_controller() in fsl_lpspi_probe() and add the corresponding spi_unregister_controller() in fsl_lpspi_remove().

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.

The block subsystem in the Linux kernel before 5.2 has a use-after-free that can lead to arbitrary code execution in the kernel context and privilege escalation, aka CID-c3e2219216c9. This is related to blk_mq_free_rqs and blk_cleanup_queue.

In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Fix possible invalid memory access after FLR In the case that the first Function Level Reset (FLR) concludes correctly, but in the second FLR the scratch area for the saved configuration cannot be allocated, it's possible for a invalid memory access to happen. Always set the deallocated scratch area to NULL after FLR completes.

In the Linux kernel, the following vulnerability has been resolved: can: isotp: fix tx.buf use-after-free in isotp_sendmsg() isotp_sendmsg() uses only cmpxchg() on so->tx.state to serialize access to so->tx.buf. isotp_release() waits for ISOTP_IDLE via wait_event_interruptible() and then calls kfree(so->tx.buf). If a signal interrupts the wait_event_interruptible() inside close() while tx.state is ISOTP_SENDING, the loop exits early and release proceeds to force ISOTP_SHUTDOWN and continues to kfree(so->tx.buf) while sendmsg may still be reading so->tx.buf for the final CAN frame in isotp_fill_dataframe(). The so->tx.buf can be allocated once when the standard tx.buf length needs to be extended. Move the kfree() of this potentially extended tx.buf to sk_destruct time when either isotp_sendmsg() and isotp_release() are done.

In the Linux kernel, the following vulnerability has been resolved: net: fix fanout UAF in packet_release() via NETDEV_UP race `packet_release()` has a race window where `NETDEV_UP` can re-register a socket into a fanout group's `arr[]` array. The re-registration is not cleaned up by `fanout_release()`, leaving a dangling pointer in the fanout array. `packet_release()` does NOT zero `po->num` in its `bind_lock` section. After releasing `bind_lock`, `po->num` is still non-zero and `po->ifindex` still matches the bound device. A concurrent `packet_notifier(NETDEV_UP)` that already found the socket in `sklist` can re-register the hook. For fanout sockets, this re-registration calls `__fanout_link(sk, po)` which adds the socket back into `f->arr[]` and increments `f->num_members`, but does NOT increment `f->sk_ref`. The fix sets `po->num` to zero in `packet_release` while `bind_lock` is held to prevent NETDEV_UP from linking, preventing the race window. This bug was found following an additional audit with Claude Code based on CVE-2025-38617.

In the Linux kernel, the following vulnerability has been resolved: net: macb: use the current queue number for stats There's a potential mismatch between the memory reserved for statistics and the amount of memory written. gem_get_sset_count() correctly computes the number of stats based on the active queues, whereas gem_get_ethtool_stats() indiscriminately copies data using the maximum number of queues, and in the case the number of active queues is less than MACB_MAX_QUEUES, this results in a OOB write as observed in the KASAN splat. ================================================================== BUG: KASAN: vmalloc-out-of-bounds in gem_get_ethtool_stats+0x54/0x78 [macb] Write of size 760 at addr ffff80008080b000 by task ethtool/1027 CPU: [...] Tainted: [E]=UNSIGNED_MODULE Hardware name: raspberrypi rpi/rpi, BIOS 2025.10 10/01/2025 Call trace: show_stack+0x20/0x38 (C) dump_stack_lvl+0x80/0xf8 print_report+0x384/0x5e0 kasan_report+0xa0/0xf0 kasan_check_range+0xe8/0x190 __asan_memcpy+0x54/0x98 gem_get_ethtool_stats+0x54/0x78 [macb 926c13f3af83b0c6fe64badb21ec87d5e93fcf65] dev_ethtool+0x1220/0x38c0 dev_ioctl+0x4ac/0xca8 sock_do_ioctl+0x170/0x1d8 sock_ioctl+0x484/0x5d8 __arm64_sys_ioctl+0x12c/0x1b8 invoke_syscall+0xd4/0x258 el0_svc_common.constprop.0+0xb4/0x240 do_el0_svc+0x48/0x68 el0_svc+0x40/0xf8 el0t_64_sync_handler+0xa0/0xe8 el0t_64_sync+0x1b0/0x1b8 The buggy address belongs to a 1-page vmalloc region starting at 0xffff80008080b000 allocated at dev_ethtool+0x11f0/0x38c0 The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff00000a333000 pfn:0xa333 flags: 0x7fffc000000000(node=0|zone=0|lastcpupid=0x1ffff) raw: 007fffc000000000 0000000000000000 dead000000000122 0000000000000000 raw: ffff00000a333000 0000000000000000 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff80008080b080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff80008080b100: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff80008080b180: 00 00 00 00 00 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ^ ffff80008080b200: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ffff80008080b280: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ================================================================== Fix it by making sure the copied size only considers the active number of queues.

In the Linux kernel, the following vulnerability has been resolved: net: bonding: fix use-after-free in bond_xmit_broadcast() bond_xmit_broadcast() reuses the original skb for the last slave (determined by bond_is_last_slave()) and clones it for others. Concurrent slave enslave/release can mutate the slave list during RCU-protected iteration, changing which slave is "last" mid-loop. This causes the original skb to be double-consumed (double-freed). Replace the racy bond_is_last_slave() check with a simple index comparison (i + 1 == slaves_count) against the pre-snapshot slave count taken via READ_ONCE() before the loop. This preserves the zero-copy optimization for the last slave while making the "last" determination stable against concurrent list mutations. The UAF can trigger the following crash: ================================================================== BUG: KASAN: slab-use-after-free in skb_clone Read of size 8 at addr ffff888100ef8d40 by task exploit/147 CPU: 1 UID: 0 PID: 147 Comm: exploit Not tainted 7.0.0-rc3+ #4 PREEMPTLAZY Call Trace: <TASK> dump_stack_lvl (lib/dump_stack.c:123) print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) kasan_report (mm/kasan/report.c:597) skb_clone (include/linux/skbuff.h:1724 include/linux/skbuff.h:1792 include/linux/skbuff.h:3396 net/core/skbuff.c:2108) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5334) bond_start_xmit (drivers/net/bonding/bond_main.c:5567 drivers/net/bonding/bond_main.c:5593) dev_hard_start_xmit (include/linux/netdevice.h:5325 include/linux/netdevice.h:5334 net/core/dev.c:3871 net/core/dev.c:3887) __dev_queue_xmit (include/linux/netdevice.h:3601 net/core/dev.c:4838) ip6_finish_output2 (include/net/neighbour.h:540 include/net/neighbour.h:554 net/ipv6/ip6_output.c:136) ip6_finish_output (net/ipv6/ip6_output.c:208 net/ipv6/ip6_output.c:219) ip6_output (net/ipv6/ip6_output.c:250) ip6_send_skb (net/ipv6/ip6_output.c:1985) udp_v6_send_skb (net/ipv6/udp.c:1442) udpv6_sendmsg (net/ipv6/udp.c:1733) __sys_sendto (net/socket.c:730 net/socket.c:742 net/socket.c:2206) __x64_sys_sendto (net/socket.c:2209) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) </TASK> Allocated by task 147: Freed by task 147: The buggy address belongs to the object at ffff888100ef8c80 which belongs to the cache skbuff_head_cache of size 224 The buggy address is located 192 bytes inside of freed 224-byte region [ffff888100ef8c80, ffff888100ef8d60) Memory state around the buggy address: ffff888100ef8c00: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc ffff888100ef8c80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff888100ef8d00: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ^ ffff888100ef8d80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb ffff888100ef8e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ==================================================================

A use-after-free flaw was found in the Linux kernel’s Atheros wireless adapter driver in the way a user forces the ath9k_htc_wait_for_target function to fail with some input messages. This flaw allows a local user to crash or potentially escalate their privileges on the system.

A use-after-free exists in the Linux Kernel in tc_new_tfilter that could allow a local attacker to gain privilege escalation. The exploit requires unprivileged user namespaces. We recommend upgrading past commit 04c2a47ffb13c29778e2a14e414ad4cb5a5db4b5

A flaw was found in KVM. When updating a guest's page table entry, vm_pgoff was improperly used as the offset to get the page's pfn. As vaddr and vm_pgoff are controllable by user-mode processes, this flaw allows unprivileged local users on the host to write outside the userspace region and potentially corrupt the kernel, resulting in a denial of service condition.