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: 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.

A use-after-free vulnerability in the Linux kernel's netfilter: nf_tables component can be exploited to achieve local privilege escalation. Due to a race condition between nf_tables netlink control plane transaction and nft_set element garbage collection, it is possible to underflow the reference counter causing a use-after-free vulnerability. We recommend upgrading past commit 3e91b0ebd994635df2346353322ac51ce84ce6d8.

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: 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: 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: 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.

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.

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: drm/amd/display: Do not skip unrelated mode changes in DSC validation Starting with commit 17ce8a6907f7 ("drm/amd/display: Add dsc pre-validation in atomic check"), amdgpu resets the CRTC state mode_changed flag to false when recomputing the DSC configuration results in no timing change for a particular stream. However, this is incorrect in scenarios where a change in MST/DSC configuration happens in the same KMS commit as another (unrelated) mode change. For example, the integrated panel of a laptop may be configured differently (e.g., HDR enabled/disabled) depending on whether external screens are attached. In this case, plugging in external DP-MST screens may result in the mode_changed flag being dropped incorrectly for the integrated panel if its DSC configuration did not change during precomputation in pre_validate_dsc(). At this point, however, dm_update_crtc_state() has already created new streams for CRTCs with DSC-independent mode changes. In turn, amdgpu_dm_commit_streams() will never release the old stream, resulting in a memory leak. amdgpu_dm_atomic_commit_tail() will never acquire a reference to the new stream either, which manifests as a use-after-free when the stream gets disabled later on: BUG: KASAN: use-after-free in dc_stream_release+0x25/0x90 [amdgpu] Write of size 4 at addr ffff88813d836524 by task kworker/9:9/29977 Workqueue: events drm_mode_rmfb_work_fn Call Trace: <TASK> dump_stack_lvl+0x6e/0xa0 print_address_description.constprop.0+0x88/0x320 ? dc_stream_release+0x25/0x90 [amdgpu] print_report+0xfc/0x1ff ? srso_alias_return_thunk+0x5/0xfbef5 ? __virt_addr_valid+0x225/0x4e0 ? dc_stream_release+0x25/0x90 [amdgpu] kasan_report+0xe1/0x180 ? dc_stream_release+0x25/0x90 [amdgpu] kasan_check_range+0x125/0x200 dc_stream_release+0x25/0x90 [amdgpu] dc_state_destruct+0x14d/0x5c0 [amdgpu] dc_state_release.part.0+0x4e/0x130 [amdgpu] dm_atomic_destroy_state+0x3f/0x70 [amdgpu] drm_atomic_state_default_clear+0x8ee/0xf30 ? drm_mode_object_put.part.0+0xb1/0x130 __drm_atomic_state_free+0x15c/0x2d0 atomic_remove_fb+0x67e/0x980 Since there is no reliable way of figuring out whether a CRTC has unrelated mode changes pending at the time of DSC validation, remember the value of the mode_changed flag from before the point where a CRTC was marked as potentially affected by a change in DSC configuration. Reset the mode_changed flag to this earlier value instead in pre_validate_dsc(). (cherry picked from commit cc7c7121ae082b7b82891baa7280f1ff2608f22b)

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: 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: bpf: Fix undefined behavior in interpreter sdiv/smod for INT_MIN The BPF interpreter's signed 32-bit division and modulo handlers use the kernel abs() macro on s32 operands. The abs() macro documentation (include/linux/math.h) explicitly states the result is undefined when the input is the type minimum. When DST contains S32_MIN (0x80000000), abs((s32)DST) triggers undefined behavior and returns S32_MIN unchanged on arm64/x86. This value is then sign-extended to u64 as 0xFFFFFFFF80000000, causing do_div() to compute the wrong result. The verifier's abstract interpretation (scalar32_min_max_sdiv) computes the mathematically correct result for range tracking, creating a verifier/interpreter mismatch that can be exploited for out-of-bounds map value access. Introduce abs_s32() which handles S32_MIN correctly by casting to u32 before negating, avoiding signed overflow entirely. Replace all 8 abs((s32)...) call sites in the interpreter's sdiv32/smod32 handlers. s32 is the only affected case -- the s64 division/modulo handlers do not use abs().

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: 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: xfs: stop reclaim before pushing AIL during unmount The unmount sequence in xfs_unmount_flush_inodes() pushed the AIL while background reclaim and inodegc are still running. This is broken independently of any use-after-free issues - background reclaim and inodegc should not be running while the AIL is being pushed during unmount, as inodegc can dirty and insert inodes into the AIL during the flush, and background reclaim can race to abort and free dirty inodes. Reorder xfs_unmount_flush_inodes() to stop inodegc and cancel background reclaim before pushing the AIL. Stop inodegc before cancelling m_reclaim_work because the inodegc worker can re-queue m_reclaim_work via xfs_inodegc_set_reclaimable.

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.

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: net/smc: fix double-free of smc_spd_priv when tee() duplicates splice pipe buffer smc_rx_splice() allocates one smc_spd_priv per pipe_buffer and stores the pointer in pipe_buffer.private. The pipe_buf_operations for these buffers used .get = generic_pipe_buf_get, which only increments the page reference count when tee(2) duplicates a pipe buffer. The smc_spd_priv pointer itself was not handled, so after tee() both the original and the cloned pipe_buffer share the same smc_spd_priv *. When both pipes are subsequently released, smc_rx_pipe_buf_release() is called twice against the same object: 1st call: kfree(priv) sock_put(sk) smc_rx_update_cons() [correct] 2nd call: kfree(priv) sock_put(sk) smc_rx_update_cons() [UAF] KASAN reports a slab-use-after-free in smc_rx_pipe_buf_release(), which then escalates to a NULL-pointer dereference and kernel panic via smc_rx_update_consumer() when it chases the freed priv->smc pointer: BUG: KASAN: slab-use-after-free in smc_rx_pipe_buf_release+0x78/0x2a0 Read of size 8 at addr ffff888004a45740 by task smc_splice_tee_/74 Call Trace: <TASK> dump_stack_lvl+0x53/0x70 print_report+0xce/0x650 kasan_report+0xc6/0x100 smc_rx_pipe_buf_release+0x78/0x2a0 free_pipe_info+0xd4/0x130 pipe_release+0x142/0x160 __fput+0x1c6/0x490 __x64_sys_close+0x4f/0x90 do_syscall_64+0xa6/0x1a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f </TASK> BUG: kernel NULL pointer dereference, address: 0000000000000020 RIP: 0010:smc_rx_update_consumer+0x8d/0x350 Call Trace: <TASK> smc_rx_pipe_buf_release+0x121/0x2a0 free_pipe_info+0xd4/0x130 pipe_release+0x142/0x160 __fput+0x1c6/0x490 __x64_sys_close+0x4f/0x90 do_syscall_64+0xa6/0x1a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f </TASK> Kernel panic - not syncing: Fatal exception Beyond the memory-safety problem, duplicating an SMC splice buffer is semantically questionable: smc_rx_update_cons() would advance the consumer cursor twice for the same data, corrupting receive-window accounting. A refcount on smc_spd_priv could fix the double-free, but the cursor-accounting issue would still need to be addressed separately. The .get callback is invoked by both tee(2) and splice_pipe_to_pipe() for partial transfers; both will now return -EFAULT. Users who need to duplicate SMC socket data must use a copy-based read path.

In the Linux kernel, the following vulnerability has been resolved: xfrm: prevent policy_hthresh.work from racing with netns teardown A XFRM_MSG_NEWSPDINFO request can queue the per-net work item policy_hthresh.work onto the system workqueue. The queued callback, xfrm_hash_rebuild(), retrieves the enclosing struct net via container_of(). If the net namespace is torn down before that work runs, the associated struct net may already have been freed, and xfrm_hash_rebuild() may then dereference stale memory. xfrm_policy_fini() already flushes policy_hash_work during teardown, but it does not synchronize policy_hthresh.work. Synchronize policy_hthresh.work in xfrm_policy_fini() as well, so the queued work cannot outlive the net namespace teardown and access a freed struct net.

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: 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: 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: 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: xfrm: iptfs: only publish mode_data after clone setup iptfs_clone_state() stores x->mode_data before allocating the reorder window. If that allocation fails, the code frees the cloned state and returns -ENOMEM, leaving x->mode_data pointing at freed memory. The xfrm clone unwind later runs destroy_state() through x->mode_data, so the failed clone path tears down IPTFS state that clone_state() already freed. Keep the cloned IPTFS state private until all allocations succeed so failed clones leave x->mode_data unset. The destroy path already handles a NULL mode_data pointer.

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.

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: 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: net: openvswitch: Avoid releasing netdev before teardown completes The patch cited in the Fixes tag below changed the teardown code for OVS ports to no longer unconditionally take the RTNL. After this change, the netdev_destroy() callback can proceed immediately to the call_rcu() invocation if the IFF_OVS_DATAPATH flag is already cleared on the netdev. The ovs_netdev_detach_dev() function clears the flag before completing the unregistration, and if it gets preempted after clearing the flag (as can happen on an -rt kernel), netdev_destroy() can complete and the device can be freed before the unregistration completes. This leads to a splat like: [ 998.393867] Oops: general protection fault, probably for non-canonical address 0xff00000001000239: 0000 [#1] SMP PTI [ 998.393877] CPU: 42 UID: 0 PID: 55177 Comm: ip Kdump: loaded Not tainted 6.12.0-211.1.1.el10_2.x86_64+rt #1 PREEMPT_RT [ 998.393886] Hardware name: Dell Inc. PowerEdge R740/0JMK61, BIOS 2.24.0 03/27/2025 [ 998.393889] RIP: 0010:dev_set_promiscuity+0x8d/0xa0 [ 998.393901] Code: 00 00 75 d8 48 8b 53 08 48 83 ba b0 02 00 00 00 75 ca 48 83 c4 08 5b c3 cc cc cc cc 48 83 bf 48 09 00 00 00 75 91 48 8b 47 08 <48> 83 b8 b0 02 00 00 00 74 97 eb 81 0f 1f 80 00 00 00 00 90 90 90 [ 998.393906] RSP: 0018:ffffce5864a5f6a0 EFLAGS: 00010246 [ 998.393912] RAX: ff00000000ffff89 RBX: ffff894d0adf5a05 RCX: 0000000000000000 [ 998.393917] RDX: 0000000000000000 RSI: 00000000ffffffff RDI: ffff894d0adf5a05 [ 998.393921] RBP: ffff894d19252000 R08: ffff894d19252000 R09: 0000000000000000 [ 998.393924] R10: ffff894d19252000 R11: ffff894d192521b8 R12: 0000000000000006 [ 998.393927] R13: ffffce5864a5f738 R14: 00000000ffffffe2 R15: 0000000000000000 [ 998.393931] FS: 00007fad61971800(0000) GS:ffff894cc0140000(0000) knlGS:0000000000000000 [ 998.393936] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 998.393940] CR2: 000055df0a2a6e40 CR3: 000000011c7fe003 CR4: 00000000007726f0 [ 998.393944] PKRU: 55555554 [ 998.393946] Call Trace: [ 998.393949] <TASK> [ 998.393952] ? show_trace_log_lvl+0x1b0/0x2f0 [ 998.393961] ? show_trace_log_lvl+0x1b0/0x2f0 [ 998.393975] ? dp_device_event+0x41/0x80 [openvswitch] [ 998.394009] ? __die_body.cold+0x8/0x12 [ 998.394016] ? die_addr+0x3c/0x60 [ 998.394027] ? exc_general_protection+0x16d/0x390 [ 998.394042] ? asm_exc_general_protection+0x26/0x30 [ 998.394058] ? dev_set_promiscuity+0x8d/0xa0 [ 998.394066] ? ovs_netdev_detach_dev+0x3a/0x80 [openvswitch] [ 998.394092] dp_device_event+0x41/0x80 [openvswitch] [ 998.394102] notifier_call_chain+0x5a/0xd0 [ 998.394106] unregister_netdevice_many_notify+0x51b/0xa60 [ 998.394110] rtnl_dellink+0x169/0x3e0 [ 998.394121] ? rt_mutex_slowlock.constprop.0+0x95/0xd0 [ 998.394125] rtnetlink_rcv_msg+0x142/0x3f0 [ 998.394128] ? avc_has_perm_noaudit+0x69/0xf0 [ 998.394130] ? __pfx_rtnetlink_rcv_msg+0x10/0x10 [ 998.394132] netlink_rcv_skb+0x50/0x100 [ 998.394138] netlink_unicast+0x292/0x3f0 [ 998.394141] netlink_sendmsg+0x21b/0x470 [ 998.394145] ____sys_sendmsg+0x39d/0x3d0 [ 998.394149] ___sys_sendmsg+0x9a/0xe0 [ 998.394156] __sys_sendmsg+0x7a/0xd0 [ 998.394160] do_syscall_64+0x7f/0x170 [ 998.394162] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 998.394165] RIP: 0033:0x7fad61bf4724 [ 998.394188] Code: 89 02 b8 ff ff ff ff eb bb 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 f3 0f 1e fa 80 3d c5 e9 0c 00 00 74 13 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 48 83 ec 28 89 54 24 1c 48 89 [ 998.394189] RSP: 002b:00007ffd7e2f7cb8 EFLAGS: 00000202 ORIG_RAX: 000000000000002e [ 998.394191] RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007fad61bf4724 [ 998.394193] RDX: 0000000000000000 RSI: 00007ffd7e2f7d20 RDI: 0000000000000003 [ 998.394194] RBP: 00007ffd7e2f7d90 R08: 0000000000000010 R09: 000000000000003f [ 998.394195] R10: 000055df11558010 R11: 0000000000000202 R12: 00007ffd7e2 ---truncated---

The sock_setsockopt function in net/core/sock.c in the Linux kernel before 3.5 mishandles negative values of sk_sndbuf and sk_rcvbuf, which allows local users to cause a denial of service (memory corruption and system crash) or possibly have unspecified other impact by leveraging the CAP_NET_ADMIN capability for a crafted setsockopt system call with the (1) SO_SNDBUF or (2) SO_RCVBUF option.

A use-after-free vulnerability in the Linux kernel's net/sched: cls_route component can be exploited to achieve local privilege escalation. When route4_change() is called on an existing filter, the whole tcf_result struct is always copied into the new instance of the filter. This causes a problem when updating a filter bound to a class, as tcf_unbind_filter() is always called on the old instance in the success path, decreasing filter_cnt of the still referenced class and allowing it to be deleted, leading to a use-after-free. We recommend upgrading past commit b80b829e9e2c1b3f7aae34855e04d8f6ecaf13c8.

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix incorrect pruning due to atomic fetch precision tracking When backtrack_insn encounters a BPF_STX instruction with BPF_ATOMIC and BPF_FETCH, the src register (or r0 for BPF_CMPXCHG) also acts as a destination, thus receiving the old value from the memory location. The current backtracking logic does not account for this. It treats atomic fetch operations the same as regular stores where the src register is only an input. This leads the backtrack_insn to fail to propagate precision to the stack location, which is then not marked as precise! Later, the verifier's path pruning can incorrectly consider two states equivalent when they differ in terms of stack state. Meaning, two branches can be treated as equivalent and thus get pruned when they should not be seen as such. Fix it as follows: Extend the BPF_LDX handling in backtrack_insn to also cover atomic fetch operations via is_atomic_fetch_insn() helper. When the fetch dst register is being tracked for precision, clear it, and propagate precision over to the stack slot. For non-stack memory, the precision walk stops at the atomic instruction, same as regular BPF_LDX. This covers all fetch variants. Before: 0: (b7) r1 = 8 ; R1=8 1: (7b) *(u64 *)(r10 -8) = r1 ; R1=8 R10=fp0 fp-8=8 2: (b7) r2 = 0 ; R2=0 3: (db) r2 = atomic64_fetch_add((u64 *)(r10 -8), r2) ; R2=8 R10=fp0 fp-8=mmmmmmmm 4: (bf) r3 = r10 ; R3=fp0 R10=fp0 5: (0f) r3 += r2 mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1 mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10 mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_add((u64 *)(r10 -8), r2) mark_precise: frame0: regs=r2 stack= before 2: (b7) r2 = 0 6: R2=8 R3=fp8 6: (b7) r0 = 0 ; R0=0 7: (95) exit After: 0: (b7) r1 = 8 ; R1=8 1: (7b) *(u64 *)(r10 -8) = r1 ; R1=8 R10=fp0 fp-8=8 2: (b7) r2 = 0 ; R2=0 3: (db) r2 = atomic64_fetch_add((u64 *)(r10 -8), r2) ; R2=8 R10=fp0 fp-8=mmmmmmmm 4: (bf) r3 = r10 ; R3=fp0 R10=fp0 5: (0f) r3 += r2 mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1 mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10 mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_add((u64 *)(r10 -8), r2) mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0 mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1 mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8 6: R2=8 R3=fp8 6: (b7) r0 = 0 ; R0=0 7: (95) exit

In the Linux kernel, the following vulnerability has been resolved: crypto: caam - fix overflow on long hmac keys When a key longer than block size is supplied, it is copied and then hashed into the real key. The memory allocated for the copy needs to be rounded to DMA cache alignment, as otherwise the hashed key may corrupt neighbouring memory. The copying is performed using kmemdup, however this leads to an overflow: reading more bytes (aligned_len - keylen) from the keylen source buffer. Fix this by replacing kmemdup with kmalloc, followed by memcpy.

In the Linux kernel, the following vulnerability has been resolved: vsock/virtio: Initialization of the dangling pointer occurring in vsk->trans During loopback communication, a dangling pointer can be created in vsk->trans, potentially leading to a Use-After-Free condition. This issue is resolved by initializing vsk->trans to NULL.

In the Linux kernel, the following vulnerability has been resolved: RDMA/iwcm: Fix a use-after-free related to destroying CM IDs iw_conn_req_handler() associates a new struct rdma_id_private (conn_id) with an existing struct iw_cm_id (cm_id) as follows: conn_id->cm_id.iw = cm_id; cm_id->context = conn_id; cm_id->cm_handler = cma_iw_handler; rdma_destroy_id() frees both the cm_id and the struct rdma_id_private. Make sure that cm_work_handler() does not trigger a use-after-free by only freeing of the struct rdma_id_private after all pending work has finished.

In the Linux kernel, the following vulnerability has been resolved: mlxsw: core_linecards: Fix double memory deallocation in case of invalid INI file In case of invalid INI file mlxsw_linecard_types_init() deallocates memory but doesn't reset pointer to NULL and returns 0. In case of any error occurred after mlxsw_linecard_types_init() call, mlxsw_linecards_init() calls mlxsw_linecard_types_fini() which performs memory deallocation again. Add pointer reset to NULL. Found by Linux Verification Center (linuxtesting.org) with SVACE.

In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: ASSERT when failing to find index by plane/stream id [WHY] find_disp_cfg_idx_by_plane_id and find_disp_cfg_idx_by_stream_id returns an array index and they return -1 when not found; however, -1 is not a valid index number. [HOW] When this happens, call ASSERT(), and return a positive number (which is fewer than callers' array size) instead. This fixes 4 OVERRUN and 2 NEGATIVE_RETURNS issues reported by Coverity.

In the Linux kernel, the following vulnerability has been resolved: crypto: hisilicon/debugfs - Fix debugfs uninit process issue During the zip probe process, the debugfs failure does not stop the probe. When debugfs initialization fails, jumping to the error branch will also release regs, in addition to its own rollback operation. As a result, it may be released repeatedly during the regs uninit process. Therefore, the null check needs to be added to the regs uninit process.

In the Linux kernel, the following vulnerability has been resolved: ASoC: mediatek: mt8195: Add platform entry for ETDM1_OUT_BE dai link Commit e70b8dd26711 ("ASoC: mediatek: mt8195: Remove afe-dai component and rework codec link") removed the codec entry for the ETDM1_OUT_BE dai link entirely instead of replacing it with COMP_EMPTY(). This worked by accident as the remaining COMP_EMPTY() platform entry became the codec entry, and the platform entry became completely empty, effectively the same as COMP_DUMMY() since snd_soc_fill_dummy_dai() doesn't do anything for platform entries. This causes a KASAN out-of-bounds warning in mtk_soundcard_common_probe() in sound/soc/mediatek/common/mtk-soundcard-driver.c: for_each_card_prelinks(card, i, dai_link) { if (adsp_node && !strncmp(dai_link->name, "AFE_SOF", strlen("AFE_SOF"))) dai_link->platforms->of_node = adsp_node; else if (!dai_link->platforms->name && !dai_link->platforms->of_node) dai_link->platforms->of_node = platform_node; } where the code expects the platforms array to have space for at least one entry. Add an COMP_EMPTY() entry so that dai_link->platforms has space.

In the Linux kernel, the following vulnerability has been resolved: nilfs2: add missing check for inode numbers on directory entries Syzbot reported that mounting and unmounting a specific pattern of corrupted nilfs2 filesystem images causes a use-after-free of metadata file inodes, which triggers a kernel bug in lru_add_fn(). As Jan Kara pointed out, this is because the link count of a metadata file gets corrupted to 0, and nilfs_evict_inode(), which is called from iput(), tries to delete that inode (ifile inode in this case). The inconsistency occurs because directories containing the inode numbers of these metadata files that should not be visible in the namespace are read without checking. Fix this issue by treating the inode numbers of these internal files as errors in the sanity check helper when reading directory folios/pages. Also thanks to Hillf Danton and Matthew Wilcox for their initial mm-layer analysis.

A use-after-free flaw was found in the Linux kernel’s Netfilter functionality when adding a rule with NFTA_RULE_CHAIN_ID. This flaw allows a local user to crash or escalate their privileges on the system.

Integer overflow in fs/aio.c in the Linux kernel before 3.4.1 allows local users to cause a denial of service or possibly have unspecified other impact via a large AIO iovec.

In the Linux kernel, the following vulnerability has been resolved: cachefiles: wait for ondemand_object_worker to finish when dropping object When queuing ondemand_object_worker() to re-open the object, cachefiles_object is not pinned. The cachefiles_object may be freed when the pending read request is completed intentionally and the related erofs is umounted. If ondemand_object_worker() runs after the object is freed, it will incur use-after-free problem as shown below. process A processs B process C process D cachefiles_ondemand_send_req() // send a read req X // wait for its completion // close ondemand fd cachefiles_ondemand_fd_release() // set object as CLOSE cachefiles_ondemand_daemon_read() // set object as REOPENING queue_work(fscache_wq, &info->ondemand_work) // close /dev/cachefiles cachefiles_daemon_release cachefiles_flush_reqs complete(&req->done) // read req X is completed // umount the erofs fs cachefiles_put_object() // object will be freed cachefiles_ondemand_deinit_obj_info() kmem_cache_free(object) // both info and object are freed ondemand_object_worker() When dropping an object, it is no longer necessary to reopen the object, so use cancel_work_sync() to cancel or wait for ondemand_object_worker() to finish.

In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check pipe offset before setting vblank pipe_ctx has a size of MAX_PIPES so checking its index before accessing the array. This fixes an OVERRUN issue reported by Coverity.

In the Linux kernel, the following vulnerability has been resolved: net: ethernet: lantiq_etop: fix double free in detach The number of the currently released descriptor is never incremented which results in the same skb being released multiple times.

In the Linux kernel, the following vulnerability has been resolved: KVM: PPC: Book3S HV: Prevent UAF in kvm_spapr_tce_attach_iommu_group() Al reported a possible use-after-free (UAF) in kvm_spapr_tce_attach_iommu_group(). It looks up `stt` from tablefd, but then continues to use it after doing fdput() on the returned fd. After the fdput() the tablefd is free to be closed by another thread. The close calls kvm_spapr_tce_release() and then release_spapr_tce_table() (via call_rcu()) which frees `stt`. Although there are calls to rcu_read_lock() in kvm_spapr_tce_attach_iommu_group() they are not sufficient to prevent the UAF, because `stt` is used outside the locked regions. With an artifcial delay after the fdput() and a userspace program which triggers the race, KASAN detects the UAF: BUG: KASAN: slab-use-after-free in kvm_spapr_tce_attach_iommu_group+0x298/0x720 [kvm] Read of size 4 at addr c000200027552c30 by task kvm-vfio/2505 CPU: 54 PID: 2505 Comm: kvm-vfio Not tainted 6.10.0-rc3-next-20240612-dirty #1 Hardware name: 8335-GTH POWER9 0x4e1202 opal:skiboot-v6.5.3-35-g1851b2a06 PowerNV Call Trace: dump_stack_lvl+0xb4/0x108 (unreliable) print_report+0x2b4/0x6ec kasan_report+0x118/0x2b0 __asan_load4+0xb8/0xd0 kvm_spapr_tce_attach_iommu_group+0x298/0x720 [kvm] kvm_vfio_set_attr+0x524/0xac0 [kvm] kvm_device_ioctl+0x144/0x240 [kvm] sys_ioctl+0x62c/0x1810 system_call_exception+0x190/0x440 system_call_vectored_common+0x15c/0x2ec ... Freed by task 0: ... kfree+0xec/0x3e0 release_spapr_tce_table+0xd4/0x11c [kvm] rcu_core+0x568/0x16a0 handle_softirqs+0x23c/0x920 do_softirq_own_stack+0x6c/0x90 do_softirq_own_stack+0x58/0x90 __irq_exit_rcu+0x218/0x2d0 irq_exit+0x30/0x80 arch_local_irq_restore+0x128/0x230 arch_local_irq_enable+0x1c/0x30 cpuidle_enter_state+0x134/0x5cc cpuidle_enter+0x6c/0xb0 call_cpuidle+0x7c/0x100 do_idle+0x394/0x410 cpu_startup_entry+0x60/0x70 start_secondary+0x3fc/0x410 start_secondary_prolog+0x10/0x14 Fix it by delaying the fdput() until `stt` is no longer in use, which is effectively the entire function. To keep the patch minimal add a call to fdput() at each of the existing return paths. Future work can convert the function to goto or __cleanup style cleanup. With the fix in place the test case no longer triggers the UAF.

In the Linux kernel, the following vulnerability has been resolved: scsi: mpi3mr: Sanitise num_phys Information is stored in mr_sas_port->phy_mask, values larger then size of this field shouldn't be allowed.

In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Skip finding free audio for unknown engine_id [WHY] ENGINE_ID_UNKNOWN = -1 and can not be used as an array index. Plus, it also means it is uninitialized and does not need free audio. [HOW] Skip and return NULL. This fixes 2 OVERRUN issues reported by Coverity.

In the Linux kernel, the following vulnerability has been resolved: f2fs: check validation of fault attrs in f2fs_build_fault_attr() - It missed to check validation of fault attrs in parse_options(), let's fix to add check condition in f2fs_build_fault_attr(). - Use f2fs_build_fault_attr() in __sbi_store() to clean up code.

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix may_goto with negative offset. Zac's syzbot crafted a bpf prog that exposed two bugs in may_goto. The 1st bug is the way may_goto is patched. When offset is negative it should be patched differently. The 2nd bug is in the verifier: when current state may_goto_depth is equal to visited state may_goto_depth it means there is an actual infinite loop. It's not correct to prune exploration of the program at this point. Note, that this check doesn't limit the program to only one may_goto insn, since 2nd and any further may_goto will increment may_goto_depth only in the queued state pushed for future exploration. The current state will have may_goto_depth == 0 regardless of number of may_goto insns and the verifier has to explore the program until bpf_exit.